Almost all solutions in modern lighting systems are based on LED technology. Luminance and obvious ease of control are the key characteristics of this light source. At the same time, luminances at the level of 10 8 cd/m 2 are a significant advantage of LED in design applications, where high luminous intensity amplification is important. However, in general and in road lighting applications, LED luminaires represent a source of potential discomfort glare. Unfortunately, lighting technology's metrology lags behind LED parameter development and optimization. The results of luminance measurements of the same luminaires, made with a luminance camera and meters with a measuring field, differ. The differences even appear for the same imaging luminance measuring devices with different lenses. This article presents the results of experiments and detailed analyzes related to modern digital luminance photometry based on the use of digital image sensors. Luminance tests were conducted on multi-source research models of luminaires. Traditional luminance measuring equipment with a measuring field was used in the experiment. The research was also supplemented with the measurements made using CCD/CMOS luminance cameras with selected components where the angular field of view of each pixel was a 0.45 min arc corresponding to the highest average human sight parameters. The results confirm that the average luminance value for multi-source luminaires depends on the measurement system configuration. It has been proposed to standardize the angular field of view parameters of all measurement systems, where the measurement aims to obtain a value that directly relates to human visual impressions (e.g. glare).

For the proper operation of intelligent lighting, the precise detection of a human silhouette on the scene is necessary. Correctly adjusting the light beam divergence requires locating the detected figure in virtual three-dimensional coordinates in real time. The market is currently dominated by the markers systems. This paper is focused on the advanced solution of the markerless system of identifying and tracking characters based on deep learning methods. Analyses of the selected pose detection, holistic detection (including BalzePose and MoveNet models), and body segmentation (BlazePose and tfbodypix) algorithms are presented. The BlazePose model was implemented for both pose tracking and body segmentation in the markerless dynamic lighting and mapping system. This article presents the results of the accuracy analysis of matching the displayed content to a moving silhouette. An assessment of the illumination precision was done as the function of the movement speed for the system with and without delay compensation.

For 30 years the photometric descriptions of luminaires that are used in simulation, design and photometric calculations have not changed. For many years, technology did not allow for the detailing of digital photometric data of light sources and luminaires. In the second decade of the 21st century digital luminance cameras debuted on the markct., Theoretically these cameras offered the possibility of changing digital descriptions of luminaire parameters. Unfortunately, the huge amount of digital data associated with a single light source (even in excess of 1TB) significantly halted the development in this area. The author of this publication with his team developed a luminance camera, optimisation and verification algorithms which were used to propose the novel simplified luminance description of luminaires and light sources based on advanced methods of digital analysis of luminance data. This publication presents the result of the implementation of the presented method and compares it with the results from the popular lighting simulation calculation programs.