Motion clustering on video sequences using a competitive learning network

It is necessary to track human movements in crowded places and environments such as stations, subways, metros, and schoolyards, where security is of great importance. As a result, undesired injuries, accidents, and unusual movements can be determined and various precautionary measures can be taken against them. In this study, real-time or existing video sequences are used within the system. These video sequences are obtained from objects such as humans or vehicles, moving actively in various environments. At first, some preprocesses are made respectively, such as converting gray scale, finding the edges of the objects existing in the images, and thresholding the images. Next, motion vectors are generated by utilizing a full search algorithm. Afterwards, k-means, nearest neighbor, image subdivision, and a competitive learning network are used as clustering methods to determine dense active regions on the video sequence using these motion vectors, and then their performances are compared. It is seen that the competitive learning network significantly determines the classification of dense active regions, including motion. Moreover, the algorithms are analyzed in terms of their time performances.