郑州大学学报（理学版）2025，Vol.57Issue(4)：1-7,7.DOI:10.13705/j.issn.1671-6841.2024027
复杂场景下的多人人体姿态估计算法
Multi-person Pose Estimation Algorithm in Complex Scenes
摘要
Abstract
The cross-obscuration of individuals in complex scenes led to low accuracy and incorrect skele-ton connections in existing human pose estimation algorithms.Therefore,a multi-person pose estimation optimization algorithm in complex scenes was proposed.Firstly,the ordinary convolution was replaced with the grouped cascade convolution,which was combined with feature fusion to promote the exchange of information between channels.The accuracy of the algorithm was improved without incurring additional computational costs.Secondly,the spatial attention mechanism was introduced to mine the spatial seman-tic features related to the human pose estimation task,and the network structure was parallelized to en-hance the performance of the algorithm.Finally,the embedding positions of the large convolutional ker-nel and the attention mechanism were lightweighted to reduce temporal overhead.Compared to the exist-ing bottom-up pose estimation algorithm OpenPifPaf++,the proposed algorithm improved the average ac-curacy by 0.8 percentage points on the COCO 2017 dataset.Compared with the OpenPifPaf algorithm,the proposed algorithm improved the average accuracy by 1.2 percentage points on the CrowdPose data-set,and the corresponding accuracy for complex scenes by 1.5 percentage points.关键词
复杂场景/多人人体姿态估计/分组卷积/空间注意力机制/轻量化Key words
complex scene/multi-person pose estimation/group convolution/spatial attention mecha-nism/lightweight分类
计算机与自动化引用本文复制引用
石磊,王天宝,孟彩霞,王清贤,高宇飞,卫琳..复杂场景下的多人人体姿态估计算法[J].郑州大学学报（理学版）,2025,57(4):1-7,7.基金项目
国家自然科学基金项目(62006210) （62006210）
国家重点研发计划项目(2020YFB1712401-1) （2020YFB1712401-1）
