Multi-target tracking using predefined reference set in Non-Overlapping Cameras by AdaBoost algorithm

Abstract

Abstract-Multi-target tracking is still recent approach which is used to find the same object across different camera views and also used to find the location and sizes of different object at different places [7]. Tracking and detection of moving objects are challenging research topic of many computer vision applications. Nowadays, the demand of surveillance camera is increasing rapidly which is useful for developing surveillance as well as monitoring purpose. Some previous methods are used for multi-target tracking that are color histogram, brightness transfer function (BTF) [11]. Many times it is not possible to cover complete area of interest by using single camera, such a cases there is need to use multi-target tracking system with non-overlapping field of views (FOV) [2]. In this paper we use method of feature extractions that is AdaBoost. The paper proposes the reference set based tracking in non-overlapping FOV"s due to overlapping FOV"s are having high cost. In this work widely used features HSV color histograms, Local Binary Pattern (LBP), Histogram of Gradient (HOG) are used to extract color, texture, shape of target. We use LBP, HOG, HSV color histogram features to determine person"s characteristics.