Military objects detection using a convolutional neural network on radar images formed in jamming conditions

The MSTAR objects detection on noised radar images using the YOLOv4-tiny detector results are presented. It has been shown that on a homogeneous background detector work is satisfactory when the signal-to-noise ratio is 10 dB or more, and completely disrupted when the signal-to-noise ratio is less than 0 dB.