Discriminatively trained part based model armed with biased saliency

Huapeng Yu; Yongxin Chang; Pei Lu; Zhiyong Xu; Chengyu Fu; Yafei Wang

doi:10.1117/12.2064960

10 February 2015 Discriminatively trained part based model armed with biased saliency

Huapeng Yu, Yongxin Chang, Pei Lu, Zhiyong Xu, Chengyu Fu, Yafei Wang

Proceedings Volume 9255, XX International Symposium on High-Power Laser Systems and Applications 2014; 92553H (2015) https://doi.org/10.1117/12.2064960
Event: XX International Symposium on High Power Laser Systems and Applications, 2014, Chengdu, China

Abstract

Discriminatively trained Part based Model (DPM) is one of the state-of-the-art object detectors. However, DPM complies little with real vision procedure. In this paper, we try arming DPM with biologically inspired approaches. On the one hand, we use Gabor instead of Histogram of Oriented Gradient (HOG) as low level features to simulate the receptive fields of simple cells. We show Gabor outperforms or is on par with HOG. On the other hand, we learn biased saliency of the object with the same Gabor features to simulate the search procedure of real vision. We combine DPM and biased saliency in a single Bayesian framework, which at least partially reflects the interactions between top-down and bottom-up vision procedures. We show these biologically inspired procedures can effectively improve the performance and efficiency of DPM. We present experimental results on both challenging PASCAL VOC2007 dataset and publicly available sequences.

Citation Download Citation

Huapeng Yu, Yongxin Chang, Pei Lu, Zhiyong Xu, Chengyu Fu, and Yafei Wang "Discriminatively trained part based model armed with biased saliency", Proc. SPIE 9255, XX International Symposium on High-Power Laser Systems and Applications 2014, 92553H (10 February 2015); https://doi.org/10.1117/12.2064960

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