Object Detection From a Few LIDAR Scanning Planes

Abstract

LIDAR sensors enable object and free-space detection for intelligent transportation systems and vehicles. This paper proposes a recognition method for LIDARs based on only a few detection planes. This method is useful especially in the case when the angular resolution of the scan is sufficient, but in the vertical direction the planes are far from each other. We use Fourier descriptor to characterize a scan plane and Convolutional Neural Network for classification. Our method exploits both time varying shape information and contours from multiple scan planes if available. The method performs at least as well as the state of the art algorithms in case of near field, and it also expands the detection range. It was evaluated on tens of thousands of samples from large public datasets and we did separate evaluation for far field objects as well.