Object codetection based on a higher-order conditional random field

Linfeng Jiang; Weilin Zhong; Jinsheng Ji; Huilin Xiong

doi:10.1117/1.JEI.28.2.023019

23 March 2019 Object codetection based on a higher-order conditional random field

Linfeng Jiang, Weilin Zhong, Jinsheng Ji, Huilin Xiong

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 2, 023019 (March 2019). https://doi.org/10.1117/1.JEI.28.2.023019

Abstract

In recent years, codetecting objects through the use of contextual information across multiple images has attracted considerable attention. We introduce an object codetection method that exploits contextual information among multiple images through a higher-order conditional random field (CRF). First, we obtain object candidates from each image of a test set by using a pretrained detector. Second, we feed the object candidates into a higher-order CRF that captures the appearance similarity using pairwise potentials and object category co-occurrence constraints using higher-order potentials. Finally, we jointly predict the category labels of all object candidates through the mean field inference in the CRF. Experimental results on the Caltech Pedestrian, PASCAL VOC 2007, PASCAL VOC 2012, and COCO datasets demonstrate the effectiveness of the proposed method compared to the baseline method.

Citation Download Citation

Linfeng Jiang, Weilin Zhong, Jinsheng Ji, and Huilin Xiong "Object codetection based on a higher-order conditional random field," Journal of Electronic Imaging 28(2), 023019 (23 March 2019). https://doi.org/10.1117/1.JEI.28.2.023019

Received: 11 November 2018; Accepted: 5 March 2019; Published: 23 March 2019

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