To investigate the applicability of four commonly used color difference formulas(CIELAB,CIE94,CMC(1:1),and CIEDE2000)in the printing field on 3D objects,as well as the impact of four standard light sources(D65,D50,A,a...To investigate the applicability of four commonly used color difference formulas(CIELAB,CIE94,CMC(1:1),and CIEDE2000)in the printing field on 3D objects,as well as the impact of four standard light sources(D65,D50,A,and TL84)on 3D color difference evaluations,50 glossy spheres with a diameter of 2cm based on the Sailner J4003D color printing device were created.These spheres were centered around the five recommended colors(gray,red,yellow,green,and blue)by CIE.Color difference was calculated according to the four formulas,and 111 pairs of experimental samples meeting the CIELAB gray scale color difference requirements(1.0-14.0)were selected.Ten observers,aged between 22 and 27 with normal color vision,were participated in this study,using the gray scale method from psychophysical experiments to conduct color difference evaluations under the four light sources,with repeated experiments for each observer.The results indicated that the overall effect of the D65 light source on 3D objects color difference was minimal.In contrast,D50 and A light sources had a significant impact within the small color difference range,while the TL84 light source influenced both large and small color difference considerably.Among the four color difference formulas,CIEDE2000 demonstrated the best predictive performance for color difference in 3D objects,followed by CMC(1:1),CIE94,and CIELAB.展开更多
Augmented reality(AR)is an emerging dynamic technology that effectively supports education across different levels.The increased use of mobile devices has an even greater impact.As the demand for AR applications in ed...Augmented reality(AR)is an emerging dynamic technology that effectively supports education across different levels.The increased use of mobile devices has an even greater impact.As the demand for AR applications in education continues to increase,educators actively seek innovative and immersive methods to engage students in learning.However,exploring these possibilities also entails identifying and overcoming existing barriers to optimal educational integration.Concurrently,this surge in demand has prompted the identification of specific barriers,one of which is three-dimensional(3D)modeling.Creating 3D objects for augmented reality education applications can be challenging and time-consuming for the educators.To address this,we have developed a pipeline that creates realistic 3D objects from the two-dimensional(2D)photograph.Applications for augmented and virtual reality can then utilize these created 3D objects.We evaluated the proposed pipeline based on the usability of the 3D object and performance metrics.Quantitatively,with 117 respondents,the co-creation team was surveyed with openended questions to evaluate the precision of the 3D object created by the proposed photogrammetry pipeline.We analyzed the survey data using descriptive-analytical methods and found that the proposed pipeline produces 3D models that are positively accurate when compared to real-world objects,with an average mean score above 8.This study adds new knowledge in creating 3D objects for augmented reality applications by using the photogrammetry technique;finally,it discusses potential problems and future research directions for 3D objects in the education sector.展开更多
This paper presents a complete system for scanning the geometry and texture of a large 3D object, then the automatic registration is performed to obtain a whole realistic 3D model. This system is composed of one line ...This paper presents a complete system for scanning the geometry and texture of a large 3D object, then the automatic registration is performed to obtain a whole realistic 3D model. This system is composed of one line strip laser and one color CCD camera. The scanned object is pictured twice by a color CCD camera. First, the texture of the scanned object is taken by a color CCD camera. Then the 3D information of the scanned object is obtained from laser plane equations. This paper presents a practical way to implement the three dimensional measuring method and the automatic registration of a large 3D object and a pretty good result is obtained after experiment verification.展开更多
Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmenta...Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmentation techniques for point clouds,where global augmentation is applied to the entire point cloud of the scene,and cut-paste samples objects from other frames into the current frame.Both types of data augmentation can improve performance,but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling,which may be counterproductive and may hurt the overall performance.In addition,LiDAR is susceptible to signal loss,external occlusion,extreme weather and other factors,which can easily cause object shape changes,while global augmentation and cut-paste cannot effectively enhance the robustness of the model.To this end,we propose Syn-Aug,a synchronous data augmentation framework for LiDAR-based 3D object detection.Specifically,we first propose a novel rendering-based object augmentation technique(Ren-Aug)to enrich training data while enhancing scene realism.Second,we propose a local augmentation technique(Local-Aug)to generate local noise by rotating and scaling objects in the scene while avoiding collisions,which can improve generalisation performance.Finally,we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames.We verify the proposed framework with four different types of 3D object detectors.Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets,proving the effectiveness and generality of Syn-Aug.On KITTI,four different types of baseline models using Syn-Aug improved mAP by 0.89%,1.35%,1.61%and 1.14%respectively.On nuScenes,four different types of baseline models using Syn-Aug improved mAP by 14.93%,10.42%,8.47%and 6.81%respectively.The code is available at https://github.com/liuhuaijjin/Syn-Aug.展开更多
