Jose A. Piedra-Fernández

Feature Selection in AVHRR Ocean Satellite Images by Means of Filter Methods

Automatic retrieval and interpretation of satellite images is critical for managing the enormous volume of environmental remote sensing data available today. It is particularly useful in oceanography and climate studies for examination of the spatio-temporal evolution of mesoscalar ocean structures appearing in the satellite images taken by visible, infrared, and radar sensors. This is because they change so quickly and several images of the same place can be acquired at different times within the same day. This paper describes the use of filter measures and the Bayesian networks to reduce the number of irrelevant features necessary for ocean structure recognition in satellite images, thereby improving the overall interpretation system performance and reducing the computational time. We present our results for the National Oceanographic and Atmospheric Administration satellite Advanced Very High Resolution Radiometer (AVHRR) images. We have automatically detected and located mesoscale ocean phenomena of interest in our study area (North-East Atlantic and the Mediterranean), such as upwellings, eddies, and island wakes, using an automatic selection methodology which reduces the features used for description by about 80%. Finally, Bayesian network classifiers are used to assess classification quality. Knowledge about these structures is represented with numeric and nonnumeric features.

A Framework for Ocean Satellite Image Classification Based on Ontologies

In this paper we present a framework for ocean image classification based on ontologies. With this aim, we will describe how low and high level content of ocean satellite images can be modeled with an ontology. In addition, we will show how the image classification can be modeled with the ontology in which decision tree based classifiers and rule-based expert systems are represented. Particularly, the rule based expert systems include rules about low-level features (called training and labeling rules), and rules defined from the labeling (called human expert rules). The modeling with the ontology provides an extensible framework in which accommodate several methods of image classification. One of the main aims of our proposal is to provide a mechanism to share data about image classification between applications. We have developed an extensible Protégé plugin to classify images.

Contextual and Hierarchical Classification of Satellite Images Based on Cellular Automata

Satellite image classification is an important technique used in remote sensing for the computerized analysis and pattern recognition of satellite data, which facilitates the automated interpretation of a large amount of information. Today, there exist many types of classification algorithms, such as parallelepiped and minimum distance classifiers, but it is still necessary to improve their performance in terms of accuracy rate. On the other hand, over the last few decades, cellular automata have been used in remote sensing to implement processes related to simulations. Although there is little previous research of cellular automata related to satellite image classification, they offer many advantages that can improve the results of classical classification algorithms. This paper discusses the development of a new classification algorithm based on cellular automata which not only improves the classification accuracy rate in satellite images by using contextual techniques but also offers a hierarchical classification of pixels divided into levels of membership degree to each class and includes a spatial edge detection method of classes in the satellite image.

Fuzzy Content-Based Image Retrieval for Oceanic Remote Sensing

The detection of mesoscale oceanic structures, such as upwellings or eddies, from satellite images has significance for marine environmental studies, coastal resource management, and ocean dynamics studies. Nevertheless, there is a lack of tools that allow us to retrieve automatically relevant mesoscale structures from large satellite image databases. This paper focuses on the development and validation of a content-based image retrieval system to classify and retrieve oceanic structures from satellite images. The images were obtained from the National Oceanic and Atmospheric Administration satellites Advanced Very High Resolution Radiometer sensor. The study area is about W2° - 21°, N19° - 45°. This system conducts labeling and retrieval of the most relevant and typical mesoscale oceanic structures, such as upwellings, eddies, and island wakes located in the Canary Islands area and in the Mediterranean and Cantabrian seas. Our work is based on several soft computing technologies such as fuzzy logic and neurofuzzy systems.

Application of Fuzzy Lattice Neurocomputing (FLN) in Ocean Satellite Images for Pattern Recognition

The main objective of this work is to improve the automated interpretation of ocean satellite images using a fuzzy lattice system that recognizes the most important ocean structures in satellite AVHRR (Advanced Very High Resolution Radiometer) images. This chapter presents a hybrid model based on an expert system segmentation method, a method of correlation-based feature selection, and a few classifiers including Bayesian nets (BN) and fuzzy lattice neural networks. The results obtained by the fuzzy lattice system are clearly better than the results obtained by ANNs (Artificial Neural Nets), knowledge based reasoning systems, and graphic expert system (GES).

