Title
Structured learning for detection of social groups in crowd
Abstract
Group detection in crowds will play a key role in future behavior analysis surveillance systems. In this work we build a new Structural SVM-based learning framework able to solve the group detection task by exploiting annotated video data to deduce a sociologically motivated distance measure founded on Hall's proxemics and Granger's causality. We improve over state-of-the-art results even in the most crowded test scenarios, while keeping the classification time affordable for quasi-real time applications. A new scoring scheme specifically designed for the group detection task is also proposed.
Year
DOI
Venue
2013
10.1109/AVSS.2013.6636608
Advanced Video and Signal Based Surveillance
Keywords
Field
DocType
learning (artificial intelligence),object detection,support vector machines,video surveillance,Granger causality,Hall proxemics,SVM-based learning,behavior analysis surveillance system,crowd detection,quasi-real time application,scoring scheme,social group detection,sociologically motivated distance measure,structured learning,video data
Social group,Object detection,Crowds,Computer vision,Causality,Computer science,Support vector machine,Proxemics,Structured prediction,Scenario testing,Artificial intelligence,Machine learning
Conference
Citations 
PageRank 
References 
10
0.50
10
Authors
3
Name
Order
Citations
PageRank
Francesco Solera1100.84
Simone Calderara293654.25
Rita Cucchiara34174300.55