تعيين و تشخيص خودکار تاج درختان بلوط ايرانی به کمک الگوريتم حداکثر فيلتر محلی
محورهای موضوعی : منابع طبیعیحامد صادقیان 1 , علیرضا صالحی 2 * , زهرا عزيزی 3
1 - دانشجوی کارشناسی ارشد جنگلداری، گروه جنگلداری، دانشکده کشاورزی و منابع طبیعی، دانشگاه یاسوج، یاسوج، ایران.
2 - دانشیار، گروه علوم و مهندسی جنگل، دانشکده کشاورزی و منابع طبیعی، دانشگاه یاسوج، یاسوج، ایران. * (مسوول مکاتبات)
3 - دانشیار، دپارتمان منابع طبیعی و محیط زیست، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.
کلید واژه: الگوریتم تعیین و تشخیص, بلوط ایرانی, تصویر UltraCam-D.,
چکیده مقاله :
زمينه و هدف: امروزه تصاوير سنجش از دور فرصت مناسبي را جهت تجزيه و تحليل خودکار مشخصههای جنگل فراهم ميکنند. این پژوهش با هدف ارزیابی نتایج به کار گیری الگوریتم خودکار حداکثر فیلتر محلی برای تعیین مساحت تاج و تشخیص تاج تک درختان بلوط ایرانی بر روی تصاویر هوایی UltraCam-D در مقایسه با روش تفسیر بصری بر روی این تصاویر و اندازهگیری زمینی، انجام گرفته است.
روش بررسی: مساحت تاج 100 اصله درخت، انتخاب شده به صورت تصادفی و قابل تشخیص در عرصه جنگل و تصویر هوایی، به روش تفسیر بصری بر روی تصویر هوایی، اندازهگیری، محاسبه و به عنوان مساحت واقعی در نظر گرفته شد. در روش آماربرداری زمینی، مساحت تاج و تعداد پایه هر کدام از درختان مذکور اندازهگیری و ثبت شد. سپس الگوریتم حداکثر فیلتر محلی با برنامه نویسی در محیط نرم افزار Matlab R2014b جهت تعیین مساحت و تشخیص تعداد قلههای تاج بر روی تصویر یادشده اعمال شد.
يافتهها: با آزمون تحلیل واریانس یک طرفه، اختلاف معنی داری بین میانگین سطح تاج حاصل از این روشها مشاهده نگردید. درصد RMSE جهت برآورد دقت الگوریتم حداکثر فیلتر محلی و روش زمینی نسبت به روش تفسیر بصری به ترتیب 82/5 درصد و 08/6 درصد به دستآمد. همچنین صحت کلی و ضریب کاپا در ارتباط با برآورد دقت الگوریتم حداکثر فیلتر محلی جهت تشخیص تعداد قله تاج درختان به ترتیب 64 درصد و 59 درصد به دستآمد.
بحث و نتيجهگيری: استفاده از الگوریتم حداکثر فیلتر محلی جهت تعیین و تشخیص تاج بلوط ایرانی و به دنبال آن بررسی وضعیت شاخه زادی این درختان قابل توصیه میباشد.
Background and Objective: Remote sensing images provide a good opportunity to be analyzed automatically the features of the forests. This study aims to evaluate the use of an automatic algorithm under the name of the local maximum filter to determine and recognize the crown area of Persian oak trees, using Ultra Cam-D aerial imageries, in comparison to the results of visual interpretation of images and measurements on the field.
Material and Methodology: Crown area of 100 Persian oak trees selected randomly in the forest, also recognizable in aerial images, were measured and calculated by mentioned methods, while the results of the visual interpretation was considered as the control method. The local maximum filtering algorithm was programmed, using Matlab R2014b software. This program was used to diagnose the number of peaks of a crown and to determine the area of that.
Findings: Using ANOVA analysis, no significant differences were observed between the mean values of canopy resulted by these methods. The RMSEs for estimating the accuracy of the local maximum filtering and the field measurement method in comparison to the visual interpretation methods were obtained 5.82% and 6.08 %, respectively. The overall accuracy and kappa coefficient associated with the estimation by the algorithm to determine the numbers of peaks of tree crowns are 64% and 59%, respectively.
Discussion and Conclusion: The use of local maximum filtering algorithm for determining the canopy of Persian oak trees could be recommended.
1. Ozanne, CMP., Anhuf, D., Boulter, SL. and Keller, M. 2003. Biodiversity meets the atmosphere: a global view of forest canopies. Science, 301: 183-186.
2. Ke, Y and Quackenbursh, LJ. 2011. A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing. International Journal of Remote Sensing, 32 (17): 4725–4747.
3. Hudak, AT., Strand, EK., Vierling, LA., Byrne, JC., Eitel, JUH., Martinuzzi, SN & Falkowski, MJ. 2012. Quantifying above ground forest carbon pools and fluxes from repeat LIDAR surveys. Remote Sensing of Environment, 123: 25–40.
4. Reese, H., Nilsson, M., Granqvist Pahlén,T., Hagner, O., Joyce, S., Tingelöf, U., Egberth, M. and Olsson, H. 2003. Countrywide Estimates of Forest Variables Using Satellite Data and Field Data from the National Forest Inventory. A Journal of the Human Environment, 32: 542-548.
