Detection of road traffic crashes based on collision estimation

TL;DR

This paper presents a computer vision-based framework that detects road traffic crashes in real-time using CCTV cameras, accurately reporting location and time to emergency services with minimal false alarms.

Contribution

It introduces a novel collision estimation approach integrated with vehicle detection, tracking, and classification modules for accurate crash detection.

Findings

High detection accuracy demonstrated in experiments

Reduced false alarm rate compared to existing methods

Real-time crash reporting with precise location and timing

Abstract

This paper introduces a framework based on computer vision that can detect road traffic crashes (RCTs) by using the installed surveillance/CCTV camera and report them to the emergency in real-time with the exact location and time of occurrence of the accident. The framework is built of five modules. We start with the detection of vehicles by using YOLO architecture; The second module is the tracking of vehicles using MOSSE tracker, Then the third module is a new approach to detect accidents based on collision estimation. Then the fourth module for each vehicle, we detect if there is a car accident or not based on the violent flow descriptor (ViF) followed by an SVM classifier for crash prediction. Finally, in the last stage, if there is a car accident, the system will send a notification to the emergency by using a GPS module that provides us with the location, time, and date of the accident to be sent to the emergency with the help of the GSM module. The main objective is to achieve higher accuracy with fewer false alarms and to implement a simple system based on pipelining technique.