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
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
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
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
Human pose estimation(HPE)is a procedure for determining the structure of the body pose and it is considered a challenging issue in the computer vision(CV)communities.HPE finds its applications in several fields namel...Human pose estimation(HPE)is a procedure for determining the structure of the body pose and it is considered a challenging issue in the computer vision(CV)communities.HPE finds its applications in several fields namely activity recognition and human-computer interface.Despite the benefits of HPE,it is still a challenging process due to the variations in visual appearances,lighting,occlusions,dimensionality,etc.To resolve these issues,this paper presents a squirrel search optimization with a deep convolutional neural network for HPE(SSDCNN-HPE)technique.The major intention of the SSDCNN-HPE technique is to identify the human pose accurately and efficiently.Primarily,the video frame conversion process is performed and pre-processing takes place via bilateral filtering-based noise removal process.Then,the EfficientNet model is applied to identify the body points of a person with no problem constraints.Besides,the hyperparameter tuning of the EfficientNet model takes place by the use of the squirrel search algorithm(SSA).In the final stage,the multiclass support vector machine(M-SVM)technique was utilized for the identification and classification of human poses.The design of bilateral filtering followed by SSA based EfficientNetmodel for HPE depicts the novelty of the work.To demonstrate the enhanced outcomes of the SSDCNN-HPE approach,a series of simulations are executed.The experimental results reported the betterment of the SSDCNN-HPE system over the recent existing techniques in terms of different measures.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
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
Three-dimensional (3D) human pose tracking has recently attracted more and more attention in the computer vision field. Real-time pose tracking is highly useful in various domains such as video surveillance, somatosen...Three-dimensional (3D) human pose tracking has recently attracted more and more attention in the computer vision field. Real-time pose tracking is highly useful in various domains such as video surveillance, somatosensory games, and human-computer interaction. However, vision-based pose tracking techniques usually raise privacy concerns, making human pose tracking without vision data usage an important problem. Thus, we propose using Radio Frequency Identification (RFID) as a pose tracking technique via a low-cost wearable sensing device. Although our prior work illustrated how deep learning could transfer RFID data into real-time human poses, generalization for different subjects remains challenging. This paper proposes a subject-adaptive technique to address this generalization problem. In the proposed system, termed Cycle-Pose, we leverage a cross-skeleton learning structure to improve the adaptability of the deep learning model to different human skeletons. Moreover, our novel cycle kinematic network is proposed for unpaired RFID and labeled pose data from different subjects. The Cycle-Pose system is implemented and evaluated by comparing its prototype with a traditional RFID pose tracking system. The experimental results demonstrate that Cycle-Pose can achieve lower estimation error and better subject generalization than the traditional system.展开更多
Lots of progress has been made recently on 2 D human pose tracking with tracking-by-detection approaches. However,several challenges still remain in this area which is due to self-occlusions and the confusion between ...Lots of progress has been made recently on 2 D human pose tracking with tracking-by-detection approaches. However,several challenges still remain in this area which is due to self-occlusions and the confusion between the left and right limbs during tracking. In this work,a head orientation detection step is introduced into the tracking framework to serve as a complementary tool to assist human pose estimation. With the face orientation determined,the system can decide whether the left or right side of the human body is exactly visible and infer the state of the symmetric counterpart. By granting a higher priority for the completely visible side,the system can avoid double counting to a great extent when inferring body poses. The proposed framework is evaluated on the HumanEva dataset. The results show that it largely reduces the occurrence of double counting and distinguishes the left and right sides consistently.展开更多
Recovering human pose from RGB images and videos has drawn increasing attention in recent years owing to minimum sensor requirements and applicability in diverse fields such as human-computer interaction,robotics,vide...Recovering human pose from RGB images and videos has drawn increasing attention in recent years owing to minimum sensor requirements and applicability in diverse fields such as human-computer interaction,robotics,video analytics,and augmented reality.Although a large amount of work has been devoted to this field,3D human pose estimation based on monocular images or videos remains a very challenging task due to a variety of difficulties such as depth ambiguities,occlusion,background clutters,and lack of training data.In this survey,we summarize recent advances in monocular 3D human pose estimation.We provide a general taxonomy to cover existing approaches and analyze their capabilities and limitations.We also present a summary of extensively used datasets and metrics,and provide a quantitative comparison of some representative methods.Finally,we conclude with a discussion on realistic challenges and open problems for future research directions.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
