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
3D human pose estimation is a major focus area in the field of computer vision,which plays an important role in practical applications.This article summarizes the framework and research progress related to the estimat...3D human pose estimation is a major focus area in the field of computer vision,which plays an important role in practical applications.This article summarizes the framework and research progress related to the estimation of monocular RGB images and videos.An overall perspective ofmethods integrated with deep learning is introduced.Novel image-based and video-based inputs are proposed as the analysis framework.From this viewpoint,common problems are discussed.The diversity of human postures usually leads to problems such as occlusion and ambiguity,and the lack of training datasets often results in poor generalization ability of the model.Regression methods are crucial for solving such problems.Considering image-based input,the multi-view method is commonly used to solve occlusion problems.Here,the multi-view method is analyzed comprehensively.By referring to video-based input,the human prior knowledge of restricted motion is used to predict human postures.In addition,structural constraints are widely used as prior knowledge.Furthermore,weakly supervised learningmethods are studied and discussed for these two types of inputs to improve the model generalization ability.The problem of insufficient training datasets must also be considered,especially because 3D datasets are usually biased and limited.Finally,emerging and popular datasets and evaluation indicators are discussed.The characteristics of the datasets and the relationships of the indicators are explained and highlighted.Thus,this article can be useful and instructive for researchers who are lacking in experience and find this field confusing.In addition,by providing an overview of 3D human pose estimation,this article sorts and refines recent studies on 3D human pose estimation.It describes kernel problems and common useful methods,and discusses the scope for further research.展开更多
The field of vision-based human hand three-dimensional(3D)shape and pose estimation has attracted significant attention recently owing to its key role in various applications,such as natural human computer interaction...The field of vision-based human hand three-dimensional(3D)shape and pose estimation has attracted significant attention recently owing to its key role in various applications,such as natural human computer interactions.With the availability of large-scale annotated hand datasets and the rapid developments of deep neural networks(DNNs),numerous DNN-based data-driven methods have been proposed for accurate and rapid hand shape and pose estimation.Nonetheless,the existence of complicated hand articulation,depth and scale ambiguities,occlusions,and finger similarity remain challenging.In this study,we present a comprehensive survey of state-of-the-art 3D hand shape and pose estimation approaches using RGB-D cameras.Related RGB-D cameras,hand datasets,and a performance analysis are also discussed to provide a holistic view of recent achievements.We also discuss the research potential of this rapidly growing field.展开更多
In this article,a comprehensive survey of deep learning-based(DLbased)human pose estimation(HPE)that can help researchers in the domain of computer vision is presented.HPE is among the fastest-growing research domains...In this article,a comprehensive survey of deep learning-based(DLbased)human pose estimation(HPE)that can help researchers in the domain of computer vision is presented.HPE is among the fastest-growing research domains of computer vision and is used in solving several problems for human endeavours.After the detailed introduction,three different human body modes followed by the main stages of HPE and two pipelines of twodimensional(2D)HPE are presented.The details of the four components of HPE are also presented.The keypoints output format of two popular 2D HPE datasets and the most cited DL-based HPE articles from the year of breakthrough are both shown in tabular form.This study intends to highlight the limitations of published reviews and surveys respecting presenting a systematic review of the current DL-based solution to the 2D HPE model.Furthermore,a detailed and meaningful survey that will guide new and existing researchers on DL-based 2D HPE models is achieved.Finally,some future research directions in the field of HPE,such as limited data on disabled persons and multi-training DL-based models,are revealed to encourage researchers and promote the growth of HPE research.展开更多
The 6D pose estimation is important for the safe take-off and landing of the aircraft using a single RGB image. Due to the large scene and large depth, the exiting pose estimation methods have unstratified performance...The 6D pose estimation is important for the safe take-off and landing of the aircraft using a single RGB image. Due to the large scene and large depth, the exiting pose estimation methods have unstratified performance on the accuracy. To achieve precise 6D pose estimation of the aircraft, an end-to-end method using an RGB image is proposed. In the proposed method, the2D and 3D information of the keypoints of the aircraft is used as the intermediate supervision,and 6D pose information of the aircraft in this intermediate information will be explored. Specifically, an off-the-shelf object detector is utilized to detect the Region of the Interest(Ro I) of the aircraft to eliminate background distractions. The 2D projection and 3D spatial information of the pre-designed keypoints of the aircraft is predicted by the keypoint coordinate estimator(Kp Net).The proposed method is trained in an end-to-end fashion. In addition, to deal with the lack of the related datasets, this paper builds the Aircraft 6D Pose dataset to train and test, which captures the take-off and landing process of three types of aircraft from 11 views. Compared with the latest Wide-Depth-Range method on this dataset, our proposed method improves the average 3D distance of model points metric(ADD) and 5° and 5 m metric by 86.8% and 30.1%, respectively. Furthermore, the proposed method gets 9.30 ms, 61.0% faster than YOLO6D with 23.86 ms.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 by the Program of Entrepreneurship and Innovation Ph.D.in Jiangsu Province(JSSCBS20211175)the School Ph.D.Talent Funding(Z301B2055)the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(21KJB520002).