OBIA System for Identifying Mesoscale Oceanic Structures in SeaWiFS and MODIS-Aqua Images

The ocean covers over 70% of the surface of our planet and plays a key role in the global climate. Most ocean circulation is mesoscale (scales of 50-500 km and 10-100 days), and the energy in mesoscale circulation is at least one order of magnitude greater than general circulation; therefore, the study of mesoscale oceanic structures (MOS) is crucial to ocean dynamics, making it especially useful for analyzing global changes. The detection of MOS, such as upwellings or eddies, from satellites images is significant for marine environmental studies and coastal resource management. In this paper, we present an object-based image analysis (OBIA) system which segments and classifies regions contained in sea-viewing field-of-view sensor (SeaWiFS) and Moderate Resolution Imaging Spectro-radiometer (MODIS)-Aqua sensor satellite images into MOS. After color clustering and hierarchical data format (HDF) file processing, the OBIA system segments images and extracts image descriptors, producing primary regions. Then, it merges regions, recalculating image descriptors for MOS identification and definition. First, regions are labeled by a human-expert, who identifies MOS: upwellings, eddies, cool, and warm eddies. Labeled regions are then classified by learning algorithms (i.e., decision tree, Bayesian network, artificial neural network, genetic algorithm, and near neighbor algorithm) from selected features. Finally, the OBIA system enables images to be queried from the user interface and retrieved by means of fuzzy descriptors and oceanic structures. We tested our system with images from the Canary Islands and the North West African coast.

A location-based approach to the classification of mesoscale oceanic structures in SeaWiFS and Aqua-MODIS images of Northwest Africa

This study presents a different approach to the classification of Mesoscale Oceanic Structures (MOS) present in the Northwest African area, based on their location. The main improvement stems from the partition of this area in four large zones perfectly differentiated by their morphological characteristics, with attention to seafloor topography and coastal relief. This decomposition makes it easier to recognize structures under adverse conditions, basically the presence of clouds partly hiding them. This is observed particularly well in upwellings, which are usually very large structures with a different morphology and genesis in each zone. This approach not only improves the classification of the upwellings, but also makes it possible to analyse changes in the MOS over time, thereby improving the prediction of its morphological evolution. To identify and label the MOS classified in the Sea-viewing Wide Field-of-view Sensor (SeaWiFS) and Aqua-MODIS (Moderate Resolution Imaging Spectroradiometer) chlorophyll-a and temperature images, we used a tool specifically designed by our group for this purpose and which has again shown its validity in this new proposal.

Locating visual storm signatures from satellite images

Weather forecasting is a problem where an enormous amount of data must be processed. Severe storms cause a significant amount of damages and loss every year in part due to the insufficiency of the current techniques in producing reliable forecasts. We propose an algorithm that analyzes satellite images from the vast historical archives to predict severe storms. Conventional weather forecasting involves solving numerical models based on sensory data. It has been challenging for computers to make forecasts based on the visual patterns from satellite images. In our system we extract and summarize important visual storm evidence from satellite image sequences in a way similar to how meteorologists interpret these images. Particularly, the algorithm extracts and fits local cloud motions from image sequences to model the storm-related cloud patches. Image data of an entire year are adopted to train the model. The historical storm reports since the year 2000 are used as the ground-truth and statistical priors in the modeling process. Experiments demonstrate the usefulness and potential of the algorithm for producing improved storm forecasts.

Hand Posture Recognition with Standard Webcam for Natural Interaction

This paper presents an experimental prototype designed for natural human-computer interaction in an environmental intelligence system. Using computer vision resources, it analyzes the images captured by a webcam to recognize a person’s hand movements. There is now a strong trend in interpreting these hand and body movements in general, with computer vision, which is a very attractive field of research. In this study, a mechanism for natural interaction was implemented by analyzing images captured by a webcam based on hand geometry and posture, to show its movements in our model. A camera is installed in such a manner that it can discriminate the movements a person makes using Background Subtraction. Then hands are searched for assisted by segmentation by skin color detection and a series of classifiers. Finally, the geometric characteristics of the hands are extracted to distinguish defined control action positions.

Adaptive Domotic System in Green Buildings

This paper presents an adaptive domotic system in green buildings. In our case, the data of sensor and devices were controlled in CIESOL center. The adaptive domotic system uses a Fuzzy Lattice Reasoning classifier for predicting building energy performance depending on the user condition. Training and testing of classifiers were carried out with temperature condition data acquired for 4 months (February, May, July and November) in the case building called CIESOL. The results show a high accuracy rates with a mean absolute error between 0% and 0.21%.