An iterative classification approach for mapping natural resources from satellite imagery

Miguel-Ayanz, Jesús San; Biging, Gregory S.

doi:10.1080/01431169608949058

Cited by 32 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a consequence, there are a number of studies from North America with similar scope, methodology and results (Heath 1974, Kilpelä et al 1978, Beaubien 1979, Bryant et al 1980, Walsh 1980, Teillet et al 1981, Congalton et al 1983, Fox et al 1983, Peterson 1983a, Nelson et al 1984, Benson & DeGloria 1985, Williams & Nelson 1986, Cibula & Nyquist 1987, Hudson 1987, Hopkins et al 1988, Franklin & Peddle 1990, Marceau et al 1990, Moore & Bauer 1990, Bolstad & Lillesand 1992, Wilson et al 1994, Ghitter et al 1995, Sader et al 1995. In Scandinavia, several similar studies have been carried out , 1988, Wastenson et al 1981, Häme 1984, Olesen 1991, Colpaert 1993, Mozgeris 1996 as is also the case in other temperate and boreal regions (Schneider & Hirsch 1984, Chamignon & Manière 1990, Groom et al 1996, San Miguel-Ayanzi & Biging 1996.…”

Section: Land Classification (Timber Type Classifications)mentioning

confidence: 79%

Satellite remote sensing for forestry planning—A review

Holmgren

Thuresson

1998

Scandinavian Journal of Forest Research

150

View full text Add to dashboard Cite

Satellite remote sensing for forestry planning-a review. This review attempts, from a critical perspective, to put 25 years of satellite remote sensing research into the context of forestry planning. It is limited to temperate and boreal regions and to remote sensing in the visible and near infra-red spectra. It is structured as follows: firstly, the forestry planning problem is defined and information requirements are identified; secondly, the attempts to use satellite remote sensing as an information source for forestry planning are reviewed, divided into the topics inventory and monitoring; and, finally, the methods for extracting forest information from satellite images are re-examined, and their inherent limitations and methodological weaknesses are discussed.It is concluded that satellite images seldom contain enough information to support the decision process in applied forestry. Although regional level applications may be useful, few successful and reliable applications for local forest inventory, planning or damage monitoring have evolved. Stratification for multi-stage sampling and monitoring of clear-cuts are areas in which satellite images have been shown to be feasible. However, it is doubtful whether the costs involved can be justified for such uses alone. A further conclusion is that many studies have adopted simplistic views of the information needs in the forestry planning process. These studies do not relate the analysis to management decisions, but instead assume that plain and approximate mapping of the forest has a great value. Present developments in the discipline involve complex modelling of reflectance, taking into consideration internal shading, topography and other features, yet without dramatic improvements compared with earlier studies. Furthermore, satellite remote sensing and digital image analysis are no longer technologically spectacular, facts which may affect future research in the discipline. It is, perhaps, time to draw the conclusion that current satellite sensors are not in general suitable for forestry planning, since (a) they contain little relevant information, and (b) for forest management planning purposes there are often more efficient ways of collecting the information required.

show abstract

Section: Land Classification (Timber Type Classifications)mentioning

confidence: 79%

Satellite remote sensing for forestry planning—A review

Holmgren

Thuresson

1998

Scandinavian Journal of Forest Research

150

View full text Add to dashboard Cite

show abstract

“…Mather, 1987). Information gained by ratio transformation is not obtained from either of bands independently (San Miguel-Ayanz and Biging, 1996). For albite discrimination using surface emissivity data (level 2B04), the effective band ratio used in this study area based on the shapes of laboratory emissivity spectrum of albite granite samples and albite mineral spectra is b12/b11.…”

Section: Band Ratiomentioning

confidence: 99%

Processing and interpretation of ASTER TIR data for mapping of rare-metal-enriched albite granitoids in the Central Eastern Desert of Egypt

Aboelkhair

Ninomiya

Watanabe

et al. 2010

Journal of African Earth Sciences

View full text Add to dashboard Cite

“…At each iteration, a band selection process was performed and one or two cover types were classified using that band or bands. Ancillary information, such as elevation, was also used for band selection and classification [12]. Another technique took into account knowledge about sensors, the multiple viewing notion, and the uncertainty and imprecision of models and data modeled with the possibility theory.…”

Section: A Data Fusion For Image Classificationmentioning

confidence: 99%

Information fusion for estimation of summer MIZ ice concentration from SAR imagery

Haverkamp

Tsatsoulis

1999

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-In this paper we define the concept of information fusion and show how we used it to estimate summer sea ice concentration in the marginal ice zone (MIZ) from single-channel SAR satellite imagery. We used data about melt stage, wind speed, and surface temperature to generate temporally-accumulated information, and fused this information with the SAR image, resulting in an interpretation of summer MIZ imagery. We also used the results of previous classifications of the same area to guide and correct future interpretations, thus fusing historical information with imagery and nonimagery data. We chose to study the summer MIZ since summer melt conditions cause classification based upon backscatter intensity to fail, as the backscatter of open water, thin ice, first-year ice, and multiyear ice overlap to a large degree. This makes it necessary to fuse various information and data to achieve proper segmentation and automated classification of the image. Our results were evaluated qualitatively and showed that our approach produces very good ice concentration estimates in the summer MIZ.

show abstract

An iterative classification approach for mapping natural resources from satellite imagery

Cited by 32 publications

References 11 publications

Satellite remote sensing for forestry planning—A review

Satellite remote sensing for forestry planning—A review

Processing and interpretation of ASTER TIR data for mapping of rare-metal-enriched albite granitoids in the Central Eastern Desert of Egypt

Information fusion for estimation of summer MIZ ice concentration from SAR imagery

Contact Info

Product

Resources

About