Affiliation:
1. College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China
Abstract
This paper presents a novel approach to address the problem of increasing the number of parameters in existing human posture estimation network models while trying to improve prediction accuracy. We propose a human posture estimation optimization network model, called BDENet, which is based on the high-resolution detection network (HRNet). BDENet incorporates a bottleneck structure and depth-separable convolution to reduce the number of parameters. Additionally, it introduces an efficient channel attention (ECA) lightweight attention mechanism to enhance accuracy. We evaluate the proposed model using the MSCOCO dataset and compare it with HRNet. The experimental results demonstrate that BDENet achieves a 41.4% reduction in the number of parameters compared to HRNet, while achieving a 0.6% increase in accuracy. These findings confirm that the network model proposed in this paper can effectively improve accuracy while reducing the number of parameters.
Funder
the Chongqing Normal University
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference30 articles.
1. Jhuang, H., Gall, J., Zuffi, S., Schmid, C., and Black, M.J. (2013, January 1–8). Towards understanding action recognition. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia.
2. A survey of augmented reality;Azuma;Presence Virtual Augment. Real.,1997
3. Mobile gaming: Industry challenges and policy implications;Feijoo;Telecommun. Policy,2012
4. Robust pose estimation from a planar target;Schweighofer;IEEE Trans. Pattern Anal. Mach. Intell.,2006
5. Wang, R., Mou, S., Wang, X., Xiao, W., Ju, Q., Shi, C., and Xie, X. (2021, January 12–23). Graph structure estimation neural networks. Proceedings of the Web Conference 2021, Online.