Introduction: The ability to interpret the image is one of the key and important features in the ability of imaging systems, which is usually used in the concept of the ability to extract information from the image. Quantifying this feature is one of the main challenges in the fields of information content and image integration in remote sensing, which is needed and important in various applications such as target detection. By evaluating the interpretability of remote sensing images, it is possible to estimate the appropriate image characteristics for various target detection applications.
In general, the interpretability of remote sensing images depends on the conditions of imaging, environment and target. Polarimetric radar images are a very useful source of data in target detection applications with more resolution than single-channel radar images. So far, various methods and models have been presented to evaluate the performance of detection in polarimetric radar images; most of them are based on the theory of signal detection or based on the probability of target detection and false alarm. National Image Interpretability Rating Scale (NIIRS) models, the automatic target detection (ATD) and simultaneous tracking and tracking and recognition (STAR) models are among the common and conventional methods of evaluating the interpretability of radar images in target detection applications. The NIIRS radar is based on the general image quality equation (GIQE) and takes into account the parameters of resolution, landing angle, squint and background type. The ATD model is designed based on false alarm analysis and estimates the measure of performance (MoP) according to available ground information. The STAR model is also based on the modelling of parameters related to the environment, target and sensor and calculates the probability of success in detecting, detecting and identifying the target in the radar image for a target with specific dimensions and physical conditions.
Proposed method: In this study, a unified method has been presented to evaluate the interpretability of polarimetric radar images in the application of target detection. In this method, the performance of the radar detector is first calculated based on the parameters of the detector in the STAR model. After that, for each of the images related to the channels and polarimetric parameters, the target detection performance is calculated by calculating the performance measure (MoP), which relates the detection probability to the false alarm rate is determined. Finally, by combining the information obtained from the MoP criterion and the STAR model, the interpretability of polarimetric radar images is calculated.
Experimental results: In this study, the L-band polarimetric radar dataset related to the Flevoland region of the Netherlands, which was obtained by the AIRSAR sensor in 2009, is used to evaluate the effectiveness of the proposed method. Based on the obtained results, the proposed method increases the probability of detecting, detecting and identifying the target by 30% compared to the STAR model.
For the development of this research, it is suggested to improve the performance of the radar sensor by using the techniques of combining radar data with optical data and auxiliary data. This case, especially in tracking targets in complex environments, can significantly improve continuous target tracking.
Type of Study: Research |
Subject: Photo&RS Received: 2023/10/26
References
1. B. Kahler, E. Blasch, and L. Goodwon, "Operating condition modeling for ATR fusion assessment," in Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2007, 2007, pp. 119-129. [DOI:10.1117/12.718803]
2. B. Kahler and E. Blasch, "Sensor management fusion using operating conditions," in 2008 IEEE National Aerospace and Electronics Conference, 2008, pp. 281-288. [DOI:10.1109/NAECON.2008.4806559]
3. B. Kahler and E. Blasch, "Impact of HRR radar processing on moving target identification performance," in 2009 12th International Conference on Information Fusion, 2009, pp. 858-865.
4. B. Kahler, J. Querns, and G. Arnold, "An ATR challenge problem using HRR data," in Algorithms for Synthetic Aperture Radar Imagery XV, 2008, pp. 217-228. [DOI:10.1117/12.778018]
5. R. Schumacher and J. Schiller, "Non-cooperative target identification of battlefield targets-classification results based on SAR images," in IEEE International Radar Conference, 2005., 2005, pp. 167-172.
6. R. C. DiPietro, R. P. Perry, and R. L. Fante, "SAR imaging and detection of moving targets," in Algorithms for Synthetic Aperture Radar Imagery V, 1998, pp. 73-84. [DOI:10.1117/12.321873]
7. D. Gutchess, J. M. Irvine, M. Young, and M. S. Snorrason, "Predicting the effectiveness of SAR imagery for target detection," in Algorithms for Synthetic Aperture Radar Imagery XVIII, 2011, pp. 359-370. [DOI:10.1117/12.882712]
8. J. Irvine and R. Driggers, "National imagery intelligence rating scale (NIIRS)," The Encyclopedia of Optical Engineering, Marcel Dekker, 2003.
