Data-Driven Optimization of Urban Traffic using AI and Real-Time Analysis

Abstract

Optimizing urban traffic is a significant problem for cities all over the world. This research aims to tackle this issue by utilizing real-time analysis and artificial intelligence (AI). The project's key components are data collection, the creation of a 2D map, object detection using the YOLO algorithm, 3D segmentation, visualization, and data integration. To ensure the precision of data collection, we employ a multi-GNSS RTK approach for precise location determination. This method allows us to generate exact coordinates for urban road networks, which provides the basis for additional research. We are able to display urban traffic flows on a 2D visualization map, allowing us to spot crowded locations and improve traffic flow. The YOLO method is used in conjunction with 3D segmentation to identify objects. Through training, we allow this algorithm to recognize and categorize a wide range of objects, including moving vehicles, pedestrians, and particular vehicle types (such as minibusses and taxis), which significantly contribute to traffic congestion. Our project makes better use of real-time object detection to enable wellinformed decision-making and improve understanding of the traffic situation.