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.

/pdf/a-survey-of-image-classification-methods-and-techniques-for-5bc5ltr9dq.pdf

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

The amount and spatial distribution of forest biomass in the Amazon basin is a major source of uncertainty in estimating the flux of carbon released from land-cover and land-use change. Direct measurements of aboveground live biomass (AGLB) are limited to small areas of forest inventory plots and site-specific allometric equations that cannot be readily generalized for the entire basin. Furthermore, there is no spaceborne remote sensing instrument that can measure tropical forest biomass directly. To determine the spatial distribution of forest biomass of the Amazon basin, we report a method based on remote sensing metrics representing various forest structural parameters and environmental variables, and more than 500 plot measurements of forest biomass distributed over the basin. A decision tree approach was used to develop the spatial distribution of AGLB for seven distinct biomass classes of lowland old-growth forests with more than 80% accuracy. AGLB for other vegetation types, such as the woody and herbaceous savanna and secondary forests, was directly estimated with a regression based on satellite data. Results show that AGLB is highest in Central Amazonia and in regions to the east and north, including the Guyanas. Biomass is generally above 300Mgha(sup 1) here except in areas of intense logging or open floodplains. In Western Amazonia, from the lowlands of Peru, Ecuador, and Colombia to the Andean mountains, biomass ranges from 150 to 300Mgha(sup 1). Most transitional and seasonal forests at the southern and northwestern edges of the basin have biomass ranging from 100 to 200Mgha(sup 1). The AGLB distribution has a significant correlation with the length of the dry season. We estimate that the total carbon in forest biomass of the Amazon basin, including the dead and below ground biomass, is 86 PgC with +/- 20% uncertainty.

Distribution of Aboveground Live Biomass in the Amazon Basin

Dual-season mapping of wetland inundation and vegetation for the central Amazon basin

408 N. Indiana Avenue, Bloomington, Indiana 47408, USA; e-mail: dlu@indiana.edu(Received 26 October 2004; in final form 28 January 2005)The complicated forest stand structure and associated abundant tree species inthe Amazon often induce difficulty in estimating aboveground biomass (AGB)using remotely sensed data. This paper explores AGB estimation using LandsatThematic Mapper (TM) data in the eastern and western Brazilian Amazon, anddiscusses the impacts of forest stand structure on AGB estimation. EstimatingAGB is still a challenging task, especially for the sites with complicatedbiophysical environments. The TM spectral responses are more suitable for AGBestimation in the sites with relatively simple forest stand structure than for thesites with complicated forest stand structure. Conversely, textures appear moreimportant than spectral responses in AGB estimation in the sites withcomplicated forest stand structure. A combination of spectral responses andtextures improves AGB estimation performance. Different study areas havingvarious biophysical conditions affect AGB estimation performance.

Aboveground biomass estimation using Landsat TM data in the

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.

Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon

In this paper, a multiscale texture-based classifier for mapping tropical forest land cover types is discussed. The classifier was implemented using the Japanese Earth Remote Sensing Satellite (JERS-1) 100 m resolution radar data acquired over the Amazon Rainforest as part of the Global Rainforest Mapping (GRFM) Project. Demonstrated here is the use of the information content present in different texture measurements at different scales to separate three categories of land cover types: forest from nonforest, terre firme from floodplain vegetation, and grassland from woodland savanna. Various combinations of first-order image statistics known as texture measures were used at different scales as feature dimensions to aid the class discrimination. Eight of the most common first-order texture measures found in the literature were used. The best combination of texture measures at each scale were determined by employing a class separability test using the Bhattachuryya distance. The results were then used as in...

E. Podest

Papers

Application of multiscale texture in classifying JERS-1 radar data over tropical vegetation