基于改进骨架毛刺剪除的人体关节点定位方法

摘要

人体骨架提取及关节点定位是人体动作识别中的重要问题.本文针对人体骨架提取过程中基于长度约束易将骨架主体误判为毛刺的问题,提出了基于斜率约束的人体骨架提取方法.针对关节点定位采用传统链码遍历结构适用性不强的缺点,扩展了遍历结构搜索范围;针对最大三角形面积法在四肢曲率较小时四肢拐点定位误差大的不足,采用关节比例对四肢拐点进行定位,提高定位精度和适应性.实验结果表明,本文提出的改进方法能准确剪除毛刺,提取人体骨架,采用改进的关节点定位方法实现了人体关节点的准确定位,提高了拐点定位精度.%Human skeleton extraction and joints location are important steps in human action recognition.Slope constraint for human skeleton extraction is proposed for the skeleton burrs to solve the wrong judgment caused by the method of length constraint in human skeleton extraction.Search range of traversal structure has been extended to improve the applicability of traditional chain code traversal structure.The human body proportion method for limb joints location was proposed to solve the large deviation caused by the method of maximum triangle area when curvature of limbs was small.Experiment results showed that the burrs were removed and the body skeleton was remained correctly and the body joints were located accurately based on the methods proposed in the paper.