Low-Resolution Ground Surveillance Radar Target Classification Based on 1D-CNN

摘要

The performance of radar automatic target recognition (ATR) highly depends on the quality of training database, theextracted features and classification algorithm. Radar target is detected by the Doppler effect in radar echo signal. Throughprocessing the echo signals in different domains, the distinctive characteristic can be obtained intuitively. Furthermore, wecan utilize the extracted features to complete radar target classification. This paper proposes a novel target recognitionmethod based on 1D-convolution neural network (CNN) aiming at the ATR of low-resolution ground surveillance radar.The proposed approach uses 1D-CNN as feature extractor and softmax layer as classifier. We tested our method on actualcollected database to classify human and car, which reached an accuracy of 98%. Compared with conventional artificialfeature extraction approaches, our model shows better performance and adaptability.