To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determ...To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determining the position of the grasping information.These results can then be used to guide the visually impaired or to execute grasping tasks with a robotic arm.In this paper,we collected,annotated,and published the benchmark TQUGraspingObject dataset for testing,validation,and evaluation of deep learning(DL)models for detecting,recognizing,and localizing grasping objects in 2D and 3D space,especially 3D point cloud data.Our dataset is collected in a shared room,with common everyday objects placed on the tabletop in jumbled positions by Intel RealSense D435(IR-D435).This dataset includes more than 63k RGB-D pairs and related data such as normalized 3D object point cloud,3D object point cloud segmented,coordinate system normalizationmatrix,3D object point cloud normalized,and hand pose for grasping each object.At the same time,we also conducted experiments on fourDL networks with the best performance:SSD-MobileNetV3,ResNet50-Transformer,ResNet101-Transformer,and YOLOv12.The results present that YOLOv12 has the most suitable results in detecting and recognizing objects in images.All data,annotations,toolkit,source code,point cloud data,and results are publicly available on our project website:https://github.com/HuaTThanhIT2327Tqu/datasetv2.展开更多
Discontinuities in rock masses critically impact the stability and safety of underground engineering.Mainstream discontinuities identificationmethods,which rely on normal vector estimation and clustering algorithms,su...Discontinuities in rock masses critically impact the stability and safety of underground engineering.Mainstream discontinuities identificationmethods,which rely on normal vector estimation and clustering algorithms,suffer from accuracy degradation,omission of critical discontinuities when orientation density is unevenly distributed,and need manual intervention.To overcome these limitations,this paper introduces a novel discontinuities identificationmethod based on geometric feature analysis of rock mass.By analyzing spatial distribution variability of point cloud and integrating an adaptive region growing algorithm,the method accurately detects independent discontinuities under complex geological conditions.Given that rock mass orientations typically follow a Fisher distribution,an adaptive hierarchical clustering algorithm based on statistical analysis is employed to automatically determine the optimal number of structural sets,eliminating the need for preset clusters or thresholds inherent in traditional methods.The proposed approach effectively handles diverse rock mass shapes and sizes,leveraging both local and global geometric features to minimize noise interference.Experimental validation on three real-world rock mass models,alongside comparisons with three conventional directional clustering algorithms,demonstrates superior accuracy and robustness in identifying optimal discontinuity sets.The proposed method offers a reliable and efficienttool for discontinuities detection and grouping in underground engineering,significantlyenhancing design and construction outcomes.展开更多
Human object detection and recognition is essential for elderly monitoring and assisted living however,models relying solely on pose or scene context often struggle in cluttered or visually ambiguous settings.To addre...Human object detection and recognition is essential for elderly monitoring and assisted living however,models relying solely on pose or scene context often struggle in cluttered or visually ambiguous settings.To address this,we present SCENET-3D,a transformer-drivenmultimodal framework that unifies human-centric skeleton features with scene-object semantics for intelligent robotic vision through a three-stage pipeline.In the first stage,scene analysis,rich geometric and texture descriptors are extracted from RGB frames,including surface-normal histograms,angles between neighboring normals,Zernike moments,directional standard deviation,and Gabor-filter responses.In the second stage,scene-object analysis,non-human objects are segmented and represented using local feature descriptors and complementary surface-normal information.In the third stage,human-pose estimation,silhouettes are processed through an enhanced MoveNet to obtain 2D anatomical keypoints,which are fused with depth information and converted into RGB-based point clouds to construct pseudo-3D skeletons.Features from all three stages are fused and fed in a transformer encoder with multi-head attention to resolve visually similar activities.Experiments on UCLA(95.8%),ETRI-Activity3D(89.4%),andCAD-120(91.2%)demonstrate that combining pseudo-3D skeletonswith rich scene-object fusion significantly improves generalizable activity recognition,enabling safer elderly care,natural human–robot interaction,and robust context-aware robotic perception in real-world environments.展开更多
