Aircraft surface inspection includes detecting surface defects caused by corrosion and cracks and stains from the oil spill, grease, dirt\nsediments, etc. In the conventional aircraft surface inspection process, human visual inspection is performed which is timeconsuming\nand inefficient whereas robots with onboard vision systems can inspect the aircraft skin safely, quickly, and\naccurately. This work proposes an aircraft surface defect and stain detection model using a reconfigurable climbing robot and an\nenhanced deep learning algorithm. A reconfigurable, teleoperated robot, named as â??Kiropter,â? is designed to capture the aircraft\nsurface images with an onboard RGB camera. An enhanced SSD MobileNet framework is proposed for stain and defect\ndetection from these images. A Self-filtering-based periodic pattern detection filter has been included in the SSD MobileNet\ndeep learning framework to achieve the enhanced detection of the stains and defects on the aircraft skin images. The model has\nbeen tested with real aircraft surface images acquired from a Boeing 737 and a compact aircraftâ??s surface using the teleoperated\nrobot. The experimental results prove that the enhanced SSD MobileNet framework achieves improved detection accuracy of\naircraft surface defects and stains as compared to the conventional models.
Loading....