%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.23.19.30.09
%2 sid.inpe.br/marte2/2017/10.23.19.30.10
%@isbn 978-85-17-00088-1
%F 59498
%T Estudo comparativo de dois métodos para a contagem de árvores em mosaicos de fotografias obtidas por VANT
%D 2017
%A Mlenek, Dyeison Cesar,
%A Centeno, Jorge Antonio Silva,
%A Silva, Luís Fernando Da,
%A Cosiaki, Luis Guilherme,
%@electronicmailaddress guilhermeluislg@yahoo.com.br
%E Gherardi, Douglas Francisco Marcolino,
%E Aragão, Luiz Eduardo Oliveira e Cruz de,
%B Simpósio Brasileiro de Sensoriamento Remoto, 18 (SBSR)
%C Santos
%8 28-31 maio 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 1099-1106
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X The problem of extracting features in digital images has been, for a long time, a very large challenge in various areas of engineering. For example, Kovalevskii (1967) used the dynamic programming algorithm to extract tipografados characters and manuscripts. The use of small format digital cameras aboard unmanned aerial vehicles UAV is a popular option for the mapping of tree plantations as a tool for forest management. This article describes a comparative study of two methods for counting trees in mosaics of photographs obtained by VANT. The first method is the well-known classification supervised and the second is a method based on segmentation and classification of segments after the image be transformed to a most advantageous color system that allows the derivation of an index of vegetation. The results show that both methods are capable of producing equivalent results, but the method of segmentation is faster and easy to apply. The results presented by both methods show that the methods used are not totally accurate, but rather tools for an estimate close to reality. In general the methods pose a good estimate for the solution of the problem, and can the undertaking in question employ both. With that concluded that the results are satisfactory.
%9 Floresta e outros tipos de vegetação
%@language pt
%3 59498.pdf