Flatness pattern recognition is the key of the flatness control. The accuracy of the present flatness pattern recognition is limited and the shape defects cannot be reflected intuitively. In order to improve it, a nov...Flatness pattern recognition is the key of the flatness control. The accuracy of the present flatness pattern recognition is limited and the shape defects cannot be reflected intuitively. In order to improve it, a novel method via T-S cloud inference network optimized by genetic algorithm(GA) is proposed. T-S cloud inference network is constructed with T-S fuzzy neural network and the cloud model. So, the rapid of fuzzy logic and the uncertainty of cloud model for processing data are both taken into account. What's more, GA possesses good parallel design structure and global optimization characteristics. Compared with the simulation recognition results of traditional BP Algorithm, GA is more accurate and effective. Moreover, virtual reality technology is introduced into the field of shape control by Lab VIEW, MATLAB mixed programming. And virtual flatness pattern recognition interface is designed.Therefore, the data of engineering analysis and the actual model are combined with each other, and the shape defects could be seen more lively and intuitively.展开更多
This paper presents a method for hand gesture recognition based on 3D point cloud. Digital image processing technology is used in this research. Based on the 3D point from depth camera, the system firstly extracts som...This paper presents a method for hand gesture recognition based on 3D point cloud. Digital image processing technology is used in this research. Based on the 3D point from depth camera, the system firstly extracts some raw data of the hand. After the data segmentation and preprocessing, three kinds of appearance features are extracted, including the number of stretched fingers, the angles between fingers and the gesture region’s area distribution feature. Based on these features, the system implements the identification of the gestures by using decision tree method. The results of experiment demonstrate that the proposed method is pretty efficient to recognize common gestures with a high accuracy.展开更多
Snow cover plays a critical role in global climate regulation and hydrological processes.Accurate monitoring is essential for understanding snow distribution patterns,managing water resources,and assessing the impacts...Snow cover plays a critical role in global climate regulation and hydrological processes.Accurate monitoring is essential for understanding snow distribution patterns,managing water resources,and assessing the impacts of climate change.Remote sensing has become a vital tool for snow monitoring,with the widely used Moderate-resolution Imaging Spectroradiometer(MODIS)snow products from the Terra and Aqua satellites.However,cloud cover often interferes with snow detection,making cloud removal techniques crucial for reliable snow product generation.This study evaluated the accuracy of four MODIS snow cover datasets generated through different cloud removal algorithms.Using real-time field camera observations from four stations in the Tianshan Mountains,China,this study assessed the performance of these datasets during three distinct snow periods:the snow accumulation period(September-November),snowmelt period(March-June),and stable snow period(December-February in the following year).The findings showed that cloud-free snow products generated using the Hidden Markov Random Field(HMRF)algorithm consistently outperformed the others,particularly under cloud cover,while cloud-free snow products using near-day synthesis and the spatiotemporal adaptive fusion method with error correction(STAR)demonstrated varying performance depending on terrain complexity and cloud conditions.This study highlighted the importance of considering terrain features,land cover types,and snow dynamics when selecting cloud removal methods,particularly in areas with rapid snow accumulation and melting.The results suggested that future research should focus on improving cloud removal algorithms through the integration of machine learning,multi-source data fusion,and advanced remote sensing technologies.By expanding validation efforts and refining cloud removal strategies,more accurate and reliable snow products can be developed,contributing to enhanced snow monitoring and better management of water resources in alpine and arid areas.展开更多
3D laser scanning technology is widely used in underground openings for high-precision,rapid,and nondestructive structural evaluations.Segmenting large 3D point cloud datasets,particularly in coal mine roadways with m...3D laser scanning technology is widely used in underground openings for high-precision,rapid,and nondestructive structural evaluations.Segmenting large 3D point cloud datasets,particularly in coal mine roadways with multi-scale targets,remains challenging.This paper proposes an enhanced segmentation method integrating improved PointNet++with a coverage-voted strategy.The coverage-voted strategy reduces data while preserving multi-scale target topology.The segmentation is achieved using an enhanced PointNet++algorithm with a normalization preprocessing head,resulting in a 94%accuracy for common supporting components.Ablation experiments show that the preprocessing head and coverage strategies increase segmentation accuracy by 20%and 2%,respectively,and improve Intersection over Union(IoU)for bearing plate segmentation by 58%and 20%.The accuracy of the current pretraining segmentation model may be affected by variations in surface support components,but it can be readily enhanced through re-optimization with additional labeled point cloud data.This proposed method,combined with a previously developed machine learning model that links rock bolt load and the deformation field of its bearing plate,provides a robust technique for simultaneously measuring the load of multiple rock bolts in a single laser scan.展开更多
