TransitReID: Transit OD Data Collection with Occlusion-Resistant Dynamic Passenger Re-Identification

2025-04-15

AI Summary

To address the high cost and limited coverage of origin-destination (OD) data collection in complex bus environments, and the low matching accuracy of visual person re-identification (ReID) under severe occlusion and large viewpoint variations, this paper proposes a lightweight, passenger-level OD sensing method tailored for edge devices. Our approach introduces three key innovations: (1) an occlusion-robust VAE-guided region-attention ReID model, where attention weights are optimized via reconstruction loss; (2) a hierarchical storage–dynamic matching (HSDM) mechanism enabling low-storage, near-real-time identity matching; and (3) the first ReID benchmark dataset specifically designed for challenging bus scenarios. The system integrates a multi-threaded edge computing framework with a privacy-preserving video processing module. Experiments demonstrate a ReID accuracy of 90%, significantly surpassing state-of-the-art methods while maintaining high computational efficiency and practical deployability on resource-constrained edge hardware.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Transit Origin-Destination (OD) data are essential for transit planning, particularly in route optimization and demand-responsive paratransit systems. Traditional methods, such as manual surveys, are costly and inefficient, while Bluetooth and WiFi-based approaches require passengers to carry specific devices, limiting data coverage. On the other hand, most transit vehicles are equipped with onboard cameras for surveillance, offering an opportunity to repurpose them for edge-based OD data collection through visual person re-identification (ReID). However, such approaches face significant challenges, including severe occlusion and viewpoint variations in transit environments, which greatly reduce matching accuracy and hinder their adoption. Moreover, designing effective algorithms that can operate efficiently on edge devices remains an open challenge. To address these challenges, we propose TransitReID, a novel framework for individual-level transit OD data collection. TransitReID consists of two key components: (1) An occlusion-robust ReID algorithm featuring a variational autoencoder guided region-attention mechanism that adaptively focuses on visible body regions through reconstruction loss-optimized weight allocation; and (2) a Hierarchical Storage and Dynamic Matching (HSDM) mechanism specifically designed for efficient and robust transit OD matching which balances storage, speed, and accuracy. Additionally, a multi-threaded design supports near real-time operation on edge devices, which also ensuring privacy protection. We also introduce a ReID dataset tailored for complex bus environments to address the lack of relevant training data. Experimental results demonstrate that TransitReID achieves state-of-the-art performance in ReID tasks, with an accuracy of approximately 90% in bus route simulations.

Problem

• Collecting transit OD data efficiently without manual surveys
• Overcoming occlusion and viewpoint challenges in passenger ReID
• Designing edge-compatible algorithms for real-time OD matching

Innovation

• Occlusion-robust ReID with variational autoencoder region-attention
• Hierarchical Storage and Dynamic Matching for efficient OD
• Multi-threaded edge design ensures real-time privacy protection