THE INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS INC. S I G N a L P R O C E S S I N G algorithms, architectures, arrangements, and applications S P a 2 0 2 2 September 21 st - 22 nd , 2022, Poznań, POLAND Intelligent vision system for quality classification of airport lamp prisms Jakub Suder, Kacper Podbucki, Tomasz Marciniak, Adam Dąbrowski Poznan University of Technology, Faculty of Automatic Control, Robotics, and Electrical Engineering Institute of Automatic Control and Robotics Division of Electronic Systems and Signal Processing Jana Pawła II 24, 60-965 Poznań, Poland e-mail: jakub.a.suder@doctorate.put.poznan.pl Abstract—The article presents a concept of the analysis of mechanical wear of prisms in the in-pavement airport lamps. The solution is based on image processing technique that requires an appropriate selection of parameters due to the specificity of the objects. During the experimental tests, a database consisting of 316 photos of IDM airport lamps mounted in the airport areas was used. The proposed solution using an artificial neural network allows for the classification of lamps with an efficiency of 81.4%. Keywords-vision system; airport; lighting control; neural networks; artificial intelligence; Hough transform I. INTRODUCTION Due to growing requirements of the aviation agencies, airports all over the world are increasingly burdened with tasks to improve safety of the air operations [1]. One of the important aspects in this field is the correct lighting of the airport areas, especially runways, where the most critical air operations occur. For this purpose, measuring devices are built [2, 3], which are able to measure the luminous efficiency of each lamp, assess its wear and then classify it as suitable for further use or requiring replacement [4]. Reduction of the luminous efficiency occurs through weather conditions and the operation of the runway (e.g., through sticky, powdered rubber from aircraft tires). Machines that keep runways and taxiways clean may also damage lamp housings and their prisms, especially during snow removal. Metal brushes scratch the lamp holders and chip their prisms, making it necessary to replace the damaged lamps. For example, on the runway of the Poznań-Ławica airport, there are 356 in-pavement lamps, distributed over a distance of approx. 2.5 km. Lamp performance is specified in the European Aviation Safety Agency (EASA) standard in the Chapter U — Colours for aeronautical ground lights, markings, signs and panels [1]. This document presents the intensity of illumination of individual lights and their dependence on the angle of incidence. The given values differ depending on the lamp type and the light color. The standards also define the requirements relating to the airport category. One of the most important parameters is the minimum luminous intensity for the main beam, which is in a different angular range depending on the lamp type. It should be noted that stricter guidelines have been provided for the runway than for other airport areas, which is justified by the safety requirements of air operations. Fig. 1 shows a lamp damaged after the winter season and a new lamp. Figure 1. An example of a built-in airport lamp, damaged (left) and new (right) [2] Quality of airport lamps can be assessed stationary (using a light goniometer) or mobile (using luminous intensity measuring platforms [2] or drones [5, 6]). The stationary method is a very time-consuming as it requires disassembly of the lamps. The use of measurement platforms or drones, due to the short time gaps between air operations, ranging from 5 to 10 minutes, necessitates short occupations of the runway areas. An alternative mobile method is the use of a vision system that allows analyzing the degree of mechanical wear of lamps, mainly their prisms. An advantage of such solution, in relation to the luminous intensity measurement, is the precise assessment of the degree of degradation of the prisms’ frontal plane. The presented solution can also be a supplement to the sensory luminous intensity measurement system. Image acquisition and processing can be performed with the use of embedded systems [7, 8], using dedicated vision sensors [9-11]. Fig. 2 shows a general concept of the described mobile vision system. Figure 2. Concept of intelligent vision system for the analysis of mechanical wear of the prisms of in-pavement airport lamps The paper presents various stages of image processing of the built-in airport lamps. For the final classification assessment, a two-layer neural network with forward feed was used, based on the sigmoidal function in the hidden layer and the softmax function (normalized exponential function) in the output layer. Experimental research was carried out using the proprietary database and the Matlab 2022a environment [12]. This research was funded partly by the 2022 subvention and partly with the SMART4ALL EU Horizon 2020 project, Grant Agreement No 872614. 151 Authorized licensed use limited to: Politechnika Poznanska. Downloaded on November 10,2022 at 09:11:15 UTC from IEEE Xplore. Restrictions apply.