Intelligent Vehicle Detection System
MSc Thesis Defense by:
Aahan Singh Charak
Date: 24/03/2026
Time: 1:00pm
Location: OBB04
Abstract:
A steady increase in the number of vehicles on roads around the world has increased the need for Intelligent Traffic System (ITS). Vehicle detection, classification, and license plate recognition are essential for traffic analysis and ITS. License plate detectors are especially helpful to the law agencies, as they assist in catching criminals by recognizing license plates. Systems employing Artificial Intelligence (AI) utilize image classification and object detection to monitor and analyze traffic on roads and highways. These systems are powered by state-of-the-art neural network architectures (e.g the Convolutional Neural Network (CNN) for classification), which enable accurate detection and processing of real-time traffic data. Most vehicle monitoring systems, however, focus on only one aspect of vehicle tracking at a time. This thesis introduces a novel approach to vehicle monitoring systems, which involves focusing on all attributes simultaneously. Our vehicle recognition system achieves an average accuracy of 91.2% across all the different classification subtasks whereas the license plate detection system achieves an accuracy of 93.46%. To further solidify our research, we compared our approach against a multi-headed network architecture, as such architectures are commonly used for solving multi-attribute classification tasks and serve as a strong baseline for evaluating performance. We also tested our system on images of different aspect ratios and evaluated its ability to detect multiple vehicles in a single image to demonstrate robustness.
