Real-Time Vehicle Accident Recognition from Traffic Video Surveillance using YOLOV8 and OpenCV

Abstract

The automatic detection of traffic accidents is a significant topic in traffic monitoring systems. It can reduce irresponsible driving behavior, improve emergency response, improve traffic management, and encourage safer driving practices. Computer vision can be a promising technique for automatic accident detection because it provides a reliable, automated, and speedy accident detection system that can improve emergency response times and ultimately save lives. This paper proposed an ensemble model that uses the YOLOv8 approach for efficient and precise event detection. The model framework's robustness is evaluated using YouTube video sequences with various lighting circumstances. The proposed model has been trained using the open-source dataset Crash Car Detection Dataset, and its produced precision, recall, and mAP are 93.8% and 98%, 96.1%, respectively, which is a significant improvement above the prior precision, recall, and mAP figures of 91.3%, 87.6%, and 93.8%. The effectiveness of the proposed approach in real-time traffic surveillance applications is proved by experimental results using actual traffic video data.

Real-Time Vehicle Detection for Traffic Monitoring: A Deep Learning Approach

“…• Step 2 -Image Pre-processing: We apply techniques like resizing to 416x416 pixels as used in (2) , normalization to scale pixel values between 0-1 (3) , and Gaussian blurring to reduce noise. (4) This improves consistency across varying conditions. • Step 3 -Background Separation: We adopt semantic segmentation as in (5) to classify each pixel as road, vehicle, or background.…”

“…(1,2) However, these methods using handcrafted features struggle with realworld variations in lighting, weather, occlusion and clutter. (3,4) Recently, deep learning has catalyzed immense progress in object detection across domains. (5,6) Convolutional neural networks (CNNs) now dominate, significantly outperforming prior techniques.…”

“…(3) Though highly accurate, R-CNN was extremely slow. Subsequent works like Fast R-CNN (3) and Faster R-CNN (4) optimized it through shared convolutions and region proposal networks. Single shot detectors like YOLO (5) and SSD (6) enabled real-time processing by eliminating region proposals.…”

“…However, small, occluded vehicles remain challenging While benchmark results are strong, performance degrades under complex real-world conditions with weather, lighting, occlusion, etc. (2,3,4) Limited training data diversity also poses problems. (5,6) Traffic-specific enhancements are needed.…”

“…Arnold et al (3) developed a 1D CNN for detecting bridge crossing events from ground-based radar data, outperforming a comparative random forest model. Mane et al (4) leveraged YOLOv8 for improved precision, recall and mAP in traffic accident recognition from video data. Khoshboresh-Masouleh and Shah-Hosseini (5) addressed real-time vehicle detection challenges in oblique UAV images with SA-Net.v2 using uncertainty estimation and metalearning.…”