In current interactive television schemes, the viewpoints should be manipulated by the user. However, there is no efficient method, to assist a user in automatically identifying and tracking the optimum viewpoint when...In current interactive television schemes, the viewpoints should be manipulated by the user. However, there is no efficient method, to assist a user in automatically identifying and tracking the optimum viewpoint when the user observes the object of interest because many objects, most often humans, move rapidly and frequently. This paper proposes a novel framework for determining and tracking the virtual camera to best capture the front of the person of interest (PoI). First, one PoI is interactively chosen in a segmented 3D scene reconstructed by space carving method. Second, key points of the human torso of the PoI are detected by using a model-based method and the human's global motion including rotation and translation is estimated by using a close-formed method with 3 corresponding points. At the last step, the front direction of PoI is tracked temporally by using the unscented particle filter (UPF). Experimental results show that the method can properly compute the front direction of the PoI and robustly track the best viewpoints.展开更多
Deep neural networks are vulnerable to attacks from adversarial inputs.Corresponding attack research on human pose estimation(HPE),particularly for body joint detection,has been largely unexplored.Transferring classif...Deep neural networks are vulnerable to attacks from adversarial inputs.Corresponding attack research on human pose estimation(HPE),particularly for body joint detection,has been largely unexplored.Transferring classification-based attack methods to body joint regression tasks is not straightforward.Another issue is that the attack effectiveness and imperceptibility contradict each other.To solve these issues,we propose local imperceptible attacks on HPE networks.In particular,we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack.Furthermore,we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection.Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness.We conducted a series of imperceptible attacks against state-of-the-art HPE methods,including HigherHRNet,DEKR,and ViTPose.The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels.Approximately 4%of the pixels can achieve sufficient attacks on HPE.展开更多
Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,huma...Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,humanpose estimation has achieved great success in multiple fields such as animation and sports.However,to obtainaccurate positioning results,existing methods may suffer from large model sizes,a high number of parameters,and increased complexity,leading to high computing costs.In this paper,we propose a new lightweight featureencoder to construct a high-resolution network that reduces the number of parameters and lowers the computingcost.We also introduced a semantic enhancement module that improves global feature extraction and networkperformance by combining channel and spatial dimensions.Furthermore,we propose a dense connected spatialpyramid pooling module to compensate for the decrease in image resolution and information loss in the network.Finally,ourmethod effectively reduces the number of parameters and complexitywhile ensuring high performance.Extensive experiments show that our method achieves a competitive performance while dramatically reducing thenumber of parameters,and operational complexity.Specifically,our method can obtain 89.9%AP score on MPIIVAL,while the number of parameters and the complexity of operations were reduced by 41%and 36%,respectively.展开更多
With the advancement of image sensing technology, estimating 3Dhuman pose frommonocular video has becomea hot research topic in computer vision. 3D human pose estimation is an essential prerequisite for subsequentacti...With the advancement of image sensing technology, estimating 3Dhuman pose frommonocular video has becomea hot research topic in computer vision. 3D human pose estimation is an essential prerequisite for subsequentaction analysis and understanding. It empowers a wide spectrum of potential applications in various areas, suchas intelligent transportation, human-computer interaction, and medical rehabilitation. Currently, some methodsfor 3D human pose estimation in monocular video employ temporal convolutional network (TCN) to extractinter-frame feature relationships, but the majority of them suffer from insufficient inter-frame feature relationshipextractions. In this paper, we decompose the 3D joint location regression into the bone direction and length, wepropose the TCG, a temporal convolutional network incorporating Gaussian error linear units (GELU), to solvebone direction. It enablesmore inter-frame features to be captured andmakes the utmost of the feature relationshipsbetween data. Furthermore, we adopt kinematic structural information to solve bone length enhancing the use ofintra-frame joint features. Finally, we design a loss function for joint training of the bone direction estimationnetwork with the bone length estimation network. The proposed method has extensively experimented on thepublic benchmark dataset Human3.6M. Both quantitative and qualitative experimental results showed that theproposed method can achieve more accurate 3D human pose estimations.展开更多
Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has at...Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has attractedmany researchers to this field. Inspired by the existing recognition systems,this paper proposes a new and efficient human-object interaction recognition(HOIR) model which is based on modeling human pose and scene featureinformation. There are different aspects involved in an interaction, includingthe humans, the objects, the various body parts of the human, and the backgroundscene. Themain objectives of this research include critically examiningthe importance of all these elements in determining the interaction, estimatinghuman pose through image foresting transform (IFT), and detecting the performedinteractions based on an optimizedmulti-feature vector. The proposedmethodology has six main phases. The first phase involves preprocessing theimages. During preprocessing stages, the videos are converted into imageframes. Then their contrast is adjusted, and noise is removed. In the secondphase, the human-object pair is detected and extracted from each image frame.The third phase involves the identification of key body parts of the detectedhumans using IFT. The fourth phase relates to three different kinds of featureextraction techniques. Then these features are combined and optimized duringthe fifth phase. The optimized vector is used to classify the interactions in thelast phase. TheMSRDaily Activity 3D dataset has been used to test this modeland to prove its efficiency. The proposed system obtains an average accuracyof 91.7% on this dataset.展开更多
Human pose estimation is a critical research area in the field of computer vision,playing a significant role in applications such as human-computer interaction,behavior analysis,and action recognition.In this paper,we...Human pose estimation is a critical research area in the field of computer vision,playing a significant role in applications such as human-computer interaction,behavior analysis,and action recognition.In this paper,we propose a U-shaped keypoint detection network(DAUNet)based on an improved ResNet subsampling structure and spatial grouping mechanism.This network addresses key challenges in traditional methods,such as information loss,large network redundancy,and insufficient sensitivity to low-resolution features.DAUNet is composed of three main components.First,we introduce an improved BottleNeck block that employs partial convolution and strip pooling to reduce computational load and mitigate feature loss.Second,after upsampling,the network eliminates redundant features,improving the overall efficiency.Finally,a lightweight spatial grouping attention mechanism is applied to enhance low-resolution semantic features within the feature map,allowing for better restoration of the original image size and higher accuracy.Experimental results demonstrate that DAUNet achieves superior accuracy compared to most existing keypoint detection models,with a mean PCKh@0.5 score of 91.6%on the MPII dataset and an AP of 76.1%on the COCO dataset.Moreover,real-world experiments further validate the robustness and generalizability of DAUNet for detecting human bodies in unknown environments,highlighting its potential for broader applications.展开更多
Human pose estimation is a basic and critical task in the field of computer vision that involves determining the position(or spatial coordinates)of the joints of the human body in a given image or video.It is widely u...Human pose estimation is a basic and critical task in the field of computer vision that involves determining the position(or spatial coordinates)of the joints of the human body in a given image or video.It is widely used in motion analysis,medical evaluation,and behavior monitoring.In this paper,the authors propose a method for multi-view human pose estimation.Two image sensors were placed orthogonally with respect to each other to capture the pose of the subject as they moved,and this yielded accurate and comprehensive results of three-dimensional(3D)motion reconstruction that helped capture their multi-directional poses.Following this,we propose a method based on 3D pose estimation to assess the similarity of the features of motion of patients with motor dysfunction by comparing differences between their range of motion and that of normal subjects.We converted these differences into Fugl–Meyer assessment(FMA)scores in order to quantify them.Finally,we implemented the proposed method in the Unity framework,and built a Virtual Reality platform that provides users with human–computer interaction to make the task more enjoyable for them and ensure their active participation in the assessment process.The goal is to provide a suitable means of assessing movement disorders without requiring the immediate supervision of a physician.展开更多