The inherent limitations of 2D object detection,such as inadequate spatial reasoning and susceptibility to environmental occlusions,pose significant risks to the safety and reliability of autonomous driving systems.To...The inherent limitations of 2D object detection,such as inadequate spatial reasoning and susceptibility to environmental occlusions,pose significant risks to the safety and reliability of autonomous driving systems.To address these challenges,this paper proposes an enhanced 3D object detection framework(FastSECOND)based on an optimized SECOND architecture,designed to achieve rapid and accurate perception in autonomous driving scenarios.Key innovations include:(1)Replacing the Rectified Linear Unit(ReLU)activation functions with the Gaussian Error Linear Unit(GELU)during voxel feature encoding and region proposal network stages,leveraging partial convolution to balance computational efficiency and detection accuracy;(2)Integrating a Swin-Transformer V2 module into the voxel backbone network to enhance feature extraction capabilities in sparse data;and(3)Introducing an optimized position regression loss combined with a geometry-aware Focal-EIoU loss function,which incorporates bounding box geometric correlations to accelerate network convergence.While this study currently focuses exclusively on the detection of the Car category,with experiments conducted on the Car class of the KITTI dataset,future work will extend to other categories such as Pedestrian and Cyclist to more comprehensively evaluate the generalization capability of the proposed framework.Extensive experimental results demonstrate that our framework achieves a more effective trade-off between detection accuracy and speed.Compared to the baseline SECOND model,it achieves a 21.9%relative improvement in 3D bounding box detection accuracy on the hard subset,while reducing inference time by 14 ms.These advancements underscore the framework’s potential for enabling real-time,high-precision perception in autonomous driving applications.展开更多
Virtual globes(VGs)allow Internet users to view geographic data of heterogeneous quality created by other users.This article presents a new approach for collecting and visualizing information about the perceived quali...Virtual globes(VGs)allow Internet users to view geographic data of heterogeneous quality created by other users.This article presents a new approach for collecting and visualizing information about the perceived quality of 3D data in VGs.It aims atimproving users’awareness of the qualityof 3D objects.Instead of relying onthe existing metadata or on formal accuracy assessments that are often impossible in practice,we propose a crowd-sourced quality recommender system based on the five-star visualization method successful in other types of Web applications.Four alternative five-star visualizations were implemented in a Google Earth-based prototype and tested through a formal user evaluation.These tests helped identifying the most effective method for a 3D environment.Results indicate that while most websites use a visualization approach that shows a‘number of stars’,this method was the least preferred by participants.Instead,participants ranked the‘number within a star’method highest as it allowed reducing the visual clutter in urban settings,suggesting that 3D environments such as VGs require different designapproachesthan2Dornon-geographicapplications.Resultsalsoconfirmed that expert and non-expert users in geographic data share similar preferences for the most and least preferred visualization methods.展开更多
Multi-modal 3D object detection has achieved remarkable progress,but it is often limited in practical industrial production because of its high cost and low efficiency.The multi-view camera-based method provides a fea...Multi-modal 3D object detection has achieved remarkable progress,but it is often limited in practical industrial production because of its high cost and low efficiency.The multi-view camera-based method provides a feasible solution due to its low cost.However,camera data lacks geometric depth,and only using camera data to obtain high accuracy is challenging.This paper proposes a multi-modal Bird-Eye-View(BEV)distillation framework(MMDistill)to make a trade-off between them.MMDistill is a carefully crafted two-stage distillation framework based on teacher and student models for learning cross-modal knowledge and generating multi-modal features.It can improve the performance of unimodal detectors without introducing additional costs during inference.Specifically,our method can effectively solve the cross-gap caused by the heterogeneity between data.Furthermore,we further propose a Light Detection and Ranging(LiDAR)-guided geometric compensation module,which can assist the student model in obtaining effective geometric features and reduce the gap between different modalities.Our proposed method generally requires fewer computational resources and faster inference speed than traditional multi-modal models.This advancement enables multi-modal technology to be applied more widely in practical scenarios.Through experiments,we validate the effectiveness and superiority of MMDistill on the nuScenes dataset,achieving an improvement of 4.1%mean Average Precision(mAP)and 4.6%NuScenes Detection Score(NDS)over the baseline detector.In addition,we also present detailed ablation studies to validate our method.展开更多
Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,w...Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,we propose Rail-PillarNet,a three-dimensional(3D)LIDAR(Light Detection and Ranging)railway foreign object detection method based on the improvement of PointPillars.Firstly,the parallel attention pillar encoder(PAPE)is designed to fully extract the features of the pillars and alleviate the problem of local fine-grained information loss in PointPillars pillars encoder.Secondly,a fine backbone network is designed to improve the feature extraction capability of the network by combining the coding characteristics of LIDAR point cloud feature and residual structure.Finally,the initial weight parameters of the model were optimised by the transfer learning training method to further improve accuracy.The experimental results on the OSDaR23 dataset show that the average accuracy of Rail-PillarNet reaches 58.51%,which is higher than most mainstream models,and the number of parameters is 5.49 M.Compared with PointPillars,the accuracy of each target is improved by 10.94%,3.53%,16.96%and 19.90%,respectively,and the number of parameters only increases by 0.64M,which achieves a balance between the number of parameters and accuracy.展开更多
Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input t...Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.展开更多
As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advan...As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.展开更多
3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments.It is critical for such systems to recognize and segment the 3D object instances that they encou...3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments.It is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent basis.The computer vision,graphics,and machine learning fields have all given it a lot of attention.Traditionally,3D segmentation was done with hand-crafted features and designed approaches that didn’t achieve acceptable performance and couldn’t be generalized to large-scale data.Deep learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer vision.However,the task of instance segmentation is currently less explored.In this paper,we propose a novel approach for efficient 3D instance segmentation using red green blue and depth(RGB-D)data based on deep learning.The 2D region based convolutional neural networks(Mask R-CNN)deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of objects.In order to generate 3D point cloud coordinates(x,y,z),segmented 2D pixels(u,v)of recognized object regions in the RGB image are merged into(u,v)points of the depth image.Moreover,we conducted an experiment and analysis to compare our proposed method from various points of view and distances.The experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.展开更多
The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.I...The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.展开更多
In order to find better simplicity measurements for 3D object recognition, a new set of local regularities is developed and tested in a stepwise 3D reconstruction method, including localized minimizing standard deviat...In order to find better simplicity measurements for 3D object recognition, a new set of local regularities is developed and tested in a stepwise 3D reconstruction method, including localized minimizing standard deviation of angles（L-MSDA）, localized minimizing standard deviation of segment magnitudes（L-MSDSM）, localized minimum standard deviation of areas of child faces （L-MSDAF）, localized minimum sum of segment magnitudes of common edges （L-MSSM）, and localized minimum sum of areas of child face （L-MSAF）. Based on their effectiveness measurements in terms of form and size distortions, it is found that when two local regularities： L-MSDA and L-MSDSM are combined together, they can produce better performance. In addition, the best weightings for them to work together are identified as 10% for L-MSDSM and 90% for L-MSDA. The test results show that the combined usage of L-MSDA and L-MSDSM with identified weightings has a potential to be applied in other optimization based 3D recognition methods to improve their efficacy and robustness.展开更多
In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection ...In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.展开更多
The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpow...The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.展开更多
LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previou...LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box positioning.To address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate information.To improve the detection accuracy,a shell-based modeling method is proposed.It roughly determines which spherical shell the coordinates belong to.Then,the results are refined to ground truth,thereby narrowing the localization range and improving the detection accuracy.To improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection structure.Some of these features are highlighted by weighting them on the feature dimensions.After training,it makes the feature weights that are favorable for object detection get larger.Thus,the extracted features are more adapted to the object detection task.Extensive comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.展开更多
Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).Howe...Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).However,the sparse and disordered nature of the 3D point cloud poses significant challenges to feature extraction.Overcoming limitations is critical for 3D point cloud processing.3D point cloud object detection is a very challenging and crucial task,in which point cloud processing and feature extraction methods play a crucial role and have a significant impact on subsequent object detection performance.In this overview of outstanding work in object detection from the 3D point cloud,we specifically focus on summarizing methods employed in 3D point cloud processing.We introduce the way point clouds are processed in classical 3D object detection algorithms,and their improvements to solve the problems existing in point cloud processing.Different voxelization methods and point cloud sampling strategies will influence the extracted features,thereby impacting the final detection performance.展开更多