It is very important to locate and track weather systems which cause severe calamity,such as severeconvective clouds (SCC),in nowcasting. In this paper the recognition and tracking of SCC is studied withGMS IR images ...It is very important to locate and track weather systems which cause severe calamity,such as severeconvective clouds (SCC),in nowcasting. In this paper the recognition and tracking of SCC is studied withGMS IR images using computer image techniques. As an IR image preprocessing, a SCC futerlng algorithm is put forward that combines a segment smoothing filtering and a removal procedure by thresholds. To the filtered SCCs the T algorithm and IP algorithm of contour coding method are applied to extract the contour line and its initial point. The description of SCCs includes four characteristic quanti-ties, i. e. center of gravity, cloud size, moment invariant M and R-shaped descriptor. Pattern recosnitionand pattern matching techniques are used to track the SCCs. Two procedures of rough and fine matchingare given. The former procedure include the setting of searching area and recognition of area and the latter is composed by the matching of shape descriptor R and moment invariant M and the analysis of correlative brightness temperature analysis.展开更多
Point cloud based place recognition plays an important role in mobile robotics. In this paper, we propose a weighted aggregation method from structure information adaptively for point cloud place recognition. Firstly,...Point cloud based place recognition plays an important role in mobile robotics. In this paper, we propose a weighted aggregation method from structure information adaptively for point cloud place recognition. Firstly, to preserve the prior distributions and local geometric structures, we fuse learned hidden features with handcrafted features in the beginning. Secondly, we further extract and aggregate adaptively weighted features concerning density and relative spatial information from these fused features, named Weighted Aggregation with Density Estimation (WADE) module. Then, we conduct the WADE block iteratively to group the latent manifold structures. Finally, comparison results on two public datasets Oxford Robotcar and KITTI show that the proposed approach exceeds the comparison approaches on recall rate averagely 7% - 8%.展开更多
The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was ...The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system.展开更多
Because of similar reflective characteristics of snow and cloud, the weather status seriously affects snow monitoring using optical remote sensing data. Cloud amount analysis during 2010 to 2011 snow seasons shows tha...Because of similar reflective characteristics of snow and cloud, the weather status seriously affects snow monitoring using optical remote sensing data. Cloud amount analysis during 2010 to 2011 snow seasons shows that cloud cover is the major limitation for snow cover monitoring using MOD10A1 and MYD10A1. By use of MODIS daily snow cover products and AMSR-E snow wa- ter equivalent products （SWE）, several cloud elimination methods were integrated to produce a new daily cloud flee snow cover product, and information of snow depth from 85 climate stations in Tibetan Plateau area （TP） were used to validate the accuracy of the new composite snow cover product. The results indicate that snow classification accuracy of the new daily snow cover product reaches 91.7% when snow depth is over 3 cm. This suggests that the new daily snow cover mapping algorithm is suitable for monitoring snow cover dynamic changes in TP.展开更多
The snow enhancement experiments, carried out by injecting AgI and water vapor into orographically enhanced clouds （fog）, have been conducted to confirm Li and Pitter＇s forced condensation process in a natural situ...The snow enhancement experiments, carried out by injecting AgI and water vapor into orographically enhanced clouds （fog）, have been conducted to confirm Li and Pitter＇s forced condensation process in a natural situation. Nine ground-based experiments have been conducted at Daegwallyeong in the Taebaek Mountains for the easterly foggy days from January-February 2006. We then obtained the optimized conditions for the Daegwallyeong region as follows： the small seeding rate （1.04 g min-1） of AgI for the easterly cold fog with the high humidity of Gangneung. Additional experiments are needed to statistically estimate the snowfall increment caused by the small AgI seeding into the orographical fog （cloud） over the Taeback Mountains.展开更多
