3D Point Cloud Analysis for Detection and Characterization of Defects on Airplane Exterior Surface

Abstract

Three-dimensional surface defect inspection remains a challenging task. This paper describes a novel automatic vision-based inspection system that is capable of detecting and characterizing defects on an airplane exterior surface. By analyzing 3D data collected with a 3D scanner, our method aims to identify and extract the information about the undesired defects such as dents, protrusions or scratches based on local surface properties. Surface dents and protrusions are identified as the deviations from an ideal, smooth surface. Given an unorganized point cloud, we first smooth noisy data by using Moving Least Squares algorithm. The curvature and normal information are then estimated at every point in the input data. As a next step, Region Growing segmentation algorithm divides the point cloud into defective and non-defective regions using the local normal and curvature information. Further, the convex hull around each defective region is calculated in order to englobe the suspicious irregularity. Finally, we use our new technique to measure the dimension, depth, and orientation of the defects. We tested and validated our novel approach on real aircraft data obtained from an Airbus A320, for di↵erent types of defect. The accuracy of the system is evaluated by comparing the measurements of our approach with ground truth measurements obtained by a high-accuracy measuring device. The result shows that our work is robust, e↵ective and promising for industrial applications.

Non-Contact Body Measurement for Qinchuan Cattle with LiDAR Sensor

“…Before surface reconstruction, there exists a need to smooth the modelled surface in case of region deviations. For the extra data after the registration, the VGF is employed to reduce the number of points to improve operational efficiency, and the Moving Least Squares (MLS) algorithm [ 61 ] to resample the registered data in case of overlapped surface. Based on high numerical accuracy and the approximating function of meshless method, the MLS is applied to fit cattle body curves and surfaces.…”

Classification using a three-dimensional sensor in a structured industrial environment

“…6,7 AVI in industry is also a topic of our earlier publications, which propose various solutions for existing problems in the field. [8][9][10][11] There is another direction from which the problem of AVI can be tackled. Machine learning techniques are currently gaining an influx of attention in the computer vision community, providing more generalization for some of the tasks.…”

Impact of motion blur on stereo‐digital image correlation with the focus on a drone‐carried stereo rig

“…Since fuselage panels are often damaged by bird strikes or collisions with luggage belts, a portable DIC setup could be a viable measurement tool for identifying the dent depth. Especially, a fully wireless system on a drone could be very efficient since it would decrease the amount of manual work and increase the accuracy of identified dents, since the evaluation is mainly done manually (although some automated tools or extensive tools are reported in the literature). In any case, monitoring fuselage dents is an activity of key importance for airline operation, since denting may decrease fatigue life of aeronautic aluminium alloys up to 20%, as demonstrated in Guijt, Hill, Rausch, and Fawaz (2005) .…”