No abstract

In this paper the development of an object detection system in a controlled two-dimensional space using computer vision techniques is presented. The detected objects have a rigid geometry and are exposed to real light; therefore, the system is robust to changes in lighting and shading. In order to handle the large amount of data to be processed in real time, a MyRIO device which contains an FPGA is used. This device allows communication with the LabVIEW software where the user interface resides. Using LabVIEW a tracking by color algorithm is implemented, in order to attend to a reactive agent, which uses an infrared sensor to detect the distance to an obstacle and perform the functions of foraging and storage. In order to improve performance, a supervisory system was implemented using a Kinect device that provides information relative to the position of the objects in the test area. This information allows eliminating occlusion problems.

In this work we propose a methodology that allows establishing the relationships between the location of the facilities and the clients' allocation with a dense demand. The use of this application lets us know the optimal location of production facilities, warehouses or distribution centers in a geographical space. We solve as well, the customers' dense demand for goods or services; this is, finding the proper location of the facilities in a populated geographic territory, where the population has a demand for services in a constant basis. Finding the location means obtaining the decimal geographical coordinates where the facility should be located, such that the transportation of products or services costs the least. The implications and practical benefits of the results of this work have allowed an enterprise to design an efficient logistics plan in benefit of its supply chain. Firstly, the territory must be partitioned by a heuristic method, due do nature combinatory of the partitioning. After this process, the best partition is selected with the application of factorial experiment design and the surface response methodology. Once the territory has been partitioned into k zones, where the center of each zone is the distribution center, we apply the continuous dense demand function by solving the location-allocation for an area where the population has a dense demand for services.

Resumen. En este trabajo se presenta un sistema para reconocimiento y clasificación de las letras que componen el lenguaje de señas en español, diseñado para apoyar en el entrenamiento de personas sordomudas y facilitar su comunicación con el resto de las personas. Se basa en un guante de bajo costo que captura el movimiento de la mano, el cual contiene un acelerómetro en cada dedo para detectar posición, y está conectado a una tarjeta de adquisición de datos. La información de los sensores se envía de forma inalámbrica a una computadora que contiene una interface desarrollada en LabVIEW, donde se genera una base de datos de símbolos. Para el reconocimiento de las letras, se aplicó un tratamiento estadístico a los datos en dicha base obteniendo una precisión superior al 96% independientemente del usuario.