Development of a novel visual feature detection-based method for aircraft door identification using vision approach

This paper describes the outcomes of relevant feature extraction and identification methods to aid successfully aircraft door detection. The system has to work day and night, rain or shine under all-weather conditions. The proposed solution consists of a suite of relevant extracted and identified features that characterize aircraft door (e.g. door windows, handle, text, footplate, arrow, frame lines). Furthermore, preliminary evaluation of the extracted features gave detection with more than 97% success rate (except for the footplate), a promising outcome that sets the scene for a potential successful door position identification under all lighting and weather conditions. The robustness of the proposed method is accomplished by the logical structure for the decision process for the identification of the aircraft door using the various features. Here, features with high success rates will be assigned higher weight.