Estimating 3D human pose from 2D images in real world contexts remains a challenge,characterized by unique data constraints.Large general datasets of motion-captured 3D adult human poses paired with 2D images exist,bu...Estimating 3D human pose from 2D images in real world contexts remains a challenge,characterized by unique data constraints.Large general datasets of motion-captured 3D adult human poses paired with 2D images exist,but in many application settings,collection of further motion-captured data is impossible,precluding a straightforward fine-tuning approach to adaptation.We present a method for improving 3D pose estimation transfer learning to domains where there are only depth camera images available as supervision.Our heuristic weakly supervised 3D human pose(HW-HuP)estimation method learns partial pose priors from general 3D human pose datasets and employs weak supervision with depth data to guide learning in an optimization and regression cycle.We show that HW-HuP meaningfully improves upon state-of-the-art models in the adult in-bed setting,as well as on large scale public 3D human pose datasets,under comparable supervision conditions.Our model code and data are publicly available at https://github.com/ostadabbas/hw-hup.A significantly expanded version of this paper,with supplementary material,is available as a preprint on arXiv at https://arxiv.org/abs/2105.10996.展开更多
Human pose estimation is an important task in computer vision,which can provide key point detection of human body and obtain bone information.At present,human pose estimation is mainly utilized for detection of large ...Human pose estimation is an important task in computer vision,which can provide key point detection of human body and obtain bone information.At present,human pose estimation is mainly utilized for detection of large targets,and there is no solution for detection of small targets.This paper proposes a multi-channel spatial information feature based human pose(MCSF-Pose)estimation algorithm to address the issue of medium and small targets inaccurate detection of human key points in scenarios involving occlusion and multiple poses.The MCSF-Pose network is a bottom-up regression network.Firstly,an UP-Focus module is designed to expand the feature information while reducing parameter computation during the up-sampling process.Then,the channel segmentation strategy is adopted to cut the features,and the feature information of multiple dimensions is retained through different convolutional groups,which reduces the parameter lightweight network model and makes up for the loss of the feature information associated with the depth of the network.Finally,the three-layer PANet structure is designed to reduce the complexity of the model.With the aid of the structure,it also to improve the detection accuracy and anti-interference ability of human key points.The experimental results indicate that the proposed algorithm outperforms YOLO-Pose and other human pose estimation algorithms on COCO2017 and MPII human pose datasets.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 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.
文摘Human pose estimation(HPE)is a procedure for determining the structure of the body pose and it is considered a challenging issue in the computer vision(CV)communities.HPE finds its applications in several fields namely activity recognition and human-computer interface.Despite the benefits of HPE,it is still a challenging process due to the variations in visual appearances,lighting,occlusions,dimensionality,etc.To resolve these issues,this paper presents a squirrel search optimization with a deep convolutional neural network for HPE(SSDCNN-HPE)technique.The major intention of the SSDCNN-HPE technique is to identify the human pose accurately and efficiently.Primarily,the video frame conversion process is performed and pre-processing takes place via bilateral filtering-based noise removal process.Then,the EfficientNet model is applied to identify the body points of a person with no problem constraints.Besides,the hyperparameter tuning of the EfficientNet model takes place by the use of the squirrel search algorithm(SSA).In the final stage,the multiclass support vector machine(M-SVM)technique was utilized for the identification and classification of human poses.The design of bilateral filtering followed by SSA based EfficientNetmodel for HPE depicts the novelty of the work.To demonstrate the enhanced outcomes of the SSDCNN-HPE approach,a series of simulations are executed.The experimental results reported the betterment of the SSDCNN-HPE system over the recent existing techniques in terms of different measures.
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supported in part by the US National Science Foundation(NSF)under Grants ECCS-1923163 and CNS-2107190through the Wireless Engineering Research and Education Center at Auburn University.
文摘Three-dimensional (3D) human pose tracking has recently attracted more and more attention in the computer vision field. Real-time pose tracking is highly useful in various domains such as video surveillance, somatosensory games, and human-computer interaction. However, vision-based pose tracking techniques usually raise privacy concerns, making human pose tracking without vision data usage an important problem. Thus, we propose using Radio Frequency Identification (RFID) as a pose tracking technique via a low-cost wearable sensing device. Although our prior work illustrated how deep learning could transfer RFID data into real-time human poses, generalization for different subjects remains challenging. This paper proposes a subject-adaptive technique to address this generalization problem. In the proposed system, termed Cycle-Pose, we leverage a cross-skeleton learning structure to improve the adaptability of the deep learning model to different human skeletons. Moreover, our novel cycle kinematic network is proposed for unpaired RFID and labeled pose data from different subjects. The Cycle-Pose system is implemented and evaluated by comparing its prototype with a traditional RFID pose tracking system. The experimental results demonstrate that Cycle-Pose can achieve lower estimation error and better subject generalization than the traditional system.
