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

[Benjamin Nuernberger]

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/20130219/0185e749/attachment.html>