Unified End-to-End YOLOv5-HR-TCM Framework for Automatic 2D/3D Human Pose Estimation for Real-Time Applications

Nguyen, Hung‐Cuong; Nguyen, Thi-Hao; Scherer, Rafał; Le, Van-Hung

doi:10.3390/s22145419

Cited by 24 publications

(16 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Inspired by CAN ( Hou et al, 2019 ), other low-resolution visual markers will interact with the highest resolution visual markers in the cross attention with multi-scales to enhance the resolution of low-resolution visual markers. (3) Two groups of key point markers are cross-extracted in the fusion module to obtain visual marker information of different resolutions ( Le, 2022 ; Dai et al, 2022 ).…”

Section: A Human Pose Estimation Methods Based On Cross-attention For...mentioning

confidence: 99%

Analysis of the mixed teaching of college physical education based on the health big data and blockchain technology

Liu

2023

PeerJ Computer Science

View full text Add to dashboard Cite

In the era of health big data, with the continuous development of information technology, students’ physical health management also relies more on various information technologies. Blockchain, as an emerging technology in recent years, has the characteristics of high efficiency and intelligence. College physical education is an important part of college students’ health big data. Unlike cultural classes, physical education with its rich movements and activities, leaves teachers no time to monitor students’ real classroom performance. Therefore, we propose a human pose estimation method based on cross-attention-based Transformer multi-scale representation learning to monitor students’ class concentration. Firstly, the feature maps with different resolution are obtained by deep convolutional network and these feature maps are transformed into multi-scale visual markers. Secondly, we propose a cross-attention module with the multi-scales. The module reduces the redundancy of key point markers and the number of cross fusion operations through multiple interactions between feature markers with different resolutions and the strategy of moving key points for key point markers. Finally, the cross-attention fusion module extracts feature information of different scales from feature tags to form key tags. We can confirm the performance of the cross-attention module and the fusion module by the experimental results conducting on MSCOCO datasets, which can effectively promote the Transformer encoder to learn the association relationship between key points. Compared with the completive TokenPose method, our method can reduce the computational cost by 11.8% without reducing the performance.

show abstract

Section: A Human Pose Estimation Methods Based On Cross-attention For...mentioning

confidence: 99%

Analysis of the mixed teaching of college physical education based on the health big data and blockchain technology

Liu

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…According to the differences in human posture dimensions, human posture estimation tasks can be divided into 2D human posture estimation and 3D human posture estimation [5]. The goal of 2D human pose estimation (2D HPE) [6] is to locate and identify the key points of the human body, and connect these key points according to the joint sequence to form a projection on the two-dimensional plane of the image, so as to obtain the human skeleton consistent with the real person [7].…”

Section: Human Posture Recognition Categorymentioning

confidence: 99%

“…In recent years, with the successful application of deep learning in the field of human posture estimation, the accuracy and generalization ability of 2D HPE have been significantly improved. The more advanced is the open-source library Openpose [5] developed by Carnegie Mellon University (CMU) based on convolutional neural network and supervised learning, which is the most popular 2D human posture estimation method at present, and it is an open-source real-time multi-person detection with high accuracy key points, However, 3D human posture data cannot be recognized, and the robustness is poor, and the requirements for computer graphics card equipment are high [8].…”

Section: Human Pose Recognition Algorithms At Home and Abroadmentioning

confidence: 99%

Detection of 3D Human Posture Based on Improved Mediapipe

Lin¹,

Jiao²,

Zhao³

2023

JCC

View full text Add to dashboard Cite

Based on the continuous development of motion capture technology for ordinary video images, unmarked optical motion capture has become the fastest human posture recognition technology. Compared with other technical products, Google's 3D human body recognition framework-Mediapipe is the most mature representative in this field. However, Mediapipe also has many defects in the detection of 3D human posture. In this paper, firstly, to solve the problem of inaccurate detection of human posture by Mediapipe, the accuracy of 2D human posture detection is improved through the speed threshold correction method for each joint; According to the problem that the monocular camera can not detect the depth Z value in the human posture data accurately, the Z value of the joint point is corrected for the human tilt angle through statistics; Then, according to the inaccurate recognition of Z value caused by large body posture, the accurate correction of Z value of human posture under different body posture is realized by normalizing the simulation proportion of each body limb; Finally, in order to solve the problem of jitter, lag problem and periodic noise in multiple frames caused by the speed change of human joints, one euro filtering and mean filtering of joint data are carried out. This paper verifies that the accuracy of 3D human posture detection based on the improved Mediapipe is more than 90% through the multi-pose recognition test for people of different heights, weights, ages and gender.

show abstract

“…All these methods require a large number of computational resources to accurately estimate the attitude. To solve this problem, Hung-Cuong et al [ 11 ] proposed a fast, unified end-to-end model for estimating the 3D human pose, called YOLOv5-HR-TCM ( YOLOv5-HRet-Temporal Convolution Model). Hung-Cuong et al also applied the YOLOv5-HR-TCM to the assessment and scoring of artistic gymnastics and training and dance assessments.…”

Section: Related Workmentioning

confidence: 99%

Faster Deep Inertial Pose Estimation with Six Inertial Sensors

Xia

Zhu

Zhang

2022

Sensors

View full text Add to dashboard Cite

We propose a novel pose estimation method that can predict the full-body pose from six inertial sensors worn by the user. This method solves problems encountered in vision, such as occlusion or expensive deployment. We address several complex challenges. First, we use the SRU network structure instead of the bidirectional RNN structure used in previous work to reduce the computational effort of the model without losing its accuracy. Second, our model does not require joint position supervision to achieve the best results of the previous work. Finally, since sensor data tend to be noisy, we use SmoothLoss to reduce the impact of inertial sensors on pose estimation. The faster deep inertial poser model proposed in this paper can perform online inference at 90 FPS on the CPU. We reduce the impact of each error by more than 10% and increased the inference speed by 250% compared to the previous state of the art.

show abstract

Unified End-to-End YOLOv5-HR-TCM Framework for Automatic 2D/3D Human Pose Estimation for Real-Time Applications

Cited by 24 publications

References 79 publications

Analysis of the mixed teaching of college physical education based on the health big data and blockchain technology

Analysis of the mixed teaching of college physical education based on the health big data and blockchain technology

Detection of 3D Human Posture Based on Improved Mediapipe

Faster Deep Inertial Pose Estimation with Six Inertial Sensors

Contact Info

Product

Resources

About