Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly,meaning that skeleton s...Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly,meaning that skeleton structure information is not utilized and multi-view pose information is not completely fused.Moreover,existing graph convolutional operations do not consider the specificity of different joints and different views of pose information when processing skeleton graphs,making the correlation weights between nodes in the graph and their neighborhood nodes shared.Existing Graph Convolutional Networks(GCNs)cannot extract global and deeplevel skeleton structure information and view correlations efficiently.To solve these problems,pre-estimated multiview 2D poses are designed as a multi-view skeleton graph to fuse skeleton priors and view correlations explicitly to process occlusion problem,with the skeleton-edge and symmetry-edge representing the structure correlations between adjacent joints in each viewof skeleton graph and the view-edge representing the view correlations between the same joints in different views.To make graph convolution operation mine elaborate and sufficient skeleton structure information and view correlations,different correlation weights are assigned to different categories of neighborhood nodes and further assigned to each node in the graph.Based on the graph convolution operation proposed above,a Residual Graph Convolution(RGC)module is designed as the basic module to be combined with the simplified Hourglass architecture to construct the Hourglass-GCN as our 3D pose estimation network.Hourglass-GCNwith a symmetrical and concise architecture processes three scales ofmulti-viewskeleton graphs to extract local-to-global scale and shallow-to-deep level skeleton features efficiently.Experimental results on common large 3D pose dataset Human3.6M and MPI-INF-3DHP show that Hourglass-GCN outperforms some excellent methods in 3D pose estimation accuracy.展开更多
Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain su...Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.展开更多
This paper presents a manifold-optimized Error-State Kalman Filter(ESKF)framework for unmanned aerial vehicle(UAV)pose estimation,integrating Inertial Measurement Unit(IMU)data with GPS or LiDAR to enhance estimation ...This paper presents a manifold-optimized Error-State Kalman Filter(ESKF)framework for unmanned aerial vehicle(UAV)pose estimation,integrating Inertial Measurement Unit(IMU)data with GPS or LiDAR to enhance estimation accuracy and robustness.We employ a manifold-based optimization approach,leveraging exponential and logarithmic mappings to transform rotation vectors into rotation matrices.The proposed ESKF framework ensures state variables remain near the origin,effectively mitigating singularity issues and enhancing numerical stability.Additionally,due to the small magnitude of state variables,second-order terms can be neglected,simplifying Jacobian matrix computation and improving computational efficiency.Furthermore,we introduce a novel Kalman filter gain computation strategy that dynamically adapts to low-dimensional and high-dimensional observation equations,enabling efficient processing across different sensor modalities.Specifically,for resource-constrained UAV platforms,this method significantly reduces computational cost,making it highly suitable for real-time UAV applications.展开更多
Vision-based relative pose estimation plays a pivotal role in various space missions.Deep learning enhances monocular spacecraft pose estimation,but high computational demands necessitate model simplification for onbo...Vision-based relative pose estimation plays a pivotal role in various space missions.Deep learning enhances monocular spacecraft pose estimation,but high computational demands necessitate model simplification for onboard systems.In this paper,we aim to achieve an optimal balance between accuracy and computational efficiency.We present a Perspective-n-Point(PnP)based method for spacecraft pose estimation,leveraging lightweight neural networks to localize semantic keypoints and reduce computational load.Since the accuracy of keypoint localization is closely related to the heatmap resolution,we devise an efficient upsampling module to increase the resolution of heatmaps with minimal overhead.Furthermore,the heatmaps predicted by the lightweight models tend to show high-level noise.To tackle this issue,we propose a weighting strategy by analyzing the statistical characteristics of predicted semantic keypoints and substantially improve the pose estimation accuracy.The experiments carried out on the SPEED dataset underscore the prospect of our method in engineering applications.We dramatically reduce the model parameters to 0.7 M,merely 2.5%of that required by the top-performing method,and achieve lower pose estimation error and better real-time performance.展开更多
Pose estimation of spacecraft targets is a key technology for achieving space operation tasks,such as the cleaning of failed satellites and the detection and scanning of non-cooperative targets.This paper reviews the ...Pose estimation of spacecraft targets is a key technology for achieving space operation tasks,such as the cleaning of failed satellites and the detection and scanning of non-cooperative targets.This paper reviews the target pose estimation methods based on image feature extraction and PnP,the target estimation methods based on registration,and the spacecraft target pose estimation methods based on deep learning,and introduces the corresponding research methods.展开更多
[Objective]Fish pose estimation(FPE)provides fish physiological information,facilitating health monitoring in aquaculture.It aids decision-making in areas such as fish behavior recognition.When fish are injured or def...[Objective]Fish pose estimation(FPE)provides fish physiological information,facilitating health monitoring in aquaculture.It aids decision-making in areas such as fish behavior recognition.When fish are injured or deficient,they often display abnormal behaviors and noticeable changes in the positioning of their body parts.Moreover,the unpredictable posture and orientation of fish during swimming,combined with the rapid swimming speed of fish,restrict the current scope of research in FPE.In this research,a FPE model named HPFPE is presented to capture the swimming posture of fish and accurately detect their key points.[Methods]On the one hand,this model incorporated the CBAM module into the HRNet framework.The attention module enhanced accuracy without adding computational complexity,while effectively capturing a broader range of contextual information.On the other hand,the model incorporated dilated convolution to increase the receptive field,allowing it to capture more spatial context.[Results and Discussions]Experiments showed that compared with the baseline method,the average precision(AP)of HPFPE based on different backbones and input sizes on the oplegnathus punctatus datasets had increased by 0.62,1.35,1.76,and 1.28 percent point,respectively,while the average recall(AR)had also increased by 0.85,1.50,1.40,and 1.00,respectively.Additionally,HPFPE outperformed other mainstream methods,including DeepPose,CPM,SCNet,and Lite-HRNet.Furthermore,when compared to other methods using the ornamental fish data,HPFPE achieved the highest AP and AR values of 52.96%,and 59.50%,respectively.[Conclusions]The proposed HPFPE can accurately estimate fish posture and assess their swimming patterns,serving as a valuable reference for applications such as fish behavior recognition.展开更多
Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral method...Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral methods,most efforts on tree shrew behavior are limited to simple measures,resulting in the loss of much behavioral information.Methods:T o address this issue,we present a deep learning(DL)approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews,including drinking,eating,resting,and staying in the dark house,etc.Results:T his high-t hroughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period.Additionally,we demonstrated an innovative system with reliable apparatus,paradigms,and analysis methods for investigating food grasping behavior.The median duration for each bout of grasping was 0.20 s.Conclusion:T his study provides an efficient tool for quantifying and understand tree shrews'natural behaviors.展开更多
Human pose estimation has received much attention from the research community because of its wide range of applications.However,current research for pose estimation is usually complex and computationally intensive,esp...Human pose estimation has received much attention from the research community because of its wide range of applications.However,current research for pose estimation is usually complex and computationally intensive,especially the feature loss problems in the feature fusion process.To address the above problems,we propose a lightweight human pose estimation network based on multi-attention mechanism(LMANet).In our method,network parameters can be significantly reduced by lightweighting the bottleneck blocks with depth-wise separable convolution on the high-resolution networks.After that,we also introduce a multi-attention mechanism to improve the model prediction accuracy,and the channel attention module is added in the initial stage of the network to enhance the local cross-channel information interaction.More importantly,we inject spatial crossawareness module in the multi-scale feature fusion stage to reduce the spatial information loss during feature extraction.Extensive experiments on COCO2017 dataset and MPII dataset show that LMANet can guarantee a higher prediction accuracy with fewer network parameters and computational effort.Compared with the highresolution network HRNet,the number of parameters and the computational complexity of the network are reduced by 67%and 73%,respectively.展开更多
Human pose estimation is a challenging task in computer vision.Most algorithms perform well in regular scenes,but lack good performance in occlusion scenarios.Therefore,we propose a multi-type feature fusion network b...Human pose estimation is a challenging task in computer vision.Most algorithms perform well in regular scenes,but lack good performance in occlusion scenarios.Therefore,we propose a multi-type feature fusion network based on importance weighting,which consists of three modules.In the first module,we propose a multi-resolution backbone with two feature enhancement sub-modules,which can extract features from different scales and enhance the feature expression ability.In the second module,we enhance the expressiveness of keypoint features by suppressing obstacle features and compensating for the unique and shared attributes of keypoints and topology.In the third module,we perform importance weighting on the adjacency matrix to enable it to describe the correlation among nodes,thereby improving the feature extraction ability.We conduct comparative experiments on the keypoint detection datasets of common objects in Context 2017(COCO2017),COCO-Wholebody and CrowdPose,achieving the accuracy of 78.9%,67.1%and 77.6%,respectively.Additionally,a series of ablation experiments are designed to show the performance of our work.Finally,we present the visualization of different scenarios to verify the effectiveness of our work.展开更多
Virtual maintenance,as an important means of industrial training and education,places strict requirements on the accuracy of participant pose perception and assessment of motion standardization.However,existing resear...Virtual maintenance,as an important means of industrial training and education,places strict requirements on the accuracy of participant pose perception and assessment of motion standardization.However,existing research mainly focuses on human pose estimation in general scenarios,lacking specialized solutions for maintenance scenarios.This paper proposes a virtual maintenance human pose estimation method based on multi-scale feature enhancement(VMHPE),which integrates adaptive input feature enhancement,multi-scale feature correction for improved expression of fine movements and complex poses,and multi-scale feature fusion to enhance keypoint localization accuracy.Meanwhile,this study constructs the first virtual maintenance-specific human keypoint dataset(VMHKP),which records standard action sequences of professional maintenance personnel in five typical maintenance tasks and provides a reliable benchmark for evaluating operator motion standardization.The dataset is publicly available at.Using high-precision keypoint prediction results,an action assessment system utilizing topological structure similarity was established.Experiments show that our method achieves significant performance improvements:average precision(AP)reaches 94.4%,an increase of 2.3 percentage points over baseline methods;average recall(AR)reaches 95.6%,an increase of 1.3 percentage points.This research establishes a scientific four-level evaluation standard based on comparative motion analysis and provides a reliable solution for standardizing industrial maintenance training.展开更多
