scholarly journals Probabilistic Relaxation Labeling: A Short Survey on Object Recognition

2019 ◽  
Vol 181 (38) ◽  
pp. 40-44
Author(s):  
Abbas Zohrevand
Keyword(s):  
Object Recognition ◽  
Relaxation Labeling ◽  
Short Survey ◽  
Probabilistic Relaxation

Contextual word recognition using probabilistic relaxation labeling

1988 ◽  
Vol 21 (5) ◽  
pp. 455-462 ◽  
Author(s):  
Ardeshir Goshtasby ◽  
Roger W. Ehrich
Keyword(s):  
Word Recognition ◽  
Relaxation Labeling ◽  
Probabilistic Relaxation

Improving the labeling accuracy by a new probabilistic relaxation labeling

1985 ◽  
Vol 3 (6) ◽  
pp. 399-402 ◽  
Author(s):  
Ja Young Koo ◽  
Kyu Ho Park ◽  
Myunghwan Kim
Keyword(s):  
Relaxation Labeling ◽  
Probabilistic Relaxation

TRACKING MULTIPLE PERSONS BASED ON ATTRIBUTED RELATIONAL GRAPH

2011 ◽  
Vol 25 (05) ◽  
pp. 713-739 ◽  
Author(s):  
QIN WAN ◽  
YAONAN WANG ◽  
HONGSHAN YU ◽  
XIAOFANG YUAN ◽  
JUAN LU
Keyword(s):  
Experimental Validation ◽  
Spatial Information ◽  
Appearance Model ◽  
Body Parts ◽  
Main Difficulty ◽  
Relaxation Labeling ◽  
Tracking Method ◽  
Probabilistic Relaxation ◽  
Attributed Relational Graph ◽  
Indoor And Outdoor

The appearance model is very effective in tracking multiple persons. The main difficulty in tracking persons is to represent appearance reliably and effectively, especially in the presence of occlusions. In this paper, an effective Attributed Relational Graph (ARG) based tracking algorithm is presented to track multiple persons even under occlusions. The appearance of each person is expressed by an ARG model which not only combines color feature with spatial information but also illustrates the relations among body parts. The similarity of ARG models is computed to build a matching matrix in consecutive frames. Four tracking situations are determined according to the matching matrix. In addition, to track persons under occlusions, probabilistic relaxation labeling in the ARG models of body parts is deduced to label occluded persons optimally. Experimental validation of the proposed tracking method is verified and presented on indoor and outdoor sequences.

Sign in / Sign up

Export Citation Format

Share Document