ABSTRACT

This paper aims to study and develop a vehicle tracking and detection system based on artificial intelligence and decision technology. By integrating deep learning algorithm, computer vision technology and intelligent decision support module, the system realizes the accurate tracking and real-time detection of vehicle targets in road traffic scenes. The paper first analyzes the current development status of vehicle tracking and detection technology and points out the limitations of traditional methods in the face of complex traffic environment. Based on this, this paper proposes a multi-level vehicle target feature extraction method, combining convolutional neural network (CNN) and recurrent neural network (RNN), to achieve robust feature extraction for vehicle target. At the same time, by building a decision model based on reinforcement learning, the system can dynamically adjust the strategy during the tracking process to adapt to the target changes in different traffic environments. The experimental results show that the proposed vehicle target tracking and detection system shows high accuracy and real-time in various traffic scenarios, which provides strong support for the further development of intelligent transportation systems.

Keywords: artificial intelligence, deep learning, intelligent decision making, target detection, vehicle tracking
https://doi.org/ 10.57180/xnwj1657