Background In this work,we focus on the label layout problem:specifying the positions of overlaid virtual annotations in Virtual/Augmented Reality scenarios.Methods Designing a layout of labels that does not violate d...Background In this work,we focus on the label layout problem:specifying the positions of overlaid virtual annotations in Virtual/Augmented Reality scenarios.Methods Designing a layout of labels that does not violate domain-specific design requirements,while at the same time satisfying aesthetic and functional principles of good design,can be a daunting task even for skilled visual designers.Presenting the annotations in 3D object space instead of projection space,allows for the preservation of spatial and depth cues.This results in stable layouts in dynamic environments,since the annotations are anchored in 3D space.Results In this paper we make two major contributions.First,we propose a technique for managing the layout and rendering of annotations in Virtual/Augmented Reality scenarios by manipulating the annotations directly in 3D space.For this,we make use of Artificial Potential Fields and use 3D geometric constraints to adapt them in 3D space.Second,we introduce PartLabeling:an open source platform in the form of a web application that acts as a much-needed generic framework allowing to easily add labeling algorithms and 3D models.This serves as a catalyst for researchers in this field to make their algorithms and implementations publicly available,as well as ensure research reproducibility.The PartLabeling framework relies on a dataset that we generate as a subset of the original PartNet dataset consisting of models suitable for the label management task.The dataset consists of 10003D models with part annotations.展开更多
The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific networks.In this paper,we introduce a pretrained 3D backbone,call...The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific networks.In this paper,we introduce a pretrained 3D backbone,called Swin3D,for 3D indoor scene understanding.We designed a 3D Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and datasets.We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance.We pretrained a large Swin3D model on a synthetic Structured3D dataset,which is an order of magnitude larger than the ScanNet dataset.Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3DIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.展开更多
The perception of Bird's Eye View(BEV)has become a widely adopted approach in 3D object detection due to its spatial and dimensional consistency.However,the increasing complexity of neural network architectures ha...The perception of Bird's Eye View(BEV)has become a widely adopted approach in 3D object detection due to its spatial and dimensional consistency.However,the increasing complexity of neural network architectures has resulted in higher training memory,thereby limiting the scalability of model training.To address these challenges,we propose a novel model,RevFB-BEV,which is based on the Reversible Swin Transformer(RevSwin)with Forward-Backward View Transformation(FBVT)and LiDAR Guided Back Projection(LGBP).This approach includes the RevSwin backbone network,which employs a reversible architecture to minimise training memory by recomputing intermediate parameters.Moreover,we introduce the FBVT module that refines BEV features extracted from forward projection,yielding denser and more precise camera BEV representations.The LGBP module further utilises LiDAR BEV guidance for back projection to achieve more accurate camera BEV features.Extensive experiments on the nuScenes dataset demonstrate notable performance improvements,with our model achieving over a 4 x reduction in training memory and a more than 12x decrease in single-backbone training memory.These efficiency gains become even more pronounced with deeper network architectures.Additionally,RevFB-BEV achieves 68.1 mAP(mean Average Precision)on the validation set and 68.9 mAP on the test set,which is nearly on par with the baseline BEVFusion,underscoring its effectiveness in resource-constrained scenarios.展开更多
文摘To investigate the applicability of four commonly used color difference formulas(CIELAB,CIE94,CMC(1:1),and CIEDE2000)in the printing field on 3D objects,as well as the impact of four standard light sources(D65,D50,A,and TL84)on 3D color difference evaluations,50 glossy spheres with a diameter of 2cm based on the Sailner J4003D color printing device were created.These spheres were centered around the five recommended colors(gray,red,yellow,green,and blue)by CIE.Color difference was calculated according to the four formulas,and 111 pairs of experimental samples meeting the CIELAB gray scale color difference requirements(1.0-14.0)were selected.Ten observers,aged between 22 and 27 with normal color vision,were participated in this study,using the gray scale method from psychophysical experiments to conduct color difference evaluations under the four light sources,with repeated experiments for each observer.The results indicated that the overall effect of the D65 light source on 3D objects color difference was minimal.In contrast,D50 and A light sources had a significant impact within the small color difference range,while the TL84 light source influenced both large and small color difference considerably.Among the four color difference formulas,CIEDE2000 demonstrated the best predictive performance for color difference in 3D objects,followed by CMC(1:1),CIE94,and CIELAB.