文摘Lots of progress has been made recently on 2 D human pose tracking with tracking-by-detection approaches. However,several challenges still remain in this area which is due to self-occlusions and the confusion between the left and right limbs during tracking. In this work,a head orientation detection step is introduced into the tracking framework to serve as a complementary tool to assist human pose estimation. With the face orientation determined,the system can decide whether the left or right side of the human body is exactly visible and infer the state of the symmetric counterpart. By granting a higher priority for the completely visible side,the system can avoid double counting to a great extent when inferring body poses. The proposed framework is evaluated on the HumanEva dataset. The results show that it largely reduces the occurrence of double counting and distinguishes the left and right sides consistently.
基金National Natural Science Foundation of China(61806176)the Fundamental Research Funds for the Central Universities(2019QNA5022).
文摘Recovering human pose from RGB images and videos has drawn increasing attention in recent years owing to minimum sensor requirements and applicability in diverse fields such as human-computer interaction,robotics,video analytics,and augmented reality.Although a large amount of work has been devoted to this field,3D human pose estimation based on monocular images or videos remains a very challenging task due to a variety of difficulties such as depth ambiguities,occlusion,background clutters,and lack of training data.In this survey,we summarize recent advances in monocular 3D human pose estimation.We provide a general taxonomy to cover existing approaches and analyze their capabilities and limitations.We also present a summary of extensively used datasets and metrics,and provide a quantitative comparison of some representative methods.Finally,we conclude with a discussion on realistic challenges and open problems for future research directions.
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the Shanghai Municipal Education Commission Project (No. SDL10026)
文摘In current interactive television schemes, the viewpoints should be manipulated by the user. However, there is no efficient method, to assist a user in automatically identifying and tracking the optimum viewpoint when the user observes the object of interest because many objects, most often humans, move rapidly and frequently. This paper proposes a novel framework for determining and tracking the virtual camera to best capture the front of the person of interest (PoI). First, one PoI is interactively chosen in a segmented 3D scene reconstructed by space carving method. Second, key points of the human torso of the PoI are detected by using a model-based method and the human's global motion including rotation and translation is estimated by using a close-formed method with 3 corresponding points. At the last step, the front direction of PoI is tracked temporally by using the unscented particle filter (UPF). Experimental results show that the method can properly compute the front direction of the PoI and robustly track the best viewpoints.
基金National Natural Science Foundation of China,No.61972458Natural Science Foundation of Zhejiang Province,No.LZ23F020002.
文摘Deep neural networks are vulnerable to attacks from adversarial inputs.Corresponding attack research on human pose estimation(HPE),particularly for body joint detection,has been largely unexplored.Transferring classification-based attack methods to body joint regression tasks is not straightforward.Another issue is that the attack effectiveness and imperceptibility contradict each other.To solve these issues,we propose local imperceptible attacks on HPE networks.In particular,we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack.Furthermore,we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection.Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness.We conducted a series of imperceptible attacks against state-of-the-art HPE methods,including HigherHRNet,DEKR,and ViTPose.The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels.Approximately 4%of the pixels can achieve sufficient attacks on HPE.
基金the National Natural Science Foundation of China(Grant Number 62076246).
文摘Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,humanpose estimation has achieved great success in multiple fields such as animation and sports.However,to obtainaccurate positioning results,existing methods may suffer from large model sizes,a high number of parameters,and increased complexity,leading to high computing costs.In this paper,we propose a new lightweight featureencoder to construct a high-resolution network that reduces the number of parameters and lowers the computingcost.We also introduced a semantic enhancement module that improves global feature extraction and networkperformance by combining channel and spatial dimensions.Furthermore,we propose a dense connected spatialpyramid pooling module to compensate for the decrease in image resolution and information loss in the network.Finally,ourmethod effectively reduces the number of parameters and complexitywhile ensuring high performance.Extensive experiments show that our method achieves a competitive performance while dramatically reducing thenumber of parameters,and operational complexity.Specifically,our method can obtain 89.9%AP score on MPIIVAL,while the number of parameters and the complexity of operations were reduced by 41%and 36%,respectively.
