Document Detail

Tracking Pedestrians using Local Spatio-temporal Motion Patterns in Extremely Crowded Scenes.
MedLine Citation:
PMID:  21844618     Owner:  NLM     Status:  Publisher    
Tracking pedestrians is a vital component of many computer vision applications including surveillance, scene understanding, and behavior analysis. Videos of crowded scenes present significant challenges to tracking due to the large number of pedestrians and the frequent partial occlusions that they produce. The movement of each pedestrian, however, contributes to the overall crowd motion (i.e., the collective motions of the scene's constituents over the entire video) that exhibits an underlying spatially and temporally varying structured pattern. In this paper, we present a novel Bayesian framework for tracking pedestrians in videos of crowded scenes using a space-time model of the crowd motion. We represent the crowd motion with a collection of hidden Markov models trained on local spatio-temporal motion patterns, i.e., the motion patterns exhibited by pedestrians as they move through local space-time regions of the video. Using this unique representation, we predict the next local spatio-temporal motion pattern a tracked pedestrian will exhibit based on the observed frames of the video. We then use this prediction as a prior for tracking the movement of an individual in videos of extremely crowded scenes. We show that our approach of leveraging the crowd motion enables tracking in videos of complex scenes that present unique difficulty to other approaches.
Louis Kratz; Ko Nishino
Related Documents :
12402288 - Wave properties of action potentials from fast and slow motor units of rats.
20600738 - Monaural spectral processing differs between the lateral superior olive and the inferio...
12872008 - Estimation of postsynaptic potentials in rat hypoglossal motoneurones: insights for hum...
10413538 - Song types as fundamental units in vocal repertoires.
19855498 - Light-induced absorption in photorefractive strontium barium niobate.
3407418 - On the processing rate of gratings superimposed on gratings.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2011-8-11
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  -     ISSN:  1939-3539     ISO Abbreviation:  -     Publication Date:  2011 Aug 
Date Detail:
Created Date:  2011-8-16     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Drexel University, Philadelphia.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Direct kinematic modeling of the upper limb during trunk-assisted reaching.
Next Document:  Quantifying and Transferring Contextual Information in Object Detection.