TY - GEN
T1 - Histograms of optical flow orientation for abnormal events detection
AU - Wang, Tian
AU - Snoussi, Hichem
PY - 2013
Y1 - 2013
N2 - In this paper, we propose an algorithm to detect abnormal events based on video streams. The algorithm is based on histograms of the orientation of optical flow descriptor and one-class SVM classifier. We introduce grids of Histograms of the Orientation of Optical Flow (HOF) as the descriptors for motion information of the monolithic video frame. The one-class SVM, after a learning period characterizing normal behaviors, detects the abnormality which is considered as the event needed to be recognized in the current frame. Extensive testing on dataset corroborates the effectiveness of the proposed detection method.
AB - In this paper, we propose an algorithm to detect abnormal events based on video streams. The algorithm is based on histograms of the orientation of optical flow descriptor and one-class SVM classifier. We introduce grids of Histograms of the Orientation of Optical Flow (HOF) as the descriptors for motion information of the monolithic video frame. The one-class SVM, after a learning period characterizing normal behaviors, detects the abnormality which is considered as the event needed to be recognized in the current frame. Extensive testing on dataset corroborates the effectiveness of the proposed detection method.
UR - https://www.scopus.com/pages/publications/84881099347
U2 - 10.1109/PETS.2013.6523794
DO - 10.1109/PETS.2013.6523794
M3 - 会议稿件
AN - SCOPUS:84881099347
SN - 9781467356497
T3 - IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, PETS
SP - 45
EP - 52
BT - 2013 IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, PETS 2013
T2 - 2013 IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, PETS 2013
Y2 - 15 January 2013 through 17 January 2013
ER -