Real-time vehicle tracking on highway

Abstract

We propose a macroscopic method, which can perform real-time tracking of moving vehicles on highway. In addition to dealing with the problem caused by occlusion and noise, the proposed method can also track a vehicle doing lane change. The proposed method consists of two phases: the detection phase and the tracking phase. In the detection phase, we use entropy-based features to check the existence of vehicles. Then, we use the flux theory, which is commonly used in fluid mechanics to perform the tracking task. By conducting a great number of experiments, we have demonstrated the efficiency as well as the effectiveness of the proposed system.