Centro UTN CInApTIC (Centro de Investigación Aplicada a las TIC)

Permanent URI for this communityhttp://48.217.138.120/handle/20.500.12272/672

Browse

Author: search.filters.author.Rodrigues da Fonseca, Claudio

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Low-cost image and video processing using high-performance middleware in single-board computers with open internet standards
    (2020-02-03) Pérez, Carlos Alejandro; Cleva, Mario Sergio; Liska, Diego Orlando; Rodrigues da Fonseca, Claudio; Aquino, Dominga Concepción
    Image processing is becoming ubiquitous in many activities. This kind of systems use industry-standard libraries, such as OpenCV, and GPGPU techniques such as CUDA and OpenCL. Nowadays, these are being ported to many computing platforms, offering significant processing power even in devices with limited resources. However, the only model that is truly ubiquitous, is the web itself. Modern browsers feature quite complex internals and offer sophisticated development and profiling tools, in order to offer the best user experience. Introduction of HTML5 allows Realtime video and image manipulation, in browser space, without any plugin. In addition, Wasm (web assembly) Javascript execution engine provides fastest possible performance by means of highly customized compiler and runtime, in almost any browser, including embedded ones. This paper presents an image processing system, architected as a modular web application, using only Raspberry PIs with a compact but fast middleware server, that performs all image operations in browser space by means of web assemblies. All components, including database support, can run in a single board, providing image and video processing speeds that match, or surpass, their native compiled C counterparts on the same platform. This solution has a very low cost, that fits with emerging markets, making it ideal for LATAM scenarios.
  • Thumbnail Image
    Item
    A cloud-based and flexible architecture for beans images processing
    (2023-06-04) Villaverde, Jorge; Aquino, Dominga Concepción; Rodrigues da Fonseca, Claudio
    Food quality is a paramount feature in agriculture technology, analyzing and classifying properly grains requires specialized work (Gomes and Leta, 2012). Nowadays, advanced computer vision technologies are available in vast life environments, however they require a software intensive approach to acquire and process a large amount of data at an acceptable level. In parallel, cloud-based services became full featured and highly available through different types of data networks. These advances together empower the Industry 4.0 solutions to accomplish flexible needs in modern factories. In this work we present an extensible architecture that allows decentralization of the digital image processing suitable in food quality context. We integrate modern computer technologies to decrease the latency between the Edge of image acquisition and Data Centers, leveraging IIoT technologies into the food quality control systems. This approach lets the end user capture images using low or high technology cameras and process them using cloud based technologies. The proposed approach, also, describes architectural components that allow an easy way of adding and combining new components for automatic image processing.
  • Thumbnail Image
    Item
    Comunicación bidireccional para aplicaciones de visión automática
    (2021-10-05) Rodrigues da Fonseca, Claudio; Bernaola, Martín; Aquino, Dominga Concepción
    En aplicaciones de visión computarizada se requiere software para el procesamiento de las imágenes y extracción de información significativa para el usuario del dominio de la aplicación. Además, el soporte del hardware con piezas mecánicas como cintas transportadoras, sensores y actuadores, juega un rol imprescindible para permitir el manejo físico de los objetos de interés. Para lograr una solución de visión automatizada se requiere del control síncrono de las partes físicas al tiempo que las imágenes son capturadas y procesadas. Los sistemas en un chip como Raspberry Pi ofrecen actualmente una excelente relación de costo-prestaciones. Estas computadoras, con un entorno amigable para soluciones de usuario final, tienen rendimiento computacional suficiente para la ejecución de aplicaciones de visión computarizada. Arduino es una plataforma que ha alcanzado gran madurez en aspectos de control de hardware. Es un entorno potente, con una amplia variedad de periféricos, de fácil empleo para la interacción con componentes físicos. Ambas plataformas ofrecen interfaces de comunicación estándares que permiten su interacción. Así es posible aprovechar al máximo sus capacidades y lograr aplicaciones integradas de visión automática. El objetivo de este trabajo es obtener un módulo de software para la comunicación bidireccional entre sistemas Arduino y Raspberry Pi. Permitirá la integración sencilla y fiable de estas plataformas, a través de una red de comunicación serial I2C. Dispondrá de una interfaz de servicio para que aplicaciones de visión automática puedan conocer y controlar el estado de componentes hardware conectados a placas Arduino. La interacción humana será mediante una página web.