小波特征和协同表示的步态识别研究

Research ongait recognition of wavelet and cooperative representation

提出一种步态能量图(Gait Energy Image,GEI)的Gabor小波特征与协同表示的步态识别算法.首先通过运动目标检测,二值化和形态学处理等预处理操作得到步态轮廓图,然后进一步从步态轮廓图计算得到步态能量图.该算法将步态能量图的Gabor特征作为特征矢量,采用协同表示的方法进行步态识别.在实验阶段,通过在中科院自动化研究所CASIA步态数据库的Dataset B上进行测试,证明上述算法具有运行速度快的优点,并且对于跨视角步态识别具有一定的鲁棒性.

A gait recognition algorithm based on Gabor wavelet feature of GEI and collaborative representation was proposed. The detected moving target was processed with binarization and morphological precessing to get the gait contour map and calculate the gait energy image. The algorithm represented the gait recognition by using the collaborative method with Gabor gait energy image as the feature vector. In the experimental stage, tested by the Chinese Academy of Sciences Institute of Automation CASIA Dataset B gait database, it shows that the algorithm has the advantages of fast operation speed, and is robust to cross view gait recognition.