Large-scale conditional random field for natural outdoor scene labeling

Mingjun Wang; Jun Zhou; Jun Tu; Chengliang Liu

doi:10.1117/1.3250201

1 October 2009 Large-scale conditional random field for natural outdoor scene labeling

Mingjun Wang, Jun Zhou, Jun Tu, Chengliang Liu

Author Affiliations +

Optical Engineering, Vol. 48, Issue 10, 107205 (October 2009). https://doi.org/10.1117/1.3250201

Abstract

We propose a novel large-scale conditional random field model with respect to the problem of natural outdoor scene labeling. The novelty of the proposed method lies in three aspects: 1. features from two neighboring regions are concatenated to form the input of the pair-wise classifier to compensate for the simultaneous feature deviation of neighboring regions; 2. the definition of a generalized neighboring system and the incorporation of direction-specific patterns in conditional random field models based on the generalized neighboring system to better simulate the visual cognition of human being; and 3. the definition of a similarity criterion based on the bags-of-words expression to facilitate the incorporation of semantic patterns. The proposed model is first evaluated over the Corel dataset. Both qualitative and quantitative results show that our model is capable of modeling large-scale spatial relationships between objects in natural outdoor scenes, and achieves better results than other existing conditional random field models. Furthermore, our model is also evaluated over several other natural datasets, which are taken from logged field tests, to further demonstrate the adaptability of our model to different lighting conditions.

©(2009) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Mingjun Wang, Jun Zhou, Jun Tu, and Chengliang Liu "Large-scale conditional random field for natural outdoor scene labeling," Optical Engineering 48(10), 107205 (1 October 2009). https://doi.org/10.1117/1.3250201

Published: 1 October 2009

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