Human Tracking in Video Surveillance

Video Surveillance has become area of research and development due to increase in terrorist activities, thefts and other activities that can cause harm to human property and lives. Due to this researchers have been trying to add more and more intelligence in the video monitoring systems, so that it could automatically detect the malicious activities in the area under surveillance and raise alarm. The goal of visual surveillance is not only to put cameras in place of human eyes, but also to accomplish the entire surveillance task as automatically as possible. We can say that video surveillance is nothing but taking the video, identifying unwanted entities, tracking their actions, understanding their actions and raising an alarm. In this paper, we will be study the phases of the video surveillance system. We will study how a video is divided into frames, those frames are then sent to detect any change detection (human detection), further this information about detected humans in one frame is correlated with the information of the other frame and thus the detected human is tracked in the subsequent frame and this is called human tracking. We will see most salient region method for tracking and in this paper we propose a method of handling occlusion using velocity and direction information.