Crime Intention Detection System Using Deep Learning

Abstract

Circuit Television Cameras (CCTV’s) are widely used to control occurrence of crimes in the surroundings. Although CCTV’s are deployed at various public and private areas to monitor the surroundings there is no improvement in the control of crimes. This is because CCTV requires human supervision which may lead to human prone errors like missing of some important crime events by human while monitoring so many screens recorded by CCTV’s at same time. To overcome this issue, we came up with Crime Intension Detection System that detects crime in real time videos, images and alerts the human supervisor to take the necessary actions. To alert the supervisors or nearby police station about the occurrence of crime. We added SMS sending module to our system which sends SMS to concern person whenever crimes are detected. The proposed system is implemented using Pre-trained deep learning model VGGNet-19 which detects gun and knife in the hand of person pointing to some other person. We also compared the working of two different pre-trained models like GoogleNet InceptionV3 in training. The results obtained with VGG19 are more accurate in terms of training accuracy. This motivated us to use VGG19 with little fine tuning to detect crime intention in videos and images to overcome the issues with existing approaches with more accuracy. And we made use of Fast RCNN and RCNN these algorithms are well known as Faster RCNN this helps us to draw the bounding box over objects in images like person, gun, knife and some untrained images are marked with N/A. Algorithms help for detection and classifications of objects over images.