Measurement-based Evaluation of CNN-based Detection and Estimation for ISAC Systems

TL;DR

This paper evaluates a CNN-based method for target detection and estimation in ISAC systems, trained on synthetic data and tested on real measurement data, demonstrating its practical effectiveness in complex outdoor scenarios.

Contribution

It introduces a CNN approach trained on synthetic data and validated on real measurement data for robust target detection and estimation in ISAC systems.

Findings

The CNN approach performs well on measurement data.

Detection probability and accuracy are satisfactory in outdoor scenarios.

Method is suitable for real-time joint detection and estimation.

Abstract

In wireless sensing applications, such as ISAC, one of the first crucial signal processing steps is the detection and estimation targets from a channel estimate. Effective algorithms in this context must be robust across a broad SNR range, capable of handling an unknown number of targets, and computationally efficient for real-time implementation. During the last decade, different Machine Learning methods have emerged as promising solutions, either as standalone models or as complementing existing techniques. However, since models are often trained and evaluated on synthetic data from existing models, applying them to measurement is challenging. All the while, training directly on measurement data is prohibitive in complex propagation scenarios as a groundtruth is not available. Therefore, in this paper, we train a CNN approach for target detection and estimation on synthetic data and evaluate it on measurement data from a suburban outdoor measurement. Using knowledge of the environment as well as available groundtruth positions, we study the detection probability and accuracy of our approach. The results demonstrate that our approach works on measurement data and is suitable for joint detection and estimation of sensing targets in ISAC systems.