A solution of virtual human skeleton system is proposed. Some issues on integration of anatomical geometry, biodynamics and computer animation are studied. The detailed skeleton system model that incorporates the biod...A solution of virtual human skeleton system is proposed. Some issues on integration of anatomical geometry, biodynamics and computer animation are studied. The detailed skeleton system model that incorporates the biodynamic and geometric characteristics of a human skeleton system allows some performance studies in greater detail than that performed before. It may provide an effective and convenient way to analyze and evaluate the movement performance of a human body when the personalized anatomical data are used in the models. An example shows that the proposed solution is effective for the stated problems.展开更多
<b><span style="font-family:;" "="">Aim:</span></b><span><span><span style="font-family:;" "=""> To perform a vector 3D recon...<b><span style="font-family:;" "="">Aim:</span></b><span><span><span style="font-family:;" "=""> To perform a vector 3D reconstruction of the neck skeleton from the anatomical sections of the “Korean Visible Human” for educational purposes. <b>Material and Methods: </b>The anatomical subject was a 33-year-old Korean male who died of leukemia. It measured 164 cm and weighed 55</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span><span><span style="font-family:;" "="">kgs.</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span><span><span style="font-family:;" "="">The anatomical cuts were made in 2010 after an MRI and a CT scan. A special saw (cryomacrotome) made it possible to make cuts on the frozen body of 0.2 mm thick or 5960 slices. Sections numbered 1500 to 2000 (500 neck sections) were used for this study. Manual contouring segmentation of each anatomical element of the anterior neck area was done using Winsurf software version 3.5 on a PC. <b>Results</b>: Our vector 3D neck model includes the following: cervical vertebrae, hyoid bone, sternum manubrium and clavicles. This vector model has been integrated into the virtual dissection table</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span><span><span style="font-family:;" "="">Diva3d, a new educational tool used by universities and medical schools to learn anatomy. This model was also put online on the Sketchfab website and printed in 3D using an ENDER 3 printer. <b>Conclusion:</b> This original work is a remarkable educational tool for the study of the skeleton of the neck and can also serve as a 3D atlas for simulation purposes for training therapeutic gestures.</span></span></span>展开更多
In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accurac...In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.展开更多
针对人体动作识别任务中特征值选取不当导致识别率低、使用多模态数据导致训练成本高等问题,提出一种轻量级人体动作识别方法。首先使用OpenPose、PoseNet提取出人体骨架信息,使用BWT69CL传感器提取姿势信息;其次对数据进行预处理、特...针对人体动作识别任务中特征值选取不当导致识别率低、使用多模态数据导致训练成本高等问题,提出一种轻量级人体动作识别方法。首先使用OpenPose、PoseNet提取出人体骨架信息,使用BWT69CL传感器提取姿势信息;其次对数据进行预处理、特征融合,对人体动作进行深度学习分类识别;最后,为验证此方法的有效性,在公开数据集WISDM、UCIHAR、HASC和自建的人体动作数据集上进行实验验证,并使用改进的目标引导注意力机制(target-guided attention,TGA)–长短期记忆(long short term memory,LSTM)网络输出最终的分类结果。实验结果表明,在自建数据集下融合姿势和骨架特征达到99.87%准确率,相比于只使用姿势信息特征,识别准确率提高了约5.31个百分点;相比于只使用人体骨架特征,识别准确率提高了约1.87个百分点;在识别时间上相比于只使用姿势信息,识别时间降低了约29.73 s;相比于只使用人体骨架数据,识别时间降低了约9 s。使用该方法能及时有效地反映人体的运动意图,有助于提高人体动作和行为的识别准确率和训练效率。展开更多
The key pose frames of a human motion pose sequence,play an important role in the compression,retrieval and semantic analysis of continuous human motion.The current available clustering methods in literatures are diff...The key pose frames of a human motion pose sequence,play an important role in the compression,retrieval and semantic analysis of continuous human motion.The current available clustering methods in literatures are difficult to determine the number of key pose frames automatically,and may destroy the postures’ temporal relationships while extracting key frames.To deal with this problem,this paper proposes a new key pose frames extraction method on the basis of 3D space distances of joint points and the improved X-means clustering algorithm.According to the proposed extraction method,the final key pose frame sequence could be obtained by describing the posture of human body with space distance of particular joint points and then the time-constraint X-mean algorithm is applied to cluster and filtrate the posture sequence.The experimental results show that the proposed method can automatically determine the number of key frames and save the temporal characteristics of motion frames according to the motion pose sequence.展开更多
为准确识别乘客搭乘自动扶梯时的异常行为,避免安全事故的发生,提出了一种基于人体骨架的扶梯乘客异常行为识别方法。首先使用YOLOX-Tiny对视频中乘客位置进行检测,通过Alphapose算法提取骨骼关键点坐标,降低复杂背景的干扰;再使用多流...为准确识别乘客搭乘自动扶梯时的异常行为,避免安全事故的发生,提出了一种基于人体骨架的扶梯乘客异常行为识别方法。首先使用YOLOX-Tiny对视频中乘客位置进行检测,通过Alphapose算法提取骨骼关键点坐标,降低复杂背景的干扰;再使用多流膨胀3D卷积模块增强时空特征提取能力,聚合乘客骨架的全局特征;然后将其输入改进后的时空图卷积网络中提取乘客骨架信息,通过MS-TCN模块扩大接受域以增强时间特征的提取,联合人体关键点注意力模块(Key Point Attention Module,KPAM)提升网络对相似动作的关键骨架的关注度;最后通过Softmax对异常动作进行分类。采集扶梯运行现场视频制作数据集,试验结果表明,本文算法对乘客异常行为的识别精度达到96.1%,可应用于扶梯现场的视频监控系统,提高安全管理信息化水平。展开更多
文摘A solution of virtual human skeleton system is proposed. Some issues on integration of anatomical geometry, biodynamics and computer animation are studied. The detailed skeleton system model that incorporates the biodynamic and geometric characteristics of a human skeleton system allows some performance studies in greater detail than that performed before. It may provide an effective and convenient way to analyze and evaluate the movement performance of a human body when the personalized anatomical data are used in the models. An example shows that the proposed solution is effective for the stated problems.
