Real Time Violence Detection in Video with ViF and Horn-Schunck
Karla Mariel Fernández Fabián
Juan Carlos Gutiérrez Cáceres
| ||
Real Time Violence Detection in Video with ViF and Horn-Schunck | ||
| Published in: | Engineering Innovations for Global Sustainability: Proceedings of the 14th Latin American and Caribbean Conference for Engineering and Technology | |
| Date of Conference: | July 20-22, 2016 | |
| Location of Conference: | San Jose, Costa Rica | |
| Authors: | Vicente Enrique Machaca Arceda Karla Mariel Fernández Fabián Juan Carlos Gutiérrez Cáceres | |
| Refereed Paper: | #122 | |
Abstract:We propose a ViF variation using Horn-Schunck as optical flow algorithm and SVM as classifier, we evaluated the performance in different datasets. In Hockey dataset Horn-Schunck has a better performance but in Movies and Crowded datasets the original algorithm of ViF (IRLS) was better, but Horn-Schunck has a very low cost of 0.25 seconds against 7.80 seconds of IRLS enabling its use in real time. | ||