Vehicle Movement Detection using AI and ML

This master’s thesis focuses on vehicle detection and tracking. The research tries to detect vehicles in images and videos. It deploys a dataset from Udacity in order to train the algorithms. Two machine learning algorithms. Support Vector Machine (SVM) and Decision Tree have been developed for the detection and tracking tasks. Python programming language have been utilized as the development language for the creation and training of both models. These two algorithms have been developed, trained, tested, and compared to each other to specify the weaknesses and strengths of each of them, although to present and suggest the best model among these two. For the evaluation purpose multiple techniques are used in order to compare and identify the more accurate model. The primary goal and target of the thesis is to develop a system in which the system should be able to detect and track the vehicles automatically whether they are static or moving in images and videos. Efficient management of vehicle traffic and parking is crucial for large campuses to ensure smooth operations and enhance user experience. This problem statement addresses the need for an intelligent solution capable of analyzing vehicle movement patterns and monitoring parking occupancy in real-time. The proposed solution aims to analyze the frequency and timing of vehicle movements in and out of the campus, enabling the identification of peak traffic times and movement patterns. By understanding these patterns, campus administrators can optimize traffic flow, reduce congestion, and improve overall safety and efficiency.