EFFICIENT CLASSIFICATION OF LOW-RESOLUTION RANGE PROFILES OF AUTOMOBILES USING A COMBINATION OF USEFUL FEATURES

The range profile (RP) of an automobile is derived by compressing the wideband radar signal, and it can be utilized for the classification and thus contribute to lane change and collision avoidance. However, the limited radar bandwidth due to the cost and the system complexity impedes the successful classification. This paper proposes an efficient method to construct an efficient feature vector of the automobile RP through combined use of the central moment, the information on the maximum-minimum and the peak information. Simulation results using the five automobile models composed of point scatterers and a simple nearest neighbor classifier prove that the proposed method improves the classification result, especially in the multi-aspect classification.