用公交摄像头数据重建出行流向，为非洲交通研究提供新方法
Recovering Origin Destination Flows from Bus CCTV: Early Results from Nairobi and Kigali
- 结合目标检测、跟踪与车牌时间戳，从已有监控视频中提取乘客上下车信息
- 在光线好、人少场景下识别准确率超90%，生成的出行矩阵接近人工统计结果
- 揭示了拥挤、变色等现实问题对系统的影响，推动更鲁棒的行人重识别技术发展
撒哈拉以南非洲（SSA）公共交通常处于超载状态，现有自动化系统难以可靠获取乘客流动数据。利用已部署于公交车上的监控摄像头，我们提出一个基准流程，结合YOLOv12检测、BotSORT跟踪、OSNet嵌入、OCR时间标记及基于车辆定位数据的站点分类，以恢复公交起讫点（OD）客流。在内罗毕和基加利公交车的标注视频片段上，系统在低密度、光照良好条件下达到高计数准确率（召回率≈95%，精确率≈91%，F1≈93%），生成的OD矩阵与人工统计高度吻合。但在真实压力场景下，如拥挤、色彩转灰度、姿态变化及非标准车门使用时，性能显著下降（例如高峰时段上车量约低估40%，灰度片段召回率下降约17个百分点），暴露出部署相关失效模式，提示需开发更鲁棒、面向实际部署的行人重识别方法用于SSA公共交通。
原文摘要 · Abstract (English)
Public transport in sub-Saharan Africa (SSA) often operates in overcrowded conditions where existing automated systems fail to capture reliable passenger flow data. Leveraging onboard CCTV already deployed for security, we present a baseline pipeline that combines YOLOv12 detection, BotSORT tracking, OSNet embeddings, OCR-based timestamping, and telematics-based stop classification to recover bus origin--destination (OD) flows. On annotated CCTV segments from Nairobi and Kigali buses, the system attains high counting accuracy under low-density, well-lit conditions (recall $\approx$95\%, precision $\approx$91\%, F1 $\approx$93\%). It produces OD matrices that closely match manual tallies. Under realistic stressors such as overcrowding, color-to-monochrome shifts, posture variation, and non-standard door use, performance degrades sharply (e.g., $\sim$40\% undercount in peak-hour boarding and a $\sim$17 percentage-point drop in recall for monochrome segments), revealing deployment-specific failure modes and motivating more robust, deployment-focused Re-ID methods for SSA transit.
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。