DashCop: Automated E-ticket Generation for Two-Wheeler Traffic Violations Using Dashcam Videos

2025-03-01

AI Summary

To address the challenges of detecting traffic violations involving two-wheeled vehicles—such as overloading (i.e., three occupants) and helmet non-compliance—characterized by low detection accuracy, imprecise rider-vehicle matching, and frequent tracking failures, this paper proposes an end-to-end video analytics system. Methodologically: (i) we design a Segmentation-and-Cross-Association (SAC) module to achieve pixel-level precise matching between riders and vehicles; (ii) we introduce a robust cross-frame multi-object association tracking algorithm resilient to high density, occlusion, and abrupt scale changes; (iii) we construct RideSafe-400, the first annotated video dataset specifically for two-wheeler violation recognition, comprising 400 real-world road videos. Experiments demonstrate that our system significantly improves violation detection accuracy on RideSafe-400 (mAP ↑12.6%) and enables real-time electronic ticket generation, validating its effectiveness and practical deployability in complex urban traffic environments.

Technology Category

• Computer Vision: Motion & Tracking
• Application Domains: Transportation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Motorized two-wheelers are a prevalent and economical means of transportation, particularly in the Asia-Pacific region. However, hazardous driving practices such as triple riding and non-compliance with helmet regulations contribute significantly to accident rates. Addressing these violations through automated enforcement mechanisms can enhance traffic safety. In this paper, we propose DashCop, an end-to-end system for automated E-ticket generation. The system processes vehicle-mounted dashcam videos to detect two-wheeler traffic violations. Our contributions include: (1) a novel Segmentation and Cross-Association (SAC) module to accurately associate riders with their motorcycles, (2) a robust cross-association-based tracking algorithm optimized for the simultaneous presence of riders and motorcycles, and (3) the RideSafe-400 dataset, a comprehensive annotated dashcam video dataset for triple riding and helmet rule violations. Our system demonstrates significant improvements in violation detection, validated through extensive evaluations on the RideSafe-400 dataset.

Problem

• Automates e-ticket generation for two-wheeler traffic violations.
• Detects violations like triple riding and helmet non-compliance.
• Improves traffic safety using dashcam video analysis.

Innovation

• Segmentation and Cross-Association module for rider-motorcycle association
• Cross-association-based tracking algorithm for simultaneous rider-motorcycle detection
• RideSafe-400 dataset for triple riding and helmet violation annotations