Detection and handling of occlusion in an object detection system

Ron M. G. op het Veld; R. G. J. Wijnhoven; Y. Bondarev; Peter H. N. de With

doi:10.1117/12.2077175

4 March 2015 Detection and handling of occlusion in an object detection system

Ron M. G. op het Veld, R. G. J. Wijnhoven, Y. Bondarev, Peter H. N. de With

Proceedings Volume 9407, Video Surveillance and Transportation Imaging Applications 2015; 94070N (2015) https://doi.org/10.1117/12.2077175
Event: SPIE/IS&T Electronic Imaging, 2015, San Francisco, California, United States

Abstract

Object detection is an important technique for video surveillance applications. Although different detection algorithms were proposed, they all have problems in detecting occluded objects. In this paper, we propose a novel system for occlusion handling and integrate this in a sliding-window detection framework using HOG features and linear classification. The occlusion handling is obtained by applying multiple classifiers, each covering a different level of occlusion and focusing on the non-occluded object parts. Experiments show that our approach based on 17 classifiers, obtains an increase of 8% in detection performance. To limit computational complexity, we propose a cascaded implementation that only increases the computational cost by 3.4%. Although the paper presents results for pedestrian detection, our approach is not limited to this object class. Finally, our system does not need an additional dataset for training, covering all possible types of occlusions.

Citation Download Citation

Ron M. G. op het Veld, R. G. J. Wijnhoven, Y. Bondarev, and Peter H. N. de With "Detection and handling of occlusion in an object detection system", Proc. SPIE 9407, Video Surveillance and Transportation Imaging Applications 2015, 94070N (4 March 2015); https://doi.org/10.1117/12.2077175

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available