Structural Surface Assessment of Ship Structures Intended for Robotic Inspection Applications

Merchant vessels experience regular structural assessments. Traditionally, surveys are performed physically by surveyors being expansive and time-consuming. Imagery based, cracks recognition is a topic obtaining considerable interest in commercial and scientific sectors. By using computer vision algorithms, authors propose a new approach to expedite crack detection, visualize the cracks efficiently in ship structures and then measure their length. The process includes two parts: at first, crack images are captured manually by using low-cost handheld cameras. Afterward, image is imported into software and processed. To make analysis easier, image is compressed and converted into grayscale. Image contrast is then stretched to enhance the contrast between background and crack. After obtaining latent crack identification features, images are elaborated by pre-processing, feature extraction, image segmentation, thus estimating the region of interest and determining whether the image includes a crack or not. Based on experiments and comparing results to traditional naked-eyes approaches, the algorithm is found efficient in crack detection, hence reducing cost and making crack identification system more portable, accurate and integrated.