用视觉系统实时监控交通，替代昂贵地感线圈。
Video Detector: A Dual-Phase Vision-Based System for Real-Time Traffic Intersection Control and Intelligent Transportation Analysis
- 分两阶段处理：实时控制+离线分析，兼顾效率与深度。
- 检测准确率最高达90%，[email protected]达29.5，37帧/秒流畅运行。
- 适合城市智能交通、智慧城市建设者使用。
城市交通管理日益需要能适应动态交通状况、无需昂贵基础设施改造的智能感知系统。基于视觉的车辆检测因此成为现代智能交通系统的关键技术。本文提出Video Detector（VD），一种双阶段视觉交通路口管理系统，作为传统地感线圈探测器的灵活且低成本替代方案。该框架集成实时模块（VD-RT）用于路口控制，以及离线分析模块（VD-Offline）用于详细交通行为分析。采用SSD Inception v2、Faster R-CNN Inception v2和CenterNet ResNet-50 V1 FPN三种模型，基于总计108,000张标注图像、涵盖6–10类车辆的数据集进行训练。实验结果显示，检测性能最高达90%测试准确率和29.5 [email protected]，同时在高清视频流上保持37 FPS的实时吞吐量。与伊斯坦布尔交通局及Smart City Technologies Inc.（ISBAK）合作开展的实地部署表明，系统在多种环境条件下运行稳定。该系统支持虚拟环形检测、车辆计数、多目标追踪、队列估计、速度分析及多类别车辆分类，实现无需嵌入式道路传感器的全面路口监测。所使用的标注数据集与训练流程已公开，以支持可复现性。结果表明，该框架为智能交通系统与智慧城市交通管理提供了可扩展、可部署的视觉解决方案。
原文摘要 · Abstract (English)
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 [email protected], 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。