Recent multimedia and computer vision research has focused on analyzing human behavior and activity using images.Skeleton estimation,known as pose estimation,has received a significant attention.For human pose estimat...Recent multimedia and computer vision research has focused on analyzing human behavior and activity using images.Skeleton estimation,known as pose estimation,has received a significant attention.For human pose estimation,deep learning approaches primarily emphasize on the keypoint features.Conversely,in the case of occluded or incomplete poses,the keypoint feature is insufficiently substantial,especially when there are multiple humans in a single frame.Other features,such as the body border and visibility conditions,can contribute to pose estimation in addition to the keypoint feature.Our model framework integrates multiple features,namely the human body mask features,which can serve as a constraint to keypoint location estimation,the body keypoint features,and the keypoint visibility via mask region-based convolutional neural network(Mask-RCNN).A sequential multi-feature learning setup is formed to share multi-features across the structure,whereas,in the Mask-RCNN,the only feature that could be shared through the system is the region of interest feature.By two-way up-scaling with the shared weight process to produce the mask,we have addressed the problems of improper segmentation,small intrusion,and object loss when Mask-RCNN is used,for instance,segmentation.Accuracy is indicated by the percentage of correct keypoint,and our model can identify 86.1%of the correct keypoints.展开更多
Due to self-occlusion and high degree of freedom,estimating 3D hand pose from a single RGB image is a great challenging problem.Graph convolutional networks(GCNs)use graphs to describe the physical connection relation...Due to self-occlusion and high degree of freedom,estimating 3D hand pose from a single RGB image is a great challenging problem.Graph convolutional networks(GCNs)use graphs to describe the physical connection relationships between hand joints and improve the accuracy of 3D hand pose regression.However,GCNs cannot effectively describe the relationships between non-adjacent hand joints.Recently,hypergraph convolutional networks(HGCNs)have received much attention as they can describe multi-dimensional relationships between nodes through hyperedges;therefore,this paper proposes a framework for 3D hand pose estimation based on HGCN,which can better extract correlated relationships between adjacent and non-adjacent hand joints.To overcome the shortcomings of predefined hypergraph structures,a kind of dynamic hypergraph convolutional network is proposed,in which hyperedges are constructed dynamically based on hand joint feature similarity.To better explore the local semantic relationships between nodes,a kind of semantic dynamic hypergraph convolution is proposed.The proposed method is evaluated on publicly available benchmark datasets.Qualitative and quantitative experimental results both show that the proposed HGCN and improved methods for 3D hand pose estimation are better than GCN,and achieve state-of-the-art performance compared with existing methods.展开更多
Advancements in animal behavior quantification methods have driven the development of computational ethology,enabling fully automated behavior analysis.Existing multianimal pose estimation workflows rely on tracking-b...Advancements in animal behavior quantification methods have driven the development of computational ethology,enabling fully automated behavior analysis.Existing multianimal pose estimation workflows rely on tracking-bydetection frameworks for either bottom-up or top-down approaches,requiring retraining to accommodate diverse animal appearances.This study introduces InteBOMB,an integrated workflow that enhances top-down approaches by incorporating generic object tracking,eliminating the need for prior knowledge of target animals while maintaining broad generalizability.InteBOMB includes two key strategies for tracking and segmentation in laboratory environments and two techniques for pose estimation in natural settings.The“background enhancement”strategy optimizesforeground-backgroundcontrastiveloss,generating more discriminative correlation maps.The“online proofreading”strategy stores human-in-the-loop long-term memory and dynamic short-term memory,enabling adaptive updates to object visual features.The“automated labeling suggestion”technique reuses the visual features saved during tracking to identify representative frames for training set labeling.Additionally,the“joint behavior analysis”technique integrates these features with multimodal data,expanding the latent space for behavior classification and clustering.To evaluate the framework,six datasets of mice and six datasets of nonhuman primates were compiled,covering laboratory and natural scenes.Benchmarking results demonstrated a24%improvement in zero-shot generic tracking and a 21%enhancement in joint latent space performance across datasets,highlighting the effectiveness of this approach in robust,generalizable behavior analysis.展开更多
With the rapid progress of the artificial intelligence(AI)technology and mobile internet,3D hand pose estimation has become critical to various intelligent application areas,e.g.,human-computer interaction.To avoid th...With the rapid progress of the artificial intelligence(AI)technology and mobile internet,3D hand pose estimation has become critical to various intelligent application areas,e.g.,human-computer interaction.To avoid the low accuracy of single-modal estimation and the high complexity of traditional multi-modal 3D estimation,this paper proposes a novel multi-modal multi-view(MMV)3D hand pose estimation system,which introduces a registration before translation(RT)-translation before registration(TR)jointed conditional generative adversarial network(cGAN)to train a multi-modal registration network,and then employs the multi-modal feature fusion to achieve high-quality estimation,with low hardware and software costs both in data acquisition and processing.Experimental results demonstrate that the MMV system is effective and feasible in various scenarios.It is promising for the MMV system to be used in broad intelligent application areas.展开更多
The lack of autonomous aerial refueling capabilities is one of the greatest limitations of unmanned aerial vehicles. This paper discusses the vision-based estimation of the relative pose of a tanker and unmanned aeria...The lack of autonomous aerial refueling capabilities is one of the greatest limitations of unmanned aerial vehicles. This paper discusses the vision-based estimation of the relative pose of a tanker and unmanned aerial vehicle, which is a key issue in autonomous aerial refueling. The main task of this paper is to study the relative pose estimation for a tanker and unmanned aerial vehicle in the phase of commencing refueling and during refueling. The employed algorithm includes the initialization of the orientation parameters and an orthogonal iteration algorithm to estimate the optimal solution of rotation matrix and translation vector. In simulation experiments, because of the small variation in the rotation angle in aerial refueling, the method in which the initial rotation matrix is the identity matrix is found to be the most stable and accurate among methods. Finally, the paper discusses the effects of the number and configuration of feature points on the accuracy of the estimation results when using this method.展开更多