文摘Augmented reality(AR)is an emerging dynamic technology that effectively supports education across different levels.The increased use of mobile devices has an even greater impact.As the demand for AR applications in education continues to increase,educators actively seek innovative and immersive methods to engage students in learning.However,exploring these possibilities also entails identifying and overcoming existing barriers to optimal educational integration.Concurrently,this surge in demand has prompted the identification of specific barriers,one of which is three-dimensional(3D)modeling.Creating 3D objects for augmented reality education applications can be challenging and time-consuming for the educators.To address this,we have developed a pipeline that creates realistic 3D objects from the two-dimensional(2D)photograph.Applications for augmented and virtual reality can then utilize these created 3D objects.We evaluated the proposed pipeline based on the usability of the 3D object and performance metrics.Quantitatively,with 117 respondents,the co-creation team was surveyed with openended questions to evaluate the precision of the 3D object created by the proposed photogrammetry pipeline.We analyzed the survey data using descriptive-analytical methods and found that the proposed pipeline produces 3D models that are positively accurate when compared to real-world objects,with an average mean score above 8.This study adds new knowledge in creating 3D objects for augmented reality applications by using the photogrammetry technique;finally,it discusses potential problems and future research directions for 3D objects in the education sector.
文摘This paper presents a complete system for scanning the geometry and texture of a large 3D object, then the automatic registration is performed to obtain a whole realistic 3D model. This system is composed of one line strip laser and one color CCD camera. The scanned object is pictured twice by a color CCD camera. First, the texture of the scanned object is taken by a color CCD camera. Then the 3D information of the scanned object is obtained from laser plane equations. This paper presents a practical way to implement the three dimensional measuring method and the automatic registration of a large 3D object and a pretty good result is obtained after experiment verification.
基金supported by National Natural Science Foundation of China(61673186 and 61871196)Beijing Normal University Education Reform Project(jx2024040)Guangdong Undergraduate Universities Teaching Quality and Reform Project(jx2024309).
文摘Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmentation techniques for point clouds,where global augmentation is applied to the entire point cloud of the scene,and cut-paste samples objects from other frames into the current frame.Both types of data augmentation can improve performance,but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling,which may be counterproductive and may hurt the overall performance.In addition,LiDAR is susceptible to signal loss,external occlusion,extreme weather and other factors,which can easily cause object shape changes,while global augmentation and cut-paste cannot effectively enhance the robustness of the model.To this end,we propose Syn-Aug,a synchronous data augmentation framework for LiDAR-based 3D object detection.Specifically,we first propose a novel rendering-based object augmentation technique(Ren-Aug)to enrich training data while enhancing scene realism.Second,we propose a local augmentation technique(Local-Aug)to generate local noise by rotating and scaling objects in the scene while avoiding collisions,which can improve generalisation performance.Finally,we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames.We verify the proposed framework with four different types of 3D object detectors.Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets,proving the effectiveness and generality of Syn-Aug.On KITTI,four different types of baseline models using Syn-Aug improved mAP by 0.89%,1.35%,1.61%and 1.14%respectively.On nuScenes,four different types of baseline models using Syn-Aug improved mAP by 14.93%,10.42%,8.47%and 6.81%respectively.The code is available at https://github.com/liuhuaijjin/Syn-Aug.
基金funded by the National Key R&D Program of China(Grant No.2022YFB4703400)the China Three Gorges Corporation(Grant No.2324020012)+2 种基金the National Natural Science Foundation of China(Grant No.62476080)the Jiangsu Province Natural Science Foundation(Grant No.BK20231186)Key Laboratory about Maritime Intelligent Network Information Technology of the Ministry of Education(EKLMIC202405).
