Simultaneous multi-source and multi-temporal land cover classification using a Compound Maximum Likelihood classifier

نویسندگان

  • Mariane Souza Reis
  • Luciano Vieira Dutra
  • Maria Isabel Sobral Escada
چکیده

The most widely used change detection method is to classify remote sensing images independently for each date, and stack them to form a class sequence vector. However, impossible transitions within the sequences might occur and errors might be accumulated. To solve this, we propose a novel algorithm called Compound Maximum Likelihood (CML), based on the Maximum Likelihood classifier (ML). In CML information from all images is used jointly by considering the a priori probability of each class sequence. The algorithm was tested for Synthetic Aperture Radar and optical images classification in a study area in Pará state, within the Brazilian Amazon. CML presented either similar or very improved accuracy index values over ML land cover classifications. Resumo. O método de detecção de mudanças mais comumumente utilizado é comparar imagens classificadas independentemente para obter vetores de sequências de classes no tempo. No entanto, transições impossı́veis podem ser classificadas e erros são acumulados. Para solucionar esses problemas, propõese o algoritmo de Máxima Verossimilhança Composta (MVC), como uma extensão do classificador de Máxima Verossimilhança (MaxVer). No MVC, todas as imagens são usadas em conjunto, dada a probabilidade a priori de cada sequência de classes. Testou-se o MVC para classificar imagens ópticas e de Radar de Abertura Sintética de uma área do estado do Pará, na Amazônia. O MVC apresentou resultados ou similares ou consideravelmente melhores que MaxVer.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Land Cover Classification Using IRS-1D Data and a Decision Tree Classifier

Land cover is one of basic data layers in geographic information system for physical planning and environmentalmonitoring. Digital image classification is generally performed to produce land cover maps from remote sensing data,particularly for large areas. In the present study the multispectral image from IRS LISS-III image along with ancillary datasuch as vegetation indices, principal componen...

متن کامل

Consistency Analysis of Multi-Source Remotely Sensed Images for Land Cover Classification

The importance of accurately describing the nature of land cover resources is increasing. With the aim to analyze the consistency of remotely sensed images from different sensors for land cover classification, three medium spatial resolution optical image sources in Xuzhou city were classified in the study, including CBERS, ETM, and ASTER. Land cover classification was conducted by Maximum Like...

متن کامل

Land Cover Classification Using Combinations of L- and C-band Sar and Optical Satellite Images

Whereas C-band SAR data mainly provides information on the upper layer of land covers, properties of the lower surfaces can be captured using L-band SAR because of its higher capability of penetration. Moreover, optical imagery illuminates different characteristics of ground surfaces compared to radar images since they are obtained at different frequencies of the electro-magnetic spectrum. Henc...

متن کامل

Classification of Multi-spectral, Multi-temporal and Multi-sensor Images Using Principal Components Analysis and Artificial Neural Networks: Beykoz Case

The thematic maps derived from remotely-sensed images are invaluable sources of information for various investigations since they provide spatial and temporal information about the nature of Earth surface materials and objects. The robustness of classification techniques used to produce these thematic maps can be crucial especially for complex classification problems. This study aims to determi...

متن کامل

مقایسه روش‌های طبقه‌بندی‌کننده حداکثر مشابهت و حداقل فاصله از میانگین در تهیه نقشه پوشش اراضی (مطالعه موردی: استان اصفهان)

Land cover maps derived from satellite images play a key role in regional and national land cover assessments. In order to compare maximum likelihood and minimum distance to mean classifiers, LISS-III images from IRS-P6 satellite were acquired in August 2008 from the western part of Isfahan. First, the LISS-III image was georeferenced. The Root Mean Square error of less than one pixel was the r...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017