Embedded Image Capture System for Liquid Monitoring in the Smart Chemical Industry
Résumé
The work presented in this paper is carried out as a part of the design of a supervision system based on a visual wireless sensor network dedicated to the Smart Chemical Industry. Since the visual sensor nodes are battery powered, our objective is to reach a compromise between the energy consumption and the exploitability of the captured images. In this article, we are interested in how to highlight some important details of the image at the moment of its capture, a topic which has not yet been exhaustively covered in previous research works. As light is absorbed by materials through which it is passing, a correct image exploitability can be reached when applying the adequate light color. Thus, this paper studies the color light effects on the captured images. For that, one visual sensor node, based on Raspberry Pi and a camera, is designed to conduct experiments. In addition, a laboratory glass container including liquids is developed and used as an emulator of the real system.