An Optimized YOLOv5 Based Approach For Real-time Vehicle Detection At Road Intersections Using Fisheye Cameras

2025-02-06

AI Summary

To address nonlinear distortion, illumination variations (especially at night), and poor localization of small vehicles in real-time fisheye camera-based urban intersection detection, this paper proposes a lightweight day-night adaptive collaborative optimization framework. Methodologically: (1) a novel CNN-based day-night classifier guides YOLOv5’s dynamic inference; (2) fisheye distortion compensation preprocessing and upsampling-based augmentation for small-vehicle samples are introduced; (3) a multi-source dataset hybrid ensemble training strategy is adopted. Evaluated on the real-world VIP Cup fisheye intersection dataset, the method achieves an mAP@0.5 of 72.4%, outperforming standard YOLOv5 by 13.7 percentage points. It significantly improves robustness under low-light conditions and detection accuracy for small vehicles, while maintaining computational efficiency suitable for edge deployment.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Real time vehicle detection is a challenging task for urban traffic surveillance. Increase in urbanization leads to increase in accidents and traffic congestion in junction areas resulting in delayed travel time. In order to solve these problems, an intelligent system utilizing automatic detection and tracking system is significant. But this becomes a challenging task at road intersection areas which require a wide range of field view. For this reason, fish eye cameras are widely used in real time vehicle detection purpose to provide large area coverage and 360 degree view at junctions. However, it introduces challenges such as light glare from vehicles and street lights, shadow, non-linear distortion, scaling issues of vehicles and proper localization of small vehicles. To overcome each of these challenges, a modified YOLOv5 object detection scheme is proposed. YOLOv5 is a deep learning oriented convolutional neural network (CNN) based object detection method. The proposed scheme for detecting vehicles in fish-eye images consists of a light-weight day-night CNN classifier so that two different solutions can be implemented to address the day-night detection issues. Furthurmore, challenging instances are upsampled in the dataset for proper localization of vehicles and later on the detection model is ensembled and trained in different combination of vehicle datasets for better generalization, detection and accuracy. For testing, a real world fisheye dataset provided by the Video and Image Processing (VIP) Cup organizer ISSD has been used which includes images from video clips of different fisheye cameras at junction of different cities during day and night time. Experimental results show that our proposed model has outperformed the YOLOv5 model on the dataset by 13.7% mAP @ 0.5.

Problem

• Optimizing YOLOv5 for real-time vehicle detection.
• Addressing challenges in fisheye camera vehicle detection.
• Improving accuracy in day-night traffic surveillance.

Innovation

• Modified YOLOv5 for vehicle detection
• Light-weight day-night CNN classifier
• Ensembled training for improved generalization