PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Human Detection using Oriented Histograms of Flow and Appearance
Navneet Dalal, William Triggs and Cordelia Schmid
In: ECCV 2006, Graz(2005).


Detecting humans in films and videos is a challenging problem owing to the motion of the subjects, the camera and the background and to variations in pose, appearance, clothing, illumination and background clutter. We develop a detector for standing and moving people in videos with possibly moving cameras and backgrounds, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance. This motion-based detector is combined with a static appearance-based detector similar to that of Dalal & Triggs and the result is tested on several databases including a challenging test set taken from feature films and containing wide ranges of pose, motion and background variations, including moving cameras and backgrounds. The combined detector reduces the false alarm rate by a factor of 5 relative to the best appearance-based detector, for example giving false alarm rates of one per 10,000 windows tested at 8% miss rate on our first test set.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:1918
Deposited By:William Triggs
Deposited On:29 December 2005