Skip to Main Content
ASME Press Select Proceedings

International Conference on Computer and Automation Engineering, 4th (ICCAE 2012)

Jianhong Zhou
Jianhong Zhou
Search for other works by this author on:
No. of Pages:
ASME Press
Publication date:

Tracking the moving objects in video and classifying them as human or nonhuman object is an important problem in computer vision. We present real time human detection system utilizing covariance matrices as object descriptors. We describe a fast method for computation of covariance based on integral images. The idea presented here is more general than the image sums or histograms. Covariance matrices do not lie on Euclidean space, therefore we use Logitboost classifier modified for analytic manifold for classification. The algorithm is tested on CAVIAR human database where superior detection rates are observed over the previous approaches.

Key Words
1 Introduction
2 Related Work
3 Proposed Methodology
4 Experimental Results
This content is only available via PDF.
Close Modal
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close Modal
Close Modal