A multi-residual module stacked hourglass network(MRSH)was proposed to improve the accuracy and robustness of human body pose estimation.The network uses multiple hourglass sub-networks and three new residual modules....A multi-residual module stacked hourglass network(MRSH)was proposed to improve the accuracy and robustness of human body pose estimation.The network uses multiple hourglass sub-networks and three new residual modules.In the hourglass sub-network,the large receptive field residual module(LRFRM)and the multi-scale residual module(MSRM)are first used to learn the spatial relationship between features and body parts at various scales.Only the improved residual module(IRM)is used when the resolution is minimized.The final network uses four stacked hourglass sub-networks,with intermediate supervision at the end of each hourglass,repeating high-low(from high resolution to low resolution)and low-high(from low resolution to high resolution)learning.The network was tested on the public datasets of Leeds sports poses(LSP)and MPII human pose.The experimental results show that the proposed network has better performance in human pose estimation.展开更多
Error or drift is frequently produced in pose estimation based on geometric"feature detection and tracking"monocular visual odometry(VO)when the speed of camera movement exceeds 1.5 m/s.While,in most VO meth...Error or drift is frequently produced in pose estimation based on geometric"feature detection and tracking"monocular visual odometry(VO)when the speed of camera movement exceeds 1.5 m/s.While,in most VO methods based on deep learning,weight factors are in the form of fixed values,which are easy to lead to overfitting.A new measurement system,for monocular visual odometry,named Deep Learning Visual Odometry(DLVO),is proposed based on neural network.In this system,Convolutional Neural Network(CNN)is used to extract feature and perform feature matching.Moreover,Recurrent Neural Network(RNN)is used for sequence modeling to estimate camera’s 6-dof poses.Instead of fixed weight values of CNN,Bayesian distribution of weight factors are introduced in order to effectively solve the problem of network overfitting.The 18,726 frame images in KITTI dataset are used for training network.This system can increase the generalization ability of network model in prediction process.Compared with original Recurrent Convolutional Neural Network(RCNN),our method can reduce the loss of test model by 5.33%.And it’s an effective method in improving the robustness of translation and rotation information than traditional VO methods.展开更多
Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively u...Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively utilize multi-modal remote sensing data to break through the performance bottleneck of single-modal interpretation.In addition,semantic segmentation and height estimation in remote sensing data are two tasks with strong correlation,but existing methods usually study individual tasks separately,which leads to high computational resource overhead.To this end,we propose a Multi-Task learning framework for Multi-Modal remote sensing images(MM_MT).Specifically,we design a Cross-Modal Feature Fusion(CMFF)method,which aggregates complementary information of different modalities to improve the accuracy of semantic segmentation and height estimation.Besides,a dual-stream multi-task learning method is introduced for Joint Semantic Segmentation and Height Estimation(JSSHE),extracting common features in a shared network to save time and resources,and then learning task-specific features in two task branches.Experimental results on the public multi-modal remote sensing image dataset Potsdam show that compared to training two tasks independently,multi-task learning saves 20%of training time and achieves competitive performance with mIoU of 83.02%for semantic segmentation and accuracy of 95.26%for height estimation.展开更多
In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interac...In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interaction(HOI)is important in terms of visual relationship detection and human pose estimation.Activities understanding and interaction recognition between human and object along with the pose estimation and interaction modeling have been explained.Some existing algorithms and feature extraction procedures are complicated including accurate detection of rare human postures,occluded regions,and unsatisfactory detection of objects,especially small-sized objects.The existing HOI detection techniques are instancecentric(object-based)where interaction is predicted between all the pairs.Such estimation depends on appearance features and spatial information.Therefore,we propose a novel approach to demonstrate that the appearance features alone are not sufficient to predict the HOI.Furthermore,we detect the human body parts by using the Gaussian Matric Model(GMM)followed by object detection using YOLO.We predict the interaction points which directly classify the interaction and pair them with densely predicted HOI vectors by using the interaction algorithm.The interactions are linked with the human and object to predict the actions.The experiments have been performed on two benchmark HOI datasets demonstrating the proposed approach.展开更多
Controlling multiple multi-joint fish-like robots has long captivated the attention of engineers and biologists,for which a fundamental but challenging topic is to robustly track the postures of the individuals in rea...Controlling multiple multi-joint fish-like robots has long captivated the attention of engineers and biologists,for which a fundamental but challenging topic is to robustly track the postures of the individuals in real time.This requires detecting multiple robots,estimating multi-joint postures,and tracking identities,as well as processing fast in real time.To the best of our knowledge,this challenge has not been tackled in the previous studies.In this paper,to precisely track the planar postures of multiple swimming multi-joint fish-like robots in real time,we propose a novel deep neural network-based method,named TAB-IOL.Its TAB part fuses the top-down and bottom-up approaches for vision-based pose estimation,while the IOL part with long short-term memory considers the motion constraints among joints for precise pose tracking.The satisfying performance of our TAB-IOL is verified by testing on a group of freely swimming fish-like robots in various scenarios with strong disturbances and by a deed comparison of accuracy,speed,and robustness with most state-of-the-art algorithms.Further,based on the precise pose estimation and tracking realized by our TAB-IOL,several formation control experiments are conducted for the group of fish-like robots.The results clearly demonstrate that our TAB-IOL lays a solid foundation for the coordination control of multiple fish-like robots in a real working environment.We believe our proposed method will facilitate the growth and development of related fields.展开更多
基金supported in part by the National Natural Science Foundation of China under Grants 61973065,U20A20197,61973063.
