Radar system using machine learning model for stationary object detection

This document describes techniques and systems related to radar systems using machine learning models for stationary object detection. A radar system includes a processor capable of receiving radar data in the form of a time series frame associated with electromagnetic (EM) energy. The processor uses the radar data to generate a distance-time map of EM energy input to the machine learning model. The machine learning model can receive, as input, features corresponding to stationary objects extracted from distance-time maps of a plurality of distance intervals at each time series frame. In this manner, the described radar systems and techniques can accurately detect stationary objects of various sizes and extract key features corresponding to the stationary objects. 本文档描述了与使用用于静止对象检测的机器学习模型的雷达系统相关的技术和系统。雷达系统包括处理器，该处理器能够接收与电磁(EM)能量相关联的时间序列帧形式的雷达数据。处理器使用雷达数据来生成输入到机器学习模型的EM能量的距离时间图。机器学习模型能够接收从每个时间序列帧处的多个距离区间的距离时间图中提取的与静止对象相对应的特征作为输入。以此方式，所描述的雷达系统和技术能够准确地检测各种大小的静止对象并且提取与静止对象对应的关键特征。