Chaff Discrimination Using Convolutional Neural Networks and Range Profile Data

In this paper a method for chaff and ship discrimination is discussed. The method uses one dimensional range profile data for the input of the convolutional neural network (CNN). The classification results for the CNN running on MATLAB and using Levenberg-Marquardt algorithm are presented for a database composed of 3 types of ship and one type of chaff. This input database is corrupted with different levels of sea clutter in order to conclude on the performance of the CNN in different SCR conditions. The same CNN is also built using Python with Tensorflow backend. The CNN is tested for the database corrupted with sea clutter having a Gaussian spectral function on Python. Classification rates starting from %87 for low SCR (5 dB) up to %99 for high SCR (20 dB) are obtained for the ship and chaff database which are corrupted with sea clutter.