OBJECT TRACKING IN VIDEO IMAGE

Abstract

Object tracking is currently active research topic in the field of computer vision. The use of object tracking is challenging in the field of video surveillance, vehicle navigation system, weather monitoring etc. due to its high computational complexity. Video surveillance in a dynamic environment, especially for humans and vehicles, is one of the current challenging research topics in computer vision. It is a key technology to fight against terrorism, crime, public safety and for efficient management of traffic. Object tracking based techniques is the most popular choice to detect stationary foreground objects because they work reasonably well when the camera is stationary and the change in ambient lighting is gradual, and they also represent the most popular choice to separate foreground objects from the current frame. Surveillance networks are typically monitored by a few people, viewing several monitors displaying the camera feeds. It is very difficult for a human operator to effectively detect events as they happen. Recently computer vision research has to address ways to automatically some of this data, to assist human operators. We can also use the concept of object detection and tracking to develop video search engine. In this report we have discussed few feature selection techniques using LBP. We have also introduced few method which is basically the improvement of original local binary pattern. Apart from feature vector we have discussed an object tracking method i.e. mean shift tracking algorithm. We have proposed our algorithm based on joint enhance color texture feature for tracking which is better than most of the texture based algorithm.