Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Practical Radar Sensing Using Two Stage Neural Network for Denoising OTFS Signals

Ashok S Kumar, Sheetal Kalyani

TL;DR

The proposed two-stage approach can predict the range and velocity of multiple targets, even in very low signal-to-noise ratio scenarios, with high accuracy and outperforms existing methods.

Abstract

Our objective is to derive the range and velocity of multiple targets from the delay-Doppler domain for radar sensing using orthogonal time frequency space (OTFS) signaling. Noise contamination affects the performance of OTFS signals in real-world environments, making radar sensing challenging. This work introduces a two-stage approach to tackle this issue. In the first stage, we use a generative adversarial network to denoise the corrupted OTFS samples, significantly improving the data quality. Following this, the denoised signals are passed to a convolutional neural network model to predict the values of the velocities and ranges of multiple targets. The proposed two-stage approach can predict the range and velocity of multiple targets, even in very low signal-to-noise ratio scenarios, with high accuracy and outperforms existing methods.

Practical Radar Sensing Using Two Stage Neural Network for Denoising OTFS Signals

TL;DR

The proposed two-stage approach can predict the range and velocity of multiple targets, even in very low signal-to-noise ratio scenarios, with high accuracy and outperforms existing methods.

Abstract

Our objective is to derive the range and velocity of multiple targets from the delay-Doppler domain for radar sensing using orthogonal time frequency space (OTFS) signaling. Noise contamination affects the performance of OTFS signals in real-world environments, making radar sensing challenging. This work introduces a two-stage approach to tackle this issue. In the first stage, we use a generative adversarial network to denoise the corrupted OTFS samples, significantly improving the data quality. Following this, the denoised signals are passed to a convolutional neural network model to predict the values of the velocities and ranges of multiple targets. The proposed two-stage approach can predict the range and velocity of multiple targets, even in very low signal-to-noise ratio scenarios, with high accuracy and outperforms existing methods.
Paper Structure (7 sections, 11 equations, 4 figures)

This paper contains 7 sections, 11 equations, 4 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. Proposed Approach
  4. First Stage: Denoising OTFS Signals Using GAN
  5. Second Stage: CNN Architecture for Predicting the Range and Velocity of the Target
  6. Simulation Results
  7. Performance Analysis and Comparison With the State-of-the-Art Methods

Figures (4)

  • Figure 1: Block diagram of GAN for denoising
  • Figure 2: Proposed CNN architecture for predicting the range and velocity of the target
  • Figure 3: The DD matrices obtained by performing the 2D correlation between low noise signal and transmitted signal in the DD domain. This 2D clean data is given as input to the discriminator.
  • Figure 4: The DD matrices obtained by performing the 2D correlation between corrupted signal and transmitted signal in the DD domain. This 2D corrupted data is given as input to the generator.