Volume 6, Issue 4 (2018)                   IQBQ 2018, 6(4): 241-257 | Back to browse issues page

XML Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Taghi Mollaei Y, Karamshahi A, Erfanifard S. Valuation of Object-Based and Decision Tree Classification Methods in Estimating the Quantitative Characteristics of Single Oak Trees on WorldView-2 and UAV Images. IQBQ. 2018; 6 (4) :241-257
URL: http://journals.modares.ac.ir/article-24-18920-en.html
1- Forest Sciences Department, Agriculture & Natural Resources Faculty, Ilam University, Ilam, Iran , taghimollei@yahoo.com
2- Forest Sciences Department, Agriculture & Natural Resources Faculty, Ilam University, Ilam, Iran
3- Natural Resources & Environment Department, Agriculture Faculty, Shiraz University, Shiraz, Iran
Abstract:   (107 Views)
Aims: One of the most commonly used applications in forestry is the identification of single trees and tree species compassions using object-based image analysis (OBIA) and classification of satellite or aerial images. The aims of this study were the valuation of OBIA and decision tree (DT) classification methods in estimating the quantitative characteristics of single oak trees on WorldView-2 and unmanned aerial vehicle (UAV) images.
Materials & Methods: In this experimental study Haft-Barm forest, Shiraz, Iran, was considered as the study area in order to examine the potential of Worldview-2 satellite imagery. The estimation of forest parameters was evaluated by focusing on single tree extraction using OBIA and DT methods of classification with a complex matrix evaluation and area under operating characteristic curve (AUC) method with the help of the 4th UAV phantom bird image in two distinct regions. Data were analyzed by paired t-test, multivariate regression analysis, using SPSS 25, Excel 2016, eCognation v. 8.7, ENVI, 5, PCI Geomatica 16, and Google Earth 7.3 Software.
Findings: The base object classification had the highest and best accuracy in estimating single-tree parameters. Basic object classification method was a very useful method for identifying Oak tree Zagros Mountains forest. With using WV-2 data, the parameters of single trees in the forest can extract.
Conclusion: The accuracy of OBIA is 83%. While UAV has the potential to provide flexible and feasible solutions for forest mapping, some issues related to image quality still need to be addressed in order to improve the classification performance.
Full-Text [PDF 3518 kb]   (31 Downloads)    

Received: 2018/04/13 | Accepted: 2018/09/2 | Published: 2018/11/21
* Corresponding Author Address: Forest Sciences Department, Pazhohesh Boulevard, Ilam Province, Iran

References
1. White JC, Stepper C, Tompalski P, Coops NC, Wulder MA. Comparing ALS and Image-Based Point Cloud Metrics and Modelled Forest Inventory Attributes in a Complex Coastal Forest Environment. For. 2015;6(10):3704-32. [Link] [DOI:10.3390/f6103704]
2. Zöhrer F. Forstinventur: Ein leitfaden für studium und praxis. Hamburg: Parey; 1980. p. 207. [German] [Link]
3. Hudak AT, Haren, AT, Crookston NL, Liebermann RJ, Ohmann, JL. Imputing forest structure attributes from stand inventory and remotely sensed data in western Oregon, USA. For Sci. 2014;60(2):253-69. [Link] [DOI:10.5849/forsci.12-101]
4. Wulder MA, White JC, Hay GJ, Castilla G. Towards automated segmentation of forest inventory polygons on high spatial resolution satellite imagery. For Chron. 2008;84(2):221-30. [Link] [DOI:10.5558/tfc84221-2]