Airborne LIDAR can flexibly obtain point cloud data with three-dimensional structural information,which can improve its effectiveness of automatic target recognition in the complex environment.Compared with 2D informa...Airborne LIDAR can flexibly obtain point cloud data with three-dimensional structural information,which can improve its effectiveness of automatic target recognition in the complex environment.Compared with 2D information,3D information performs better in separating objects and background.However,an aircraft platform can have a negative influence on LIDAR obtained data because of various flight attitudes,flight heights and atmospheric disturbances.A structure of global feature based 3D automatic target recognition method for airborne LIDAR is proposed,which is composed of offline phase and online phase.The performance of four global feature descriptors is compared.Considering the summed volume region(SVR) discrepancy in real objects,SVR selection is added into the pre-processing operations to eliminate mismatching clusters compared with the interested target.Highly reliable simulated data are obtained under various sensor’s altitudes,detection distances and atmospheric disturbances.The final experiments results show that the added step increases the recognition rate by above 2.4% and decreases the execution time by about 33%.展开更多
Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes,there still exist some challenges in the debris recognition of terrain data.Compared with hundreds of thousands of i...Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes,there still exist some challenges in the debris recognition of terrain data.Compared with hundreds of thousands of indoor point clouds,the amount of terrain point cloud is up to millions.Apart from that,terrain point cloud data obtained from remote sensing is measured in meters,but the indoor scene is measured in centimeters.In this case,the terrain debris obtained from remote sensing mapping only have dozens of points,which means that sufficient training information cannot be obtained only through the convolution of points.In this paper,we build multi-attribute descriptors containing geometric information and color information to better describe the information in low-precision terrain debris.Therefore,our process is aimed at the multi-attribute descriptors of each point rather than the point.On this basis,an unsupervised classification algorithm is proposed to divide the point cloud into several terrain areas,and regard each area as a graph vertex named super point to form the graph structure,thus effectively reducing the number of the terrain point cloud from millions to hundreds.Then we proposed a graph convolution network by employing PointNet for graph embedding and recurrent gated graph convolutional network for classification.Our experiments show that the terrain point cloud can reduce the amount of data from millions to hundreds through the super point graph based on multi-attribute descriptor and our accuracy reached 91.74%and the IoU reached 94.08%,both of which were significantly better than the current methods such as SEGCloud(Acc:88.63%,IoU:89.29%)and PointCNN(Acc:86.35,IoU:87.26).展开更多
With the development of computation technology,the augmented reality(AR)is widely applied in many fields as well as the image recognition.However,the AR application on mobile platform is not developed enough in the pa...With the development of computation technology,the augmented reality(AR)is widely applied in many fields as well as the image recognition.However,the AR application on mobile platform is not developed enough in the past decades due to the capability of the mobile processors.In recent years,the performance of mobile processors has changed rapidly,which makes it comparable to the desktop processors.This paper proposed and realized an AR system to be used on the Android mobile platform based on the image recognition through EasyAR engine and Unity 3D development tools.In this system,the image recognition could be done locally and/or using cloud recognition.Test results show that the cloud-based recognition is more efficient and accuracy than the local recognition for the mobile AR when there are more images to be recognized at the same time.展开更多
Understanding the conformational characteristics of polymers is key to elucidating their physical properties.Cyclic polymers,defined by their closed-loop structures,inherently differ from linear polymers possessing di...Understanding the conformational characteristics of polymers is key to elucidating their physical properties.Cyclic polymers,defined by their closed-loop structures,inherently differ from linear polymers possessing distinct chain ends.Despite these structural differences,both types of polymers exhibit locally random-walk-like conformations,making it challenging to detect subtle spatial variations using conventional methods.In this study,we address this challenge by integrating molecular dynamics simulations with point cloud neural networks to analyze the spatial conformations of cyclic and linear polymers.By utilizing the Dynamic Graph CNN(DGCNN)model,we classify polymer conformations based on the 3D coordinates of monomers,capturing local and global topological differences without considering chain connectivity sequentiality.Our findings reveal that the optimal local structural feature unit size scales linearly with molecular weight,aligning with theoretical predictions.Additionally,interpretability techniques such as Grad-CAM and SHAP identify significant conformational differences:cyclic polymers tend to form prolate ellipsoid shapes with pronounced elongation along the major axis,while linear polymers show elongated ends with more spherical centers.These findings reveal subtle yet critical differences in local conformations between cyclic and linear polymers that were previously difficult to discern,providing deeper insights into polymer structure-property relationships and offering guidance for future polymer science advancements.展开更多
