计算机应用研究2017，Vol.34Issue(5)：1553-1559,7.DOI:10.3969/j.issn.1001-3695.2017.05.062
一种有效的基于点云特征人体识别方法
Efficient method of human recognition based on point cloud
摘要
Abstract
The recognition of moving objects that based on visual information is an important aspect of autonomous navigation for indoors mobile robot.The existing methods have influence on the stability of human recognition because of the background noise,natural lighting,the change of the robots views.Aiming at solving this question,this paper presented an efficient object recognition method.This method recognized and filtered the point cloud of ground plane,and fused the methods of clustering segmentation and support vector machine to recognize moving objects or obstacles.The experiments show that,compared with the algorithm of human bones recognition or two dimensional histogram of oriented gradient,this method has the higher accuracy,and is more suitable for the recognition of human or obstacles in the complex environment,meeting the real-time requirement.关键词
人体识别/点云滤波/点云分割/支持向量机Key words
human recognition/points cloud filtering/point cloud segmentation/SVM分类
信息技术与安全科学引用本文复制引用
杨晶东,韩太军..一种有效的基于点云特征人体识别方法[J].计算机应用研究,2017,34(5):1553-1559,7.基金项目
国家自然科学基金资助项目(61202376,61374039) （61202376,61374039）
上海市自然基金资助项目(15ZR1429100) （15ZR1429100）
沪江基金资助项目(C14002) （C14002）
