Abstract: Analyzing human gait has found considerable interest in recent computer vision research.So far，contributions to this topic exclusively dealt with the tasks of person identification or activity recognition.A simple but effective approach to abnormal gait analysis is proposed using computer vision techniques.After segmented the foreground object，the authors extract the feature vector reflecting the abnormal gait from the aspect ratio and achieve the abnormal gait recognition by Support Vector Machines（SVM）.Experimental results show its promising performance.

Key words: computer vision, image processing, abnormal gait recognition, Support Vector Machines（SVM）

摘要： 基于计算机视觉的步态分析是计算机视觉领域的研究热点。目前的研究大多集中在通过对正常步态的分析实现身份识别，而通过异常步态分析来识别人的异常状况方面的研究却很少。提出了一种简单有效的基于计算机视觉的异常步态识别方法，通过人的宽高比提取反应步态特征的特征向量，然后用支持向量机进行异常步态的识别。实验结果表明了该方法的有效性。

关键词: 计算机视觉, 图像处理, 异常步态识别, 支持向量机