Mapping land cover types in Amazon basin using 1 km JERS-1 mosaic
Summary (1 min read)
Summary
- The 100 meter JERS-I Amazon mosaic image was used in a new classifier to generate a 1 km resolution land cover map.
- The inputs to the classifier were lkm resolution mean backscatter and seven first order texture measures derived from the 100 m data by using a 10 x 10 independent sampling window.
- The classification approach included two interdependent stages: 1) a supervised maximum a posteriori Baysian approach to classify the mean backscatter image into 5 general land cover catagories of forest, savanna, inundated, white sand, and anthropogenic vegetation classes, and 2) a texture measure decision rule approach to further discriminate subcatagory classes based on taxonimc information and biomass levels.
- Fourteen classes were successfully separated at lkm scale.
- The results were verified by examining the accuracy of the approach by comparison with the IBGE and the AVHRR 1 km resolution land.
Did you find this useful? Give us your feedback
Citations
10 citations
9 citations
Cites methods or result from "Mapping land cover types in Amazon ..."
...Although both studies employed radar imageries, Roberts et al. (2003) used a diversity of satellite sensors and Saatchi et al. (2000) compared the results with maps from other data sources and sensors....
[...]
...Alternatively, the SOM approach may have classified LUCC studies published after 2000 using radar imageries in tropical forests into other clusters, such as Saatchi et al. (2000) and Roberts et al. (2003) in the adjacent cluster 6.2....
[...]
7 citations
Cites methods from "Mapping land cover types in Amazon ..."
...Textural measures can be extracted from diVerent order histograms of an image using various degrees of statistics (Haralick et al. 1973, Anys and He 1995, Saatchi et al. 2000)....
[...]
6 citations
Cites background from "Mapping land cover types in Amazon ..."
...The GLCM is a twodimensional histogram of grey levels for pairs of pixels (reference and neighbour) that are separated by a fixed spatial relationship....
[...]
...Although most of the texture measures are computed from the GLCM directly, some texture measures are computed from a difference vector (grey level difference vector GLDV), which itself is derived from a GLCM. Texture measures should only be extracted from single-look images (Oliver and Quegan, 1998)....
[...]
...In Table 2, the different texture measures that may be generated from the GLCM are described....
[...]
...A common paradigm for measuring texture is the grey level cooccurrence matrix (GLCM) (Dutra and Huber, 1999; Saatchi et al., 2000; De Grandi et al., 2000)....
[...]
...Since all current commercial data are acquired at a single polarization and frequency, the most common profile in research is multitemporal analysis (Brown et al., 1993; Wooding, 1995; Borgeaud and Wegmueller, 1996; Schotten et al., 1995; Kurosu et al., 1997; Cloutis et al., 1999; Tso and Mather, 1999; Ban and Howarth, 1999; Saatchi et al., 2000)....
[...]
References
1,574 citations
"Mapping land cover types in Amazon ..." refers methods in this paper
...High resolution (30 m) Landsat Thematic Mapper (TM) data has been the primary source for estimating the rate of deforestation by INPE (Instituto Nacional de Pesquisas Espaciais) and the Landsat Pathfinder Program (Skole and Tucker, 1993; Justice and Townshend, 1994)....
[...]
625 citations
480 citations
452 citations