5. Allen CD, Macalady AK, Chenchouni H, Bachelet D, McDowell N, Vennetier M, et al. A global overview of drought and heat-induced tree mortality reveals emerging climate change risks for forests. For Ecol Manag. 2010;259(4):660-84. [Link] [DOI:10.1016/j.foreco.2009.09.001]
6. Breshears DD, Cobb NS, Rich PM, Price KP, Allen CD, Balice RG, et al. Regional vegetation die-off in response to global-change-type drought. Proc Natl Acad Sci. 2005;102(42):15144-8. [Link] [DOI:10.1073/pnas.0505734102]
7. Carnicer J, Coll M, Ninyerola M, Pons X, Sánchez G, Pe-uelas J. Widespread crown condition decline, food web disruption, and amplified tree mortality with increased climate change-type drought. Proc Natl Acad Sci U S A. 2011;108(4):1474-8. [Link] [DOI:10.1073/pnas.1010070108]
8. Phillips OL, Aragão LEOC, Lewis SL, Fisher JB, Lloyd J, Lόpez-González G, et al. Drought sensitivity of the Amazon rainforest. Science. 2009;323(5919):1344-7. [Link] [DOI:10.1126/science.1164033]
9. Van Mantgem PJ, Stephenson NL, Byrne JC, Daniels LD, Franklin J F, Fulé PZ, et al. Widespread increase of tree mortality rates in the western United States. Science. 2009;323(5913):521-4. [Link] [DOI:10.1126/science.1165000]
10. Karlson M, Reese H, Ostwald M. Tree crown mapping in managed woodlands (parklands) of semi-arid West Africa using WorldView-2 imagery and geographic object based image analysis. Sensors. 2014;14(12):22643-69. [Link] [DOI:10.3390/s141222643]
11. Clark DB, Soto Castro C, Alvarado LDA, Read JM. Quantifying mortality of tropical rain forest trees using high spatial-resolution satellite data. Ecol Lett. 2004;7(1):52-9. [Link] [DOI:10.1046/j.1461-0248.2003.00547.x]
12. Clark DB, Read JM, Clark ML, Cruz AM, Dotti MF, Clark DA. Application of 1-M and 4-M resolution satellite data to ecological studies of tropical rain forests. Ecol Applications. 2004;14(1):61-74. [Link] [DOI:10.1890/02-5120]
13. Gong P, Biging GS, Lee SM, Mei X, Sheng Y, Pu R, et al. Photo ecometrics for forest inventory. Geogr Inf Sci. 1999;5(1):9-14. [Link] [DOI:10.1080/10824009909480508]
14. Leckie DG, Yuan X, Ostaff DP, Piene H, MacLean DA. Analysis of high spatial resolution multispectral MEIS imagery for spruce budworm damage assessment on a single tree basis. Remote Sens Environ. 1992;40(2):125-36. [Link] [DOI:10.1016/0034-4257(92)90010-H]
15. Levesque J, J King D. Airborne digital camera image semivariance for evaluation of forest structural damage at an acid mine site. Remote Sens Environ. 1999;68(2):112-4. [Link] [DOI:10.1016/S0034-4257(98)00104-7]
16. Kelly M, Shaari D, Guo Q, Liu D. A comparison of standard and hybrid classifier methods for mapping hardwood mortality in areas affected by "sudden oak death". Photogramm Eng Remote Sens. 2004;70:1229-39. [Link] [DOI:10.14358/PERS.70.11.1229]
17. Sedliak M, Sačkov I, Kulla L. Classification of tree species composition using a combination of multispectral imagery and airborne laser scanning data. Cent Eur For J. 2017;63(1):1-9. [Link] [DOI:10.1515/forj-2017-0002]
18. Niphadkar M, Nagendra H, Tarantino C, Adamo M, Blonda P. Comparing pixel and object-based approaches to map an understory invasive shrub in tropical mixed forests. Front Plant Sci. 2017;8:892. [Link] [DOI:10.3389/fpls.2017.00892]
19. Raczko E, Zagajewski B. Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images. Eur J Remote Sens. 2016;50(1):144-54. [Link] [DOI:10.1080/22797254.2017.1299557]
