A Deep Learning-Based Compact Weighted Binary Classification Technique to Discriminate between Targets and Clutter in SAR Images

다국어 초록 (Multilingual Abstract)

The proposed approach is a deep learning-based compact weighted binary classification (DL-CWBC) method to discriminate between targets and clutter in synthetic aperture radar (SAR) images. A new modified cross-entropy error function is proposed to improve the probability of detection by controlling the rate of false alarms (FAs). The unique feature of a CWBC algorithm is reducing the FA rate and maximizing the probability of target detection without missing any target. For pre-processing, targets and clutter are detected through a constant false alarm rate (CFAR) as a conventional detection algorithm. These are then manually divided into two classes. The classified targets and clutter were trained through a ResNet-101 network. There is a trade-off between the minimization of the FA rate and the maximization of the detection probability for targets of interest (TOIs). The weighted coefficient of the modified cross-entropy error function tries to maximize the performance of this trade-off. In addition, the proposed approach enables us not to miss any targets by an extreme distinction decision. Above all, the DL-CWBC algorithm performs very well despite its simplicity.

참고문헌 (Reference)

1 L. M. Novak, "The automatic target-recognition system in SAIP" 10 (10): 187-202, 1997

2 W. Yu, "Superpixel-based CFAR target detection for high-resolution SAR images" 13 (13): 730-734, 2016

3 W. G. Carrara, "Spotlight Synthetic Aperture Radar: Signal Processing Algorithms" Artech House 2013

4 Y. L. Chang, "Ship detection based on YOLOv2 for SAR imagery" 11 (11): 786-, 2019

5 M. Ma, "Ship classification and detection based on CNN using GF-3 SAR images" 10 (10): 2043-, 2018

6 S. Chen, "SAR target recognition based on deep learning" 541-547, 2014

7 L. Zeng, "SAR target detection based on PSIFT feature clustering" 17-20, 2019

8 H. Rohling, "Radar CFAR thresholding in clutter and multiple target situations" 19 (19): 608-621, 1983

9 L. M. Novak, "Performance of a high-resolution polarimetric SAR automatic target recognition system" 6 (6): 11-24, 1993

10 S. Blake, "OS-CFAR theory for multiple targets and nonuniform clutter" 24 (24): 785-790, 1998

11 J. I. Park, "New discrimination features for SAR automatic target recognition" 10 (10): 476-480, 2013

12 P. Tait, "Introduction to Radar Target Recognition" Institution of Engineering and Technology 2009

13 L. M. Kaplan, "Improved SAR target detection via extended fractal features" 37 (37): 436-451, 2001

14 G. B. Goldstein, "False-alarm regulation in log-normal and Weibull clutter" 9 (9): 84-92, 1973

15 L. M. Novak, "Effects of polarization and resolution on SAR ATR" 33 (33): 102-116, 1997

16 D. E. Kreithen, "Discriminating targets from clutter" 6 (6): 25-52, 1993

17 S. Bao, "Detection of ocean internal waves based on Faster R-CNN in SAR images" 38 (38): 55-63, 2020

18 K. He, "Deep residual learning for image recognition" 770-778, 2016

19 G. Gao, "An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images" 47 (47): 1685-1697, 2009

20 A. Farina, "A review of CFAR detection techniques in radar systems" 29 (29): 115-128, 1986

21 Q. Pham, "A reduced false alarm rate CFAR-based prescreener for SAR ATR" 1997