Intelligent Video Surveillance System

Computer Engineering

Abstract - The frequent increase in number of vehicle crashes and accidental falls has increased over the past decade. Increasing the number of cars and excessive traffic in cities is a major problem at the current time. Statistics show that more and more accidents happen daily, and many of these could be avoided. Approximately 1.3 million people die each year as a result of road traffic crashes. Regardless of mindfulness cause, this issue is as yet expanding because of rider's poor practices, for example, drunk driving, speed driving, riding without adequate rest, riding with no cap insurance, and so forth. Accidental fall is also the most prominent factor that causes accidental death of people. This paper uses the YOLOv3 algorithm to extract features and complete the end-to-end prediction of the target frame and category at one time. In this paper, an already trained model of the coco dataset based on the YOLOv3 algorithm is used for fall and vehicle crash detection. The YOLO machine learning algorithm uses features learned by a deep convolutional neural network to detect an object. Experiments show that the YOLOv3 algorithm is a real-time object detection algorithm that offers excellent detection speed and detection accuracy.

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