Video Detector: A Dual-Phase Vision-Based System for Real-Time Traffic Intersection Control and Intelligent Transportation Analysis

TL;DR

Video Detector (VD) is a dual-phase, vision-based traffic management system that offers real-time intersection control and detailed traffic analysis, providing a cost-effective alternative to traditional sensor-based methods.

Contribution

The paper introduces a flexible, dual-phase vision-based system with high accuracy and real-time performance, integrating multiple deep learning models for comprehensive traffic monitoring.

Findings

Achieves up to 90% detection accuracy and 29.5 mAP@0.5

Operates at 37 FPS on HD video streams in real-time

Demonstrates stable deployment in diverse environmental conditions

Abstract

Urban traffic management increasingly requires intelligent sensing systems capable of adapting to dynamic traffic conditions without costly infrastructure modifications. Vision-based vehicle detection has therefore become a key technology for modern intelligent transportation systems. This study presents Video Detector (VD), a dual-phase vision-based traffic intersection management system designed as a flexible and cost-effective alternative to traditional inductive loop detectors. The framework integrates a real-time module (VD-RT) for intersection control with an offline analytical module (VD-Offline) for detailed traffic behavior analysis. Three system configurations were implemented using SSD Inception v2, Faster R-CNN Inception v2, and CenterNet ResNet-50 V1 FPN, trained on datasets totaling 108,000 annotated images across 6-10 vehicle classes. Experimental results show detection performance of up to 90% test accuracy and 29.5 mAP@0.5, while maintaining real-time throughput of 37 FPS on HD video streams. Field deployments conducted in collaboration with Istanbul IT and Smart City Technologies Inc. (ISBAK) demonstrate stable operation under diverse environmental conditions. The system supports virtual loop detection, vehicle counting, multi-object tracking, queue estimation, speed analysis, and multiclass vehicle classification, enabling comprehensive intersection monitoring without the need for embedded road sensors. The annotated dataset and training pipeline are publicly released to support reproducibility. These results indicate that the proposed framework provides a scalable and deployable vision-based solution for intelligent transportation systems and smart-city traffic management.