Estimating Luminance Measurements in Road Lighting by Deep Learning Method

Kayaku M., ÇEVİK K. K.

International Conference on Artificial Intelligence and Applied Mathematics in Engineering (ICAIAME), Antalya, Turkey, 20 - 22 April 2019, vol.43, pp.940-948 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 43
  • Doi Number: 10.1007/978-3-030-36178-5_83
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.940-948
  • Keywords: Deep learning, Road lighting, Luminance, Deep neural network, NEURAL-NETWORKS
  • Akdeniz University Affiliated: Yes


Importance of road lighting has increased day by day to provide drivers to travel in safe and comfort as the result of increasing vehicle traffic. Ideal luminance values based on the type of road is specified in 115 numbered technical report of the International Commission on Illumination. For this technical report, there are illumination classifications for five different road types. M3 road lighting group is demanded for urban main routes (speed < 50 km/h); ideal luminance value for this group is accepted as 1 cd/m(2) at least. There occur damages in time based on the use of lamps, environmental effects, and pollution factor; there also occurs decreases in total luminance. Photometric measurement of luminaires needs to be periodically performed to determine how much the luminaires are affected by these problems. Illumination measurements are made by photometric measuring instruments. Time, cost and qualified manpower are necessary for this process. Artificial intelligence-based measurement systems replaced measuring instruments in parallel with technological advancements today. This study made a prediction for luminance that is used as a road lighting measurement unit via deep learning method. Measuring points were determined by utilizing quadrature technique; luminance values of related points were measured. A mathematical correlation was established between luminance values in that area of the road and color values (R, G, B) of pixels of the image of the road. It is aimed to determine the luminance value of the road through a single image without any measuring device.