Vehicle centroid estimation based on radar multiple detections

Automotive radar application is a focus in active traffic safety research activities. And an accurate lateral position estimation from the leading target vehicle through radar is of great interest. This paper presents a method based on the regression tree, which estimates the rear centroid of leading target vehicle with a long range FLR (Forward Looking Radar) of limited resolution with multiple radar detections distributed on the target vehicle. Hours of radar log data together with reference value of leading vehicle´s lateral offset are utilized both as training data and test data as well. A ten-fold cross validation is applied to evaluate the performance of the generated regression trees together with fused decision forest for each percentage of the training data. As a result, compared with the current approach which calculates the mean of lateral offset, the regression tree and decision forest approach yield more accurate position estimation of the lateral offset from a single leading target vehicle with radar multiple detections.