Paper Info
Title
Exploiting Long-Term Connectivity and Visual Motion in CRF-Based Multi-Person Tracking
Abstract
We present a conditional random field approach to tracking-by-detection in which we model pairwise factors linking pairs of detections and their hidden labels, as well as higher order potentials defined in terms of label costs. To the contrary of previous papers, our method considers long-term connectivity between pairs of detections and models similarities as well as dissimilarities between them, based on position, color, and as novelty, visual motion cues. We introduce a set of feature-specific confidence scores, which aim at weighting feature contributions according to their reliability. Pairwise potential parameters are then learned in an unsupervised way from detections or from tracklets. Label costs are defined so as to penalize the complexity of the labeling, based on prior knowledge about the scene like the location of entry/exit zones. Experiments on PETS’09, TUD, CAVIAR, Parking Lot, and Town Center public data sets show the validity of our approach, and similar or better performance than recent state-of-the-art algorithms.
Year
DOI
Venue
2014
10.1109/TIP.2014.2324292
IEEE Transactions on Image Processing
Keywords
Field
DocType
minimisation,motion estimation,target tracking,CRF based multiperson tracking,conditional random field approach,higher order potentials,long term connectivity,pairwise factors linking pairs,visual motion,CRF,Multi-person tracking,tracking-by-detection,visual motion
Data set,Weighting,Computer science,Artificial intelligence,Motion estimation,Conditional random field,Pairwise comparison,Computer vision,Pattern recognition,Visualization,Feature extraction,Novelty,Machine learning
Journal
Volume
Issue
ISSN
23
7
1057-7149
Citations 
PageRank 
References 
14
0.56
27
Authors
3
Name
Order
Citations
PageRank
Alexandre Heili1140.56
Adolfo López-Méndez2140.56
Jean-Marc Odobez314019.50