Vehicle recognition based on Haar features and Adaboost cascade classifier

Abstract

Abstract With the progress of world science and economic development, more and more industries are developing towards intelligence and automation. In the field of intelligent driving, the intelligent vehicle environment perception method based on machine vision has become a hot research topic. Based on monocular vision system, aiming at the requirements of different target features and detection accuracy and efficiency, this paper improves the Haar feature and Adaboost cascade classifier recognition algorithm combined with gray symmetry method to adapt to the recognition environment required by vehicles. The measured results show that the improved vehicle identification method combined with the tracking method based on Kalman filter can reduce the misjudgment rate of vehicles and has good real-time performance.