Abstract

Many applications such as intelligent transportation, video surveillance, robotics of computer vision mainly depend on task of multiple target tracking. It consists of process of detection, classifications and tracking. In this novel approach of multi target tracking, cost terms are formulated to attain the global optimization which includes the entire representation of the issues such as target tracking, operational representation, collision handling and trajectory processing. Furthermore, two optimization strategies such as the gradient descent which is performed on multiple feature space to obtain local minima of a density function from the given sample of data and gradient ascent which is carried out to achieve a likelihood matching of the target and used to handle the partial evidence of the image, and also uncertainty of the various targets are minimized. . In this study, the proposed works are tested on different publicly available datasets using the metric evaluation and also compared with the various methods based on issues of target tracking. This study will also provide a better understanding of the problem, knowledge of the methods, and experimental evaluation skill for further research works.