Dengsheng Lu

A survey of image classification methods and techniques for improving classification performance

Image classification is a complex process that may be affected by many factors. This paper examines current practices, problems, and prospects of image classification. The emphasis is placed on the summarization of major advanced classification approaches and the techniques used for improving classification accuracy. In addition, some important issues affecting classification performance are discussed. This literature review suggests that designing a suitable image‐processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map. Effective use of multiple features of remotely sensed data and the selection of a suitable classification method are especially significant for improving classification accuracy. Non‐parametric classifiers such as neural network, decision tree classifier, and knowledge‐based classification have increasingly become important approaches for multisource data classification. Integration of remote sensing, geographical information systems (GIS), and expert system emerges as a new research frontier. More research, however, is needed to identify and reduce uncertainties in the image‐processing chain to improve classification accuracy.

The potential and challenge of remote sensing‐based biomass estimation

Remotely sensed data have become the primary source for biomass estimation. A summary of previous research on remote sensing‐based biomass estimation approaches and a discussion of existing issues influencing biomass estimation are valuable for further improving biomass estimation performance. The literature review has demonstrated that biomass estimation remains a challenging task, especially in those study areas with complex forest stand structures and environmental conditions. Either optical sensor data or radar data are more suitable for forest sites with relatively simple forest stand structure than the sites with complex biophysical environments. A combination of spectral responses and image textures improves biomass estimation performance. More research is needed to focus on the integration of optical and radar data, the use of multi‐source data, and the selection of suitable variables and algorithms for biomass estimation at different scales. Understanding and identifying major uncertainties caused by different stages of the biomass estimation procedure and devoting efforts to reduce these uncertainties are critical.

Spectral Mixture Analysis of the Urban Landscape in Indianapolis with Landsat ETM+ Imagery

This paper examines characteristics of urban land-use and land-cover (LULC) classes using spectral mixture analysis (SMA), and develops a conceptual model for characterizing urban LULC patterns. A Landsat Enhanced Thematic Mapper Plus (ETM+) image of Indianapolis City was used in this research and a minimum noise fraction (MNF) transform was employed to convert the ETM+ image into principal components. Five image endmembers (shade, green vegetation, impervious surface, dry soil, and dark soil) were selected, and an unconstrained least-squares solution was used to un-mix the MNF components into fraction images. Different combinations of three or four endmembers were evaluated. The best fraction images were chosen to classify LULC classes based on a hybrid procedure that combined maximum-likelihood and decision-tree algorithms. The results indicate that the SMAbased approach significantly improved classification accuracy as compared to the maximum-likelihood classifier. The fraction images were found to be effective for characterizing the urban landscape patterns.

Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon

The complicated forest stand structure and associated abundant tree species in the Amazon often induce difficulty in estimating aboveground biomass (AGB) using remotely sensed data. This paper explores AGB estimation using Landsat Thematic Mapper (TM) data in the eastern and western Brazilian Amazon, and discusses the impacts of forest stand structure on AGB estimation. Estimating AGB is still a challenging task, especially for the sites with complicated biophysical environments. The TM spectral responses are more suitable for AGB estimation in the sites with relatively simple forest stand structure than for the sites with complicated forest stand structure. Conversely, textures appear more important than spectral responses in AGB estimation in the sites with complicated forest stand structure. A combination of spectral responses and textures improves AGB estimation performance. Different study areas having various biophysical conditions affect AGB estimation performance.

A sub-pixel analysis of urbanization effect on land surface temperature and its interplay with impervious surface and vegetation coverage in Indianapolis, United States

This study developed an analytical procedure based upon a spectral unmixing model for characterizing and quantifying urban landscape changes in Indianapolis, Indiana, the United States, and for examining the environmental impact of such changes on land surface temperatures (LST). Three dates of Landsat TM/ETM+ images, acquired in 1991, 1995, and 2000, respectively, were utilized to document the historical morphological changes in impervious surface and vegetation coverage and to analyze the relationship between these changes and those occurred in LST. Three fraction endmembers, i.e., impervious surface, green vegetation, and shade, were derived with an unconstrained least-squares solution. A hybrid classification procedure, which combined maximum-likelihood and decision-tree algorithms, was developed to classify the fraction images into land use and land cover classes. Correlation analyses were conducted to investigate the changing relationships of LST with impervious surface and vegetation coverage. Results indicate that multi-temporal fraction images were effective for quantifying the dynamics of urban morphology and for deriving a reliable measurement of environmental variables such as vegetation abundance and impervious surface coverage. Urbanization created an evolved inverse relationship between impervious and vegetation coverage, and brought about new LST patterns because of LSTs correlations with both impervious and vegetation coverage. Further researches should be directed to refine spectral mixture modeling by stratification, and by the use of multiple endmembers and hyperspectral imagery.

