Recent advancements demonstrate the application of machine learning techniques to radar signal processing, particularly the use of neural networks in 1-D radar data to assist Constant False Alarm Rate (CFAR) based target detection. However, the efficacy of using neural networks alone on 2-D data for target extraction remains to be explored. This research aims to develop a novel approach of designing a Convolution Neural Network (CNN) based target detection system, for real radar data. The first step in this approach filters out the noisy images. While in the second step the CNN-based detector uses both radar data axes (fast-time and slow-time), thus utilizing additional information for better detection of targets even with low SNR. Moreover, the same CNN, in conjunction with a region-based convolutional network, exploits micro-Doppler features of rotary-wing aircraft in radar returns and uses them to further classify detected targets as fixed-wing or rotary-wing aircraft. To the best of our knowledge, no generalized methodology exists to address these two issues together. This paper also introduces a labeled range-Doppler images dataset obtained from real-world Air Traffic Control (ATC) Radar data. Experimental result demonstrates the superior performance of the proposed technique over 1-D and 2-D CFAR detectors.

Security Management for an E-Enterprise: 10.4018/978-1-59140-911-3.ch007: Enterprise integration is the key enabler for transforming the collaboration among people, organization, and technology into an enterprise. Its most important