DocumentCode
3599924
Title
Visual feature-based violent video detection
Author
Xin Ji ; Ou Wu ; Chenlong Wang ; Jinfeng Yang
Author_Institution
Coll. of Aviation Autom., Civil Aviation Univ. of China, Tianjin, China
fYear
2014
Firstpage
619
Lastpage
623
Abstract
In this paper, a novel violent video detection scheme is presented based on visual views. The violent segment is detected by using motion angle, motion intensity, shot & explosion and blood analysis. In addition, in order to improve the compute efficiency and time savings Hidden Information SVM is used. Experimental result shows that the proposed method is effective in violent video detection.
Keywords
image motion analysis; object detection; video signal processing; blood analysis; explosion analysis; hidden information SVM; motion angle; motion intensity; shot analysis; violent segment; visual feature-based violent video detection scheme; Blood; Explosions; Feature extraction; Image color analysis; Motion pictures; Support vector machines; Visualization; Blood; Motion angle; Motion intensity; SVM; Shot & explosion; Violence;
fLanguage
English
Publisher
ieee
Conference_Titel
Cloud Computing and Intelligence Systems (CCIS), 2014 IEEE 3rd International Conference on
Print_ISBN
978-1-4799-4720-1
Type
conf
DOI
10.1109/CCIS.2014.7175809
Filename
7175809
Link To Document