Papers by Keyword: Artificial Vision

Abstract: This document describes the architecture of a tracking system with two degrees of freedom (pan and tilt), endowed with artificial vision to follow the path of a moving object. The mechanism with a fixed base was designed to cover lateral and vertical ranges of movement, similar to the visual field in humans, limiting its depth by the resolution of the camera. The object that defines the motion path presents color uniformity across its surface, becoming the main feature in which the recognition and tracking algorithm were based. The tracking is performed by reducing the error between the object position and the reference axis of the camera. Several tests were carried out to evaluate the control and visual systems and to illustrate the behavior of the proposed methods.

Abstract: Resin Infusion (RI) process is one of the common techniques used in the industry for large composite parts production. This technique uses vacuum pressure to drive the resin into a laminate. Preform is laid dry into the mold and the vacuum is applied before the resin is introduced. Once a complete vacuum is achieved, resin is sucked into the laminate via placed tubing. Fig.1 shows a diagram of this process.An appropriate modeling of flow front’s shapes constrained by LRI process during filling can be based on the continuous deformation of the vent oriented flow pattern due to the driving pressure from the inlet. One of the main objectives is that the flow achieves the contour vent uniformly to avoid pressure drop and ensuring complete filling. In LRI, the flow front shape progression is mainly conditioned by the initial arrangement of the injection line allocation and the permeability of the preform that can evolve along the mold

Abstract: Wear level of tool inserts in automated processes is tried using techniques of artificial vision. An application has been developed in Matlab that allows the acquisition of images with different resolutions and later on to process them. It is explained how the vision system used has been designed and implemented. The method for acquiring tool insert images and their treatment in the pre-processing, segmentation and post-processing is commented. First results are also presented using diverse texture descriptors. These first results must be corroborated carrying out new experiments with a bigger number of images.