本研究將電磁訊號模擬結果圖像化應用於無人機目標物辨識，本研究會先針對無人機目標物的雷達截面積(Radar Cross Section,RCS)進行分析與討論，接著透過資料視覺化的方式將無人機目標物RCS數據轉為圖像形式，期望能藉由圖像辨識的方法快速地辨識出無人機目標物。
本研究的第一部分展示了在頻率26 GHz至40 GHz 範圍內的毫米波，使用電磁模擬軟體CST MICROWAVE STUDIO(CST MWS)計算得到無人機RCS的結果，同時對於無人機的尺寸、材質與主要的無人機零件進行探討，這有助於讓我們更好地瞭解到哪些因素會對無人機RCS造成影響。
本研究的第二部分將模擬得到的無人機RCS數據可視化，轉換成二維熱圖圖像，透過圖像的方式，解決RCS數據複雜且不易於分析的問題，接著分別對二維熱圖圖像進行無人機目標物辨識，本研究是使用差值哈希演算法(Difference Hash Algorithm)依照圖像的相似程度進行無人機識別，同時比較有加入圖像處理技術與沒有加入圖像處理技術的差別，圖像處理技術包含了圖像特徵提取 SIFT (Scale-Invariant Feature Transform)與圖像增強(Image Enhancement)，加入圖像特徵提取SIFT對於辨識結果的影響並不大，而加入圖像增強能有效改善辨識結果，另外也使用直方圖重合度的方法作為參考比對結果。

The Radar Cross Section (RCS) indicates the scattering intensity of the target after being exposed to radar electromagnetic waves. This study will first analyze and discuss the RCS of drones, and then convert the complex RCS data into image form to perform Target Recognition of Drones according to the similarity of the images.
CST MICROWAVE STUDIO (CST MWS) is a comprehensive electromagnetic simulation software that can calculate the RCS data of drones. We visualized the simulated RCS data of the drone and converted into a two-dimensional heat map image using the method of the Difference Hash Algorithm.We also compare the difference between the Difference Hash Algorithm with image processing technology and without image processing technology, which includes Scale-Invariant Feature Transform (SIFT) and image enhancement. Adding SIFT to the image feature extraction does not have much effect on the recognition results while adding image enhancement can effectively improve the recognition results. The method of the Histogram Coincidence is also used as a reference to compare the results.

[1] M. Ezuma, O. Ozdemir, C. K. Anjinappa, W. A. Gulzar and I. Guvenc, “Micro-UAV detection with a low-grazing angle millimeter wave radar,” 2019 IEEE Radio and Wireless Symposium (RWS), Orlando, FL, USA, January 20-23, 2019.
[2] T. S. Rappaport, S. Sun, R. Mayzus, H. Zhao, Y. Azar, K. Wang, G. N. Wong, J. K. Schulz, M. Samimi and F. Gutierrez, “Millimeter wave mobile communications for 5G cellular: it will work!” IEEE Access, vol. 1, pp. 335-349, May 10, 2013.
[3] W. Chen, F. Guo, Fei and Y. Wang, “A survey of traffic data visualization,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 6, pp. 2710-2984, June 10, 2015.
[4] L. Wilkinson and M. Friendly, “The history of the cluster heat map,” American Statistical Association, vol. 63, no. 2, pp. 179-184, May 2009.
[5] Z. G. Li, L. G. Wang and J. Liu, “Research on image recognition algorithm of valve switch state based on cosine similarity,” 2020 International Conference on Virtual Reality and Intelligent Systems (ICVRIS), Zhangjiajie, China, July 18-19, 2021.
[6] L. C. Yann, Y. Bengio and G. Hinton, “Deep learning,” Nature 521, May 27, 2015.
[7] T. E. Tice, “An overview of radar cross section measurement techniques,” IEEE Transactions on Instrumentation and Measurement, vol. 39, no. 1, pp. 205-207, February 1990.
[8] I. Nicolaescu and G. Iubu, “Simple and collected targets radar cross section,” 2007 International Conference on Electromagnetics in Advanced Applications, Turin, Italy, September 17-21, 2007.