5. Azizi, Z., Najafi, A., Sohrabi, H. 2008. Forest canopy density estimation, using satellite images. In Proceedings of the International Society for Photogrammetry and Remote Sensing Congress Commission VIII, 3-11 July, Beijing, China.
6. Rafiian, O., Darvishsafat, A.A., Babai K., S. 2009. Evaluation of the UltraCam-D digital aerial imagery object classification method for use in forests (study of images taken from northern forests). 03rd National Conference on Forest, Alborz - Karaj. (In Persian)
7. Sohrabi, H. 2009. Application of Visual and Numerical Interpretation of Aerial Images in Forest Inventory. PhD thesis in forestry, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Tehran. 100 p. (In Persian)
8. Zhou, J., Proisy, Ch., Descombes, X., le Maire, G., Nouvellon, Y., Stape, J., Viennois, G., Zerubia, J., Couteron, P. 2013. Mapping local density of young Eucalyptus plantations by individual tree detection in high spatial resolution satellite images. Forest Ecology and Management, 301: 129-141.
9. Khalid, N., Hamid, JR A., Latif, Z A. 2014. Accuracy assessment of tree crown detection using local maxima and multi-resolution segmentation. IOP Conference Series: Earth and Environmental Science, 18: 20-23.
10. Pinz, A. 1991. A computer vision system for recognition of trees in aerial photographs. In Proceedings of the International Association of Pattern Recognition Workshop, 14–15 June, College Park, MD (Washington, DC: NASA), 111–124.
11. Gougeon, FA. 1995. A crown-following approach to the automatic delineation of individual tree crowns in high spatial resolution aerial images. Canadian Journal of Remote Sensing, 21: 274–284.
12. Brandtberg, T. 1998. Automated delineation of individual tree crowns in high spatial resolution aerial images by multiple-scale analysis. Machine Vision and Applications, 11: 64–73.
13. Pollock, RJ. 1996. The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown model. PhD dissertation, University of British Columbia, Vancouver, Canada.
14. Azizi, Z., and Miraki, M. 2024. Individual urban trees detection based on point clouds derived from UAV-RGB imagery and local maxima algorithm: A case study of Fateh Garden, Iran. Environment, Development and Sustainability, 26: 2331–2344.
15. Ma'soumi (Translator), H. 2005. Geometric Calibration of the Aerial Digital Camera "ULTRACAM D". Scientific- Research Quarterly of Geographical Data (SEPEHR), 14(55): 48-50. (In Persian)
16. Erfanifard, S.Y., Faghihi, J., Zobeiri, M., Namiranian, M. 2010. Investigation of the feasibility of mapping canopy density in forests using aerial photographs and GIS. National Geomatics Conference, Karaj, 11 pages. (In Persian)
17. Azizi, Z., and Montazeri, Z. 2018. Effects of microtopography on the spatial pattern of woody species in West Iran. Arabian Journal of Geosciences, 11: 244
18. Culvenor, DS. 2002. TIDA: an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery. Computers and Geosciences, 28: 33–44.
19. Pouliot, DA., King, DJ., Bell FW., Pitt, DG. 2002. Automated tree crown detection and delineation in high-resolution digital camera imagery of coniferous forest regeneration. Remote Sensing of Environment, 82: 322–334.
20. Wulder, M., Niemann, KO., and Goodenough, DG. 2000. Local Maximum Filtering for the extraction of tree locations and basal area from high spatial resolution imagery. Remote Sensing of Environment, 73: 103–114.
21. Meyer, GE., Neto, JC. 2008. Verification of color vegetation indices for automated crop imaging applications. computers and electronics in agriculture, 6(3): 282-293.
22. Paine, DP., and Kiser, JD. 2012. Aerial photography and image interpretation (3rd ed.). John Wiley & Sons, Inc., 629 p.
23. Gougeon, FA and Leckie, DG. 2006. The individual tree crown approach applied to IKONOS images of a coniferous plantation area. Photogrammetric Engineering and Remote Sensing, 72: 1287–1297.
24. Jamshid Talebi, and Azizi, Z. 2025. Enhancing land feature classification with the BTR Extractor: A novel software package for high-accuracy analysis of aerial laser scan data. MethodsX, 14: 103090.
25. Erfanifard, S.Y. 2014. Application of ROC curve to assess pixel-based classification methods on UltraCam-D aerial imagery to discriminate tree crowns in pure stands of Brant’s oak in Zagros forests. Iranian Journal of Forest and Poplar Research, 22(4): 649–663. (In Persian)
26. Larsen, M., Eriksson, EM., Descombes, X., Perrin, G., Brandtberg, T and Gougeon, FA. 2011. Comparison of six i ndividual tree crown detection algorithms evaluated under varying forest conditions. International Journal of Remote Sensing, 32(20): 5827–5852.
27. Gbreslasie, MT., Ahmed, FB., Van Aardt, JAN., Blakeway, F. 2011. Individual tree detection based on variable and fixed window size localn maxima filtering applied to IKONOS imagery for even-aged Eucalyptus plantation forests, International Journal of Remote Sensing, 32(15): 4141-4154.