:: دوره 8، شماره 4 - ( 12-1399 ) ::
جلد 8 شماره 4 صفحات 68-45 برگشت به فهرست نسخه ها
پیشنهاد یک شبکه عصبی کانوولوشنی چندمقیاسه برای آشکارسازی خودکار ابرها و سایه ابرها در تصاویر ماهواره گائوفِن-1
مهدی خوش برش ماسوله ، رضا شاه حسینی*
دانشکده مهندسی نقشه‌برداری و اطلاعات مکانی، پردیس دانشکده‌های فنی، دانشگاه تهران
چکیده:   (2647 مشاهده)
یک گام مهم در پیش‌پردازش تصاویر ماهواره‌ای با قدرت تفکیک مکانی بالا، بازسازی اطلاعات آلوده به پوشش ابرها و سایه ابرها است. اولین گام در فرآیند خودکار بازسازی اطلاعات آلوده به ابرها و سایه ابرها، مرحله آشکارسازی خودکار ابرها و سایه ابرها است. این مرحله به دلیل عملکرد نسبتاً نامناسب روش‌های موجود در صحنه‌های پیچیده در تصاویر با قدرت تفکیک مکانی بالا، یک چالش قابل‌توجه است. در سال‌های اخیر، دقت فرآیند آشکارسازی ابرها و سایه ابرها با به‌کارگیری شبکه‌های عصبی کانوولوشنی عمیق بهبود یافته است. مسأله افزایش تعمیم‌پذیری برای آشکارسازی ابرها و سایه ابرها یکی از مشکل‌های شبکه‌های عصبی کانوولوشنی عمیق است. در این تحقیق، راه‌حلی برای مشکل تعمیم‌پذیری آشکارسازی ابرها و سایه ابرها در تصاویر ماهواره گائوفِن-1 ارائه شده است. در این راستا، یک معماری یادگیری عمیق چندمقیاسه (MultiCloud-Net) مبتنی بر فیلتر‌هایی با ابعاد مختلف برای آشکارسازی دقیق ابرها و سایه ابرها در تصاویر تک زمانه ماهواره گائوفِن-1 بر اساس طراحی بلوک‌های باقی‌مانده جدید مبتنی بر حذف تصادفی عُمق، پیشنهاد شده است. در معماری پیشنهادی، فرآیند آشکارسازی ابرها و سایه ابرها بر اساس تابع آنتروپی متقاطع وزن‌دار برای حل مسأله عدم تعادل پیکسل‌های هدف، برای تولید نقشه نهایی صورت می‌گیرد. روش پیشنهادی با استفاده از 12 تصویر ماهواره گائوفِن-1 با توزیع جهانی و با استفاده از  سرویس رایانش ابری گوگل کولَب پیاده‌سازی و اعتبارسنجی شده است. نتایج با استفاده از مجموعه تصاویر ماهواره گائوفِن-1، با کسب میانگین نمره F1 و ضریب شباهت ژاکارد برابر 97 و 96 برای کلاس ابر و مقادیر 5/95 و 5/94 برای کلاس سایه ابر و با ضریب کاپای 98/0 نشان‌دهنده دقت مناسب‌تر در آشکارسازی خودکار جزئیات حاشیه‌ای ابرها و سایه ابرها و دستیابی به هزینه محاسباتی کمتر در مقایسه با یک روش پیشرفته یادگیری عمیق و یک روش پیشرفته آماری است.
واژه‌های کلیدی: گائوفِن-1، ابرها، سایه ابرها، یادگیری عمیق، کانوولوشن چندمقیاسه.
متن کامل [PDF 2561 kb]   (857 دریافت)    
نوع مطالعه: پژوهشي | موضوع مقاله: سنجش از دور
دریافت: 1398/10/11 | پذیرش: 1399/11/7 | انتشار: 1400/1/31
فهرست منابع
1. [1] M. R. Mobasheri and Y. Rezaei, "Detection of fog and low stratus using MSG-1 images," J. College. Eng., vol. 41, no. 2, pp. 1107-1119, Mar. 2007.
2. [2] M. R. Mobasheri, N. Gholami and M. Farajzadeh ASL, "Cloud detection from multi-temporal satellite images," J. Spatial Plan., vol. 15, no. 2, pp. 81-99, Jan. 2011.
3. [3] S. Foga, P. L. Scaramuzza, S. Guo, Z. Zhu, R. D. Dilley, T. Beckmann, G. L. Schmidt, J. L. Dwyer, M. Joseph Hughes, and B. Laue, "Cloud detection algorithm comparison and validation for operational Landsat data products," Remote Sens. Environ., vol. 194, pp. 379-390, Jun. 2017, doi: 10.1016/j.rse.2017.03.026.
4. [4] J. Yang, J. Guo, H. Yue, Z. Liu, H. Hu, and K. Li, "CDnet: CNN-based cloud detection for remote sensing imagery," IEEE Trans. Geosci. Remote Sens., vol. 57, no. 8, pp. 6195-6211, Aug. 2019, doi: 10.1109/TGRS.2019.2904868.
5. [5] S. Baseri Nam, A. Esmaeily, and M. Dehghani, "Propose an algorithm to improve the accuracy of snow covered mapping using MODIS images," Eng. J. Geospatial Inf. Technol., vol. 3, no. 1, pp. 61-75, Jun. 2015, doi: 10.29252/jgit.3.1.61.
6. [6] L. L. Stowe, E. P. McClain, R. Carey, P. Pellegrino, G. G. Gutman, P. Davis, C. Long, and S. Hart, "Global distribution of cloud cover derived from NOAA/AVHRR operational satellite data," Adv. Space Res., vol. 11, no. 3, pp. 51-54, Jan. 1991, doi: 10.1016/0273-1177(91)90402-6.
7. [7] G. Gesell, "An algorithm for snow and ice detection using AVHRR data An extension to the APOLLO software package," Int. J. Remote Sens., vol. 10, no. 4-5, pp. 897-905, Apr. 1989, doi: 10.1080/01431168908903929.
8. [8] W. B. Rossow and L. C. Garder, "Cloud detection using satellite measurements of infrared and visible radiances for ISCCP," J. Clim., vol. 6, no. 12, pp. 2341-2369, Dec. 1993. https://doi.org/10.1175/1520-0442(1993)006<2341:CDUSMO>2.0.CO;2 [DOI:10.1175/1520-0442(1993)0062.0.CO;2]
9. [9] H. Guo, W. Fu, and G. Liu, "Development of Earth observation satellites," in Scientific Satellite and Moon-Based Earth Observation for Global Change, H. Guo, W. Fu, and G. Liu, Eds. Singapore: Springer Singapore, 2019, pp. 31-49.
10. [10] K. E. Sawaya, L. G. Olmanson, N. J. Heinert, P. L. Brezonik, and M. E. Bauer, "Extending satellite remote sensing to local scales: land and water resource monitoring using high-resolution imagery," Remote Sens. Environ., vol. 88, no. 1, pp. 144-156, Nov. 2003, doi: 10.1016/j.rse.2003.04.006.
11. [11] Y. Chen, R. Fan, M. Bilal, X. Yang, J. Wang, and W. Li, "Multilevel cloud detection for high-resolution remote sensing imagery using multiple convolutional neural networks," ISPRS Int. J. Geo-Inf., vol. 7, no. 5, p. 181, May 2018, doi: 10.3390/ijgi7050181.
12. [12] A. Yang, B. Zhong, W. Lv, S. Wu, and Q. Liu, "Cross-calibration of GF-1/WFV over a desert site using Landsat-8/OLI imagery and ZY-3/TLC data," Remote Sens., vol. 7, no. 8, pp. 10763-10787, Aug. 2015, doi: 10.3390/rs70810763.
13. [13] C. Huang, N. Thomas, S. N. Goward, J. G. Masek, Z. Zhu, J. R. G. Townshend, and J. E. Vogelmann, "Automated masking of cloud and cloud shadow for forest change analysis using Landsat images," Int. J. Remote Sens., vol. 31, no. 20, pp. 5449-5464, Oct. 2010, doi: 10.1080/01431160903369642.
14. [14] T. Bai, D. Li, K. Sun, Y. Chen, and W. Li, "Cloud detection for high-resolution satellite imagery using machine learning and multi-feature fusion," Remote Sens., vol. 8, no. 9, p. 715, Aug. 2016, doi: 10.3390/rs8090715.
15. [15] A. Hollstein, K. Segl, L. Guanter, M. Brell, and M. Enesco, "Ready-to-use methods for the detection of clouds, cirrus, snow, shadow, water and clear sky pixels in Sentinel-2 MSI images," Remote Sens., vol. 8, no. 8, p. 666, Aug. 2016, doi: 10.3390/rs8080666.
16. [16] Z. Li, H. Shen, H. Li, G. Xia, P. Gamba, and L. Zhang, "Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery," Remote Sens. Environ., vol. 191, pp. 342-358, Mar. 2017, doi: 10.1016/j.rse.2017.01.026.
17. [17] C. Latry, C. Panem, and P. Dejean, "Cloud detection with SVM technique," in 2007 IEEE International Geoscience and Remote Sensing Symposium, 2007, pp. 448-451, doi: 10.1109/IGARSS.2007.4422827.
18. [18] M. Wieland, Y. Li, and S. Martinis, "Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network," Remote Sens. Environ., vol. 230, p. 111203, Sep. 2019, doi: 10.1016/j.rse.2019.05.022.
19. [19] L. Sun, X. Mi, J. Wei, J. Wang, X. Tian, H. Yu, and P. Gan, "A cloud detection algorithm-generating method for remote sensing data at visible to short-wave infrared wavelengths," ISPRS J. Photogramm. Remote Sens., vol. 124, pp. 70-88, Feb. 2017, doi: 10.1016/j.isprsjprs.2016.12.005.
20. [20] R. A. Frey, S. A. Ackerman, Y. Liu, K. I. Strabala, H. Zhang, J. R. Key, and X. Wang, "Cloud detection with MODIS. Part I: improvements in the MODIS cloud mask for collection 5," J. Atmospheric Ocean. Technol., vol. 25, no. 7, pp. 1057-1072, Jul. 2008, doi: 10.1175/2008JTECHA1052.1.
21. [21] A. V. D. Vittorio and W. J. Emery, "An automated, dynamic threshold cloud-masking algorithm for daytime AVHRR images over land," IEEE Trans. Geosci. Remote Sens., vol. 40, no. 8, pp. 1682-1694, Aug. 2002, doi: 10.1109/TGRS.2002.802455.
22. [22] K. V. Khlopenkov and A. P. Trishchenko, "SPARC: New cloud, snow, and cloud shadow detection scheme for historical 1-km AVHHR data over Canada," J. Atmospheric Ocean. Technol., vol. 24, no. 3, pp. 322-343, Mar. 2007, doi: 10.1175/JTECH1987.1.
23. [23] Q. Li, W. Lu, J. Yang, and J. Z. Wang, "Thin cloud detection of all-sky images using Markov random fields," IEEE Geosci. Remote Sens. Lett., vol. 9, no. 3, pp. 417-421, May 2012, doi: 10.1109/LGRS.2011.2170953.
24. [24] Z. Shao, J. Hou, M. Jiang, and X. Zhou, "Cloud detection in Landsat imagery for Antarctic region using multispectral thresholds," in Remote Sensing of the Atmosphere, Clouds, and Precipitation V, 2014, vol. 9259, p. 92590P, doi: 10.1117/12.2070635.
25. [25] R. R. Irish, "Landsat 7 automatic cloud cover assessment," in Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VI, 2000, vol. 4049, pp. 348-355, doi: 10.1117/12.410358.
26. [26] D. Frantz, E. Haß, A. Uhl, J. Stoffels, and J. Hill, "Improvement of the Fmask algorithm for Sentinel-2 images: Separating clouds from bright surfaces based on parallax effects," Remote Sens. Environ., vol. 215, pp. 471-481, Sep. 2018, doi: 10.1016/j.rse.2018.04.046.
27. [27] O. Hagolle, M. Huc, D. V. Pascual, and G. Dedieu, "A multi-temporal method for cloud detection, applied to FORMOSAT-2, VENµS, LANDSAT and SENTINEL-2 images," Remote Sens. Environ., vol. 114, no. 8, pp. 1747-1755, Aug. 2010, doi: 10.1016/j.rse.2010.03.002.
28. [28] L. Baetens, C. Desjardins, and O. Hagolle, "Validation of Copernicus Sentinel-2 cloud masks obtained from MAJA, Sen2Cor, and FMask Processors Using Reference Cloud Masks Generated with a Supervised Active Learning Procedure," Remote Sens., vol. 11, no. 4, p. 433, Jan. 2019, doi: 10.3390/rs11040433.
29. [29] M. Hughes and D. Hayes, "Automated detection of cloud and cloud shadow in single-date Landsat imagery using neural networks and spatial post-processing," Remote Sens., vol. 6, no. 6, pp. 4907-4926, May 2014, doi: 10.3390/rs6064907.
30. [30] X. Huang and L. Zhang, "An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery," IEEE Trans. Geosci. Remote Sens., vol. 51, no. 1, pp. 257-272, Jan. 2013, doi: 10.1109/TGRS.2012.2202912.
31. [31] K. Tan, Y. Zhang, and X. Tong, "Cloud extraction from Chinese high resolution satellite imagery by probabilistic latent semantic analysis and object-based machine learning," Remote Sens., vol. 8, no. 11, p. 963, Nov. 2016, doi: 10.3390/rs8110963.
32. [32] J. E. Ball, D. T. Anderson, and C. S. Chan, "A comprehensive survey of deep learning in remote sensing: Theories, tools and challenges for the community," J. Appl. Remote Sens., vol. 11, no. 04, p. 1, Sep. 2017, doi: 10.1117/1.JRS.11.042609.
33. [33] M. Khoshboresh Masouleh and R. Shah-Hosseini, "Development and evaluation of a deep learning model for real-time ground vehicle semantic segmentation from UAV-based thermal infrared imagery," ISPRS J. Photogramm. Remote Sens., vol. 155, pp. 172-186, Sep. 2019, doi: 10.1016/j.isprsjprs.2019.07.009.
34. [34] X. X. Zhu, D. Tuia, L. Mou, G.-S. Xia, L. Zhang, F. Xu, and F. Fraundorfer, "Deep learning in remote sensing: a review," IEEE Geosci. Remote Sens. Mag., vol. 5, no. 4, pp. 8-36, Dec. 2017, doi: 10.1109/MGRS.2017.2762307.
35. [35] D. Chai, S. Newsam, H. K. Zhang, Y. Qiu, and J. Huang, "Cloud and cloud shadow detection in Landsat imagery based on deep convolutional neural networks," Remote Sens. Environ., vol. 225, pp. 307-316, May 2019, doi: 10.1016/j.rse.2019.03.007.
36. [36] Z. Li, H. Shen, Q. Cheng, Y. Liu, S. You, and Z. He, "Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors," ISPRS J. Photogramm. Remote Sens., vol. 150, pp. 197-212, Apr. 2019, doi: 10.1016/j.isprsjprs.2019.02.017.
37. [37] C.C. Liu, Y.C. Zhang, P.-Y. Chen, C.C. Lai, Y.H. Chen, J.H. Cheng, and M.H. Ko, "Clouds classification from Sentinel-2 imagery with deep residual learning and semantic image segmentation," Remote Sens., vol. 11, no. 2, p. 119, Jan. 2019, doi: 10.3390/rs11020119.
38. [38] A. Francis, P. Sidiropoulos, and J.-P. Muller, "CloudFCN: Accurate and robust cloud detection for satellite imagery with deep learning," Remote Sens., vol. 11, no. 19, p. 2312, Jan. 2019, doi: 10.3390/rs11192312.
39. [39] L. Wang, Y. Chen, L. Tang, R. Fan, and Y. Yao, "Object-based convolutional neural networks for cloud and snow detection in high-resolution multispectral imagers," Water, vol. 10, no. 11, p. 1666, Nov. 2018, doi: 10.3390/w10111666.
40. [40] J. Guo and S. Gould, "Depth Dropout: Efficient training of residual convolutional neural networks," in 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2016, pp. 1-7, doi: 10.1109/DICTA.2016.7797032.
41. [41] M. Khoshboresh Masouleh, R. Shah-Hosseini, and A. Safari, "Integration of deep learning algorithms and bilateral filters with the purpose of building extraction from mono optical aerial imagery," Eng. J. Geospatial Inf. Technol., vol. 7, no. 2, pp. 241-263, Sep. 2019.
42. [42] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," 3rd Int. Conf. Learn. Represent. ICLR, 2014.
43. [43] K. He, X. Zhang, S. Ren, and J. Sun, "Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification," in 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1026-1034, doi: 10.1109/ICCV.2015.123.
44. [44] "Loss Functions In Deep Learning," yeephycho. [Online]. Available: http://yeephycho.github.io/2017/09/16/Loss-Functions-In-Deep-Learning/index.html. [Accessed: 24-Jul-2019].
45. [45] M. Khoshboresh Masouleh and R. Shah-Hosseini, "A hybrid deep learning-based model for automatic car extraction from high-resolution airborne imagery," Appl. Geomat., Aug. 2019, doi: 10.1007/s12518-019-00285-4.
46. [46] R. R. Irish, J. L. Barker, S. N. Goward, and T. Arvidson, "Characterization of the Landsat-7 ETM+ Automated Cloud-Cover Assessment (ACCA) Algorithm," Photogramm. Eng. Remote Sens., vol. 72, no. 10, pp. 1179-1188, Oct. 2006, doi: 10.14358/PERS.72.10.1179.
47. [47] "Cloud Fraction." [Online]. Available: https://earthobservatory.nasa.gov/global-maps/MODAL2_M_CLD_FR. [Accessed: 30-Oct-2019].
48. [48] M. Khoshboresh-Masouleh (2019). "Deploying superpixel segmentation and deep learning to improve the accuracy of the building extraction from remote sensing data", University of Tehran.
49. [49] H. A. Amirkolaee and H. Arefi, "Height estimation from single aerial images using a deep convolutional encoder-decoder network," ISPRS J. Photogramm. Remote Sens., vol. 149, pp. 50-66, Mar. 2019.



XML   English Abstract   Print



بازنشر اطلاعات
Creative Commons License این مقاله تحت شرایط Creative Commons Attribution-NonCommercial 4.0 International License قابل بازنشر است.
دوره 8، شماره 4 - ( 12-1399 ) برگشت به فهرست نسخه ها