This project leverages YOLO (You Only Look Once) to detect various traffic violations in real-time, aimed at improving road safety and compliance.

This project basically aims to speed up the ticketing process for Traffic Sergeants by using their mobile phones and issue tickets by taking a couple of photos and uses Computer Vision APIs to process information from those photos.

A Python-based computer vision system that detects vehicles violating red traffic lights using video streams: the system monitors traffic signal status, identifies vehicles crossing during a red phase, and flags those as violations aimed at enhancing intersection safety and automated traffic monitoring.

Developed a full-stack traffic system with FastAPI, Flask, React, and MySQL. It manages vehicle records and violations, and uses an AI model to detect no-helmet cases from images and automatically log them with evidence.

Web (Django) application and Python appplication to keep track of traffic violations through RFID System in Raspberry Pi 3B. Hosted at: https://trafficpenaltysystemsk17.azurewebsites.net/ . Corresponding IoT/Raspberry Pi repository at: https://github.com/shashwatkathuria/IoT-TrafficMonitoringSystem

A platform, 'Traffic-Violation-Report-System', enabling users in Taiwan to upload and share responses from law enforcement to traffic violations. This system aims for greater transparency in traffic law enforcement. It utilises Django for backend and Flutter for a separated frontend web development.

This project is to determine the safest and the most dangerous neighborhoods in Chicago and provide suggestions for how to avoid many violations in certain areas.

The aim of the project is to apply different global, local and performance interpretability methods as well as model fairness evaluations to a dataset with protected attributes. The dataset regards traffic violations in Montgomery, Maryland, USA. This is a fork of a group project of my Data Science for Business Master's Degree at HEC Paris.

A high-efficiency traffic violation detection system built with YOLO26n. NanoTraffic identifies motorcycles and bicycles in real-time, specifically targeting pedestrian road incursions, crosswalk violations, and stop-line infractions. Designed as a learning project to master edge-optimized computer vision and the Ultralytics ecosystem.