Authors : G. Jemilda and S. Baulkani
Abstract: Object tracking is the process of tracking a moving object in video over time using a camera. It is an important task within the field of computer vision. It has a wide variety of applications in computer vision such as video compression, video surveillance, vision-based control, human-computer interfaces, medical imaging, augmented reality and robotics. In this study, the object is tracked in video using the following steps. First, the input given is a video which is divided into frames. For each frame the features are extracted by Gabor filter which is used to identify the edges clearly. By this process, the object can be identified in the frame. In order to track the object in video, spatial context model is used. It checks the difference between the frames and keeps track of the object. The spatial correlation not only tracks the object but also reduces the time complexity. If there is not much difference between the first frame and the third frame then the same value will be on the sec frame. Thus, the sec frame will not be processed. The proposed method can produce an accurate result.
G. Jemilda and S. Baulkani, 2016. Capturing Moving Objects in Video Using Gabor and Local Spatial Context Model. Asian Journal of Information Technology, 15: 846-854.