Combining Spectral with Texture Features into Object- oriented Classification in Mountainous Terrain Using Advanced Land Observing Satellite Image

Most existing classification studies use spectral information and those were adequate for cities or plains. This paper explores classification method suitable for the ALOS (Advanced Land Observing Satellite) in mountainous terrain. Mountainous terrain mapping using ALOS image faces numerous challenges. These include spectral confusion with other land cover features, topographic effects on spectral signatures (such as shadow). At first, topographic radiometric correction was carried out to remove the illumination effects of topography. In addition to spectral features, texture features were used to assist classification in this paper. And texture features extracted based on GLCM (Gray Level Co-occurrence Matrix) were not only used for segmentation, but also used for building rules. The performance of the method was evaluated and compared with Maximum Likelihood Classification (MLC). Results showed that the object-oriented method integrating spectral and texture features has achieved overall accuracy of 85.73% with a kappa coefficient of 0.824, which is 13.48% and 0.145 respectively higher than that got by MLC method. It indicated that texture features can significantly improve overall accuracy, kappa coefficient, and the classification precision of existing spectrum confusion features. Object-oriented method Integrating spectral and texture features is suitable for land use extraction of ALOS image in mountainous terrain.

[1]  Muhammad Sajid,et al.  SPATIOTEMPORAL ASPECTS OF PLANT COMMUNITY STRUCTURE IN OPEN SCRUB RANGELANDS OF SUB-MOUNTAINOUS HIMALAYAN PLATEAUS , 2010 .

[2]  J. Lawton,et al.  Species interactions, local and regional processes, and limits to the richness of ecological communities : a theoretical perspective , 1992 .

[3]  Wayne T. Swank,et al.  Early Regeneration of a Clear‐Cut Southern Appalachian Forest , 1981 .

[4]  R. DeConto.  Late Cretaceous Climate, Vegetation and Ocean Interactions: AN Earth System Approach to Modeling AN Extreme Climate , 1996 .

[5]  Dirk Tiede,et al.  ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data , 2010, Int. J. Geogr. Inf. Sci..

[6]  A. C. Seijmonsbergen,et al.  Improved landsat-based forest mapping in steep mountainous terrain , 2003 .

[7]  J. Singh,et al.  Replacement of oak forest with pine in the Himalaya affects the nitrogen cycle , 1984, Nature.

[8]  R. S. Tripathi,et al.  Population structure of some tree species in disturbed and protected subtropical forests of north-east India , 1987 .

[9]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Sunil Nautiyal,et al.  Revitalizing drink: An assessment of traditional knowledge system in Bhotiya community of Central Himalayas, India , 2002 .

[11]  Chandra Prakash Kala,et al.  Indigenous uses and structure of chir pine forest in Uttaranchal Himalaya, India , 2004 .

[12]  Samant,et al.  Diversity, extraction and status of fodder species in Askot Wildlife Sanctuary, West Himalaya, India , 2006 .

[13]  D. Lieberman,et al.  Structure and dynamics of a tropical dry forest in Ghana , 1990, Vegetatio.

[14]  G. C. Joshi,et al.  Patterns in litter fall and litter decomposition along an altitudinal gradient in the Binsar Wildlife Sanctuary, Central Himalaya , 2005 .

[15]  John R. Jensen.  Introductory Digital Image Processing , 2004 .

[16]  Ke Wang,et al.  Integration of texture and landscape features into object-based classification for delineating Torreya using IKONOS imagery , 2012 .

[17]  M. Austin,et al.  Current problems of environmental gradients and species response curves in relation to continuum theory , 1994 .

[18]  S. P. Singh,et al.  Biomass, Productivity, Leaf Longevity, and Forest Structure in the Central Himalaya , 1994 .

[19]  L. Hunt,et al.  Low seed availability may limit recruitment in grazed Atriplex vesicaria and contribute to its local extinction , 2001, Plant Ecology.

[20]  R. S. Tripathi,et al.  Tree diversity and population structure in undisturbed and human-impacted stands of tropical wet evergreen forest in Arunachal Pradesh, Eastern Himalayas, India , 2003, Biodiversity & Conservation.

[21]  L. D. Hansen,et al.  Fundamental Causes of the Global Patterns of Species Range and Richness1 , 2003, Russian Journal of Plant Physiology.

[22]  Stevan Harrell,et al.  Ways of Being Ethnic in Southwest China , 2003, The Journal of Asian Studies.

[23]  Uppeandra Dhar,et al.  Biodiversity status of a protected area in West Himalaya: Askot Wildlife Sanctuary , 1998 .

[24]  A. Magurran,et al.  Biological diversity : the coexistence of species on changing landscapes , 1994 .

