Human Behavioral Analysis: Intruder Detection in Videos

Authors

Presenter(s)

Manish Pavan Beesetti

Comments

This poster reflects research conducted as part of a course project designed to give students experience in the research process. Course: CPS 592

Files

Description

This research aims to develop an intruder detection system based on human behavior via front door surveillance. This is similar to the classic action recognition and scene recognition problems which are currently hot topics in the field of computer vision. To this end, we have collected YouTube videos and then annotate them as anomaly or normal labels. We then train a C3D model by considering a sequence of frames as an input. The experimental results demonstrate the effectiveness of our system.

Publication Date

4-22-2021

Project Designation

Course Project

Primary Advisor

Van Tam Nguyen

Primary Advisor's Department

Computer Science

Keywords

Stander Symposium project, College of Arts and Sciences

United Nations Sustainable Development Goals

Peace, Justice, and Strong Institutions

Recommended Citation

"Human Behavioral Analysis: Intruder Detection in Videos" (2021). Stander Symposium Projects. 2151.
https://ecommons.udayton.edu/stander_posters/2151