文摘The inherent limitations of 2D object detection,such as inadequate spatial reasoning and susceptibility to environmental occlusions,pose significant risks to the safety and reliability of autonomous driving systems.To address these challenges,this paper proposes an enhanced 3D object detection framework(FastSECOND)based on an optimized SECOND architecture,designed to achieve rapid and accurate perception in autonomous driving scenarios.Key innovations include:(1)Replacing the Rectified Linear Unit(ReLU)activation functions with the Gaussian Error Linear Unit(GELU)during voxel feature encoding and region proposal network stages,leveraging partial convolution to balance computational efficiency and detection accuracy;(2)Integrating a Swin-Transformer V2 module into the voxel backbone network to enhance feature extraction capabilities in sparse data;and(3)Introducing an optimized position regression loss combined with a geometry-aware Focal-EIoU loss function,which incorporates bounding box geometric correlations to accelerate network convergence.While this study currently focuses exclusively on the detection of the Car category,with experiments conducted on the Car class of the KITTI dataset,future work will extend to other categories such as Pedestrian and Cyclist to more comprehensively evaluate the generalization capability of the proposed framework.Extensive experimental results demonstrate that our framework achieves a more effective trade-off between detection accuracy and speed.Compared to the baseline SECOND model,it achieves a 21.9%relative improvement in 3D bounding box detection accuracy on the hard subset,while reducing inference time by 14 ms.These advancements underscore the framework’s potential for enabling real-time,high-precision perception in autonomous driving applications.
文摘Virtual globes(VGs)allow Internet users to view geographic data of heterogeneous quality created by other users.This article presents a new approach for collecting and visualizing information about the perceived quality of 3D data in VGs.It aims atimproving users’awareness of the qualityof 3D objects.Instead of relying onthe existing metadata or on formal accuracy assessments that are often impossible in practice,we propose a crowd-sourced quality recommender system based on the five-star visualization method successful in other types of Web applications.Four alternative five-star visualizations were implemented in a Google Earth-based prototype and tested through a formal user evaluation.These tests helped identifying the most effective method for a 3D environment.Results indicate that while most websites use a visualization approach that shows a‘number of stars’,this method was the least preferred by participants.Instead,participants ranked the‘number within a star’method highest as it allowed reducing the visual clutter in urban settings,suggesting that 3D environments such as VGs require different designapproachesthan2Dornon-geographicapplications.Resultsalsoconfirmed that expert and non-expert users in geographic data share similar preferences for the most and least preferred visualization methods.
基金supported by the National Natural Science Foundation of China(GrantNo.62302086)the Natural Science Foundation of Liaoning Province(Grant No.2023-MSBA-070)the Fundamental Research Funds for the Central Universities(Grant No.N2317005).
文摘Multi-modal 3D object detection has achieved remarkable progress,but it is often limited in practical industrial production because of its high cost and low efficiency.The multi-view camera-based method provides a feasible solution due to its low cost.However,camera data lacks geometric depth,and only using camera data to obtain high accuracy is challenging.This paper proposes a multi-modal Bird-Eye-View(BEV)distillation framework(MMDistill)to make a trade-off between them.MMDistill is a carefully crafted two-stage distillation framework based on teacher and student models for learning cross-modal knowledge and generating multi-modal features.It can improve the performance of unimodal detectors without introducing additional costs during inference.Specifically,our method can effectively solve the cross-gap caused by the heterogeneity between data.Furthermore,we further propose a Light Detection and Ranging(LiDAR)-guided geometric compensation module,which can assist the student model in obtaining effective geometric features and reduce the gap between different modalities.Our proposed method generally requires fewer computational resources and faster inference speed than traditional multi-modal models.This advancement enables multi-modal technology to be applied more widely in practical scenarios.Through experiments,we validate the effectiveness and superiority of MMDistill on the nuScenes dataset,achieving an improvement of 4.1%mean Average Precision(mAP)and 4.6%NuScenes Detection Score(NDS)over the baseline detector.In addition,we also present detailed ablation studies to validate our method.
基金supported by a grant from the National Key Research and Development Project(2023YFB4302100)Key Research and Development Project of Jiangxi Province(No.20232ACE01011)Independent Deployment Project of Ganjiang Innovation Research Institute,Chinese Academy of Sciences(E255J001).
