CNN‐based estimation of heading direction of vehicle using automotive radar sensor

Abstract

Modern autonomous vehicles are being equipped with various automotive sensors to perform special functions. Especially, it is important to predict the heading direction of the front vehicle to adjust the speed of the ego-vehicle and select appropriate actions. Here, we propose a method for estimating the instantaneous heading direction of a vehicle using automotive radar sensor data. First, using a frequency-modulated continuous wave (FMCW) radar in the 77 GHz band, we accumulate the automotive radar sensor data for different movements of the front vehicle (e.g., stop, going ahead, reversing, turning left, and turning right). To distinguish the different movements of the vehicle, we use the convolutional neural network (CNN) and train it using the acquired radar sensor data. Because the CNN algorithm usually uses image data as input, it is essential to convert radar sensor data into image data. Therefore, we apply a highresolution angle estimation algorithm to the obtained radar data and convert it into a two-dimensional range map. After the CNN model is trained with the obtained radar sensor data, various movements of the front vehicle can be classified with over 94% of accuracy.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Simultaneous Target Classification and Moving Direction Estimation in Millimeter-Wave Radar System

“…On the other hand, in the case of a car, its type and movement is identified with very high accuracy, because the number of detected points and the size of the point cloud are larger than those of the pedestrian and cyclist. We also compared the performance of the proposed method with that of the moving direction estimation method using a simple CNN [10]. When the same data were used as input, the average estimation accuracy was 91.4%.…”

“…In automotive radar systems, the possibility of identifying the type of detected object by applying deep learning techniques has been confirmed in many studies [8,9]. In addition, a method of estimating the moving direction of a vehicle by applying a convolutional neural network (CNN) to the range-angle detection result was proposed in [10]. In our work, we use a You Only Look Once (YOLO)-based network [11], one of the CNN-based classifiers for target detection and classification.…”