20. Juniati E, Arrofiqoh EN. Comparison of Pixel-Based and Object-Based classification using parameters and non-parameters approach for the pattern consistency of multi scale landcover. Int Arch Photogramm Remote Sens Spatial Inf Sci. 2017;XLII-2/W7:765-71. [Link] [DOI:10.5194/isprs-archives-XLII-2-W7-765-2017]
21. Pazhouhan I, Najafi A, Kamkar Rouhani A, Vahidi J. Extraction of individual tree parameters by using terrestrial laser scanner data in Hercynian forest. Ecopersia. 2017;5(3):1837-47. [Link]
22. Alem H, Mohammadi Z. Determining the water sources of lakes: A case study of lakes Haftbarm, Fars Province, Iran. Int Bull Water Resour Develop. 2014;2(2 suppl 5). [Persian] [Link]
23. Updike T, Comp C. Radiometric use of worldview-2 imagery [Internet]. Westminster: Digital Globe; 2010 [cited 2015 May 22]. Available from: https://www.yumpu.com/en/document/view/43552535/radiometric-use-of-worldview-2-imagery-technical-note-pancroma [Link]
24. DJI. PHANTOM 4 user manual [Internet]. Shenzhen: DJI; 2016 [cited 2018 March 11]. Available from: https://dl.djicdn.com/downloads/phantom_4/en/Phantom_4_User_Manual_en_v1.0.pdf. [Link]
25. Quinlan JR . Learning with continuous classes. World Sci. 1992:343-8. [Link]
26. Liang S, Liu J, Liang M. Ecological study on the mangrove communities in Beilunhekou national nature reserve. J Guangxi Norm Univ Natl Sci Ed. 2004;22(2):70-6 [Chinese] [Link]
27. Heumann BW. An Object-Based classification of mangroves using a hybrid decision tree—support vector machine approach. Remote Sens. 2011;3(11):2440-60. [Link] [DOI:10.3390/rs3112440]
28. Tooke TR, Coops NC, Goodwin NR, Voogt JA. Extracting urban vegetation characteristics using spectral mixture analysis and decision tree classifications. Remote Sens Environ. 2009;113(2):398-407. [Link] [DOI:10.1016/j.rse.2008.10.005]
29. Ghose MK, Pradhan R, Sushan Ghose S. Decision Tree Classification of Remotely Sensed Satellite Data using Spectral Separability Matrix. Int J Adv Comput Sci Appl. 2010;1(5):93-101 [Link]
30. Friedl MA, Brodley CE. Decision tree classification of land cover from remotely sensed data. Remote Sens. Environ. 1997;61(3):399-409. [Link] [DOI:10.1016/S0034-4257(97)00049-7]
31. Pal M, Mather PM. An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sens Environ. 2003;86(4):554-65. [Link] [DOI:10.1016/S0034-4257(03)00132-9]
32. Jensen JR. Introductory digital image processing: A remote sensing perspective. 3rd Edition. Upper Saddle River: Prentice Hall; 2005. [Link]
33. Quinlan JR. Induction of decision trees. Mach Learn. 1986;1(1):81-106. https://doi.org/10.1007/BF00116251 [Link] [DOI:10.1023/A:1022643204877]
34. Xu M, Watanachaturaporn P, Varshney PK, Arora MK. Decision tree regression for soft classification of remote sensing data. Remote Sens Environ. 2005;97(3):322-36. [Link] [DOI:10.1016/j.rse.2005.05.008]
35. Schowengerdt RA. Remote Sensing: Models and methods for image processing. Cambridge: Academic press; 1997. [Link] [DOI:10.1016/B978-0-08-051610-3.50009-6]
36. Woodcock CE, Strahler AH. The factor of scale in remote sensing. Remote Sens Environ. 1987;21(3):311-32. [Link] [DOI:10.1016/0034-4257(87)90015-0]
37. Benz UC, Hofmann P, Willhauck G, Lingenfelder I, Heynen M. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J Photogramm Remote Sens. 2004;58(3-4):239-58. [Link] [DOI:10.1016/j.isprsjprs.2003.10.002]
38. Drǎguţ L, Tiede D, Levick SR. ESP: A tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. Int J Geogr Inf Sci. 2010;24(6):859-71. [Link] [DOI:10.1080/13658810903174803]
