Recovering Origin Destination Flows from Bus CCTV: Early Results from Nairobi and Kigali

TL;DR

This paper presents a baseline system using CCTV footage and computer vision techniques to estimate bus origin-destination flows in Nairobi and Kigali, achieving high accuracy in controlled conditions but facing challenges under real-world stressors.

Contribution

It introduces a pipeline combining detection, tracking, embedding, OCR, and telematics to recover OD flows from CCTV footage in SSA buses, highlighting deployment-specific challenges.

Findings

High accuracy in low-density, well-lit conditions (recall 95%, precision 91%)

OD matrices closely match manual tallies in controlled settings

Performance drops significantly under overcrowding and adverse conditions

Abstract

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.