An Innovative Lighting Recognition System Based On Color Rendering Index and Computational Neural Networking

Identifying which type of lamp is installed on each public lighting pole and evaluating its luminous power is important, as the new LED-type models are much more economical in terms of energy, and energy distributors need to know the energy consumption of lighting. In Brazil, there are the following types of lamps in public lighting: incandescent, mercury vapor, sodium vapor, “mixed” lamps (composed of a mercury vapor arc tube in series with an incandescent tungsten filament), metallic lamps and modern LED (Light Emitting Diodes) type lamps. In this article, the authors describe the experimental results of the development of an automated lamp recognition system for street lighting based on the light pattern of each lamp, considering an innovative optical method that uses the Color Rendering Index (CRI) phenomenon and color cards. The objective of this study is to propose an alternative and low-cost technique in opposite use of the spectrophotometer, in order to identify the models of lamps installed on public lighting poles, from the light emitted only, using machine learning techniques and RNN.