Project Introduction

The objective of this project proposed a system that integrated real-time statistical data visualization and 2D real-time detection stream.

Vehicle detection plays an important role in analyzing traffic flow data for efficient planning of traffic management projects. Machine Learning technology has been increasingly used for vehicle detection. Adverse weather conditions prove to be challenging for 2D vehicle detection. There is a lack of research on real-time vehicle detection using LiDAR point clouds which are more resistant to adverse weather conditions. In this project, we proposed a system that collects real-time traffic data, processes it for vehicle detection, and provides a web-based user interface with real-time statistical data visualization and 2D real-time detection stream. We processed 2000 images from the 2D videos that were collected and trained a model on Darknet using YOLO algorithm.

GitHub