文摘To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determining the position of the grasping information.These results can then be used to guide the visually impaired or to execute grasping tasks with a robotic arm.In this paper,we collected,annotated,and published the benchmark TQUGraspingObject dataset for testing,validation,and evaluation of deep learning(DL)models for detecting,recognizing,and localizing grasping objects in 2D and 3D space,especially 3D point cloud data.Our dataset is collected in a shared room,with common everyday objects placed on the tabletop in jumbled positions by Intel RealSense D435(IR-D435).This dataset includes more than 63k RGB-D pairs and related data such as normalized 3D object point cloud,3D object point cloud segmented,coordinate system normalizationmatrix,3D object point cloud normalized,and hand pose for grasping each object.At the same time,we also conducted experiments on fourDL networks with the best performance:SSD-MobileNetV3,ResNet50-Transformer,ResNet101-Transformer,and YOLOv12.The results present that YOLOv12 has the most suitable results in detecting and recognizing objects in images.All data,annotations,toolkit,source code,point cloud data,and results are publicly available on our project website:https://github.com/HuaTThanhIT2327Tqu/datasetv2.
基金the National Key Research and Development Program of China(Grant No.2023YFC3009400).
文摘Discontinuities in rock masses critically impact the stability and safety of underground engineering.Mainstream discontinuities identificationmethods,which rely on normal vector estimation and clustering algorithms,suffer from accuracy degradation,omission of critical discontinuities when orientation density is unevenly distributed,and need manual intervention.To overcome these limitations,this paper introduces a novel discontinuities identificationmethod based on geometric feature analysis of rock mass.By analyzing spatial distribution variability of point cloud and integrating an adaptive region growing algorithm,the method accurately detects independent discontinuities under complex geological conditions.Given that rock mass orientations typically follow a Fisher distribution,an adaptive hierarchical clustering algorithm based on statistical analysis is employed to automatically determine the optimal number of structural sets,eliminating the need for preset clusters or thresholds inherent in traditional methods.The proposed approach effectively handles diverse rock mass shapes and sizes,leveraging both local and global geometric features to minimize noise interference.Experimental validation on three real-world rock mass models,alongside comparisons with three conventional directional clustering algorithms,demonstrates superior accuracy and robustness in identifying optimal discontinuity sets.The proposed method offers a reliable and efficienttool for discontinuities detection and grouping in underground engineering,significantlyenhancing design and construction outcomes.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human object detection and recognition is essential for elderly monitoring and assisted living however,models relying solely on pose or scene context often struggle in cluttered or visually ambiguous settings.To address this,we present SCENET-3D,a transformer-drivenmultimodal framework that unifies human-centric skeleton features with scene-object semantics for intelligent robotic vision through a three-stage pipeline.In the first stage,scene analysis,rich geometric and texture descriptors are extracted from RGB frames,including surface-normal histograms,angles between neighboring normals,Zernike moments,directional standard deviation,and Gabor-filter responses.In the second stage,scene-object analysis,non-human objects are segmented and represented using local feature descriptors and complementary surface-normal information.In the third stage,human-pose estimation,silhouettes are processed through an enhanced MoveNet to obtain 2D anatomical keypoints,which are fused with depth information and converted into RGB-based point clouds to construct pseudo-3D skeletons.Features from all three stages are fused and fed in a transformer encoder with multi-head attention to resolve visually similar activities.Experiments on UCLA(95.8%),ETRI-Activity3D(89.4%),andCAD-120(91.2%)demonstrate that combining pseudo-3D skeletonswith rich scene-object fusion significantly improves generalizable activity recognition,enabling safer elderly care,natural human–robot interaction,and robust context-aware robotic perception in real-world environments.
