Note: To be filled out on Friday or Saturday.

1. Boosting
2. Sliding window

/*

(1) object detector with boosting: 
http://people.csail.mit.edu/torralba/shortCourseRLOC/boosting/boosting.html 

*/

The classic human detection paper is by Dalal and Triggs, and it involves using the Histogram of Oriented Gradients (HOG) feature descriptor together with Support Vector Machines. It does quite well, though more modern and more expensive methods have superceded it.

Boosting as a concept is about creating a very accurate detector from a series of somewhat low accuracy detectors. The trick is to control the false positive rate (have it be very low) while tolerating false negatives. Cascading enough of these together will eventually create a detector that has bot a low false positive rate and a low false negative rate (after all, how many times can one be wrong in a row?).

ECE4580 Learning Modules