[25]  Stephen P. Hubbell,et al.  Sapling Survival, Growth, and Recruitment: Relationship to Canopy Height in a Neotropical Forest , 1991 .

[26]  D. Lieberman,et al.  Seedling recruitment patterns in a tropical dry forest in Ghana , 1992 .

[27]  Josep Maria Espelta,et al.  Patterns of seedling recruitment in West‐Mediterranean Quercus ilex forest influenced by canopy development , 1995 .

[28]  C. M. Sharma,et al.  Population Structure and Community Analysis on Different Aspects of Sal Savanna forest Type in Outer Garhwal Himalaya , 2001 .

[29]  P. B. Rao.  Effects of Environmental Factors on Germination and Seedling Growth in Quercus floribunda and Cupressus torulosa, Tree Species of Central Himalaya , 1988 .

[30]  N. Todaria,et al.  Forest vegetation patterns along an altitudinal gradient in sub-alpine zone of west Himalaya, India , 2008 .

[31]  Patrice Levang,et al.  Research, part of a Special Feature on Public policies and management of rural forests: lasting alliance or fool's dialogue? Are Local People Conservationists? Analysis of Transition Dynamics from Agroforests to Monoculture Plantations in Indonesia , 2010 .

[32]  T. Lin,et al.  The Lambertian assumption and Landsat data. , 1980 .

[33]  N. V. Joshi,et al.  Dynamics of a tropical deciduous forest: population changes (1988 through 1993) in a 50-ha plot at Mudumalai, southern India , 1998 .

[34]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[35]  Stephen V. Stehman,et al.  Design and Analysis for Thematic Map Accuracy Assessment: Fundamental Principles , 1998 .

[36]  Uppeandra Dhar,et al.  Epiphytic Orchids of Askot Wildlife Sanctuary in Kumaun Himalaya, India: Conservation Imperatives , 1995, Environmental Conservation.

[37]  R. G. Smith,et al.  The biology and silviculture of pruning planted eucalypts for clear wood production—a review , 2003 .

[38]  P. Aplin,et al.  On scales and dynamics in observing the environment , 2006 .

[39]  Pieter A. Zuidema,et al.  Climate is a stronger driver of tree and forest growth rates than soil and disturbance , 2011 .

[40]  Christian Körner,et al.  A re-assessment of high elevation treeline positions and their explanation , 1998, Oecologia.

[41]  Kristofer R. Covey,et al.  Tree species richness and the logging of natural forests: A meta-analysis , 2012 .

[42]  R. S. Tripathi,et al.  Biodiversity Conservation in Sacred Groves of Manipur, Northeast India: Population Structure and Regeneration Status of Woody Species , 2006, Biodiversity & Conservation.

[43]  Meredith Welch-Devine,et al.  Hard choices: Making trade-offs between biodiversity conservation and human well-being , 2011 .

[44]  S. S. Samant,et al.  Threat categorisation and conservation prioritisation of floristic diversity in the Indian Himalayan region: A state of art approach from Manali Wildlife Sanctuary , 2010 .

[45]  D. He,et al.  Texture analysis of IKONOS satellite imagery for urban land use and land cover classification , 2010 .

[46]  Carl Folke,et al.  Indigenous Knowledge for Biodiversity Conservation , 1993 .

[47]  J. Dymond,et al.  Correcting satellite imagery for the variance of reflectance and illumination with topography , 2003 .

[48]  Peter M. Brown,et al.  Potential for Developing Fire Histories in Chir Pine (Pinus roxburghii) Forests in the Himalayan Foothills , 2011 .

[49]  Paul J. Schulte,et al.  Growth and water relations of black locust and pine seedlings exposed to controlled water stress , 1983 .

[50]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[51]  Geeta Kharkwal,et al.  Qualitative analysis of tree species in evergreen forests of Kumaun Himalaya, Uttarakhand, India , 2009 .

[52]  D. Milchunas,et al.  Quantitative Effects of Grazing on Vegetation and Soils Over a Global Range of Environments , 1993 .

[53]  Chandra Prakash Kala,et al.  Forest structure and regeneration along the altitudinal gradient in the Binsar Wildlife Sanctuary, Uttarakhand Himalaya, India , 2010, Russian Journal of Ecology.

[54]  Craig A. Coburn,et al.  A multiscale texture analysis procedure for improved forest stand classification , 2004 .

[55]  Bert Guindon,et al.  Landsat urban mapping based on a combined spectral–spatial methodology , 2004 .

[56]  R. Semwal,et al.  ECOLOGY OF FOREST FIRES IN CHIR PINE (PINUS ROXBURGHII SARG.) FORESTS OF GARHWAL HIMALAYA , 1996 .