文摘Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly,meaning that skeleton structure information is not utilized and multi-view pose information is not completely fused.Moreover,existing graph convolutional operations do not consider the specificity of different joints and different views of pose information when processing skeleton graphs,making the correlation weights between nodes in the graph and their neighborhood nodes shared.Existing Graph Convolutional Networks(GCNs)cannot extract global and deeplevel skeleton structure information and view correlations efficiently.To solve these problems,pre-estimated multiview 2D poses are designed as a multi-view skeleton graph to fuse skeleton priors and view correlations explicitly to process occlusion problem,with the skeleton-edge and symmetry-edge representing the structure correlations between adjacent joints in each viewof skeleton graph and the view-edge representing the view correlations between the same joints in different views.To make graph convolution operation mine elaborate and sufficient skeleton structure information and view correlations,different correlation weights are assigned to different categories of neighborhood nodes and further assigned to each node in the graph.Based on the graph convolution operation proposed above,a Residual Graph Convolution(RGC)module is designed as the basic module to be combined with the simplified Hourglass architecture to construct the Hourglass-GCN as our 3D pose estimation network.Hourglass-GCNwith a symmetrical and concise architecture processes three scales ofmulti-viewskeleton graphs to extract local-to-global scale and shallow-to-deep level skeleton features efficiently.Experimental results on common large 3D pose dataset Human3.6M and MPI-INF-3DHP show that Hourglass-GCN outperforms some excellent methods in 3D pose estimation accuracy.
基金supported in part by the National Natural Science Foundation of China under Grants 62071345。
文摘Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.
基金National Natural Science Foundation of China(Grant No.62266045)National Science and Technology Major Project of China(No.2022YFE0138600)。
文摘This paper presents a manifold-optimized Error-State Kalman Filter(ESKF)framework for unmanned aerial vehicle(UAV)pose estimation,integrating Inertial Measurement Unit(IMU)data with GPS or LiDAR to enhance estimation accuracy and robustness.We employ a manifold-based optimization approach,leveraging exponential and logarithmic mappings to transform rotation vectors into rotation matrices.The proposed ESKF framework ensures state variables remain near the origin,effectively mitigating singularity issues and enhancing numerical stability.Additionally,due to the small magnitude of state variables,second-order terms can be neglected,simplifying Jacobian matrix computation and improving computational efficiency.Furthermore,we introduce a novel Kalman filter gain computation strategy that dynamically adapts to low-dimensional and high-dimensional observation equations,enabling efficient processing across different sensor modalities.Specifically,for resource-constrained UAV platforms,this method significantly reduces computational cost,making it highly suitable for real-time UAV applications.
基金co-supported by the National Natural Science Foundation of China(Nos.12302252 and 12472189)the Research Program of National University of Defense Technology,China(No.ZK24-31).
文摘Vision-based relative pose estimation plays a pivotal role in various space missions.Deep learning enhances monocular spacecraft pose estimation,but high computational demands necessitate model simplification for onboard systems.In this paper,we aim to achieve an optimal balance between accuracy and computational efficiency.We present a Perspective-n-Point(PnP)based method for spacecraft pose estimation,leveraging lightweight neural networks to localize semantic keypoints and reduce computational load.Since the accuracy of keypoint localization is closely related to the heatmap resolution,we devise an efficient upsampling module to increase the resolution of heatmaps with minimal overhead.Furthermore,the heatmaps predicted by the lightweight models tend to show high-level noise.To tackle this issue,we propose a weighting strategy by analyzing the statistical characteristics of predicted semantic keypoints and substantially improve the pose estimation accuracy.The experiments carried out on the SPEED dataset underscore the prospect of our method in engineering applications.We dramatically reduce the model parameters to 0.7 M,merely 2.5%of that required by the top-performing method,and achieve lower pose estimation error and better real-time performance.
文摘Pose estimation of spacecraft targets is a key technology for achieving space operation tasks,such as the cleaning of failed satellites and the detection and scanning of non-cooperative targets.This paper reviews the target pose estimation methods based on image feature extraction and PnP,the target estimation methods based on registration,and the spacecraft target pose estimation methods based on deep learning,and introduces the corresponding research methods.
文摘[Objective]Fish pose estimation(FPE)provides fish physiological information,facilitating health monitoring in aquaculture.It aids decision-making in areas such as fish behavior recognition.When fish are injured or deficient,they often display abnormal behaviors and noticeable changes in the positioning of their body parts.Moreover,the unpredictable posture and orientation of fish during swimming,combined with the rapid swimming speed of fish,restrict the current scope of research in FPE.In this research,a FPE model named HPFPE is presented to capture the swimming posture of fish and accurately detect their key points.[Methods]On the one hand,this model incorporated the CBAM module into the HRNet framework.The attention module enhanced accuracy without adding computational complexity,while effectively capturing a broader range of contextual information.On the other hand,the model incorporated dilated convolution to increase the receptive field,allowing it to capture more spatial context.[Results and Discussions]Experiments showed that compared with the baseline method,the average precision(AP)of HPFPE based on different backbones and input sizes on the oplegnathus punctatus datasets had increased by 0.62,1.35,1.76,and 1.28 percent point,respectively,while the average recall(AR)had also increased by 0.85,1.50,1.40,and 1.00,respectively.Additionally,HPFPE outperformed other mainstream methods,including DeepPose,CPM,SCNet,and Lite-HRNet.Furthermore,when compared to other methods using the ornamental fish data,HPFPE achieved the highest AP and AR values of 52.96%,and 59.50%,respectively.[Conclusions]The proposed HPFPE can accurately estimate fish posture and assess their swimming patterns,serving as a valuable reference for applications such as fish behavior recognition.
