Leonardo Enrique Solaque Guzmán

A Comparative Analysis of Weed Images Classification Approaches in Vegetables Crops

This paper exposes a comparative analysis of three weed classification strategies based on area and texture features over images of vegetable crops, focus on provide a technological tool to support farmers in their maintenance tasks. The classification alternatives embrace a basic approach which defines an umbral according to scene features, indeed, a detection with a certain degree of uncertainty on the decision region is purposed and a rigid boundary decision arrangement are exposed. A first mode carries out an unsupervised learning, it uses area and color features with a practical thresholding classifier to differentiate between weed and vegetable classes, the following two, extracts statistical measures of autocorrelation, contrast, correlation and others, from grey level cooccurrence matrices to calculate texture features, next, a principal component analysis is made for dimensionality reduction. These patterns serve as basis for training K-Nearest Neighbor and Support Vector Machine classifiers. The algorithms performance is measured calculating sensitivity (SN), specificity (SP), positive and negative predicted values (PPV and NPV), also, the execution time is stored and tabulated in order to evaluate the proposed methods. Finally, the results show a similar performance of correct classification over 90 and 80% on SN and SP indices respectively, however, approaches present a clear difference in execution time respect of train an evaluation stages.

Procesamiento de imágenes para la identificación de plagas en los cultivos de espinaca

This article on implementing a machine vision process, such as to enable support processes of agriculture. Work is born of the problems presented by different crops, causing great losses in both time and costs. Using machine vision every inconvenience that occurs from the stage of germination and growth to the maturation phase of each culture was analyzed. To this end, different methods of image processing such as segmentation, feature extraction and pattern recognition were used. Finally the results of image processing is achieved evidence which affects the culture, whether pests or weeds who are altering a given area of cultivation, and so have an early detection of the disease to prevent it from spreading to all cultivation.

Seguimiento de trayectorias con un robot móvil de configuración diferencial

En este trabajo se desarrolla un sistema de control, aplicado en un robot movil de configuracion diferencial, para seguir una trayectoria determinada. Para dar solucion al problema, primero se implementa la cinematica directa del robot para simular el comportamiento del mismo. Luego para cumplir el objetivo, dos sistemas de control (holonomico y no-holonomico), fueron desarrollados e implementados a partir de la cinematica inversa. Posteriormente, se desarrollan pruebas que permiten comparar el rendimiento de los dos controladores, determinando cual proporciona la mejor solucion.

FORMACIÓN DE ROBOTS MÓVILES MEDIANTE EL USO DE CONTROLADORES

El manejo de sistemas multi-robots, ha adquirido gran atencion en las ultimas decadas, destacandose en aplicaciones tales como la elaboracion de mapas, el transporte de objetos e incluso el rescate de personas. Teniendo en cuenta esta motivacion, se realizo la busqueda de trabajos que abordaron el tema, encontrando diferentes tipos de controladores aplicados a estos sistemas manteniendo la configuracion lider-seguidor.

Implementation and validation of a micropilot control system for Vector-P aircraft in flight level

The purpose of this research is to validate the implementation of Micropilot control system in Matlab®. by comparing the simulation in both softwares and to calculate the gains through the application of Linear Quadratic Regulator (LQR) control techniques using Lyapnov equation.