Classification Of High-resolution Imagery Research Articles

Classification of high resolution imagery based on fusion of multiscale texture features

In high resolution data classification process, combining texture features with spectral bands can effectively improve the classification accuracy. However, the window size which is difficult to choose is regarded as an important factor influencing overall classification accuracy in textural classification and current approaches to image texture analysis only depend on a single moving window which ignores different scale features of various land cover types. In this paper, we propose a new method based on the fusion of multiscale texture features to overcome these problems. The main steps in new method include the classification of fixed window size spectral/textural images from 3×3 to 15×15 and comparison of all the posterior possibility values for every pixel, as a result the biggest probability value is given to the pixel and the pixel belongs to a certain land cover type automatically. The proposed approach is tested on University of Pavia ROSIS data. The results indicate that the new method improve the classification accuracy compared to results of methods based on fixed window size textural classification.

Historic land cover change in the agricultural Midwest using an object-based approach for classification of high-resolution imagery

A semiautomated classification methodology was implemented using historic, high-resolution aerial photography in a dominant agricultural landscape. An object-based segmentation approach was applied to study land cover change from 1930 through 1990 in Johnson County, Iowa, in the Midwestern United States. A critical analysis of the approach is discussed, emphasizing the ability of the methodology to generate landscape metrics that can accurately characterize the quality of the landscape, particularly the high-resolution landscape features that are so important in a highly modified landscape. Landscape analysis includes a discussion of both the changes in the areal composition of land cover types and also the structural changes that are captured using both patch- and landscape-level metrics. Results were compared with countywide statistics from the United States Department of Agriculture as well as similar landscape studies, and provide evidence of agricultural intensification. Results also indicate some counterintuitive processes occurring from what is expected of a landscape undergoing this type of transformation, suggesting that altering the scale of study may provide different insight into land cover change dynamics.

Efficient Classification of High Resolution Imagery for Urban Area

An efficient method for the unsupervised classification of high resolution imagery is suggested in this paper. It employs pixel-linking and merging based on the adjacency graph. The proposed algorithm uses the neighbor lines of 8 directions to include information in spatial proximity. Two approaches are suggested to employ neighbor lines in the linking. One is to compute the dissimilarity measure for the pixel-linking using information from the best lines with the smallest non. The other is to select the best directions for the dissimilarity measure by comparing the non-homogeneity of each line in the same direction of two adjacent pixels. The resultant partition of pixel-linking is segmented and classified by the merging based on the regional and spectral adjacency graphs. This study performed extensive experiments using simulation data and a real high resolution data of IKONOS. The experimental results show that the new approach proposed in this study is quite effective to provide segments of high quality for object-based analysis and proper land-cover map for high resolution imagery of urban area.

Object-oriented Classification of High Resolution Imagery Based on Watershed Transform and Spatial Clustering

Object-oriented classification of high spatial resolution remote sensing imagery is a very popular theme in the field of remote sensing science.A new approach of object-oriented combining improved water-shed transform with spatial clustering is proposed to classify high resolution remote sensing imagery in this paper.Firstly,gradient image is obtained by applying phase congruency model to the QuickBird panchro-matic image with log Gabor wavelet filters from multi-scale and multi-direction.Extended minima trans-form and minima imposition are used to get foreground marking of interesting objects and present gradient reconstruction,thus to achieve better segmentation using watershed transform based on these improvement measures.Secondly,spectral feature is obtained from multi-spectral remote sensing images,texture vector is achieved by Gabor wavelet and selected by Independence Component Analyses,and clustering based on the two features of objects.Finally,topological relationships between objects are fully considered in order to classify the uncertain objects after the former clustering.Results of experiments demonstrate that the new method can get desired classification results and improve the automatization of remote sensing data classifi-cation to some extent.

Reducing Edge Effects in the Classification of High Resolution Imagery

Edge effects have been a problem in image classification especially when scale-based textural methods were included in the classification process. This paper proposes a new approach to reducing edge effects. The essence of the new approach is that all pixels in a moving window make use of the textural information instead of only the center pixel as in the traditional moving window method. The performance of the new approach was tested in three classification scenarios. The results show that the new approach generally produced higher accuracy with larger window size and was much less affected by the edge issues than the traditional moving window method. The new approach yields satisfactory results as long as the window size is smaller than the land-use polygons and the class boundaries are not too complex.

Integração de dados de sensoriamento remoto multi resoluções para a representação da cobertura da terra utilizando campos contínuos de vegetação e classificação por árvores de decisão

Este trabalho objetiva desenvolver uma metodologia de integração de multisensores para um sistema de monitoramento da Amazônia. O sistema proposto baseia-se no Vegetation Continuous Fields (VCF) que utiliza um algoritmo de árvore de decisão. O algoritmo utiliza um conjunto de variáveis independentes, no caso métricas multitemporais do MODIS, para recursivamente particionar uma variável dependente, no caso dados de treinamentos provenientes de classes de uso da terra, em subconjuntos, que maximizam a redução do quadrado da soma residual. Os dados de treinamentos são obtidos pela classificação de imagens de alta resolução (Landsat/TM, ETM+ e CBERS 2/CCD). Neste estudo, um algoritmo foi desenvolvido a partir da linguagem IDL, no programa ENVI, e uma rotina estatística do programa S-PLUS. A área de estudo é o Estado do Mato Grosso com uma extensa área de cobertura de Floresta Amazônica. As cenas são classificadas em três classes: floresta, não floresta e água. Comparações do produto final com o mapa regional de uso da terra derivado do PRODES revelam uma concordância geral. Portanto, os resultados desse estudo sugerem que a metodologia é apropriada para a determinação da cobertura da terra na Floresta Amazônica.

Segmentation and classification of high resolution imagery for mapping individual species in a closed canopy, deciduous forest

In this paper we investigate the use of a shadow-based delineation program for identifying segments in imagery of a closed canopy, deciduous forest, in West Virginia, USA, as a way to reduce the noise associated with per-pixel classification in forested environments. Shadows typically cluster along the boundaries of trees and therefore can be used to provide a network of nodes for the delineation of segments. A minimum cost path algorithm, where cost is defined as the cumulative sum of brightness values traversed along the connecting route, was used to connect shadow clumps. To test this approach, a series of classifications was undertaken using a multispectral digital aerial image of a six hectare test site and a minimum cost path segmentation. Three species were mapped: oaks, red maple and yellow poplar. The accuracy of an aspatial maximum likelihood classification (termed PERPIXEL classification) was 68.5%, compared to 74.0% for classification using the mean vector of the segments identified with the minimum cost path algorithm (MEAN_SEG), and 78% when the most common class present in the segment is assigned to the entire segment (POSTCLASS_SEG). By comparison, multispectral classification of the multispectral data using the field-mapped polygons of individual trees as segments, produced an accuracy of 82.3% when the mean vector of the polygon was used for classification (MEAN_TREE), and 85.7% when the most common class was assigned to the entire polygon (POSTCLASS_TREE). A moving window-based post-classification majority filter (POSTCLASS_MAJ5BY5) produced an intermediate accuracy value, 73.8%. The minimum cost path segmentation algorithm was found to correctly delineate approximately 28% of the trees. The remaining trees were either segmented, aggregated, or a combination of both segmented and aggregated. Varying the threshold that was used to discriminate shadows appeared to have little effect on the number of correctly delineated trees, or on the overall accuracy of the multispectral classification, although it did have a notable effect on the proportions of aggregated and segmented trees.