Extraction of urban impervious surfaces from an IKONOS image

Impervious surface has been recognised as an important indicator in urban environmental assessment. However, accurate extraction of impervious surface information in urban areas is a challenge because of the complexity of impervious materials. This paper explores different approaches for impervious surface extraction with IKONOS imagery in Indianapolis, U.S.A., by using decision tree classifier (DTC) and linear spectral mixture analysis (LSMA). This research indicates that DTC is an effective approach for extraction of different impervious surface classes, including high‐, medium‐ and low‐reflectivity impervious surfaces and that LSMA‐based approach can provide quantitative measure of imperviousness. A critical step is to separate dark impervious objects/features from shadows cast by tall buildings and tree canopy and from water.

Urban classification using full spectral information of landsat ETM+ imagery in Marion County, Indiana

This paper compares different image processing routines to identify suitable remote sensing variables for urban classifi- cation in the Marion County, Indiana, USA, using a Landsat 7 Enhanced Thematic Mapper Plus (ETM� ) image. The ETMmultispectral, panchromatic, and thermal images are used. Incorporation of spectral signature, texture, and surface temperature is examined, as well as data fusion techniques for combining a higher spatial resolution image with lower spatial resolution multispectral images. Results indicate that incorporation of texture from lower spatial resolution images or of a temperature image cannot improve classification accuracies. However, incorporation of textures derived from a higher spatial resolution panchromatic image improves the classification accuracy. In particular, use of data fusion result and texture image yields the best classifi- cation accuracy with an overall accuracy of 78 percent and a kappa index of 0.73 for eleven land use and land cover classes.

COMPARISON OF LAND-COVER CLASSIFICATION METHODS IN THE BRAZILIAN AMAZON BASIN

Four distinctly different classifiers were used to analyze multispectral data. Which of these classifiers is most suitable for a specific study area is not always clear. This paper provides a comparison of minimum-distance classifier (MDC), maximumlikelihood classifier (MLC), extraction and classification of homogeneous objects (ECHO), and decision-tree classifier based on linear spectral mixture analysis (DTC-LSMA). Each of the classifiers used both Landsat Thematic Mapper data and identical field-based training sample datasets in a western Brazilian Amazon study area. Seven land-cover classes— mature forest, advanced secondary succession, initial secondary succession, pasture lands, agricultural lands, bare lands, and water—were classified. Classification results indicate that the DTC-LSMA and ECHO classifiers were more accurate than were the MDC and MLC. The overall accuracy of the DTCLSMA approach was 86 percent with a 0.82 kappa coefficient and ECHO had an accuracy of 83 percent with a 0.79 kappa coefficient. The accuracy of the other classifiers ranged from 77 to 80 percent with kappa coefficients from 0.72 to 0.75.

Land‐cover binary change detection methods for use in the moist tropical region of the Amazon: a comparative study

Many land‐cover change detection techniques have been developed; however, different conclusions about the value or appropriateness of each exist. This difference of opinion is often influenced by the landscape complexity of study areas and data used for analysis. Which method is most suitable for land‐cover change detection in Amazon tropical regions remains unclear. In this paper, 10 binary change detection methods were implemented and compared with respect to their capability to detect land‐cover change and no change conditions in moist tropical regions. They are image differencing (ID), modified image differencing (MID), a combination of image differencing and principal component analysis (IDPCA), principal component differencing (PCD), multitemporal PCA (MPCA), change vector analysis (CVA), vegetation index differencing (VID), image ratioing (IR), modified image ratioing (MIR), and a combination of image ratioing and PCA (IRPCA). Multi‐temporal Thematic Mapper (TM) data were used to conduct land‐cover binary change detection. Research results indicate that MID, PCD and ID using TM band 5 are significantly better than other binary change detection methods and they are recommended specifically for implementation in the Amazon basin.

Land Cover Classification in a Complex Urban-Rural Landscape with Quickbird Imagery.

High spatial resolution images have been increasingly used for urban land use/cover classification, but the high spectral variation within the same land cover, the spectral confusion among different land covers, and the shadow problem often lead to poor classification performance based on the traditional per-pixel spectral-based classification methods. This paper explores approaches to improve urban land cover classification with Quickbird imagery. Traditional per-pixel spectral-based supervised classification, incorporation of textural images and multispectral images, spectral-spatial classifier, and segmentation-based classification are examined in a relatively new developing urban landscape, Lucas do Rio Verde in Mato Grosso State, Brazil. This research shows that use of spatial information during the image classification procedure, either through the integrated use of textural and spectral images or through the use of segmentation-based classification method, can significantly improve land cover classification performance.