Distributed Radar Interval Distance Estimation Based on Deep Neural Network

Abstract

In recent years, millimeter wave (mmWave) radar has played an indispensable role in several applications. mm Wave radars can measure the distance, speed, and angle of objects, but the transmit power of a single mm Wave radar is limited. By deploying multiple mm Wave radars in a distributed manner and fusing signals from them, detection results will be improved. Before data fusion, it is necessary to accurately measure the external parameters between different radars to complete the coordinates calibration of the radar network. Current methods focus on the calibration method by jointly observing moving objects in overlapping view fields of the radar network. The calibration process requires one target to move within a defined area. Because the radar cross section (RCS) characteristics of the target in all directions are usually inconsistent, if the reflected signal of this target is weak during the calibration process, the error of this method will be relatively large. This paper proposes a new neural network-based method to estimate the interval distance between different radars without passing through a moving target. The distance estimation error of the proposed network can reach within 0.1 m, which is smaller than the calibration method based on moving objects. Through the verification of actual measured data, the proposed network can more accurately estimate the interval distance between radars.