Abstract | ||
---|---|---|
Existing deep learning based methods for 3D human pose estimation cannot be deployed on resource-constrained devices. In this paper, we propose a Tiny-HourglassNet for 3D human pose estimation that improves the efficiency of Stacked Hourglass Networks with a guarantee of estimation performance. To be concrete, we develop an efficient Tiny-Hourglass backbone with two different types of ShuffleNet V2 blocks. At the meantime, we present a Simple Estimation Head (SEH) to reduce the resource utility for depth prediction. Furthermore, we develop two feature enhancement modules, namely Feature Enhancement Module (FEM) and Intermediate Enhancement Module (IEM), to improve the feature representation ability of Tiny-HourglassNet without evident increment of resource usage and computational complexity. Experimental results demonstrate that Tiny-HourglassNet achieves equivalent accuracy with a reduction of 80% complexity (FLOPs) in comparison to the baselines. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICIP40778.2020.9191056 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
3D human pose estimation, resource usage, feature enhancement modules, equal-level accuracy | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bowen Shi | 1 | 0 | 1.01 |
Yuhui Xu | 2 | 12 | 5.00 |
Wenrui Dai | 3 | 64 | 25.01 |
Botao Wang | 4 | 171 | 77.07 |
Shuai Zhang | 5 | 45 | 6.63 |
Chenglin Li | 6 | 116 | 17.93 |
J. Zou | 7 | 203 | 35.51 |
Hongkai Xiong | 8 | 512 | 82.84 |