SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation
In the field of human pose estimation, heatmap-based methods have emerged as the dominant approach, and numerous studies have achieved remarkable performance based on this technique. However, the inherent drawbacks of heatmaps lead to serious performance degradation in methods based on heatmaps for...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7299 |
| _version_ | 1827727817206398976 |
|---|---|
| author | Shaohua Li Haixiang Zhang Hanjie Ma Jie Feng Mingfeng Jiang |
| author_facet | Shaohua Li Haixiang Zhang Hanjie Ma Jie Feng Mingfeng Jiang |
| author_sort | Shaohua Li |
| collection | DOAJ |
| description | In the field of human pose estimation, heatmap-based methods have emerged as the dominant approach, and numerous studies have achieved remarkable performance based on this technique. However, the inherent drawbacks of heatmaps lead to serious performance degradation in methods based on heatmaps for smaller-scale persons. While some researchers have attempted to tackle this issue by improving the performance of small-scale persons, their efforts have been hampered by the continued reliance on heatmap-based methods. To address this issue, this paper proposes the SSA Net, which aims to enhance the detection accuracy of small-scale persons as much as possible while maintaining a balanced perception of persons at other scales. SSA Net utilizes HRNetW48 as a feature extractor and leverages the TDAA module to enhance small-scale perception. Furthermore, it abandons heatmap-based methods and instead adopts coordinate vector regression to represent keypoints. Notably, SSA Net achieved an <i>AP</i> of 77.4% on the COCO Validation dataset, which is superior to other heatmap-based methods. Additionally, it achieved highly competitive results on the Tiny Validation and MPII datasets as well. |
| first_indexed | 2024-03-10T23:13:23Z |
| format | Article |
| id | doaj.art-6b6c130f7c6a484f82352c1197beb58f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:13:23Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6b6c130f7c6a484f82352c1197beb58f2023-11-19T08:48:09ZengMDPI AGSensors1424-82202023-08-012317729910.3390/s23177299SSA Net: Small Scale-Aware Enhancement Network for Human Pose EstimationShaohua Li0Haixiang Zhang1Hanjie Ma2Jie Feng3Mingfeng Jiang4School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaIn the field of human pose estimation, heatmap-based methods have emerged as the dominant approach, and numerous studies have achieved remarkable performance based on this technique. However, the inherent drawbacks of heatmaps lead to serious performance degradation in methods based on heatmaps for smaller-scale persons. While some researchers have attempted to tackle this issue by improving the performance of small-scale persons, their efforts have been hampered by the continued reliance on heatmap-based methods. To address this issue, this paper proposes the SSA Net, which aims to enhance the detection accuracy of small-scale persons as much as possible while maintaining a balanced perception of persons at other scales. SSA Net utilizes HRNetW48 as a feature extractor and leverages the TDAA module to enhance small-scale perception. Furthermore, it abandons heatmap-based methods and instead adopts coordinate vector regression to represent keypoints. Notably, SSA Net achieved an <i>AP</i> of 77.4% on the COCO Validation dataset, which is superior to other heatmap-based methods. Additionally, it achieved highly competitive results on the Tiny Validation and MPII datasets as well.https://www.mdpi.com/1424-8220/23/17/7299pose estimationscale-aware enhancementkeypoint detection |
| spellingShingle | Shaohua Li Haixiang Zhang Hanjie Ma Jie Feng Mingfeng Jiang SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation Sensors pose estimation scale-aware enhancement keypoint detection |
| title | SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation |
| title_full | SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation |
| title_fullStr | SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation |
| title_full_unstemmed | SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation |
| title_short | SSA Net: Small Scale-Aware Enhancement Network for Human Pose Estimation |
| title_sort | ssa net small scale aware enhancement network for human pose estimation |
| topic | pose estimation scale-aware enhancement keypoint detection |
| url | https://www.mdpi.com/1424-8220/23/17/7299 |
| work_keys_str_mv | AT shaohuali ssanetsmallscaleawareenhancementnetworkforhumanposeestimation AT haixiangzhang ssanetsmallscaleawareenhancementnetworkforhumanposeestimation AT hanjiema ssanetsmallscaleawareenhancementnetworkforhumanposeestimation AT jiefeng ssanetsmallscaleawareenhancementnetworkforhumanposeestimation AT mingfengjiang ssanetsmallscaleawareenhancementnetworkforhumanposeestimation |