Survey of Intelligent Surveillance System using Image Processing and Deep Learning Techniques

Abstract

Abstract

Closed-circuit television systems (CCTV) are becoming more and more pop- ular and are being deployed in many offices, housing estates and most public spaces. Thus, the job of CCTV operators is becoming very challenging as the footage contains a lot of information and gradually becomes cumbersome. Rapid advancement in the field of computer vision could be observed as an important trend in video surveillance and lead to substantial effi- ciency gains. Through this system of a neural network based intelligent intruders detection and track- ing system using Closed-Circuit Television (CCTV) images, we can inspect the various approaches and algorithms used to identify an inherent intruder and techniques to obliterate other non-threatening objects.

Keywords: CNN, R-CNN, VGG-16, SVM, N-Cut Clustering, SURF