|
|
|
|
|
| NDVI-Based Lacunarity Texture for Improving Identification of Torreya Using Object-Oriented Method |
| HAN Ning, WU Jing, Amir Reza Shah Tahmassebi, XU Hong-wei , WANG Ke |
1. Institute of Remote Sensing and Information System Application, College of Environment and Resource Science, Zhejiang University
2. School of Environment and Resource, Zhejiang Agriculture and Forestry University |
|
|
|
摘要 Normalized Difference Vegetation Index (NDVI) is a very useful feature for differentiating vegetation and non-vegetationin remote sensed imagery. In the light of the function of NDVI and the spatial patterns of the vegetation landscapes, weproposed the lacunarity texture derived from NDVI to characterize the spatial patterns of vegetation landscapes concerningthe “gappiness” or “emptiness” characteristics. The NDVI-based lacunarity texture was incorporated into object-orientedclassification for improving the identification of vegetation categories, especially Torreya which was the targeted treespecies in the present research. A three-level hierarchical network of image objects was defined and the proposed texturewas integrated as potential sources of information in the rules base. A knowledge base of rules created by classifierC5.0 indicated that the texture could potentially be applied in object-oriented classification. It was found that the additionof such texture improved the identification of every vegetation category. The results demonstrated that the texture couldcharacterize the spatial patterns of vegetation structures, which could be a promising approach for vegetation identification.
Abstract Normalized Difference Vegetation Index (NDVI) is a very useful feature for differentiating vegetation and non-vegetationin remote sensed imagery. In the light of the function of NDVI and the spatial patterns of the vegetation landscapes, weproposed the lacunarity texture derived from NDVI to characterize the spatial patterns of vegetation landscapes concerningthe “gappiness” or “emptiness” characteristics. The NDVI-based lacunarity texture was incorporated into object-orientedclassification for improving the identification of vegetation categories, especially Torreya which was the targeted treespecies in the present research. A three-level hierarchical network of image objects was defined and the proposed texturewas integrated as potential sources of information in the rules base. A knowledge base of rules created by classifierC5.0 indicated that the texture could potentially be applied in object-oriented classification. It was found that the additionof such texture improved the identification of every vegetation category. The results demonstrated that the texture couldcharacterize the spatial patterns of vegetation structures, which could be a promising approach for vegetation identification.
|
|
Received: 10 September 2010
Accepted:
|
| Fund: This research was supported by the National Natural Science Foundation of China (30671212). |
|
Corresponding Authors:
Correspondence WANG Ke, Professor, Tel/Fax: +86-571-86971272, E-mail: kwang@zju.edu.cn
E-mail: kwang@zju.edu.cn
|
Cite this article:
HAN Ning, WU Jing, Amir Reza Shah Tahmassebi, XU Hong-wei , WANG Ke.
2011.
NDVI-Based Lacunarity Texture for Improving Identification of Torreya Using Object-Oriented Method. Journal of Integrative Agriculture, 10(9): 1431-1444.
|
| [1]Allain C, Cloitre M. 1991. Characterizing the lacunarity of randomand deterministic fractal sets. Physical Review Annals, 44,3552-3558.[2]Baatz M, Schäpe A. 2000. Multiresolution segmentation: anoptimization approach for high quality multi-scale imagesegmentation. ISPRS Journal of Photogrammetry and RemoteSensing, 58, 12-23.[3]Benz U C, Hofmann P, Willhauck G, Lingenfelder I, Heynen M.2004. Multi-resolution, object-oriented fuzzy analysis ofremote sensing data for GIS-ready information. ISPRSJournal of Photogrammetry and Remote Sensing, 58, 239-258.[4]de Colstoun E C B, Story M H, Thompson C, Commisso K,Smith T G, Irons J R. 2003. National Park vegetation mappingusing multitemporal Landsat 7 data and a decision treeclassifier. Remote Sensing of Environment, 85, 316-327.