Classification Of Automotive Targets Using Inverse Synthetic Aperture Radar Images

TL;DR

This paper develops a simulation framework for automotive radar images at millimeter wave frequencies, validated with real data, and demonstrates high-accuracy classification using machine learning and deep neural networks.

Contribution

The paper introduces a realistic simulation model for automotive ISAR images that incorporates scattering, clutter, and noise, and applies transfer learning for classification.

Findings

Simulation images achieve over 90% classification accuracy.

The model is validated with real automotive radar data.

ISAR images are robust to noise and clutter.

Abstract

We present a framework for simulating realistic inverse synthetic aperture radar images of automotive targets at millimeter wave frequencies. The model incorporates radar scattering phenomenology of commonly found vehicles along with range-Doppler based clutter and receiver noise. These images provide insights into the physical dimensions of the target, the number of wheels and the trajectory undertaken by the target. The model is experimentally validated with measurement data gathered from an automotive radar. The images from the simulation database are subsequently classified using both traditional machine learning techniques as well as deep neural networks based on transfer learning. We show that the ISAR images offer a classification accuracy above 90% and are robust to both noise and clutter.