文摘<b><span style="font-family:;" "="">Aim:</span></b><span><span><span style="font-family:;" "=""> To perform a vector 3D reconstruction of the neck skeleton from the anatomical sections of the “Korean Visible Human” for educational purposes. <b>Material and Methods: </b>The anatomical subject was a 33-year-old Korean male who died of leukemia. It measured 164 cm and weighed 55</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span><span><span style="font-family:;" "="">kgs.</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span><span><span style="font-family:;" "="">The anatomical cuts were made in 2010 after an MRI and a CT scan. A special saw (cryomacrotome) made it possible to make cuts on the frozen body of 0.2 mm thick or 5960 slices. Sections numbered 1500 to 2000 (500 neck sections) were used for this study. Manual contouring segmentation of each anatomical element of the anterior neck area was done using Winsurf software version 3.5 on a PC. <b>Results</b>: Our vector 3D neck model includes the following: cervical vertebrae, hyoid bone, sternum manubrium and clavicles. This vector model has been integrated into the virtual dissection table</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span><span><span style="font-family:;" "="">Diva3d, a new educational tool used by universities and medical schools to learn anatomy. This model was also put online on the Sketchfab website and printed in 3D using an ENDER 3 printer. <b>Conclusion:</b> This original work is a remarkable educational tool for the study of the skeleton of the neck and can also serve as a 3D atlas for simulation purposes for training therapeutic gestures.</span></span></span>
基金supported by the National Natural Science Foundation of China(62272049,62236006,62172045)the Key Projects of Beijing Union University(ZKZD202301).
文摘In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.
文摘针对人体动作识别任务中特征值选取不当导致识别率低、使用多模态数据导致训练成本高等问题,提出一种轻量级人体动作识别方法。首先使用OpenPose、PoseNet提取出人体骨架信息,使用BWT69CL传感器提取姿势信息;其次对数据进行预处理、特征融合,对人体动作进行深度学习分类识别;最后,为验证此方法的有效性,在公开数据集WISDM、UCIHAR、HASC和自建的人体动作数据集上进行实验验证,并使用改进的目标引导注意力机制(target-guided attention,TGA)–长短期记忆(long short term memory,LSTM)网络输出最终的分类结果。实验结果表明,在自建数据集下融合姿势和骨架特征达到99.87%准确率,相比于只使用姿势信息特征,识别准确率提高了约5.31个百分点;相比于只使用人体骨架特征,识别准确率提高了约1.87个百分点;在识别时间上相比于只使用姿势信息,识别时间降低了约29.73 s;相比于只使用人体骨架数据,识别时间降低了约9 s。使用该方法能及时有效地反映人体的运动意图,有助于提高人体动作和行为的识别准确率和训练效率。
基金Supported by the National Natural Science Foundation of China(61303127)Project of Science and Technology Department of Sichuan Province(2014SZ0223,2014GZ0100,2015GZ0212)+1 种基金Key Program of Education Department of Sichuan Province(11ZA130,13ZA0169)Postgraduate Innovation Fund Project by Southwest University of Science and Technology(15ycx057)
文摘The key pose frames of a human motion pose sequence,play an important role in the compression,retrieval and semantic analysis of continuous human motion.The current available clustering methods in literatures are difficult to determine the number of key pose frames automatically,and may destroy the postures’ temporal relationships while extracting key frames.To deal with this problem,this paper proposes a new key pose frames extraction method on the basis of 3D space distances of joint points and the improved X-means clustering algorithm.According to the proposed extraction method,the final key pose frame sequence could be obtained by describing the posture of human body with space distance of particular joint points and then the time-constraint X-mean algorithm is applied to cluster and filtrate the posture sequence.The experimental results show that the proposed method can automatically determine the number of key frames and save the temporal characteristics of motion frames according to the motion pose sequence.
文摘为准确识别乘客搭乘自动扶梯时的异常行为,避免安全事故的发生,提出了一种基于人体骨架的扶梯乘客异常行为识别方法。首先使用YOLOX-Tiny对视频中乘客位置进行检测,通过Alphapose算法提取骨骼关键点坐标,降低复杂背景的干扰;再使用多流膨胀3D卷积模块增强时空特征提取能力,聚合乘客骨架的全局特征;然后将其输入改进后的时空图卷积网络中提取乘客骨架信息,通过MS-TCN模块扩大接受域以增强时间特征的提取,联合人体关键点注意力模块(Key Point Attention Module,KPAM)提升网络对相似动作的关键骨架的关注度;最后通过Softmax对异常动作进行分类。采集扶梯运行现场视频制作数据集,试验结果表明,本文算法对乘客异常行为的识别精度达到96.1%,可应用于扶梯现场的视频监控系统,提高安全管理信息化水平。
