Detection of Abnormal Events in Surveillance Videos

K, Srinivas (2015) Detection of Abnormal Events in Surveillance Videos. Masters thesis, Indian Institute of Technology Hyderabad.

[img] Text
CS13M1005.pdf - Submitted Version
Restricted to Registered users only until 1 July 2018.

Download (3MB) | Request a copy

Abstract

The objective of this research work is to detect abnormal events in surveillance videos. It is one of the important and major challenging tasks in surveillance videos. Surveillance cameras are used for security, controlling and analyzing the crime, analysis of abnormal events in the places like Airports, Bus stands, Railway stations and other public places. The cameras capture huge data and store, which can be used to analyze the situations after their happening. Although this helps the operators to understand but no more use for controlling. Hence semi/fully automated intelligent systems are required to intimate the operators at the time of happening, thus hope of controlling huge damage. To illustrate, this can be used in finding terror attack, bomb placement, religion disputes, attacks, accidents, violation of traffic rules, etc. With this aim, researchers have focused on Abnormal Detection in Surveillance Videos where anomaly is detected and localized. Our aim here is to develop a more robust system to handle different anomaly and help the surveillance system.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Thesis (Masters)
Uncontrolled Keywords: histograms of the orientation of optical flow (HOOF), Abnormal detection, Optical flow, Two-class SVM, TD308
Subjects: Computer science > Big Data Analytics
Divisions: Department of Computer Science & Engineering
Depositing User: Library Staff
Date Deposited: 01 Jul 2015 06:38
Last Modified: 10 Jul 2015 05:51
URI: http://raiith.iith.ac.in/id/eprint/1622
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 1622 Statistics for this ePrint Item