9. R. Eaton, M. Snorrason, J. Irvine, and S. Vanstone, "Advancement in ATD performance prediction," in Automatic Target Recognition XVIII, 2008, pp. 22-31. [DOI:10.1117/12.775066]
10. J. M. Irvine and E. Nelson, "Image quality and performance modeling for automated target detection," in Automatic Target Recognition XIX, 2009, pp. 193-201. [DOI:10.1117/12.818593]
11. J. M. Irvine, B. A. Eckstein, R. A. Hummel, R. J. Peters, and R. Ritzel, "Evaluation of the tactical utility of compressed imagery," Optical Engineering, vol. 41, pp. 1262-1272, 2002. [DOI:10.1117/1.1475740]
12. J. M. Irvine, "Assessing target search performance: The free-response operator characteristic model," Optical Engineering, vol. 43, pp. 2926-2934, 2004. [DOI:10.1117/1.1811086]
13. S. K. Ralph, R. Eaton, M. Snorrason, J. Irvine, and S. Vanstone, "Evaluation testbed for ATD performance prediction (ETAPP)," in Automatic Target Recognition XVII, 2007, pp. 319-329. [DOI:10.1117/12.719339]
14. R. G. Driggers, J. A. Ratches, J. C. Leachtenauer, and R. W. Kistner, "Synthetic aperture radar target acquisition model based on a National Imagery Interpretability Rating Scale to probability of discrimination conversion," Optical Engineering, vol. 42, pp. 2104-2112, 2003. [DOI:10.1117/1.1580831]
15. J. C. Leachtenauer, W. Malila, J. Irvine, L. Colburn, and N. Salvaggio, "General image-quality equation: GIQE," Applied optics, vol. 36, pp. 8322-8328, 1997. [DOI:10.1364/AO.36.008322]
16. J. C. Leachtenauer, "National imagery interpretability rating scales: overview and product description," in Proceedings of the American Society of Photogrammetry and Remote Sensing Annual Meetings, 1996, pp. 262-272.
17. A. R. Nolan, G. S. Goley, and M. Bakich, "Performance estimation of SAR using NIIRS techniques," in Algorithms for Synthetic Aperture Radar Imagery XIX, 2012, pp. 248-258. [DOI:10.1117/12.920849]
18. B. Kahler, "Simultaneous tracking and recognition performance model," in Algorithms for Synthetic Aperture Radar Imagery XIX, 2012, pp. 215-227. [DOI:10.1117/12.919901]
19. B. Kahler, "Multisource information fusion for enhanced simultaneous tracking and recognition," in Signal Processing, Sensor Fusion, and Target Recognition XXII, 2013, pp. 265-282. [DOI:10.1117/12.2016616]
20. W. Wei, L. Chunyan, S. Tao, Y. Jianfeng, Y. Xiaqiong, and W. Yukuan, "SAR image quality assessment of satellite TH-2-01," Acta Geodaetica et Cartographica Sinica, 2022, vol. 51, p. 2508.
21. F. Lu, J. Huang, and J. Wang, "Performance prediction of SAR noise jamming using NIIRS," in International Conference on Optics and Machine Vision (ICOMV 2022), 2022, pp. 98-102. [DOI:10.1117/12.2634425]
22. W. Schwartzkopf, J. Brown, G. Farquharson, C. Stringham, M. Duersch, and J. Heemskerk, "Radar Generalized Image Quality Equation Applied to Capella Open Dataset," in 2022 IEEE Radar Conference (RadarConf22), 2022, pp. 1-5. [DOI:10.1109/RadarConf2248738.2022.9764201]
23. K. Gromada, B. Siemiątkowska, W. Stecz, K. Płochocki, and K. Woźniak, "Real-time object detection and classification by UAV equipped with SAR," Sensors, vol. 22, p. 2068, 2022. [DOI:10.3390/s22052068]
24. S. Solaiman, E. Alsuwat, and R. Alharthi, "Simultaneous Tracking and Recognizing Drone Targets with Millimeter-Wave Radar and Convolutional Neural Network," 2023. [DOI:10.20944/preprints202306.0621.v1]
25. L. M. Novak, M. C. Burl, and W. Irving, "Optimal polarimetric processing for enhanced target detection," IEEE Transactions on Aerospace and Electronic Systems, vol. 29, pp. 234-244, 1993. [DOI:10.1109/7.249129]
26. L. M. Novak, G. J. Owirka, and C. M. Netishen, "Performance of a high-resolution polarimetric SAR automatic target recognition system," Lincoln Laboratory Journal, vol. 6, 1993.
27. J. Marcum, "A statistical theory of target detection by pulsed radar," IRE Transactions on Information Theory, vol. 6, pp. 59-267, 1960. [DOI:10.1109/TIT.1960.1057560]
28. W. J. Alberhseim, "A closed-form approximation to Robertson's detection characteristics," Proceedings of the IEEE, vol. 69, pp. 839-839, 1981. [DOI:10.1109/PROC.1981.12082]
29. D. A. Shnidman, "Approximation to probability of detection for log-normal target fluctuation," IEEE Transactions on Aerospace and Electronic Systems, pp. 161-163, 1979. [DOI:10.1109/TAES.1979.308809]
30. M. GHANBARY and S. KHAZAEI, "ESTIMATING THE ALPHA-STABLE DISTRIBUTION PARAMETERS FOR SHIP DETECTION IN POLARIMETRIC SAR IMAGES," 2015.