基金Project(LJRC013)supported by the University Innovation Team of Hebei Province Leading Talent Cultivation,China
文摘Flatness pattern recognition is the key of the flatness control. The accuracy of the present flatness pattern recognition is limited and the shape defects cannot be reflected intuitively. In order to improve it, a novel method via T-S cloud inference network optimized by genetic algorithm(GA) is proposed. T-S cloud inference network is constructed with T-S fuzzy neural network and the cloud model. So, the rapid of fuzzy logic and the uncertainty of cloud model for processing data are both taken into account. What's more, GA possesses good parallel design structure and global optimization characteristics. Compared with the simulation recognition results of traditional BP Algorithm, GA is more accurate and effective. Moreover, virtual reality technology is introduced into the field of shape control by Lab VIEW, MATLAB mixed programming. And virtual flatness pattern recognition interface is designed.Therefore, the data of engineering analysis and the actual model are combined with each other, and the shape defects could be seen more lively and intuitively.
文摘This paper presents a method for hand gesture recognition based on 3D point cloud. Digital image processing technology is used in this research. Based on the 3D point from depth camera, the system firstly extracts some raw data of the hand. After the data segmentation and preprocessing, three kinds of appearance features are extracted, including the number of stretched fingers, the angles between fingers and the gesture region’s area distribution feature. Based on these features, the system implements the identification of the gestures by using decision tree method. The results of experiment demonstrate that the proposed method is pretty efficient to recognize common gestures with a high accuracy.
基金funded by the Third Xinjiang Scientific Expedition Program(2021xjkk1400)the National Natural Science Foundation of China(42071049)+2 种基金the Natural Science Foundation of Xinjiang Uygur Autonomous Region(2019D01C022)the Xinjiang Uygur Autonomous Region Innovation Environment Construction Special Project&Science and Technology Innovation Base Construction Project(PT2107)the Tianshan Talent-Science and Technology Innovation Team(2022TSYCTD0006).
文摘Snow cover plays a critical role in global climate regulation and hydrological processes.Accurate monitoring is essential for understanding snow distribution patterns,managing water resources,and assessing the impacts of climate change.Remote sensing has become a vital tool for snow monitoring,with the widely used Moderate-resolution Imaging Spectroradiometer(MODIS)snow products from the Terra and Aqua satellites.However,cloud cover often interferes with snow detection,making cloud removal techniques crucial for reliable snow product generation.This study evaluated the accuracy of four MODIS snow cover datasets generated through different cloud removal algorithms.Using real-time field camera observations from four stations in the Tianshan Mountains,China,this study assessed the performance of these datasets during three distinct snow periods:the snow accumulation period(September-November),snowmelt period(March-June),and stable snow period(December-February in the following year).The findings showed that cloud-free snow products generated using the Hidden Markov Random Field(HMRF)algorithm consistently outperformed the others,particularly under cloud cover,while cloud-free snow products using near-day synthesis and the spatiotemporal adaptive fusion method with error correction(STAR)demonstrated varying performance depending on terrain complexity and cloud conditions.This study highlighted the importance of considering terrain features,land cover types,and snow dynamics when selecting cloud removal methods,particularly in areas with rapid snow accumulation and melting.The results suggested that future research should focus on improving cloud removal algorithms through the integration of machine learning,multi-source data fusion,and advanced remote sensing technologies.By expanding validation efforts and refining cloud removal strategies,more accurate and reliable snow products can be developed,contributing to enhanced snow monitoring and better management of water resources in alpine and arid areas.
基金supported by the National Natural Science Foundation of China(Grant Nos.52304139,52325403)the CCTEG Coal Mining Research Institute funding(Grant No.KCYJY-2024-MS-10).
文摘3D laser scanning technology is widely used in underground openings for high-precision,rapid,and nondestructive structural evaluations.Segmenting large 3D point cloud datasets,particularly in coal mine roadways with multi-scale targets,remains challenging.This paper proposes an enhanced segmentation method integrating improved PointNet++with a coverage-voted strategy.The coverage-voted strategy reduces data while preserving multi-scale target topology.The segmentation is achieved using an enhanced PointNet++algorithm with a normalization preprocessing head,resulting in a 94%accuracy for common supporting components.Ablation experiments show that the preprocessing head and coverage strategies increase segmentation accuracy by 20%and 2%,respectively,and improve Intersection over Union(IoU)for bearing plate segmentation by 58%and 20%.The accuracy of the current pretraining segmentation model may be affected by variations in surface support components,but it can be readily enhanced through re-optimization with additional labeled point cloud data.This proposed method,combined with a previously developed machine learning model that links rock bolt load and the deformation field of its bearing plate,provides a robust technique for simultaneously measuring the load of multiple rock bolts in a single laser scan.