基金supported by the Key Project of NSFC(Grant No.U1908214)Special Project of Central Government Guiding Local Science and Technology Development(Grant No.2021JH6/10500140)+5 种基金the Program for Innovative Research Team in University of Liaoning Province(LT2020015)the Support Plan for Key Field Innovation Team of Dalian(2021RT06)the Support Plan for Leading Innovation Team of Dalian University(XLJ202010)the Science and Technology Innovation Fund of Dalian(Grant No.2020JJ25CY001)in part by the National Natural Science Foundation of China under Grant 61906032the FundamentalResearch Funds for the Central Universities under Grant DUT21TD107.
文摘With the advancement of image sensing technology, estimating 3Dhuman pose frommonocular video has becomea hot research topic in computer vision. 3D human pose estimation is an essential prerequisite for subsequentaction analysis and understanding. It empowers a wide spectrum of potential applications in various areas, suchas intelligent transportation, human-computer interaction, and medical rehabilitation. Currently, some methodsfor 3D human pose estimation in monocular video employ temporal convolutional network (TCN) to extractinter-frame feature relationships, but the majority of them suffer from insufficient inter-frame feature relationshipextractions. In this paper, we decompose the 3D joint location regression into the bone direction and length, wepropose the TCG, a temporal convolutional network incorporating Gaussian error linear units (GELU), to solvebone direction. It enablesmore inter-frame features to be captured andmakes the utmost of the feature relationshipsbetween data. Furthermore, we adopt kinematic structural information to solve bone length enhancing the use ofintra-frame joint features. Finally, we design a loss function for joint training of the bone direction estimationnetwork with the bone length estimation network. The proposed method has extensively experimented on thepublic benchmark dataset Human3.6M. Both quantitative and qualitative experimental results showed that theproposed method can achieve more accurate 3D human pose estimations.
基金This research was supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2023-2018-0-01426)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation)This work has also been supported by PrincessNourah bint Abdulrahman UniversityResearchers Supporting Project Number(PNURSP2022R239),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.Alsothis work was partially supported by the Taif University Researchers Supporting Project Number(TURSP-2020/115),Taif University,Taif,Saudi Arabia.
文摘Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has attractedmany researchers to this field. Inspired by the existing recognition systems,this paper proposes a new and efficient human-object interaction recognition(HOIR) model which is based on modeling human pose and scene featureinformation. There are different aspects involved in an interaction, includingthe humans, the objects, the various body parts of the human, and the backgroundscene. Themain objectives of this research include critically examiningthe importance of all these elements in determining the interaction, estimatinghuman pose through image foresting transform (IFT), and detecting the performedinteractions based on an optimizedmulti-feature vector. The proposedmethodology has six main phases. The first phase involves preprocessing theimages. During preprocessing stages, the videos are converted into imageframes. Then their contrast is adjusted, and noise is removed. In the secondphase, the human-object pair is detected and extracted from each image frame.The third phase involves the identification of key body parts of the detectedhumans using IFT. The fourth phase relates to three different kinds of featureextraction techniques. Then these features are combined and optimized duringthe fifth phase. The optimized vector is used to classify the interactions in thelast phase. TheMSRDaily Activity 3D dataset has been used to test this modeland to prove its efficiency. The proposed system obtains an average accuracyof 91.7% on this dataset.
基金supported by the Natural Science Foundation of Hubei Province of China under grant number 2022CFB536the National Natural Science Foundation of China under grant number 62367006the 15th Graduate Education Innovation Fund of Wuhan Institute of Technology under grant number CX2023579.
