AI Driven Crowdsourced Predictive System for Real Time Traffic Violation Detection using YOLO and GPS Tagging

DOI

10.2991/978-94-6239-693-7_39How to use a DOI?

Keywords

Traffic violation detection; intelligent transportation systems; deep learning-based surveillance; YOLOv5; YOLOv8; privacy-by-design; citizen-sourced reporting; edge computing; geo-temporal heatmaps; GPS metadata; Leaflet.js; OpenStreetMap; predictive traffic analytics; smart city integration; public- participation enforcement; road-safety monitoring

Abstract

Rapid urbanization has escalated the problem of road safety in general and has also led to the concentration of these challenges in certain areas, particularly those that are manpower- and infrastructure- deficient. In such places, expensive systems such as CCTV, ANPR, and red-light detectors cannot be easily deployed, so a large number of locations are left with manual enforcement, which in turn results in detection delays. TraffIQ is a citizen-oriented, privacy-respecting traffic violation detection and reporting system, which is being proposed. It detects the violations of helmetless riding, triple riding, and signal jumping, etc. in the media from citizens and the community camera footage uploaded by citizens using YOLOv5 and YOLOv8. The privacy-by-design model of the system is intentionally installed to anonymize the faces and the vehicle registration numbers of those who are photographed for public display, while the original evidence is stored in a secure way for authorized officials. Every report carries location and time data that can be used to create geo- temporal heatmaps with the help of Leaflet.js and OpenStreetMap to identify hot spots and the times of the day when there are the most traffic violations in order to make the traffic management predictive and proactive. They are TraffIQ, which is intended for low-cost edge devices and thereby can expand monitoring beyond government infrastructure. TraffIQ thus presents a scalable, sustainable solution that is suitable for integration into future smart-city and intelligent transportation systems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Annangi Mokshini Yadav
AU  - Chindu Gowtham Naresh
AU  - Minu Susan Jacob
PY  - 2026
DA  - 2026/06/16
TI  - AI Driven Crowdsourced Predictive System for Real Time Traffic Violation Detection using YOLO and GPS Tagging
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 385
EP  - 396
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_39
DO  - 10.2991/978-94-6239-693-7_39
ID  - Yadav2026
ER  -