[9] A. Motevasselian and B. L. G. Jonsson, “Radar cross section reduction of aircraft wing front end,” 2009 International Conference on Electromagnetics in Advanced Applications, Turin, Italy, September 14-18, 2009.
[10] A. Schroder, M. Renker, U. Aulenbacher, A. Murk, U. Boniger, R. Oechslin and P. Wellig, “Numerical and experimental radar cross section analysis of the quadrocopter DJI Phantom 2,” 2015 IEEE Radar Conference, Johannesburg, South Africa, October 27-30, 2015.
[11] C. Durlu and H. T. Hayvaci, “Monostatic rcs analysis for armed and unarmed UAV,” 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting, San Diego, CA , USA, July 09-14, 2017.
[12] M. Y. Wu and L. Chen, “Image recognition based on deep learning,” 2015 Chinese Automation Congress (CAC), Wuhan, China, November 27-29, 2015.
[13] J. X. Li, C. Wang, S. Wang, H. Zhang and B. Zhang, “Classification of very high resolution SAR image based on convolutional neural network,” 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP), Shanghai, China, May 18-21, 2017.
[14] K. Yogheedha, A. S. A. Nasir, H. Jaafar and S. M. Mamduh, “Automatic vehicle license plate recognition system based on image processing and template matching approach,” 2018 International Conference on Computational Approach in Smart Systems Design and Applications (ICASSDA), Kuching, Malaysia, August 15-17, 2018.
[15] T. Arciuolo, M. Wasimuddin, S. Singh and K. Elleithy, “Iris print biometric identification using perceptual image hashing algorithms,” 2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York, USA, November 08-10, 2018.
[16] P. Bruno and F. Calimeri, “Using heatmaps for deep learning based disease classification,” 2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Siena, Italy, July 09-11, 2019.
[17] Z. Z. Chen and M. M. Ney, “Method of moments: a general framework for frequency- and time-domain numerical methods,” 2007 Workshop on Computational Electromagnetics in Time-Domain, Perugia, Italy, October 15-17, 2007.
[18] J. Gu, Z. C. Liang and X. B. Wang, “Fast computation method for electromagnetic scattering characteristics of unmanned air vehicle,” IET International Radar Conference 2015, Hangzhou, China, October 14-16, 2015.
[19] T. K. Sarkar, W. W. Lee and S. M. Rao, “Analysis of transient scattering from composite arbitrarily shaped complex structures,” IEEE Transactions on Antennas and Propagation, vol. 48, no. 10, pp. 1625-1634, October 2000.
[20] J. Y. Li and L. W. Li, “Electromagnetic scattering by a mixture of conducting and dielectric objects: analysis using method of moments,” IEEE Transactions on Vehicular Technology, vol. 53, no. 2, pp. 514-520, March 22, 2004.
[21] K. Umashankar, A. Taflove and S. Rao, “Electromagnetic scattering by arbitrary shaped three-dimensional homogeneous lossy dielectric objects,” IEEE Transactions on Antennas and Propagation, vol. 34, no. 6, pp. 758-766, June 1986.
[22] V. Semkin, J. Haarla, T. Pairon, C. Slezak, S. Rangan, V. Viikari and C. Oestges, “Analyzing radar cross section signatures of diverse drone models at mmwave frequencies,” Millimeter-wave and Terahertz Propagation, Channel Modeling and Applications, vol. 8, pp. 48958-48969, March 11, 2020.
[23] A. Papoulis, “Normal distributions,” Proceedings of the IEEE, vol. 51, no. 7, pp. 1049-1049, July 1963
[24] E. S. Yang, “A probability density analyzer,” IEEE Transactions on Instrumentation and Measurement, vol. 18, no. 1, pp. 15-18, March 1969.
[25] Difference Hash Algorithm,
https://www.hackerfactor.com/blog/index.php?/archives/529-Kind-of-Like-That.html
(Retrieved on August 5, 2022).
[26] D. G. Lowe, “Object recognition from local scale-invariant features,” Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, September 20-27, 1999.
[27] C. G. Harris and M. Stephens, “A combined corner and edge detector,” Proceedings of the Alvey Vision Conference 1988, Manchester, UK, 1988.