event
Thursday 21 Feb 2013: Tracking Learning Detection
Dr. Krystian Mikolajczyk - Centre for Vision, Speech and Signal Processing, University of surrey
Harrison 106 14:00-15:00
In this talk I will present our recent work on 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 object's location and extent or indicate that the object is not present. We proposed a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates detector's errors and updates it to avoid these errors in the future. I'll discuss our learning method (P-N learning) which estimates the errors by a pair of "experts": (i) P-expert estimates missed detections, and (ii) N-expert estimates false alarms.