SMCNet: Supervised Surface Material Classification Using mmWave Radar IQ Signals and Complex-valued CNNs

TL;DR

This paper presents SMCNet, a complex-valued CNN that classifies indoor surface materials using mmWave radar IQ signals, achieving high accuracy and robustness across multiple sensing distances.

Contribution

Introduces a novel radar-based surface material classifier using complex-valued CNNs and multi-distance training for improved generalization.

Findings

Achieved over 99% accuracy on known distances.

Range FFT pre-processing significantly improved accuracy on unseen distances.

Multi-distance training enhances robustness of material classification.

Abstract

Understanding surface material properties is crucial for enhancing indoor robot perception and indoor digital twinning. However, not all sensor modalities typically employed for this task are capable of reliably capturing detailed surface material characteristics. By analyzing the reflected RF signal from a mmWave radar sensor, it is possible to extract information about the reflective material and its composition from a certain surface. We introduce a mmWave MIMO FMCW radar-based surface material classifier SMCNet, employing a complex-valued Convolutional Neural Network (CNN) and complex radar IQ signal input for classifying indoor surface materials. While current radar-based material estimation approaches rely on a fixed sensing distance and constrained setups, our approach incorporates a setup with multiple sensing distances. We trained SMCNet using data from three distinct distances and subsequently tested it on these distances, as well as on two more unseen distances. We reached an overall accuracy of 99.12-99.53 % on our test set. Notably, range FFT pre-processing improved accuracy on unknown distances from 25.25 % to 58.81 % without re-training.