文摘Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,we propose Rail-PillarNet,a three-dimensional(3D)LIDAR(Light Detection and Ranging)railway foreign object detection method based on the improvement of PointPillars.Firstly,the parallel attention pillar encoder(PAPE)is designed to fully extract the features of the pillars and alleviate the problem of local fine-grained information loss in PointPillars pillars encoder.Secondly,a fine backbone network is designed to improve the feature extraction capability of the network by combining the coding characteristics of LIDAR point cloud feature and residual structure.Finally,the initial weight parameters of the model were optimised by the transfer learning training method to further improve accuracy.The experimental results on the OSDaR23 dataset show that the average accuracy of Rail-PillarNet reaches 58.51%,which is higher than most mainstream models,and the number of parameters is 5.49 M.Compared with PointPillars,the accuracy of each target is improved by 10.94%,3.53%,16.96%and 19.90%,respectively,and the number of parameters only increases by 0.64M,which achieves a balance between the number of parameters and accuracy.
基金supported in part by the Major Project for New Generation of AI (2018AAA0100400)the National Natural Science Foundation of China (61836014,U21B2042,62072457,62006231)the InnoHK Program。
文摘Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.
文摘3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments.It is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent basis.The computer vision,graphics,and machine learning fields have all given it a lot of attention.Traditionally,3D segmentation was done with hand-crafted features and designed approaches that didn’t achieve acceptable performance and couldn’t be generalized to large-scale data.Deep learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer vision.However,the task of instance segmentation is currently less explored.In this paper,we propose a novel approach for efficient 3D instance segmentation using red green blue and depth(RGB-D)data based on deep learning.The 2D region based convolutional neural networks(Mask R-CNN)deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of objects.In order to generate 3D point cloud coordinates(x,y,z),segmented 2D pixels(u,v)of recognized object regions in the RGB image are merged into(u,v)points of the depth image.Moreover,we conducted an experiment and analysis to compare our proposed method from various points of view and distances.The experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.
基金National Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)University Superior Discipline Construction Project of Jiangsu Province。
文摘The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.
文摘In order to find better simplicity measurements for 3D object recognition, a new set of local regularities is developed and tested in a stepwise 3D reconstruction method, including localized minimizing standard deviation of angles（L-MSDA）, localized minimizing standard deviation of segment magnitudes（L-MSDSM）, localized minimum standard deviation of areas of child faces （L-MSDAF）, localized minimum sum of segment magnitudes of common edges （L-MSSM）, and localized minimum sum of areas of child face （L-MSAF）. Based on their effectiveness measurements in terms of form and size distortions, it is found that when two local regularities： L-MSDA and L-MSDSM are combined together, they can produce better performance. In addition, the best weightings for them to work together are identified as 10% for L-MSDSM and 90% for L-MSDA. The test results show that the combined usage of L-MSDA and L-MSDSM with identified weightings has a potential to be applied in other optimization based 3D recognition methods to improve their efficacy and robustness.
基金The authors would like to thank the financial support of Natural Science Foundation of Anhui Province(No.2208085MF173)the key research and development projects of Anhui(202104a05020003)+2 种基金the anhui development and reform commission supports R&D and innovation project([2020]479)the national natural science foundation of China(51575001)Anhui university scientific research platform innovation team building project(2016-2018).
文摘In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.
基金supported by the National Key Research and Development Program of China(2020YFB1807500)the National Natural Science Foundation of China(62072360,62001357,62172438,61901367)+4 种基金the key research and development plan of Shaanxi province(2021ZDLGY02-09,2023-GHZD-44,2023-ZDLGY-54)the Natural Science Foundation of Guangdong Province of China(2022A1515010988)Key Project on Artificial Intelligence of Xi'an Science and Technology Plan(2022JH-RGZN-0003,2022JH-RGZN-0103,2022JH-CLCJ-0053)Xi'an Science and Technology Plan(20RGZN0005)the Proof-ofconcept fund from Hangzhou Research Institute of Xidian University(GNYZ2023QC0201).
文摘The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.
