Traditional image classification algorithms are mainly divided into unsupervised and supervised paradigms. In the first paradigm, algorithms are designed to automatically estimate the classes’ distributions in the feature space. The second paradigm depends on the knowledge of a domain expert to identify representative examples from the image to be used for estimating the classification model. Recent improvements in human-computer interaction (HCI) enable the construction of more intuitive graphic user interfaces (GUIs) to help users obtain desired results. In remote sensing image classification, GUIs still need advancements. In this work, we describe our efforts to develop an improved GUI for selecting the representative samples needed to estimate the classification model. The idea is to identify changes in the common strategies for sample selection to create a user-driven sample selection, which focuses on different views of each sample, and to help domain experts identify explicit classification rules, which is a well-established technique in geographic object-based image analysis (GEOBIA). We also propose the use of the well-known nearest neighbor algorithm to identify similar samples and accelerate the classification.

As imagens da série de satélites CBERS são distribuídas gratuitamente, mas para que seja possível utilizá-las, é necessário aplicar um método de correção geométrica. É proposta uma melhoria do processo de correção automática de forma a selecionar as melhores amostras de referência a partir das quais é possível definir pontos de controle usados para o cálculo dos parâmetros do modelo usado na correção. Para demonstrar a eficácia, o método proposto é aplicado em um conjunto de imagens CBERS usando as amostras de imagens selecionadas.

Image registration is the process of overlaying two or more images of the same scene taken at different times, from different viewpoints, and/or different sensors. With the increase in the number of images collected every day from different sensors, automated registration of multi-sensor, multi-spectral and multi-temporal images has become an important application. In this paper an efficient algorithm for the registration of multi-temporal images with similar spectral responses is proposed. The procedure relies on the gray level information content of the images and their local wavelet transform modulus maxima. The registration algorithm is performed at progressively higher resolutions, which allows for faster implementation and higher registration precision. For the matching process, a novel procedure for automatic point feature detection based on wavelet transform is presented. Moreover, an investigation about the performance of four similarity measures in the task of feature point matching for satellite images is also presented. The results show that the matching method based on correlation is efficient to register images of similar spectral responses even if multi-temporal changes are present. To overcome the presence of rotation angle between the images to be registered, a procedure to estimate this angle is performed before the matching process. Measurements of performance are provided, as well as extensive experimental results, to illustrate the qualitative performance of the registration algorithm. Images of different sensors and acquisition time are used in the experiments.