39. Drăguţ L, Csillik O, Eisank C, Tiede D. Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS J Photogramm Remote Sens. 2014;88:119-27. [Link] [DOI:10.1016/j.isprsjprs.2013.11.018]
40. Wen D, Huang X, Liu H, Liao W, Zhang L. Semantic classification of urban trees using very high resolution satellite imagery. IEEE J Sel Top Appl Earth Observ Remote Sens. 2017;10(4):1413-24. [Link] [DOI:10.1109/JSTARS.2016.2645798]
41. Immitzer M, Atzberger, Koukal T. Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data. Remote Sens. 2012;4(9):2661-93. [Link] [DOI:10.3390/rs4092661]
42. Chubey MS, Franklin SE, Wulder MA. Object-based analysis of Ikonos-2 imagery for extraction of forest inventory parameters. J Am Soc Photogramm Remote Sens. 2006;72(4):383-94. [Link] [DOI:10.14358/PERS.72.4.383]
43. Desclée B, Bogaert P, Defourny P. Forest change detection by statistical object-based method. Remote Sens Environ. 2006;102(1-2):1-11. [Link] [DOI:10.1016/j.rse.2006.01.013]
44. Hay GJ, Castilla G, Wulder MA, Ruiz JR. An automated object-based approach for the multiscale image segmentation of forest scenes. Int J Appl Earth Observ Geoinf. 2005;7(4):339-59. [Link] [DOI:10.1016/j.jag.2005.06.005]
45. Zhang Zh, Kazakova A, Moskal LM, Styers DM. Object-Based Tree Species Classification in Urban Ecosystems Using LiDAR and Hyperspectral Data. For. 2016;7(6):122 [Link]
46. Myint SW, Giri CP, Wang L, Zhu Z, Gillette SC. Identifying mangrove species and their surrounding land use and land cover classes using an object-oriented approach with a lacunarity spatial measure. J GIScience Remote Sens. 2008;45(2):188-208. [Link] [DOI:10.2747/1548-1603.45.2.188]
47. Wang L, Sousa WP, Gong P. Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery. Int J Remote Sens. 2004;25(24):5655-68. [Link] [DOI:10.1080/014311602331291215]
48. Shrestha R, Wynne RH. Estimating biophysical parameters of individual trees in an urban environment using small footprint discrete-return imaging Lidar. Remote Sens. 2012;4(2):484-508. [Link] [DOI:10.3390/rs4020484]
49. Pande-Chhetri R, Abd-Elrahman A, Liu T, Morton J, Wilhelm VL. Object-based classification of wetland vegetation using very high-resolution unmanned air system imagery. Eur J Remote Sens. 2017;50(1):564-76. [Link] [DOI:10.1080/22797254.2017.1373602]
50. Thanh Noi P, Kappas M. Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery. Sensors. 2017;18(1). [Link] [DOI:10.3390/s18010018]
51. Qian Y, Zhou W, Yan J, Li W, Han L. Comparing machine learning classifiers for Object-Based land cover classification using very high-resolution imagery. Remote Sens. 2015;7(1):153-68. [Link] [DOI:10.3390/rs70100153]
52. Shafri HZM, Ramle FSH. A comparison of support vector machine and decision tree classifications using satellite data of Langkawi island. Inf Technol J. 2009;8(1):64-70. [Link] [DOI:10.3923/itj.2009.64.70]
53. Shao Y, Lunetta RS. Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points. ISPRS J Photogramm Remote Sens. 2012;70:78-87. [Link] [DOI:10.1016/j.isprsjprs.2012.04.001]
54. Amami R, Ben Ayed D, Ellouze N. An Empirical comparison of SVM and some supervised learning algorithms for vowel recognition. Int J Intell Inf Proc. 2012;3(1). [Link]
55. Ghasemian N, Akhondzadeh M. Comparison of methods of artificial neural networks, support vector machine and decision tree to identify clouds in Landsat 8 satellite images. Geospat Eng J. 2016;7(4):25-36. [Persian] [Link]
