Title :
Learning crowd behavior for event recognition
Author :
Cermeno, Eduardo ; Mallor, Silvana ; Siguenza, Juan Alberto
Abstract :
This paper presents a new method for event recognition based on machine learning techniques. One machine is trained per kind of event using color, texture and shape features. Testing is performed on the PETS 2009 dataset. We evaluate accuracy of our automatic system with six different kind of events and then compare the results with human classification.
Keywords :
image colour analysis; image recognition; image texture; learning (artificial intelligence); visual databases; PETS 2009 dataset; automatic system; color features; crowd behavior learning; event recognition; human classification; machine learning techniques; shape features; texture features; Dispersion; Feature extraction; Legged locomotion; Merging; Positron emission tomography; Testing; Training;
Conference_Titel :
Performance Evaluation of Tracking and Surveillance (PETS), 2013 IEEE International Workshop on
Conference_Location :
Clearwater, FL
Print_ISBN :
978-1-4673-5649-7
Electronic_ISBN :
2157-491X
DOI :
10.1109/PETS.2013.6523788
