<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Two-dimensional human pose estimation has been widely applied in real-world applications such as sports analysis, medical fall detection, human-robot interaction, with many positive results obtained utilizing Convolutional Neural Networks (CNNs). Li et al. at CVPR 2020 proposed a study in which they achieved high accuracy in estimating 2D keypoints estimation/2D human pose estimation. However, the study performed estimation only on the cropped human image data. In this research, we propose a method for automatically detecting and estimating human poses in photos using a combination of YOLOv5 + CC (Contextual Constraints) and HRNet. Our approach inherits the speed of the YOLOv5 for detecting humans and the efficiency of the HRNet for estimating 2D keypoints/2D human pose on the images. We also performed human marking on the images by bounding boxes of the Human 3.6M dataset (Protocol #1) for human detection evaluation. Our approach obtained high detection results in the image and the processing time is 55 FPS on the Human 3.6M dataset (Protocol #1). The mean error distance is 5.14 pixels on the full size of the image (1000 × 1002). In particular, the average results of 2D human pose estimation/2D keypoints estimation are 94.8% of PCK and 99.2% of PDJ@0.4 (head joint). The results are available.</p>
</abstract>

Two-dimensional human pose estimation has been widely applied in real-world applications such as sports analysis, medical fall detection, human-robot interaction, with many positive results obtained utilizing Convolutional Neural Networks (CNNs). Li et al. at CVPR 2020 proposed a study in which they achieved high accuracy in estimating 2D keypoints estimation/2D human pose estimation. However, the study performed estimation only on the cropped human image data. In this research, we propose a method for automatically detecting and estimating human poses in photos using a combination of YOLOv5 + CC (Contextual Constraints) and HRNet. Our approach inherits the speed of the YOLOv5 for detecting humans and the efficiency of the HRNet for estimating 2D keypoints/2D human pose on the images. We also performed human marking on the images by bounding boxes of the Human 3.6M dataset (Protocol #1) for human detection evaluation. Our approach obtained high detection results in the image and the processing time is 55 FPS on the Human 3.6M dataset (Protocol #1). The mean error distance is 5.14 pixels on the full size of the image (1000 × 1002). In particular, the average results of 2D human pose estimation/2D keypoints estimation are 94.8% of PCK and 99.2% of PDJ@0.4 (head joint). The results are available.

Combined YOLOv5 and HRNet for High Accuracy 2D Keypoint and Human Pose Estimation

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Two-dimensional human pose estimation has been widely applied in real-world applications such as sports analysis, medical fall detection, human-robot...

Combined YOLOv5 and HRNet for High Accuracy 2D Keypoint and Human Pose Estimation

Published Online: Oct 29, 2022

Page range: 281 - 298

Received: Jun 15, 2022

Accepted: Oct 18, 2022

DOI: https://doi.org/10.2478/jaiscr-2022-0019

Keywords
YOLOv5, HRNet, 2D key points estimation, 2D human pose estimation

© 2022 Hung-Cuong Nguyen et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Combined YOLOv5 and HRNet for High Accuracy 2D Keypoint and Human Pose Estimation

Published Online: Oct 29, 2022

Page range: 281 - 298

Received: Jun 15, 2022

Accepted: Oct 18, 2022

DOI: https://doi.org/10.2478/jaiscr-2022-0019

KeywordsYOLOv5, HRNet, 2D key points estimation, 2D human pose estimation

© 2022 Hung-Cuong Nguyen et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
YOLOv5, HRNet, 2D key points estimation, 2D human pose estimation