基金supported by grants from the National Key Research and Development Program of China(2023YFF0724902)the China Postdoctoral Science Foundation(2020?M670027,2023TQ0183)the Local Standards Research of BeiJing Laboratory Tree Shrew(CHYX-2023-DGB001)。
文摘Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral methods,most efforts on tree shrew behavior are limited to simple measures,resulting in the loss of much behavioral information.Methods:T o address this issue,we present a deep learning(DL)approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews,including drinking,eating,resting,and staying in the dark house,etc.Results:T his high-t hroughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period.Additionally,we demonstrated an innovative system with reliable apparatus,paradigms,and analysis methods for investigating food grasping behavior.The median duration for each bout of grasping was 0.20 s.Conclusion:T his study provides an efficient tool for quantifying and understand tree shrews'natural behaviors.
基金the National Natural Science Foundation of China(Nos.61775139,62072126,61772164,and 61872242)。
文摘Human pose estimation has received much attention from the research community because of its wide range of applications.However,current research for pose estimation is usually complex and computationally intensive,especially the feature loss problems in the feature fusion process.To address the above problems,we propose a lightweight human pose estimation network based on multi-attention mechanism(LMANet).In our method,network parameters can be significantly reduced by lightweighting the bottleneck blocks with depth-wise separable convolution on the high-resolution networks.After that,we also introduce a multi-attention mechanism to improve the model prediction accuracy,and the channel attention module is added in the initial stage of the network to enhance the local cross-channel information interaction.More importantly,we inject spatial crossawareness module in the multi-scale feature fusion stage to reduce the spatial information loss during feature extraction.Extensive experiments on COCO2017 dataset and MPII dataset show that LMANet can guarantee a higher prediction accuracy with fewer network parameters and computational effort.Compared with the highresolution network HRNet,the number of parameters and the computational complexity of the network are reduced by 67%and 73%,respectively.
基金supported by Ministry of Education Industry-University Cooperation and Collaborative Education Project(China)(220603231024713).
文摘Human pose estimation is a challenging task in computer vision.Most algorithms perform well in regular scenes,but lack good performance in occlusion scenarios.Therefore,we propose a multi-type feature fusion network based on importance weighting,which consists of three modules.In the first module,we propose a multi-resolution backbone with two feature enhancement sub-modules,which can extract features from different scales and enhance the feature expression ability.In the second module,we enhance the expressiveness of keypoint features by suppressing obstacle features and compensating for the unique and shared attributes of keypoints and topology.In the third module,we perform importance weighting on the adjacency matrix to enable it to describe the correlation among nodes,thereby improving the feature extraction ability.We conduct comparative experiments on the keypoint detection datasets of common objects in Context 2017(COCO2017),COCO-Wholebody and CrowdPose,achieving the accuracy of 78.9%,67.1%and 77.6%,respectively.Additionally,a series of ablation experiments are designed to show the performance of our work.Finally,we present the visualization of different scenarios to verify the effectiveness of our work.
基金funded by the Joint Development Project with Pharmapack Technologies Corporation:Open Multi-Person Collaborative Virtual Assembly/Disassembly Training and Virtual Engineering Visualization Platform,Grant Number 23HK0101.
文摘Virtual maintenance,as an important means of industrial training and education,places strict requirements on the accuracy of participant pose perception and assessment of motion standardization.However,existing research mainly focuses on human pose estimation in general scenarios,lacking specialized solutions for maintenance scenarios.This paper proposes a virtual maintenance human pose estimation method based on multi-scale feature enhancement(VMHPE),which integrates adaptive input feature enhancement,multi-scale feature correction for improved expression of fine movements and complex poses,and multi-scale feature fusion to enhance keypoint localization accuracy.Meanwhile,this study constructs the first virtual maintenance-specific human keypoint dataset(VMHKP),which records standard action sequences of professional maintenance personnel in five typical maintenance tasks and provides a reliable benchmark for evaluating operator motion standardization.The dataset is publicly available at.Using high-precision keypoint prediction results,an action assessment system utilizing topological structure similarity was established.Experiments show that our method achieves significant performance improvements:average precision(AP)reaches 94.4%,an increase of 2.3 percentage points over baseline methods;average recall(AR)reaches 95.6%,an increase of 1.3 percentage points.This research establishes a scientific four-level evaluation standard based on comparative motion analysis and provides a reliable solution for standardizing industrial maintenance training.
