Suspicious Activity Detection from Surveillance Video using Deep Learning
Shashank Reddy Nallu, Vamshi Krishna Kunuru, Harshavardhan Reddy, Praveen H
Suspicious activity, Video Surveillance, Deep learning, LSTM, Convolutional Neural Networks.
Video surveillance has been used since long to ensure security in many sensitive places, so with this great advancement in various aspects of life, traditional surveillance operations face many challenges due to the large amount of information that has to be processed manually in a limited amount. time also the possibility of losing information that may contain important things such as suspicious behavior. Thus, a large amount of research has been conducted in the field of video surveillance recently. We provide a system that supports intelligent monitoring to detect abnormal behavior that poses a security risk. The proposed algorithm is designed to detect two cases of human activity: walking and running. There is no limit to the number of people on stage or the direction of travel. However, video is limited to internal color movies taken from a still camera. A background subtraction algorithm is used to detect moving objects related to people in the scene. We consider the moving speed of the center of the segmented foreground region and the size change speed of the segmented region as two main features to classify the activity v. The proposed algorithm determines the types of activities with high accuracy.
Article Details
Unique Paper ID: 159270

Publication Volume & Issue: Volume 9, Issue 11

Page(s): 855 - 859
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews