A desirable objective in radar detection theory is the ability to detect and recognize targets in intricate scenarios such as in the presence of clutter or multiple closely spaced targets. Herein we propose the use of artificial neural networks for radar target detection where Smallest Of (SO)-CFAR detector is used as the basis for neural network training. The SO-CFAR detector has exceptional good detectional capabilities, however, suffers from a very high false alarm rate and has therefore only been given limited attention in the literature. We show that by appropriately training a neural network on SO-CFAR detections it is possible to significantly lower the false alarm rate with only marginal decrease in probability of detection.
Paper
Full text
Training of Neural Network Target Detectors Mentored by SO-CFAR
Semantic Scholar · Engineering · 2021
Abstract
A desirable objective in radar detection theory is the ability to detect and recognize targets in intricate scenarios such as in the presence of clutter or multiple closely spaced targets. Herein we propose the use of artificial neural networks for radar target detection where Smallest Of (SO)-CFAR detector is used as the basis for neural network training. The SO-CFAR detector has exceptional good detectional capabilities, however, suffers from a very high false alarm rate and has therefore only been given limited attention in the literature. We show that by appropriately training a neural network on SO-CFAR detections it is possible to significantly lower the false alarm rate with only marginal decrease in probability of detection.