TRACKING, LEARNING AND DETECTION OF AN OBJECT IN VIDEO
Miss Afrin R Pathan, Poornima Talwai · 2017
—This paper investigate long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the objects location and extent or indicate that the object is not present. A novel approach called Tracking-Learning-Detection (TLD) framework that explicitly decomposes the long term tracking task into tracking, learning and detection. The tracker follows the object from frame to frame. The locator localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detectors errors and updates it to avoid these errors in the future.