Multiple Luminaire Identification in Airborne Images of Airport’s Approach Lighting Using Mathematical Morphology With Variable Length Structuring Element

The increasing demand for fast air transportation around the clock <br/>has increased the number of night flights in civil aviation over <br/>the past few decades. In night aviation, to land an aircraft, a <br/>pilot needs to be able to identify an airport. The approach <br/>lighting system (ALS) at an airport is used to provide <br/>identification and guidance to pilots from a distance. ALS <br/>consists of more than $100$ luminaires which are installed in a <br/>defined pattern following strict guidelines by the International <br/>Civil Aviation Organization (ICAO). ICAO also has strict <br/>regulations for maintaining the performance level of the <br/>luminaires. However, once installed, to date there is no automated <br/>technique by which to monitor the performance of the lighting. We <br/>suggest using images of the lighting pattern captured using a camera <br/>placed inside an aircraft. Based on the information contained <br/>within these images, the performance of the luminaires has to be <br/>evaluated which requires identification of over $100$ luminaires <br/>within the pattern of ALS image. This research proposes analysis <br/>of the pattern using morphology filters which use a variable <br/>length structuring element (VLSE). The dimension of the VLSE changes <br/>continuously within an image and varies for different images. <br/>A novel <br/>technique for automatic determination of the VLSE is proposed and <br/>it allows successful identification of the luminaires from the <br/>image data as verified through the use of simulated and real data. <br/> <br/>