This is a neat video of a camera panning around, while features on various objects are being selected for tracking. The data can then be used for things like pathplanning, object avoidance, and landmark recognition.http://www.nsf.gov/od/lpa/news/03/pr0380_video4-stream.htm
"The video depicts outdoor scenes shot from a handheld camcorder that were processed using the IMSC feature tracking technology. Even though there is motion and shake, the dots show where the tracking algorithm found good features to track. The dot stability and consistency are indications of how reliably the software tracks the features. Note that the system finds these points automatically as the "best suited" scene points for tracking."
I also found face tracking, which also uses feature tracking:
"FotoNation Face Tracker is a highly portable software implementation that scales in performance according to the power of the processor used in the device. This demonstration by FotoNation features a camera phone with face detection and tracking. The small footprint implementation is platform independent and is available for both Symbian Series 60 3rd edition OS (shown here) and Window Mobile™ 5.0."
and tracking of cars on a road:http://www.ri.cmu.edu/images/projects/car_track.mpg
"We have developed an algorithm to track cars in the surrounding road scene and then generate a "bird's eye view" of the road."
"Template tracking is a well studied problem in computer vision which dates back to the Lucas-Kanade algorithm of 1981. Since then the paradigm has been extended in a variety of ways including: arbitrary parametric transformations of the template, and linear appearance variation. These extensions have been combined, culminating in non-rigid appearance models such as Active Appearance Models (AAMs) and Active Blobs. One question that has received very little attention is how to update the template over time so that it remains a good model of the object being tracked. This research proposes an algorithm to update the template that avoids the "drifting" problem of the naive update algorithm. Our algorithm can be interpreted as a heuristic to avoid local minima. It can also be extended to templates with linear appearance variation. This extension can be used to convert (update) a generic, person-independent AAM into a person specific AAM."
other information of feature tracking, also called match moving
, can be found here:http://en.wikipedia.org/wiki/Match_moving
(yea, Ive been posting a lot of vision related videos lately . . . its cause im doing tons of research for the 4th vision tutorial and i keep finding these interesting things)