Ghost shuffle lightweight pose network with effective feature representation and learning for human pose estimation. Issue 6 (17th May 2022)

• Record Type: Journal Article
• Authors: Yang, Senquan; Wen, Jiajun; Fan, Junjun
• Is Part Of: IET computer vision. Volume 16:Issue 6(2022)
• Page Start: 525
• Page End: 540
• Publication Date: 2022-05-17
• Subjects: ghost shuffle lightweight module -- human pose estimation -- lightweight pose parallel attention; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/cvi2.12110
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract: Despite their success, existing human pose estimation approaches mostly have complex architectures, high cost, and lack of lightweight modules. To address this problem, this paper proposes a Ghost Shuffle Lightweight Pose Network (GSLPN) with a more lightweight and efficient network architecture than the popular Lightweight Pose Network. First, in order to condense the scale of the network while maintaining its performance, we stack two lightweight modules, depthwise convolution and the Ghost module, to build our initial prototype bottleneck. Then, we impose a channel shuffle operation on the prototype bottleneck to shuffle the sequence of the feature maps for constructing Ghost Shuffle Bottleneck (Ghost Shuffle Bottleneck) with effective feature representation so as to develop a GSLPN. Second, a lightweight, efficient parallel attention mechanism, Lightweight Pose Parallel Attention, is proposed to improve keypoint locating accuracy. An experiment validating the proposed method showed that GSLPN achieved competitive performance with a smaller model size and less computational complexity than state‐of‐the‐art methods, indicating that the GSLPN is a superior approach for human pose estimation.