文摘It is very important to locate and track weather systems which cause severe calamity,such as severeconvective clouds (SCC),in nowcasting. In this paper the recognition and tracking of SCC is studied withGMS IR images using computer image techniques. As an IR image preprocessing, a SCC futerlng algorithm is put forward that combines a segment smoothing filtering and a removal procedure by thresholds. To the filtered SCCs the T algorithm and IP algorithm of contour coding method are applied to extract the contour line and its initial point. The description of SCCs includes four characteristic quanti-ties, i. e. center of gravity, cloud size, moment invariant M and R-shaped descriptor. Pattern recosnitionand pattern matching techniques are used to track the SCCs. Two procedures of rough and fine matchingare given. The former procedure include the setting of searching area and recognition of area and the latter is composed by the matching of shape descriptor R and moment invariant M and the analysis of correlative brightness temperature analysis.
文摘Point cloud based place recognition plays an important role in mobile robotics. In this paper, we propose a weighted aggregation method from structure information adaptively for point cloud place recognition. Firstly, to preserve the prior distributions and local geometric structures, we fuse learned hidden features with handcrafted features in the beginning. Secondly, we further extract and aggregate adaptively weighted features concerning density and relative spatial information from these fused features, named Weighted Aggregation with Density Estimation (WADE) module. Then, we conduct the WADE block iteratively to group the latent manifold structures. Finally, comparison results on two public datasets Oxford Robotcar and KITTI show that the proposed approach exceeds the comparison approaches on recall rate averagely 7% - 8%.
文摘The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system.
基金supported by the China State Kay Basic Research Project(2013CBA01802)Chinese National Natural Science Foundation(41101337+2 种基金41001197and 31228021)the Fundamental Research Funds for the Central Universities(lzujbky-2013-103)
文摘Because of similar reflective characteristics of snow and cloud, the weather status seriously affects snow monitoring using optical remote sensing data. Cloud amount analysis during 2010 to 2011 snow seasons shows that cloud cover is the major limitation for snow cover monitoring using MOD10A1 and MYD10A1. By use of MODIS daily snow cover products and AMSR-E snow wa- ter equivalent products （SWE）, several cloud elimination methods were integrated to produce a new daily cloud flee snow cover product, and information of snow depth from 85 climate stations in Tibetan Plateau area （TP） were used to validate the accuracy of the new composite snow cover product. The results indicate that snow classification accuracy of the new daily snow cover product reaches 91.7% when snow depth is over 3 cm. This suggests that the new daily snow cover mapping algorithm is suitable for monitoring snow cover dynamic changes in TP.
基金supported by the Korea Science and Engineering Foundation (KOSEF)grant funded by the Korea government (MOST) R01-2006-000-10470-0 and R01-2006-000-11233-0 from the Basic Research Program of the Korea Science & Engineering Foundationby "Maintenance and Research of Cloud Phys-ical Observation System" and "Research for the Meteo-rological Observation Technology and its Application" ofMETRI, KMA project.
文摘The snow enhancement experiments, carried out by injecting AgI and water vapor into orographically enhanced clouds （fog）, have been conducted to confirm Li and Pitter＇s forced condensation process in a natural situation. Nine ground-based experiments have been conducted at Daegwallyeong in the Taebaek Mountains for the easterly foggy days from January-February 2006. We then obtained the optimized conditions for the Daegwallyeong region as follows： the small seeding rate （1.04 g min-1） of AgI for the easterly cold fog with the high humidity of Gangneung. Additional experiments are needed to statistically estimate the snowfall increment caused by the small AgI seeding into the orographical fog （cloud） over the Taeback Mountains.
基金This research was supported by National Natural Science Foundation of China(No.61271353,61871389)Major Funding Projects of National University of Defense Technology(No.ZK18-01-02)Foundation of State Key Laboratory of Pulsed Power Laser Technology(No.SKL2018ZR09).