文摘Human pose estimation is a critical research area in the field of computer vision,playing a significant role in applications such as human-computer interaction,behavior analysis,and action recognition.In this paper,we propose a U-shaped keypoint detection network(DAUNet)based on an improved ResNet subsampling structure and spatial grouping mechanism.This network addresses key challenges in traditional methods,such as information loss,large network redundancy,and insufficient sensitivity to low-resolution features.DAUNet is composed of three main components.First,we introduce an improved BottleNeck block that employs partial convolution and strip pooling to reduce computational load and mitigate feature loss.Second,after upsampling,the network eliminates redundant features,improving the overall efficiency.Finally,a lightweight spatial grouping attention mechanism is applied to enhance low-resolution semantic features within the feature map,allowing for better restoration of the original image size and higher accuracy.Experimental results demonstrate that DAUNet achieves superior accuracy compared to most existing keypoint detection models,with a mean PCKh@0.5 score of 91.6%on the MPII dataset and an AP of 76.1%on the COCO dataset.Moreover,real-world experiments further validate the robustness and generalizability of DAUNet for detecting human bodies in unknown environments,highlighting its potential for broader applications.
基金This work was supported by grants fromthe Natural Science Foundation of Hebei Province,under Grant No.F2021202021the S&T Program of Hebei,under Grant No.22375001Dthe National Key R&D Program of China,under Grant No.2019YFB1312500.
文摘Human pose estimation is a basic and critical task in the field of computer vision that involves determining the position(or spatial coordinates)of the joints of the human body in a given image or video.It is widely used in motion analysis,medical evaluation,and behavior monitoring.In this paper,the authors propose a method for multi-view human pose estimation.Two image sensors were placed orthogonally with respect to each other to capture the pose of the subject as they moved,and this yielded accurate and comprehensive results of three-dimensional(3D)motion reconstruction that helped capture their multi-directional poses.Following this,we propose a method based on 3D pose estimation to assess the similarity of the features of motion of patients with motor dysfunction by comparing differences between their range of motion and that of normal subjects.We converted these differences into Fugl–Meyer assessment(FMA)scores in order to quantify them.Finally,we implemented the proposed method in the Unity framework,and built a Virtual Reality platform that provides users with human–computer interaction to make the task more enjoyable for them and ensure their active participation in the assessment process.The goal is to provide a suitable means of assessing movement disorders without requiring the immediate supervision of a physician.
基金supported by the National Science Foundation under Grant No.1755695.
文摘Estimating 3D human pose from 2D images in real world contexts remains a challenge,characterized by unique data constraints.Large general datasets of motion-captured 3D adult human poses paired with 2D images exist,but in many application settings,collection of further motion-captured data is impossible,precluding a straightforward fine-tuning approach to adaptation.We present a method for improving 3D pose estimation transfer learning to domains where there are only depth camera images available as supervision.Our heuristic weakly supervised 3D human pose(HW-HuP)estimation method learns partial pose priors from general 3D human pose datasets and employs weak supervision with depth data to guide learning in an optimization and regression cycle.We show that HW-HuP meaningfully improves upon state-of-the-art models in the adult in-bed setting,as well as on large scale public 3D human pose datasets,under comparable supervision conditions.Our model code and data are publicly available at https://github.com/ostadabbas/hw-hup.A significantly expanded version of this paper,with supplementary material,is available as a preprint on arXiv at https://arxiv.org/abs/2105.10996.
基金supported by the Liaoning Provincial Science and Technology Plan Project 2023JH2/101300205the Shenyang Science and Technology Plan Project 23-407-3-33.
文摘Human pose estimation is an important task in computer vision,which can provide key point detection of human body and obtain bone information.At present,human pose estimation is mainly utilized for detection of large targets,and there is no solution for detection of small targets.This paper proposes a multi-channel spatial information feature based human pose(MCSF-Pose)estimation algorithm to address the issue of medium and small targets inaccurate detection of human key points in scenarios involving occlusion and multiple poses.The MCSF-Pose network is a bottom-up regression network.Firstly,an UP-Focus module is designed to expand the feature information while reducing parameter computation during the up-sampling process.Then,the channel segmentation strategy is adopted to cut the features,and the feature information of multiple dimensions is retained through different convolutional groups,which reduces the parameter lightweight network model and makes up for the loss of the feature information associated with the depth of the network.Finally,the three-layer PANet structure is designed to reduce the complexity of the model.With the aid of the structure,it also to improve the detection accuracy and anti-interference ability of human key points.The experimental results indicate that the proposed algorithm outperforms YOLO-Pose and other human pose estimation algorithms on COCO2017 and MPII human pose datasets.