基金the Industry-University-Research Cooperation Fund Project of the Eighth Research Institute of China Aerospace Science and Technology Corporation(No.USCAST2021-5)。
文摘Recent multimedia and computer vision research has focused on analyzing human behavior and activity using images.Skeleton estimation,known as pose estimation,has received a significant attention.For human pose estimation,deep learning approaches primarily emphasize on the keypoint features.Conversely,in the case of occluded or incomplete poses,the keypoint feature is insufficiently substantial,especially when there are multiple humans in a single frame.Other features,such as the body border and visibility conditions,can contribute to pose estimation in addition to the keypoint feature.Our model framework integrates multiple features,namely the human body mask features,which can serve as a constraint to keypoint location estimation,the body keypoint features,and the keypoint visibility via mask region-based convolutional neural network(Mask-RCNN).A sequential multi-feature learning setup is formed to share multi-features across the structure,whereas,in the Mask-RCNN,the only feature that could be shared through the system is the region of interest feature.By two-way up-scaling with the shared weight process to produce the mask,we have addressed the problems of improper segmentation,small intrusion,and object loss when Mask-RCNN is used,for instance,segmentation.Accuracy is indicated by the percentage of correct keypoint,and our model can identify 86.1%of the correct keypoints.
基金the National Key Research and Development Program of China(No.2021ZD0111902)the National Natural Science Foundation of China(Nos.62172022 and U21B2038)。
文摘Due to self-occlusion and high degree of freedom,estimating 3D hand pose from a single RGB image is a great challenging problem.Graph convolutional networks(GCNs)use graphs to describe the physical connection relationships between hand joints and improve the accuracy of 3D hand pose regression.However,GCNs cannot effectively describe the relationships between non-adjacent hand joints.Recently,hypergraph convolutional networks(HGCNs)have received much attention as they can describe multi-dimensional relationships between nodes through hyperedges;therefore,this paper proposes a framework for 3D hand pose estimation based on HGCN,which can better extract correlated relationships between adjacent and non-adjacent hand joints.To overcome the shortcomings of predefined hypergraph structures,a kind of dynamic hypergraph convolutional network is proposed,in which hyperedges are constructed dynamically based on hand joint feature similarity.To better explore the local semantic relationships between nodes,a kind of semantic dynamic hypergraph convolution is proposed.The proposed method is evaluated on publicly available benchmark datasets.Qualitative and quantitative experimental results both show that the proposed HGCN and improved methods for 3D hand pose estimation are better than GCN,and achieve state-of-the-art performance compared with existing methods.
基金supported by the STI 2030-Major Projects(2022ZD0211900,2022ZD0211902)STI 2030-Major Projects(2021ZD0204500,2021ZD0204503)+1 种基金National Natural Science Foundation of China(32171461)National Key Research and Development Program of China(2023YFC3208303)。
文摘Advancements in animal behavior quantification methods have driven the development of computational ethology,enabling fully automated behavior analysis.Existing multianimal pose estimation workflows rely on tracking-bydetection frameworks for either bottom-up or top-down approaches,requiring retraining to accommodate diverse animal appearances.This study introduces InteBOMB,an integrated workflow that enhances top-down approaches by incorporating generic object tracking,eliminating the need for prior knowledge of target animals while maintaining broad generalizability.InteBOMB includes two key strategies for tracking and segmentation in laboratory environments and two techniques for pose estimation in natural settings.The“background enhancement”strategy optimizesforeground-backgroundcontrastiveloss,generating more discriminative correlation maps.The“online proofreading”strategy stores human-in-the-loop long-term memory and dynamic short-term memory,enabling adaptive updates to object visual features.The“automated labeling suggestion”technique reuses the visual features saved during tracking to identify representative frames for training set labeling.Additionally,the“joint behavior analysis”technique integrates these features with multimodal data,expanding the latent space for behavior classification and clustering.To evaluate the framework,six datasets of mice and six datasets of nonhuman primates were compiled,covering laboratory and natural scenes.Benchmarking results demonstrated a24%improvement in zero-shot generic tracking and a 21%enhancement in joint latent space performance across datasets,highlighting the effectiveness of this approach in robust,generalizable behavior analysis.
文摘With the rapid progress of the artificial intelligence(AI)technology and mobile internet,3D hand pose estimation has become critical to various intelligent application areas,e.g.,human-computer interaction.To avoid the low accuracy of single-modal estimation and the high complexity of traditional multi-modal 3D estimation,this paper proposes a novel multi-modal multi-view(MMV)3D hand pose estimation system,which introduces a registration before translation(RT)-translation before registration(TR)jointed conditional generative adversarial network(cGAN)to train a multi-modal registration network,and then employs the multi-modal feature fusion to achieve high-quality estimation,with low hardware and software costs both in data acquisition and processing.Experimental results demonstrate that the MMV system is effective and feasible in various scenarios.It is promising for the MMV system to be used in broad intelligent application areas.
基金National Natural Science Foundation of China （51075207） Startup Foundation for Introduced Talents of Nanjing University of Aeronautics and Astronautics （1007-YAH10047）
文摘The lack of autonomous aerial refueling capabilities is one of the greatest limitations of unmanned aerial vehicles. This paper discusses the vision-based estimation of the relative pose of a tanker and unmanned aerial vehicle, which is a key issue in autonomous aerial refueling. The main task of this paper is to study the relative pose estimation for a tanker and unmanned aerial vehicle in the phase of commencing refueling and during refueling. The employed algorithm includes the initialization of the orientation parameters and an orthogonal iteration algorithm to estimate the optimal solution of rotation matrix and translation vector. In simulation experiments, because of the small variation in the rotation angle in aerial refueling, the method in which the initial rotation matrix is the identity matrix is found to be the most stable and accurate among methods. Finally, the paper discusses the effects of the number and configuration of feature points on the accuracy of the estimation results when using this method.
