Moving Object Classification Method Based on SOM and K-means

We do research on moving object classification in traffic video. Our aim is to classify the moving objects into pedestrians, bicycles and vehicles. Due to the advantage of self-organizing feature map (SOM), an unsupervised learning algorithm, which is simple and self organization, and the common usage of K-means clustering method, this paper combines SOM with K-means to do classification of moving objects in traffic video, constructs a system including four parts, and proposes a method based on bidirectional comparison of centroid to do tracking, and an improved method to obtain initial background when using background subtraction method to detect motion of moving objects. Experimental results show the effectiveness and robustness of the proposed approach.