Abstract :

Systems For Automated Surveillance Are Essential For Security Applications. These Systems Are Efficient At Tracking, Detecting, And Classifying Moving Objects. The First And Most Important Stage Of A Surveillance System Is Object Detection. The Precision Of The Detection Phase Has A Significant Impact On The Surveillance System S Overall Performance. There Are Several Methods For Recognizing Moving Objects. This Work Presents A Comparison Of Three Object Recognition Techniques: Kernel Density Estimation [3], Approximate Median [7], And Temporal Frame Differencing [6]. CAVIAR [13] And PETS [14], Two Common Surveillance Video Datasets, Have Been Used To Successfully Evaluate These Algorithms. The Suggested Techniques Identify Every Moving Object In Films Taken By Stationary Cameras Positioned In Moderately To Highly Complex Both Indoor And Outdoor Locations. Keywords — Visual Surveillance, Temporal Frame Differencing, Approximate Median, Kernel Density Estimation.

Published:

06-10-2018

Issue:

Vol. 18 No. 10 (2018)

Page Nos:

99-105

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite