آشکارسازی نواحی سایه در تصاویر هوایی شهری با استفاده از نقشه ‌نسبت بهینه

شناسنامه علمی شماره

نویسندگان

1 دانشکده فنی مهندسی - دانشگاه دامغان

2 دانشکده فنی مهندسی - دانشگاه شاهد

چکیده

در پردازش تصویر الگوریتم‌های زیادی به خاطر وجود سایه دچار اختلال می‌شوند. درصورتی‌که محل سایه‌ها مشخص باشد می‌توان از بروز خطا در این الگوریتم‌ها جلوگیری کرد. در این مقاله روشی بهینه برای آشکارسازی سایه در تصاویر هوایی ارائه شده است. در این پژوهش دو فضای رنگی RGB و YCbCr با هم ترکیب شده و نقشه نسبتی مناسب‌تر از نقشه نسبت‌های مشابه به وجود آمده است. علاوه بر این در اقدامی جدید، تأثیر رنگ آبی آسمان در هنگام ایجاد سایه در نقشه نسبت ارائه‌شده، در نظر گرفته شده است که این امر خود باعث افزایش میزان تفکیک‌پذیری نقشه نسبت شده است. در روش پیشنهادی از الگوریتم آستانه گذاری آتسو جهت تفکیک به دو ناحیه سایه و غیر سایه استفاده شده است. استفاده از این روش منجر به آستانه گذاری کلی شده و نیازی به بررسی محلی و ناحیه به ناحیه تصویر وجود ندارد. این امر باعث کاهش چشمگیر بار محاسباتی و امکان استفاده در کاربردهای بلادرنگ شده است. نتایج تجربی نشان می‌دهد روش ارائه‌شده نسبت به روش‌های مشابه کارایی بالاتری در آشکارسازی سایه و هزینه محاسباتی دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Shadow Detection in Arial Image Using Optimized Ratio Map

نویسندگان [English]

  • J. Abbasi Aghamaleki 1
  • S. A. Miresmaili 2
1 Faculty of Engineering, University of Damghan, Damghan, Iran
2 Faculty of Engineering, Shahed University, Tehran, Iran
چکیده [English]

In image processing many algorithms get disturbed because of shadow. These problems can be avoided if the location of shadows is clear. This article presents a new optimized algorithm for extracting shadows from a single color aerial image. Most of similar works do this by using a suite color space. In this work two RGB and YCbCr color spaces are combined and a powerful ratio map has been created. Furthermore, in a new method, effect of sky blue color is determined that improves the ratio map. Candidate shadow and non-shadow regions are separated by applying Otsu’s thresholding method. Because of ratio map performance it is not necessary to analyze region by region and leads to decrease computation cost. So it can be used in online application. The experimental results demonstrate the advantage of the proposed algorithm.

کلیدواژه‌ها [English]

  • Shadow Detection
  • Color aerial image
  • Combined ratio map
  • RGB color space
  • YCbCr color space
  • Color attenuation relationship
[1]      تقی زاده فانیذ, علی؛ علیرضا عندلیب و سیامک حقی پور، « شخیص عوارض مصنوعی (انسان - ساز) در تصاویر هوایی با استفاده از ویژگی‌های فراکتال و پردازش ریخت شناسی»، مجله مهندسی برق دانشگاه تبریز، دوره 42، شماره 2، صفحات 13-24، 1391. 
[2]      Q. Wang and L. Yan, “Anisotropic Scattering Shadow Compensation Method for Remote Sensing Image with Consideration of Terrain,” International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, vol. 41, 2016.
[3]      X. Cao and H. Foroosh, “Camera calibration and light source orientation from solar shadows,” Computer Vision and Image Understanding, vol. 105, pp. 60-72, 2007.
[4]      H. Kawasaki and R. Furukawa, “Shape reconstruction and camera self-calibration using cast shadows and scene geometries,” International Journal of Computer Vision, vol. 83, pp. 135-148, 2009.
[5]      G. Liasis and S. Stavrou, “Satellite images analysis for shadow detection and building height estimation,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 119, pp. 437-450, 2016.
[6]      P. Raju, H. Chaudhary, and A. Jha, “Shadow analysis technique for extraction of building height using high resolution satellite single image and accuracy assessment,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 40, p. 1185, 2014.
[7]      D. Chaudhuri, N. Kushwaha, A. Samal, and R. Agarwal, “Automatic building detection from high-resolution satellite images based on morphology and internal gray variance,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, pp. 1767-1779, 2016.
[8]      K.-L. Chung, Y.-R. Lin, and Y.-H. Huang, “Efficient shadow detection of color aerial images based on successive thresholding scheme,” IEEE Transactions on Geoscience and Remote sensing, vol. 47, pp. 671-682, 2009.
[9]      H. Song, B. Huang, and K. Zhang, “Shadow detection and reconstruction in high-resolution satellite images via morphological filtering and example-based learning,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, pp. 2545-2554, 2014.
[10]      Y.-F. Su and H. H. Chen, “A three-stage approach to shadow field estimation from partial boundary information,” IEEE Transactions on Image Processing, vol. 19, pp. 2749-2760, 2010.
[11]      K. Zhou and B. Gorte, “Shadow Detection from VHR Aerial Images in Urban Area by Using 3D City Models and a Decision Fusion Approach,” International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, vol. 42, 2017.
[12]      A. Makarau, R. Richter, R. Muller, and P. Reinartz, “Adaptive shadow detection using a blackbody radiator model,” IEEE Transactions on Geoscience and Remote Sensing, vol. 49, pp. 2049-2059, 2011.
[13]      J. Tian, J. Sun, and Y. Tang, “Tricolor attenuation model for shadow detection,” IEEE Transactions on image processing, vol. 18, pp. 2355-236, 2009.
[14]      G. Finlayson, C. Fredembach, and M. S. Drew, “Detecting illumination in images,” IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1-8, 2007.
[15]      G. D. Finlayson, M. S. Drew, and C. Lu, “Intrinsic images by entropy minimization,” in European conference on computer vision, pp. 582-595, 2004.
[16]      G. D. Finlayson, S. D. Hordley, and M. S. Drew, “Removing shadows from images,” in European conference on computer vision, pp. 823-836, 2002.
[17]      G. D. Finlayson, S. D. Hordley, C. Lu, and M. S. Drew, “On the removal of shadows from images,” IEEE transactions on pattern analysis and machine intelligence, vol. 28, pp. 59-68, 2006.
[18]      W. Shi and J. Li, “Shadow detection in color aerial images based on HSI space and color attenuation relationship,” EURASIP Journal on Advances in Signal Processing, vol. 2012, p. 141, 2012.
[19]      R. Guo, Q. Dai, and D. Hoiem, “Paired regions for shadow detection and removal,” IEEE transactions on pattern analysis and machine intelligence, vol. 35, pp. 2956-2967, 2013.
[20]      N. Tatar, M. Saadatseresht, H. Arefi, and A. Hadavand, “A robust object-based shadow detection method for cloud-free high resolution satellite images over urban areas and water bodies,” Advances in Space Research, vol. 6, pp. 2787-2800, 2018.
[21]      سلیمه بامری، سعید سریزدی و حسین نظام آبادی پور، « فیلترهای چند جمله‌ای مدوله شده با دوره محدود و کاربرد آن‌ها در طبقه بندی تصویر »، مجله مهندسی برق دانشگاه تبریز، دوره 40، شماره 1، صفحات 56-45، 1389.
[22]      J. Zhu, K. G. Samuel, S. Z. Masood, and M. F. Tappen, “Learning to recognize shadows in monochromatic natural images,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 223-230, 2010
[23]      H.-Y. Yu, J.-G. Sun, L.-N. Liu, Y.-H. Wang, and Y.-D. Wang, “MSER based shadow detection in high resolution remote sensing image,” in International Conference on Machine Learning and Cybernetics (ICMLC), 2010, pp. 780-783, 2010.
[24]      C. Xing, Y. Li, and K. Zhang, “Shadow detecting using PSO and Kolmogorov test,” in Sixth International Conference on Natural Computation (ICNC), pp. 572-576, 2010.
[25]      V. J. Tsai, “A comparative study on shadow compensation of color aerial images in invariant color models,” IEEE transactions on geoscience and remote sensing, vol. 44, pp. 1661-1671, 2006.
[26]      S. Murali and V. Govindan, “Shadow detection and removal from a single image using LAB color space,” Cybernetics and information technologies, vol. 13, pp. 95-103, 2013.
[27]      J.-F. Lalonde, A. A. Efros, and S. G. Narasimhan, “Detecting ground shadows in outdoor consumer photographs,” in European conference on computer vision, pp. 322-335, 2010.
[28]      J. Tian, X. Qi, L. Qu, and Y. Tang, “New spectrum ratio properties and features for shadow detection,” Pattern Recognition, vol. 51, pp. 85-96, 2016.
[29]      J. Huang, W. Xie, and L. Tang, “Detection of and compensation for shadows in colored urban aerial images,” in Fifth World Congress on Intelligent Control and Automation (WCICA), pp. 3098-3100, 2004.
[30]      Q. Liu, X. Cao, C. Deng, and X. Guo, “Identifying image composites through shadow matte consistency,” IEEE Transactions on Information Forensics and Security, vol. 6, pp. 1111-1122, 2011.
[31]      R. McFeely, C. Hughes, E. Jones, and M. Glavin, “Removal of non-uniform complex and compound shadows from textured surfaces using adaptive directional smoothing and the thin plate model,” IET image processing, vol. 5, pp. 233-248, 2011.
[32]      E. Arbel and H. Hel-Or, “Shadow removal using intensity surfaces and texture anchor points,” IEEE transactions on pattern analysis and machine intelligence, vol. 33, pp. 1202-1216, 2011.
[33]      N. Su, Y. Zhang, S. Tian, Y. Yan, and X. Miao, “Shadow detection and removal for occluded object information recovery in urban high-resolution panchromatic satellite images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, pp. 2568-2582, 2016.
[34]      A. Amato, I. Huerta, M. G. Mozerov, F. X. Roca, and J. Gonzalez, “Moving cast shadows detection methods for video surveillance applications,” in Wide Area Surveillance, Springer, pp. 23-47, 2014.
[35]      R. C. Gonzalez, R. E. Woods, and S. L. Eddins, “Digital image processing using Matlab,” Person Prentice Hall, Lexington, 2004.
[36]      A. M. Polidorio, F. C. Flores, N. N. Imai, A. M. Tommaselli, and C. Franco, “Automatic shadow segmentation in aerial color images,” in XVI Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI), pp. 270-277, 2003.
[37]      X. Zhu, R. Chen, H. Xia, and P. Zhang, “Shadow removal based on YCbCr color space,” Neurocomputing, vol. 151, pp. 252-258, 2015.
[38]      N. Tatar, M. Saadatseresht, H. Arefi, and A. Hadavand, “A new object-based framework to detect shadows in high-resolution satellite imagery over urban areas,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 40, p. 713, 2015.