[4eyes] Reading Group - Friday 2/22/13

[Benjamin Nuernberger]

Also, let's plan to meet at 11:15am. I have to help proctor an exam that
ends around 11am on the other side of campus.

On Tue, Feb 19, 2013 at 5:03 PM, Benjamin Nuernberger <
bnuernberger at cs.ucsb.edu> wrote:

> Hi everyone,
>
> Let's discuss the following paper this Friday at the reading group. It
> describes a robust, real-time approach to tracking objects that improves
> over time using machine learning. You can see some of the project's videos
> here: http://info.ee.surrey.ac.uk/Personal/Z.Kalal/tld.html.
>
> Cheers,
> Ben
>
> Tracking-Learning-Detection
> IEEE Transactions on Pattern Analysis and Machine Intelligence, July 2012
> Zdenek Kalal, Krystian Mikolajczyk, and Jiri Matas
> http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6104061
>
> Abstract:
> This paper investigates 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 propose 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 the detector's errors and updates it to avoid these errors in the
> future. We study how to identify the detector's errors and learn from them.
> We develop a novel learning method (P-N learning) which estimates the
> errors by a pair of “experts”: (1) P-expert estimates missed detections,
> and (2) N-expert estimates false alarms. The learning process is modeled as
> a discrete dynamical system and the conditions under which the learning
> guarantees improvement are found. We describe our real-time implementation
> of the TLD framework and the P-N learning. We carry out an extensive
> quantitative evaluation which shows a significant improvement over
> state-of-the-art approaches.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cs.ucsb.edu/pipermail/ilab-users/attachments/20130219/201d1847/attachment-0001.html>