A Machine Learning Based 77 GHz Radar Target Classification for Autonomous Vehicles
A Machine Learning Based 77 GHz Radar Target Classification for Autonomous Vehicles
复制标题
基于机器学习的自动驾驶车辆 77 GHz 雷达目标分类
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
K. Sarabandi
中科院分区：
文献类型：
--
作者：
Xiuzhang Cai;K. Sarabandi
77 GHz毫米波雷达是最先进和未来自动驾驶汽车的重要传感器。除了传统的毫米波雷达在目标探测、距离和速度测量方面的预期功能外，本文还表明，利用目标的RCS统计信息，对远距离目标（距离超过50米）的分类精度可以达到90%以上。对于具有波束控制能力的先进雷达，近距离分类精度可达99%以上。在这项研究中，基于人工神经网络（ANN）的机器学习技术用于数据分类问题。
77 GHz mmW radar is a powerful essential sensor for the state-of-art and future autonomous vehicles. Besides the traditional intended functionality of mmW radars in target detection and measuring its range and speed, this paper shows that by utilizing the knowledge of targets’ statistical RCS information, over 90% classification accuracy can be achieved for distant targets (range over 50m). For advanced radars with beam-steering capabilities, the classification accuracy can reach to more than 99% in the near range. In this study a machine learning technique based on artificial neural networks (ANN) is used for the data classification problem.