[5]Burnett C, Blaschke T. 2003. A multi-scale segmentation/objectrelationship modelling methodology for landscape analysis.Ecological Modelling, 168, 233-249.[6]Carleer A P, Wolff E. 2006. Urban land cover multi-level regionbasedclassification of VHR data by selecting relevantfeatures. International Journal of Remote Sensing, 27, 1035-1051.[7]Chen Y, Wen D, Jing L, Shi P. 2007. Shadow information recoveryin urban areas from very high resolution satellite imagery.International Journal of Remote Sensing, 28, 3249-3254.[8]Feagin R A, Wu X B, Feagin T. 2007. Edge effects in lacunarityanalysis. Ecological Modelling, 201, 262-268.[9]Goetz S J, Wright R K, Smith A J, Zinecker E, Schaub E. 2003.IKONOS imagery for resource management: Tree cover,impervious surfaces, and riparian buffer analyses in the mid-Atlantic region. Remote Sensing of Environment, 88, 195-208.[10]Hall O, Hay G J, Bouchard A, Marceau D J. 2004. Detectingdominant landscape objects through multiple scales: Anintegration of object-specific methods and watershedsegmentation. Landscape Ecology, 19, 59-76.[11]Houlie N, Komorowski J C, de Michele M, Kasereka M, CirabaH. 2006. Early detection of eruptive dykes revealed bynormalized difference vegetation index (NDVI) on Mt. Etnaand Mt. Nyiragongo. Earth and Planetary Science Letters,246, 231-240.[12]Johansen K, Phinn S. 2006. Mapping structural parameters andspecies composition of riparian vegetation using IKONOSand landsat ETM plus data in Australian tropical savannahs.Photogrammetric Engineering and Remote Sensing, 72, 71-80.[13]Johansen K, Coops N C, Gergel S E, Stange Y. 2007. Applicationof high spatial resolution satellite imagery for riparian andforest ecosystem classification. Remote Sensing ofEnvironment, 110, 29-44.[14]Laliberte A S, Rango A, Havstad K M, Paris J F, Beck R F,McNeely R, Gonzalez A L. 2004. Object-oriented imageanalysis for mapping shrub encroachment from 1937 to 2003in southern New Mexico. Remote Sensing of Environment,93, 198-210.[15]Malhi Y, Roman-Cuesta R M. 2008. Analysis of lacunarity andscales of spatial homogeneity in IKONOS images ofAmazonian tropical forest canopies. Remote Sensing ofEnvironment, 112, 2074-2087.[16]Mallinis G, Koutsias N, Tsakiri-Strati M, Karteris M. 2008.Object-based classification using Quickbird imagery fordelineating forest vegetation polygons in a Mediterraneantest site. ISPRS Journal of Photogrammetry and RemoteSensing, 63, 237-250.[17]Mandelbrot B B. 1983. The Fractal Geometry of Nature. W. H. Freeman and Company, New York.Myint S W, Lam N. 2005. A study of lacunarity-based textureanalysis approaches to improve urban image classificationComputers. Environment and Urban Systems, 29, 501-523.[18]Piramuthu S. 2004. Evaluating feature selection methods forlearning in data mining applications. European Journal ofOperational Research, 156, 483-494.[19]Plotnick R E, Gardner R H, Hargrove W W, Prestegaard K,Perlmutter M. 1996. Lacunarity analysis: A general techniquefor the analysis of spatial patterns. Physical Review E, 53,5461-5468.[20]Puissant A, Hirsch J, Weber C. 2005. The utility of textureanalysis to improve per-pixel classification for high to veryhigh spatial resolution imagery. International Journal ofRemote Sensing, 26, 733-745.[21]Quinlan J R. 1993. C4.5: Programs for Machine Learning.Morgan Kaufmann Publishers Inc., San Mateo, CA.Wulder M A, Hall R J, Coops N C, Franklin S E. 2004. Highspatial resolution remotely sensed data for ecosystemcharacterization. Bioscience, 54, 511-521.[22]Zhang X Y, Feng X Z, Jiang H. 2010. Object-oriented methodfor urban vegetation mapping using IKONOS imagery.International Journal of Remote Sensing, 31, 177-196.[23]Zhou W Q, Troy A. 2008. An object-oriented approach foranalysing and characterizing urban landscape at the parcellevel. International Journal of Remote Sensing, 29, 3119-3135.[24]Zhou W Q, Huang G L, Troy A, Cadenasso M L. 2009. Objectbasedland cover classification of shaded areas in high spatialresolution imagery of urban areas: A comparison study.Remote Sensing of Environment, 113, 1769-1777. |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
