Nighttime Motion Vehicle Detection Based on MILBoost

This paper propose an effective approach for detecting and tracking moving vehicles in nighttime traffic scenes. Vehicles were detected automatically from video sequences at nighttime by constructing the MILBoost model. At first, we extract SIFT feature using SIFT feature extraction algorithm, which is used to characterize moving vehicles in nighttime. Then MILBoost model is used for the on-road detection of vehicles at nighttime. In order to improve the detection accuracy, the class label information was used for the learning of the MILBoost model. Final experiments were performed and evaluate the proposed method at nighttime under urban traffic condition, the experiment results show that the average detection accuracy is over 98.17 %, which validates that the proposed vehicle detection approach is feasible and effective for the on-road detection of vehicles at nighttime and identification in various nighttime environments. Copyright © 2014 IFSA Publishing, S. L.