基金This work was supported,in part,by the National Nature Science Foundation of China under grant numbers 62272236in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box positioning.To address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate information.To improve the detection accuracy,a shell-based modeling method is proposed.It roughly determines which spherical shell the coordinates belong to.Then,the results are refined to ground truth,thereby narrowing the localization range and improving the detection accuracy.To improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection structure.Some of these features are highlighted by weighting them on the feature dimensions.After training,it makes the feature weights that are favorable for object detection get larger.Thus,the extracted features are more adapted to the object detection task.Extensive comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.
文摘Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).However,the sparse and disordered nature of the 3D point cloud poses significant challenges to feature extraction.Overcoming limitations is critical for 3D point cloud processing.3D point cloud object detection is a very challenging and crucial task,in which point cloud processing and feature extraction methods play a crucial role and have a significant impact on subsequent object detection performance.In this overview of outstanding work in object detection from the 3D point cloud,we specifically focus on summarizing methods employed in 3D point cloud processing.We introduce the way point clouds are processed in classical 3D object detection algorithms,and their improvements to solve the problems existing in point cloud processing.Different voxelization methods and point cloud sampling strategies will influence the extracted features,thereby impacting the final detection performance.
文摘Background In this work,we focus on the label layout problem:specifying the positions of overlaid virtual annotations in Virtual/Augmented Reality scenarios.Methods Designing a layout of labels that does not violate domain-specific design requirements,while at the same time satisfying aesthetic and functional principles of good design,can be a daunting task even for skilled visual designers.Presenting the annotations in 3D object space instead of projection space,allows for the preservation of spatial and depth cues.This results in stable layouts in dynamic environments,since the annotations are anchored in 3D space.Results In this paper we make two major contributions.First,we propose a technique for managing the layout and rendering of annotations in Virtual/Augmented Reality scenarios by manipulating the annotations directly in 3D space.For this,we make use of Artificial Potential Fields and use 3D geometric constraints to adapt them in 3D space.Second,we introduce PartLabeling:an open source platform in the form of a web application that acts as a much-needed generic framework allowing to easily add labeling algorithms and 3D models.This serves as a catalyst for researchers in this field to make their algorithms and implementations publicly available,as well as ensure research reproducibility.The PartLabeling framework relies on a dataset that we generate as a subset of the original PartNet dataset consisting of models suitable for the label management task.The dataset consists of 10003D models with part annotations.
文摘The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific networks.In this paper,we introduce a pretrained 3D backbone,called Swin3D,for 3D indoor scene understanding.We designed a 3D Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and datasets.We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance.We pretrained a large Swin3D model on a synthetic Structured3D dataset,which is an order of magnitude larger than the ScanNet dataset.Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3DIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.
基金supported by the Baima Lake Laboratory Joint Funds of the Zhejiang Provincial Natural Science Foundation of China under Grant LBMHD25F030001in part by NSFC No.62088101+1 种基金The authors certify that there are no competing financial interests or personal relationships influencing this work.Financial support originated exclusively from public research funds:(1)Baima Lake Laboratory Joint Funds(Zhejiang Provincial NSF,China)Grant LBMHD25F030001National Natural Science Foundation of China Grant 62088101 for the'Autonomous Intelligent Unmanned Systems'project.
文摘The perception of Bird's Eye View(BEV)has become a widely adopted approach in 3D object detection due to its spatial and dimensional consistency.However,the increasing complexity of neural network architectures has resulted in higher training memory,thereby limiting the scalability of model training.To address these challenges,we propose a novel model,RevFB-BEV,which is based on the Reversible Swin Transformer(RevSwin)with Forward-Backward View Transformation(FBVT)and LiDAR Guided Back Projection(LGBP).This approach includes the RevSwin backbone network,which employs a reversible architecture to minimise training memory by recomputing intermediate parameters.Moreover,we introduce the FBVT module that refines BEV features extracted from forward projection,yielding denser and more precise camera BEV representations.The LGBP module further utilises LiDAR BEV guidance for back projection to achieve more accurate camera BEV features.Extensive experiments on the nuScenes dataset demonstrate notable performance improvements,with our model achieving over a 4 x reduction in training memory and a more than 12x decrease in single-backbone training memory.These efficiency gains become even more pronounced with deeper network architectures.Additionally,RevFB-BEV achieves 68.1 mAP(mean Average Precision)on the validation set and 68.9 mAP on the test set,which is nearly on par with the baseline BEVFusion,underscoring its effectiveness in resource-constrained scenarios.
