基于多区域分割的步态表示与识别算法研究

Gait Representation and Classification Algorithm Based on Multi Area Segmentation

提出了一种基于多区域分割的步态表示方法,将视频中的目标人体区域部分按人体结构特点划分为多个子区,每个子区通过连接人体重心的椭圆进行拟和,建立多连接椭圆的人体结构模型,预处理阶段引入一个归一化过程以实现对各种视角下的步态序列进行表示.识别过程将模型参数作为步态特征,并引入了一定的融合机制对特征进行选择和融合.实验表明,该算法对于多个视角下的步态序列均具有较好的识别性能.

Gait, which has been developed to recognize people by their habitual walking styles, has attracted much attention in recent years. A new method of gait representation is put forward in the paper. In the pretreatment, image processing and computer vision techniques are employed to track and separate objects from the background. By means of dividing human body area in a video sequence into several sub-areas, representing each sub-area through an ellipse whose parameters can be calculated from the corresponding sub-area, a new body structure model called multi-linked ellipse model is established. In order to enable the method to represent gait of various viewing angles other than just single viewing angle, a normalization process is introduced. In the recognition stage, parameters of the model are used as gait signatures and an information fusion algorithm is proposed to select and combine these signatures. Experimental results prove the higher performance of the method.