摘要
步态识别是一种新的生物识别技术,它通过人行走的姿势来实现对人身份的鉴别。本文提出了一种基于多区域不变矩的步态识别方法,将视频序列中检测出的步态侧影分为五个子区域,提取每个子区域的不变矩特征并计算步态序列中不变矩的变化特征,从而构成描述步态序列的特征向量。最后的实验表明,提出的方法具有较好的识别性能,是一种有效的步态识别方法。
Gait recognition, a new biometrics recognition technology, can discriminate individuals by the way they walk. A gait recognition method based on moment invariants of multi-regions is proposed in this paper. Firstly, it divides the detected human silhouette into five sub-regions in the video sequence. Secondly, by means of extracting moment invariants features of each sub-region and computing their changing features in the gait sequence, the gait feature vectors can be constructed. Finally, experimental results show that our approach is valid and has encouraging recognition performance.
出处
《计算机科学》
CSCD
北大核心
2007年第11期167-169,188,共4页
Computer Science
基金
国家自然科学基金(60672074)
江苏省自然科学基金(BK2006569)
关键词
步态识别
背景减除
特征提取
不变矩
Gait recognition, Background subtraction, Feature extraction, Moment invariants