文摘3D human pose estimation is a major focus area in the field of computer vision,which plays an important role in practical applications.This article summarizes the framework and research progress related to the estimation of monocular RGB images and videos.An overall perspective ofmethods integrated with deep learning is introduced.Novel image-based and video-based inputs are proposed as the analysis framework.From this viewpoint,common problems are discussed.The diversity of human postures usually leads to problems such as occlusion and ambiguity,and the lack of training datasets often results in poor generalization ability of the model.Regression methods are crucial for solving such problems.Considering image-based input,the multi-view method is commonly used to solve occlusion problems.Here,the multi-view method is analyzed comprehensively.By referring to video-based input,the human prior knowledge of restricted motion is used to predict human postures.In addition,structural constraints are widely used as prior knowledge.Furthermore,weakly supervised learningmethods are studied and discussed for these two types of inputs to improve the model generalization ability.The problem of insufficient training datasets must also be considered,especially because 3D datasets are usually biased and limited.Finally,emerging and popular datasets and evaluation indicators are discussed.The characteristics of the datasets and the relationships of the indicators are explained and highlighted.Thus,this article can be useful and instructive for researchers who are lacking in experience and find this field confusing.In addition,by providing an overview of 3D human pose estimation,this article sorts and refines recent studies on 3D human pose estimation.It describes kernel problems and common useful methods,and discusses the scope for further research.
基金the National Key R&D Program of China(2018YFB1004600)the National Natural Science Foundation of China(61502187,61876211)the National Science Foundation Grant CNS(1951952).
文摘The field of vision-based human hand three-dimensional(3D)shape and pose estimation has attracted significant attention recently owing to its key role in various applications,such as natural human computer interactions.With the availability of large-scale annotated hand datasets and the rapid developments of deep neural networks(DNNs),numerous DNN-based data-driven methods have been proposed for accurate and rapid hand shape and pose estimation.Nonetheless,the existence of complicated hand articulation,depth and scale ambiguities,occlusions,and finger similarity remain challenging.In this study,we present a comprehensive survey of state-of-the-art 3D hand shape and pose estimation approaches using RGB-D cameras.Related RGB-D cameras,hand datasets,and a performance analysis are also discussed to provide a holistic view of recent achievements.We also discuss the research potential of this rapidly growing field.
基金supported by the[Universiti Sains Malaysia]under FRGS Grant Number[FRGS/1/2020/STG07/USM/02/12(203.PKOMP.6711930)]FRGS Grant Number[304PTEKIND.6316497.USM.].
文摘In this article,a comprehensive survey of deep learning-based(DLbased)human pose estimation(HPE)that can help researchers in the domain of computer vision is presented.HPE is among the fastest-growing research domains of computer vision and is used in solving several problems for human endeavours.After the detailed introduction,three different human body modes followed by the main stages of HPE and two pipelines of twodimensional(2D)HPE are presented.The details of the four components of HPE are also presented.The keypoints output format of two popular 2D HPE datasets and the most cited DL-based HPE articles from the year of breakthrough are both shown in tabular form.This study intends to highlight the limitations of published reviews and surveys respecting presenting a systematic review of the current DL-based solution to the 2D HPE model.Furthermore,a detailed and meaningful survey that will guide new and existing researchers on DL-based 2D HPE models is achieved.Finally,some future research directions in the field of HPE,such as limited data on disabled persons and multi-training DL-based models,are revealed to encourage researchers and promote the growth of HPE research.
基金co-supported by the Key research and development plan project of Sichuan Province,China(No.2022YFG0153).
文摘The 6D pose estimation is important for the safe take-off and landing of the aircraft using a single RGB image. Due to the large scene and large depth, the exiting pose estimation methods have unstratified performance on the accuracy. To achieve precise 6D pose estimation of the aircraft, an end-to-end method using an RGB image is proposed. In the proposed method, the2D and 3D information of the keypoints of the aircraft is used as the intermediate supervision,and 6D pose information of the aircraft in this intermediate information will be explored. Specifically, an off-the-shelf object detector is utilized to detect the Region of the Interest(Ro I) of the aircraft to eliminate background distractions. The 2D projection and 3D spatial information of the pre-designed keypoints of the aircraft is predicted by the keypoint coordinate estimator(Kp Net).The proposed method is trained in an end-to-end fashion. In addition, to deal with the lack of the related datasets, this paper builds the Aircraft 6D Pose dataset to train and test, which captures the take-off and landing process of three types of aircraft from 11 views. Compared with the latest Wide-Depth-Range method on this dataset, our proposed method improves the average 3D distance of model points metric(ADD) and 5° and 5 m metric by 86.8% and 30.1%, respectively. Furthermore, the proposed method gets 9.30 ms, 61.0% faster than YOLO6D with 23.86 ms.
