Anomalies Detection from Video Surveillance Using Support Vector Trained Deep Neural Network Classifier
Intelligent video surveillance plays a crucial role in various applications for detecting the abnormal activities. The surveillance system uses many significant technologies for detecting the anomalies in different applications but it fails to manage the accuracy while detecting the anomalies from huge crowd. This paper introduces an effective image processing technology-based classifier for recognizing and detecting the abnormality from the crowd effectively. Initially, the videos are captured using the surveillance camera, and the background has been subtracted by the robust background principal analysis method. After extracting the background from the image, the different principal bow sift descriptors are extracted. Subsequently the similar descriptors are grouped using the bee-based collaborative filtering approach. Finally, the anomaly classification is done by support vector machine training-based deep neural networks. Then the excellence of the system is evaluated by using the implementation results and the obtained results are compared with the traditional classifiers.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/1744232X
-
Supplemental Notes:
- Copyright © 2018 Inderscience Enterprises Ltd.
-
Authors:
- Giriprasad, S
- Mohan, S
- Gokul, S
- Publication Date: 2018
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: pp 286-307
-
Serial:
- International Journal of Heavy Vehicle Systems
- Volume: 25
- Issue Number: 3-4
- Publisher: Inderscience Enterprises Limited
- ISSN: 1744-232X
- EISSN: 1741-5152
- Serial URL: http://www.inderscience.com/jhome.php?jcode=IJHVS
Subject/Index Terms
- TRT Terms: Crowds; Data analysis; Filters; Neural networks; Technological innovations; Traffic flow; Traffic models; Traffic surveillance; Video
- Subject Areas: Data and Information Technology; Transportation (General);
Filing Info
- Accession Number: 01689619
- Record Type: Publication
- Files: TRIS
- Created Date: Dec 21 2018 5:18PM