基金Supported by the National Natural Science Foundation of China(61401001,61501003,61672032)。
文摘A multi-residual module stacked hourglass network(MRSH)was proposed to improve the accuracy and robustness of human body pose estimation.The network uses multiple hourglass sub-networks and three new residual modules.In the hourglass sub-network,the large receptive field residual module(LRFRM)and the multi-scale residual module(MSRM)are first used to learn the spatial relationship between features and body parts at various scales.Only the improved residual module(IRM)is used when the resolution is minimized.The final network uses four stacked hourglass sub-networks,with intermediate supervision at the end of each hourglass,repeating high-low(from high resolution to low resolution)and low-high(from low resolution to high resolution)learning.The network was tested on the public datasets of Leeds sports poses(LSP)and MPII human pose.The experimental results show that the proposed network has better performance in human pose estimation.
基金supported by National Key R&D Plan(2017YFB1301104),NSFC(61877040,61772351)Sci-Tech Innovation Fundamental Scientific Research Funds(025195305000)(19210010005),academy for multidisciplinary study of Capital Normal University。
文摘Error or drift is frequently produced in pose estimation based on geometric"feature detection and tracking"monocular visual odometry(VO)when the speed of camera movement exceeds 1.5 m/s.While,in most VO methods based on deep learning,weight factors are in the form of fixed values,which are easy to lead to overfitting.A new measurement system,for monocular visual odometry,named Deep Learning Visual Odometry(DLVO),is proposed based on neural network.In this system,Convolutional Neural Network(CNN)is used to extract feature and perform feature matching.Moreover,Recurrent Neural Network(RNN)is used for sequence modeling to estimate camera’s 6-dof poses.Instead of fixed weight values of CNN,Bayesian distribution of weight factors are introduced in order to effectively solve the problem of network overfitting.The 18,726 frame images in KITTI dataset are used for training network.This system can increase the generalization ability of network model in prediction process.Compared with original Recurrent Convolutional Neural Network(RCNN),our method can reduce the loss of test model by 5.33%.And it’s an effective method in improving the robustness of translation and rotation information than traditional VO methods.
基金National Key R&D Program of China(No.2022ZD0118401).
文摘Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively utilize multi-modal remote sensing data to break through the performance bottleneck of single-modal interpretation.In addition,semantic segmentation and height estimation in remote sensing data are two tasks with strong correlation,but existing methods usually study individual tasks separately,which leads to high computational resource overhead.To this end,we propose a Multi-Task learning framework for Multi-Modal remote sensing images(MM_MT).Specifically,we design a Cross-Modal Feature Fusion(CMFF)method,which aggregates complementary information of different modalities to improve the accuracy of semantic segmentation and height estimation.Besides,a dual-stream multi-task learning method is introduced for Joint Semantic Segmentation and Height Estimation(JSSHE),extracting common features in a shared network to save time and resources,and then learning task-specific features in two task branches.Experimental results on the public multi-modal remote sensing image dataset Potsdam show that compared to training two tasks independently,multi-task learning saves 20%of training time and achieves competitive performance with mIoU of 83.02%for semantic segmentation and accuracy of 95.26%for height estimation.
基金supported by Priority Research Centers Program through NRF funded by MEST(2018R1A6A1A03024003)the Grand Information Technology Research Center support program IITP-2020-2020-0-01612 supervised by the IITP by MSIT,Korea.
文摘In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interaction(HOI)is important in terms of visual relationship detection and human pose estimation.Activities understanding and interaction recognition between human and object along with the pose estimation and interaction modeling have been explained.Some existing algorithms and feature extraction procedures are complicated including accurate detection of rare human postures,occluded regions,and unsatisfactory detection of objects,especially small-sized objects.The existing HOI detection techniques are instancecentric(object-based)where interaction is predicted between all the pairs.Such estimation depends on appearance features and spatial information.Therefore,we propose a novel approach to demonstrate that the appearance features alone are not sufficient to predict the HOI.Furthermore,we detect the human body parts by using the Gaussian Matric Model(GMM)followed by object detection using YOLO.We predict the interaction points which directly classify the interaction and pair them with densely predicted HOI vectors by using the interaction algorithm.The interactions are linked with the human and object to predict the actions.The experiments have been performed on two benchmark HOI datasets demonstrating the proposed approach.
基金This work was supported in part by the National Natural Science Foundation of China(61973007,61633002).
文摘Controlling multiple multi-joint fish-like robots has long captivated the attention of engineers and biologists,for which a fundamental but challenging topic is to robustly track the postures of the individuals in real time.This requires detecting multiple robots,estimating multi-joint postures,and tracking identities,as well as processing fast in real time.To the best of our knowledge,this challenge has not been tackled in the previous studies.In this paper,to precisely track the planar postures of multiple swimming multi-joint fish-like robots in real time,we propose a novel deep neural network-based method,named TAB-IOL.Its TAB part fuses the top-down and bottom-up approaches for vision-based pose estimation,while the IOL part with long short-term memory considers the motion constraints among joints for precise pose tracking.The satisfying performance of our TAB-IOL is verified by testing on a group of freely swimming fish-like robots in various scenarios with strong disturbances and by a deed comparison of accuracy,speed,and robustness with most state-of-the-art algorithms.Further,based on the precise pose estimation and tracking realized by our TAB-IOL,several formation control experiments are conducted for the group of fish-like robots.The results clearly demonstrate that our TAB-IOL lays a solid foundation for the coordination control of multiple fish-like robots in a real working environment.We believe our proposed method will facilitate the growth and development of related fields.