文摘Airborne LIDAR can flexibly obtain point cloud data with three-dimensional structural information,which can improve its effectiveness of automatic target recognition in the complex environment.Compared with 2D information,3D information performs better in separating objects and background.However,an aircraft platform can have a negative influence on LIDAR obtained data because of various flight attitudes,flight heights and atmospheric disturbances.A structure of global feature based 3D automatic target recognition method for airborne LIDAR is proposed,which is composed of offline phase and online phase.The performance of four global feature descriptors is compared.Considering the summed volume region(SVR) discrepancy in real objects,SVR selection is added into the pre-processing operations to eliminate mismatching clusters compared with the interested target.Highly reliable simulated data are obtained under various sensor’s altitudes,detection distances and atmospheric disturbances.The final experiments results show that the added step increases the recognition rate by above 2.4% and decreases the execution time by about 33%.
基金This research was funded by grant from the Key Research and Development Program of Shaanxi Province(2018NY-127,2019ZDLNY07-02-01,2020NY-205)National Undergraduate Training Program for Innovation and entrepreneurship plan(S201910712240,X201910712080).
文摘Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes,there still exist some challenges in the debris recognition of terrain data.Compared with hundreds of thousands of indoor point clouds,the amount of terrain point cloud is up to millions.Apart from that,terrain point cloud data obtained from remote sensing is measured in meters,but the indoor scene is measured in centimeters.In this case,the terrain debris obtained from remote sensing mapping only have dozens of points,which means that sufficient training information cannot be obtained only through the convolution of points.In this paper,we build multi-attribute descriptors containing geometric information and color information to better describe the information in low-precision terrain debris.Therefore,our process is aimed at the multi-attribute descriptors of each point rather than the point.On this basis,an unsupervised classification algorithm is proposed to divide the point cloud into several terrain areas,and regard each area as a graph vertex named super point to form the graph structure,thus effectively reducing the number of the terrain point cloud from millions to hundreds.Then we proposed a graph convolution network by employing PointNet for graph embedding and recurrent gated graph convolutional network for classification.Our experiments show that the terrain point cloud can reduce the amount of data from millions to hundreds through the super point graph based on multi-attribute descriptor and our accuracy reached 91.74%and the IoU reached 94.08%,both of which were significantly better than the current methods such as SEGCloud(Acc:88.63%,IoU:89.29%)and PointCNN(Acc:86.35,IoU:87.26).
文摘With the development of computation technology,the augmented reality(AR)is widely applied in many fields as well as the image recognition.However,the AR application on mobile platform is not developed enough in the past decades due to the capability of the mobile processors.In recent years,the performance of mobile processors has changed rapidly,which makes it comparable to the desktop processors.This paper proposed and realized an AR system to be used on the Android mobile platform based on the image recognition through EasyAR engine and Unity 3D development tools.In this system,the image recognition could be done locally and/or using cloud recognition.Test results show that the cloud-based recognition is more efficient and accuracy than the local recognition for the mobile AR when there are more images to be recognized at the same time.
基金the National Key R&D Program of China(No.2022YFB3707303)National Natural Science Foundation of China(No.52293471)。
文摘Understanding the conformational characteristics of polymers is key to elucidating their physical properties.Cyclic polymers,defined by their closed-loop structures,inherently differ from linear polymers possessing distinct chain ends.Despite these structural differences,both types of polymers exhibit locally random-walk-like conformations,making it challenging to detect subtle spatial variations using conventional methods.In this study,we address this challenge by integrating molecular dynamics simulations with point cloud neural networks to analyze the spatial conformations of cyclic and linear polymers.By utilizing the Dynamic Graph CNN(DGCNN)model,we classify polymer conformations based on the 3D coordinates of monomers,capturing local and global topological differences without considering chain connectivity sequentiality.Our findings reveal that the optimal local structural feature unit size scales linearly with molecular weight,aligning with theoretical predictions.Additionally,interpretability techniques such as Grad-CAM and SHAP identify significant conformational differences:cyclic polymers tend to form prolate ellipsoid shapes with pronounced elongation along the major axis,while linear polymers show elongated ends with more spherical centers.These findings reveal subtle yet critical differences in local conformations between cyclic and linear polymers that were previously difficult to discern,providing deeper insights into polymer structure-property relationships and offering guidance for future polymer science advancements.
