Tracking Learning Detection

Add to your list(s) Download to your calendar using vCal

• Dr Krystian Mikolajczyk (University of Surrey)
• Wednesday 28 November 2012, 11:00-12:00
• Gabor seminar room 611 on level 6 (EEE).

If you have a question about this talk, please contact Tae-Kyun Kim.

We have another great talk in the ISN seminar series, by Dr Krystian Mikolajczyk. He is one of pioneers on interest point detectors/descriptors, an essential topic of computer vision and learning (http://scholar.google.co.uk/citations?user=s1IAWfgAAAAJ&am

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.(http://www.surrey.ac.uk/cvssp/people/krystian_mikolajczyk/index.htm)

This talk is part of the Tae-Kyun Kim's list series.

This talk is included in these lists:

• Andrea Picciau's list
• COMMSP & CP list
• COMMSP Seminar
• Featured talks
• Gabor seminar room 611 on level 6 (EEE)
• SAP Talks

Note that ex-directory lists are not shown.