软件导刊2024，Vol.23Issue(6)：136-142,7.DOI:10.11907/rjdk.241182
基于改进高分辨率网络的人体姿态估计
Human Pose Estimation Based on Improved High-Resolution Network
摘要
Abstract
To achieve more accurate positioning of human body key points,a human pose estimation model and algorithm are introduced based on a high-resolution detection network(HRNet)with a waterfall shaped cavity spatial convolution module and Transformer.Firstly,a waterfall like hollow space convolution module is constructed to replace the fourth stage of HRNet,reducing the problem of large parameter quantities caused by the fusion of features at different scales and extracting multi-scale features more efficiently;Then,a Transformer based on self attention mechanism is introduced to process the extracted high-level features,and feature enhancement is achieved by capturing the non local interaction relationships of key points in the global space to obtain global information.The experiment shows that when the input im-age resolution is 256×192,the proposed model improves AP by 2.4%and 2.3%respectively compared to the HRNet-W32 and HRNet-W48 baseline models with a decrease in parameter count.关键词
人体姿态估计/高分辨率网络/瀑布式空洞卷积/注意力机制/多尺度Key words
human pose estimation/high-resolution network/waterfall dilated convolution/attention mechanism/multi-scale分类
信息技术与安全科学引用本文复制引用
刘洁,陈志,岳文静..基于改进高分辨率网络的人体姿态估计[J].软件导刊,2024,23(6):136-142,7.基金项目
江苏省重点研发计划(社会发展)项目(BE2019739) （社会发展）
中兴通讯产学研合作基金项目(2021H2ZTE05-01) （2021H2ZTE05-01）