56. Kim J, Kim BS, Savarese S. Comparing image classification methods: K-nearest-neighbor and support-vector-machines. AMERICAN-MATH'12/CEA'12 Proceedings of the 6th WSEAS international conference on computer engineering and applications, and proceedings of the 2012 American conference on applied mathematics. Stevens Point: World Scientific and Engineering Academy and Society (WSEAS); 2012. [Link]
57. Hao P, Wang L, Niu Z. Comparison of hybrid classifiers for crop classification using normalized difference vegetation index time series: A case study for major crops in North Xinjiang, China. PLoS One. 2015;10(9):e0137748. [Link] [DOI:10.1371/journal.pone.0137748]
58. Hofmann T, Puzicha J, Buhmann JM. Unsupervised texture segmentation in a deterministic annealing framework. IEEE Transactions Pattern Anal Mach Intell. 1998;20(8):803-18. [Link] [DOI:10.1109/34.709593]
59. Chaudhuri BB, Sarkar N. Texture segmentation using fractal dimension. IEEE Transactions Pattern Anal Mach Intell. 1995;17(1):72-7. [Link] [DOI:10.1109/34.368149]
60. Baatz M, Schäpe A. Multiresolution segmentation-an optimization approach for high quality multi-scale image segmentation. In: Strobl J, editor. Angewandte geographische informationsverarbeitung XII: Beiträge zum AGIT- symposium Salzburg. Karlsruhe: Wichmann Verlag; 2000. pp. 12-23. [German] [Link]
61. Blaschke T. Object-based image analysis for remote sensing. ISPRS J Photogramm Remote Sens. 2010;65(1):2-16. [Link] [DOI:10.1016/j.isprsjprs.2009.06.004]
62. Almeida CM, Souza IM, Durand Alves C, Pinho CMD, Pereira MN, Feitosa RQ. Multilevel object-oriented classification of quick bird images for urban population estimates. GIS '07 Proceedings of the 15th annual ACM international symposium on advances in geographic information systems, Seattle, WA, USA — November 07 - 09, 2007. New York: ACM; 2007.pp. 5. [Link]
63. Yan G. Pixel-based and object-oriented image for coal fire research [Internet]. City publisher: publisher; 2003 [cited 2015 May 18]. Available from: http://www.ecognition.com/sites/default/files/gao_yan.pdf. [Link]
64. Gao Y, Mas JF, Navarrete A. The improvement of an object-oriented classification using multi-temporal MODIS EVI satellite data. Int J Digit Earth. 2009;2(3):219-36. [Link] [DOI:10.1080/17538940902818311]
65. Zhaocong W, Lina Y, Maoyun Q. Granular approach to object-oriented remote sensing image classification. In: Wen P, Li Y, Polkowski L, Yao Y, Tsumoto S, Wang G, editors. International conference on rough sets and knowledge technology. Heidelberg: Springer; 2009. pp. 563-70. [Link]
66. Platt RV, Schoennagel T. An object-oriented approach to assessing changes in tree cover in the Colorado Front Range 1938-1999. For Ecol Manag. 2009;258(7):1342-9. [Link] [DOI:10.1016/j.foreco.2009.06.039]
67. Dehvari A, Heck RJ. Comparison of object-based and pixel-based infrared airborne image classification methods using DEM thematic layer. J Geogr Reg Plan. 2009;2(4):086-96. [Link]
68. Collingwood A, Steven EF, Guo X, Stenhouse G. A medium-resolution remote sensing classification of agriculture areas in Alberta grizzly bear habit. Can J Remote Sens. 2009;35(1):22-36. [Link] [DOI:10.5589/m08-076]
69. Okojie J. Assessment of forest tree structural parameter extractability from optical imaging UAV dataset [Dissertation]. Enschede: University of Twente; 2017. [Link]

Add your comments about this article : Your username or Email:
CAPTCHA code

Send email to the article author