International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B7. Istanbul 2004 
The following developments may be considered in the future: 
The GeoCover Orthorectified Landsat Thematic Mapper 
Mosaics (Figure 3) are delivered in a Universal Transverse 
Mercator (UTM) / World Geodetic System 1984 (WGS84) 
projection. These mosaics will be used to georeference the 
satellite images using Automatic image registration system 
(Figure 4). 
  
Figure 3- GeoCover Mosaic - Chart S.20-00 
(https://zulu.ssc.nasa.gov/mrsid/) 
  
  
005106 
a trace [oor] 
ve 
  
    
  
  
  
  
  
Figure 4 - Automatic image registration system 
(http://regima.dpi.inpe.br). 
4. REFERENCES 
Alves, D. S.; Mello, E. M. K.; Moreira, J. C.:.Otntiz, 1. 0.; 
Soares, J. V.; Silva, O. F. and Almeida, S. A. S., 1996, 
Characterizing land use dynamics in Amazon using 
multitemporal imagery and segmentation techniques. In: 
Proceedings of the XVIII International Society of 
Photogrammetry and Remote Sensing Congress ( Vienna: 
ISPRS), pp.13-17. 
Bins, L. S., Erthal, G. J., and Fonseca, L. M. G., 1993, Um 
método de classificaçäo näo-supervisionada por regiôes. 
Proceedings of the Sixth Brazilian Symposium on Graphic 
Computation and Image Processing, Recife (Rio de Janeiro: 
Gráfica Wagner), pp. 65-68. 
DSG (DIRETORIA DE SERVICO GEOGRAFICO), Digitais 
Topographic Chart, 1: 100.000. (Rio de Janeiro: DSG). 
Duda, R. O., and Hart, P. E., 1973, Pattern Classification and 
Scene Analysis (New York: Wiley). 
FIBGE (FUNDAÇAO , INSTITUTO BRASILEIRO DE 
GEOGRAFIA E ESTATISTICA), Digitais Topographic Chart, 
1: 100.000. (Rio de Janeiro: FIBGE). 
INPE (Instituto Nacional de Pesquisas Espaciais) 2003, 
PRODES: Assessment of deforestation in Brazilian Amazónia 
(Sáo Paulo: INPE). http://www.obt.inpe.br/prodes/index.html 
(accessed 06 Feb. 2004) 
Mello, E.M.K.; Moreira, J.C.; Santos ,J.R.; Shimabukuro,Y.E.; 
Duarte, V.; Souza,.M.; Barbosa,C.C.; Souza,R.C.M.; Paiva, 
J.A.C. Técnicas de Modelo de Mistura Espectral, Segmentacáo 
e Classificaçäo de Imagens TM-Landsat para o Mapeamento do 
Desflorestamento da Amazónia.. In: X7 Simpósio Brasileiro de 
Sensoriamento Remoto, Belo Horizonte, Brasil, 2003, pp. 2807 
- 2814. 
Moreira, J.C., Mello, E. M. K., Santos J. R. dos, Shimabukuro 
Y. E., Duarte V., Souza, M.L, Barbosa C.C., Souza R. C. M. 
de., Paiva J.A.C. “Sistema de Informaçôes Georreferenciadas do 
Desflorestamento da Amazônia”.GISBRASIL2003, Säo Paulo- 
SP, 2003. 
Shimabukuro, Y. E. and Smith, J. A., 1991, The least-squares 
mixing models to generate fraction images derived from remote 
sensing multispectral data. /.E.E.E. Transactions on Geoscience 
and Remote Sensing, 29, pp.16-20. 
Shimabukuro, Y. E.; Batista, G. T.; Mello E. M. K.; Moreira, J. 
C. and Duarte, V. Using shade fraction image segmentation to 
evaluate deforestation in Landsat Thematic Mapper images of 
the Amazon Region. /NT. J. REMOTE SENSING, 1998, Vol. 
19, no. 3, pp.535-541 
Zucker, S. W., 1976, Region growing: Childhood and 
adolescence. Computer Graphics and Image Processing, 5, pp. 
382-399. 
5. ACNOWLEDGMENTS: 
The authors would like to acknowledge the comments of Dr. 
Joäo Argemiro de Carvalho Paiva. 
274 
  
KEYW 
ABSTR: 
Followin 
order to 
the land 
keep for 
populatic 
The artic 
fusion m 
The artic 
multi-res 
distributi 
detectior 
investiga 
indices f. 
Finally, 
The eco 
changes 
Most of 
land, wk 
shortage 
In order 
aid the g 
it’s very 
changes 
In 1999, 
Landuse 
this pro 
populati 
In the 5 
for moni 
20 units 
took or 2