Ramón Moreno

Extreme learning machines for soybean classification in remote sensing hyperspectral images

This paper focuses on the application of Extreme Learning Machines (ELM) to the classification of remote sensing hyperspectral data. The specific aim of the work is to obtain accurate thematic maps of soybean crops, which have proven to be difficult to identify by automated procedures. The classification process carried out is as follows: First, spectral data is transformed into a hyper-spherical representation. Second, a robust image gradient is computed over the hyper-spherical representation allowing an image segmentation that identifies major crop plots. Third, feature selection is achieved by a greedy wrapper approach. Finally, a classifier is trained and tested on the selected image pixel features. The classifiers used for feature selection and final classification are Single Layer Feedforward Networks (SLFN) trained with either the ELM or the incremental OP-ELM. Original image pixel features are computed following a Functional Data Analysis (FDA) characterization of the spectral data. Conventional ELM training of the SLFN improves over the classification performance of state of the art algorithms reported in the literature dealing with the data treated in this paper. Moreover, SLFN-ELM uses less features than the referred algorithms. OP-ELM is able to find competitive results using the FDA features from a single spectral band.

Linked multi-component mobile robots: Modeling, simulation and control

The Linked Multi-Component Robotic Systems (L-MCRS) consists of a group of mobile robots carrying a passive uni-dimensional object (a hose or a wire). It is a recently identified unexplored and unexploited category of multi-robot systems. In this paper we report the first effort on the modeling, control and visual servoing of L-MCRS. Modeling has been tackled from geometrical and dynamical points of view. The passive element is modeled by splines, and the dynamical modeling is achieved by the appropriate extension of Geometrically Exact Dynamic Splines (GEDS). The systems modeling allows realistic simulation, which can be used as a test bed for the evaluation of control strategies. In this paper we evaluate two such control strategies: a baseline global controller, and a fuzzy local controller based on the observation of the hose segment between two robots. Finally, we have performed physical experiments on a team of robots carrying a wire under a visual servoing scheme that provides the perceptual information about the hose for the fuzzy local controller. Visual servoing robust image segmentation is grounded in the Dichromatic Reflection Model (DRM).

A machine learning based intelligent vision system for autonomous object detection and recognition

Existing object recognition techniques often rely on human labeled data conducting to severe limitations to design a fully autonomous machine vision system. In this work, we present an intelligent machine vision system able to learn autonomously individual objects present in real environment. This system relies on salient object detection. In its design, we were inspired by early processing stages of human visual system. In this context we suggest a novel fast algorithm for visually salient object detection, robust to real-world illumination conditions. Then we use it to extract salient objects which can be efficiently used for training the machine learning-based object detection and recognition unit of the proposed system. We provide results of our salient object detection algorithm on MSRA Salient Object Database benchmark comparing its quality with other state-of-the-art approaches. The proposed system has been implemented on a humanoid robot, increasing its autonomy in learning and interaction with humans. We report and discuss the obtained results, validating the proposed concepts.

Convex Coordinates From Lattice Independent Sets for Visual Pattern Recognition

One of the key processes in nowadays intelligent systems is feature extraction. It pervades applications from computer vision to bioinformatics and data mining. The purpose of this chapter is to introduce a new feature extraction process based on the detection of extremal points on the cloud of points that represent the high dimensional data sample. These extremal points are assumed to define an approximation to the convex hull covering the data sample points. The features extracted are the coordinates of the data points relative to the extremal points, the convex coordinates. We have experimented this approach in several applications that will be summarized in the chapter.

An image color gradient preserving color constancy

We present a color gradient with good color constancy preservation properties. The approach does not need a priori information or changes in color space. It is based on the angular distance between pixel color representations in the RGB space. It is naturally invariant to intensity magnitude, implying high robustness against bright spots produced be specular reflections and dark regions of low intensity.

Hybrid color space transformation to visualize color constancy

Color constancy and chromatic edge detection are fundamental problems in artificial vision In this paper we present a way to provide a visualization of color constancy that works well even in dark scenes where such humans and computer vision algorithms have hard problems due to the noise The method is an hybrid and non linear transform of the RGB image based on the assignment of the chromatic angle as the luminosity value in the HSV space This chromatic angle is defined on the basis of the dichromatic reflection model, having thus a physical model supporting it.

A Color Transformation for Robust Detection of Color Landmarks in Robotic Contexts

We present in this work a robust color transformation which has been applied succesfully to natural scenes allowing the fast and precise segmentation of regions corresponding to color landmarks under uncontrolled lightning. The process is grounded in the the Dichromatic Reflexion Model (DRM) and the properties of the RGB space.

Segmentation of Hyperspectral Images by Tuned Chromatic Watershed

This work presents a segmentation method for multidimensional images, therefore it is valid for standard Red, Green, Blue (RGB) images, multi-spectral images or hyperspectral images. On the one hand it is based in a tuned version of watershed transform, and on the other hand it is based on a chromatic gradient that is made through Hyperspherical Coordinates. A remarkable feature of this algorithm is its robustness; it outperforms the natural oversegmentation induced by the standard watershed. Another important property of this algorithm is its robustness respect changes on the intensity: shines and shadows. Inspired on the Human Vision System (HVS) this algorithm provides segmentations according with the user expectations, where homogeneous chromatic regions of an image corespond with homogeneous convex regions of the output.

A hybrid color distance for image segmentation

Our hybrid color distance is inspired in the human vision system, simulating the sensitivity to intensity and chromaticity of the the retinas cells: cones and rods. This approach provides excellent edge detection and is the core of our method. The segmentation output depends on the hybrid distance parameters, whose values define the segmentation method balance between intensity and chromaticity preference.

Experiments on Robotic Multi-agent System for Hose Deployment and Transportation

We call Linked Multi-Component Robotic Systems (L-MCRS) to a collection of autonomous mobile robots linked through a passive non-rigid physical element. The most basic question about these systems is wether the linking element introduces some differential properties and behaviors that distinguish the L-MCRS from a group of disconnected robots. To answer this question we have modeled the simplest L-MCRS, where the linking element is modeled as a compresible spring, under a distributed cooperative control of the robot units assuming perfect knowledge of their positions. The system’s simulated task is that of trasporting a hose-like object. The simulation results show that the linking element introduces specific dynamical effects, which the cooperative control can not cope with, so the perturbations in one component’s behavior are propagated to the entire system. We also report a proof-ofconcept experiment with a collection of mobile robots autonomously controlled performing the hose transportation along a linear trajectory