[57]  S. P. Singh,et al.  Forest vegetation of the Himalaya , 2008, The Botanical Review.

[58]  F. Ulaby,et al.  Textural Infornation in SAR Images , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[59]  R. K. Maikhuri,et al.  Paradigm and ecological implication of changing agricultural land-use: A case study from Govind Wildlife Sanctuary, Central Himalaya, India , 2012, Journal of Mountain Science.

[60]  Frank D. Irving,et al.  Prescribed burning for lowland black spruce regeneration in northern Minnesota , 1984 .

[61]  B. H. Janssen,et al.  Soil fertility in Africa is at stake , 1997 .

[62]  M. Kuhle,et al.  Review on dating methods: Numerical dating in the quaternary geology of High Asia , 2010 .

[63]  D. J. Mead,et al.  Effects of pruning and understorey vegetation on crown development, biomass increment and above-ground carbon partitioning in Pinus radiata D. Don trees growing at a dryland agroforestry site , 1999 .

[64]  Hermann Kaufmann,et al.  Comparison of Topographic Correction Methods , 2009, Remote. Sens..

[65]  Bruce C. Larson,et al.  Forest Stand Dynamics , 1990 .

[66]  Shreekar Pant,et al.  Population ecology of the endangered Himalayan Yew in Khokhan Wildlife Sanctuary of North Western Himalaya for conservation management , 2008 .

[67]  K. Yoda,et al.  Climate and vegetation in China II. Distribution of main vegetation types and thermal climate , 1989, Ecological Research.

[68]  H. N. Pandey,et al.  Dynamics of tree seedling populations in a humid subtropical forest of northeast India as related to disturbance , 1996 .

[69]  M. L. Khan,et al.  Effects of seed weight and microsite characteristics on germination and seedling fitness in two species of quercus in a subtropical wet Hill forest , 1990 .

[70]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[71]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[72]  J. Nichol,et al.  Topographic correction for differential illumination effects on IKONOS satellite images , 2004 .

[73]  R. S. Tripathi,et al.  Effects of stump diameter, stump height and sprout density on the sprout growth of four tree species in burnt and unburnt forest plots , 1989 .

[74]  S. Harrell,et al.  Mountain patterns : the survival of Nuosu culture in China , 2000 .

[75]  S. K. Seth,et al.  General silviculture for India , 1968 .

[76]  F. Parmiggiani,et al.  An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters , 1995, IEEE Transactions on Geoscience and Remote Sensing.

[77]  W. H. Rickard,et al.  Alien taxa in the North American shrub-steppe four decades after cessation of livestock grazing and cultivation agriculture , 1994 .

[78]  Sharad Singh Negi.  Uttarakhand: Land and people , 1995 .

[79]  Wang Zhi.  A Description Based on Texture Direction and the Clustering and Segmentation to Directional Texture Images , 2002 .

[80]  Pooja Uniyal,et al.  Regeneration status of tree species in forest of Phakot and Pathri Rao watersheds in Garhwal Himalaya. , 2010 .

[81]  Hoe I. Ling,et al.  Debris Flow Discharge Calculation and Inundation Simulation , 2011 .

[82]  Om Prakash Tripathi,et al.  Effect of disturbance on the regenera- tion of four dominant and economically important woody species in a broad- leaved subtropical humid forest of Meghalaya, northeast India , 2003 .

[83]  Michael R. Dove,et al.  Theories of swidden agriculture, and the political economy of ignorance , 1983, Agroforestry Systems.

[84]  Am Mudabeti,et al.  Remote sensing 1 , 2013 .

[85]  Chaur-Chin Chen,et al.  Markov random fields for texture classification , 1993, Pattern Recognit. Lett..

[86]  Tetsuji Ota,et al.  Influence of using texture information in remote sensed data on the accuracy of forest type classification at different levels of spatial resolution , 2011, Journal of Forest Research.

[87]  Peijun Li,et al.  Land cover classification using CHRIS/PROBA images and multi-temporal texture , 2012 .

[88]  Sunil Nautiyal,et al.  Analysis and resolution of protected area–people conflicts in Nanda Devi Biosphere Reserve, India , 2000, Environmental Conservation.

[89]  Xiangguo Lin,et al.  Cropland Extraction from Very High Spatial Resolution Satellite Imagery by Object-Based Classification Using Improved Mean Shift and One-Class Support Vector Machines , 2011 .

[90]  Steward T. A. Pickett,et al.  Plant litter: Its dynamics and effects on plant community structure , 2008, The Botanical Review.

[91]  Peter J. Weisberg,et al.  Land-use history and topographic gradients as driving factors of subalpine Larix decidua forests , 2013, Landscape Ecology.