Artificial Intelligence (AI) is becoming increasingly pervasive across various industry sectors, demonstrating growing relevance through numerous real business applications. An applicant in the aviation sector will encounter significant challenges when attempting to safely integrate any machine learning (ML) Use functions, particularly within large commercial airplanes, as well as smaller light aircraft and military contexts. Consequently, obtaining regulatory approval will prove to be a formidable task for any applicant with a novel and untested product, especially under the scrutiny of society and media. The purpose of this paper is to provide a method for achieving the comprehensive Level of Confidence (LoC) required for the development assurance process specific to the Machine Learning (ML) Use function. It discusses how this process will be relied upon and monitored during its operational deployment. A theoretical computer vision use case, supported by illustrations, is presented for an ML supervised classification solution aimed at image-based ground and taxiing obstacle detection and alerting. This solution is intended to reduce incursion events and subsequent Aircraft on Ground (AoG) incidents and associated costs. The purpose of this paper is to provide a method for achieving the comprehensive Level of Confidence(LoC) required for the development assurance process specific to the Machine Learning (ML) Use function. It discusses how this process will be relied upon and monitored during its operational deployment. A theoretical computer vision use case, supported by illustrations, is presented for an ML supervised classification solution aimed at image-based ground and taxiing obstacle detection and alerting. This solution is intended to reduce incursion events and subsequent Aircraft on Ground (AoG) incidents and associated costs.