Robust crack detection for unmanned aerial vehicles inspection in ana-contrariodecision framework

Abstract

Mascle. Robust crack detection for unmanned aerial vehicles inspection in an a-contrario decision framework.Abstract. We are interested in the performance of currently available algorithms for the detection of cracks in the specific context of aerial inspection, which is characterized by image quality degradation. We focus on two widely used families of algorithms based on minimal cost path analysis and on image percolation, and we highlight their limitations in this context. Furthermore, we propose an improved strategy based on a-contrario modeling which is able to withstand significant motion blur due to the absence of various thresholds which are usually required in order to cope with varying crack appearances and with varying levels of degradation. The experiments are performed on real image datasets to which we applied complex blur, and the results show that the proposed strategy is effective, while other methods which perform well on good quality data experience significant difficulties with degraded images.

Crack detection based on a Marked Point Process model

“…In order to validate our new approach, we compared it with the percolation based local method of [7], and with NFA [8]. Figure 3 shows the comparison on four meaningful images of CTD.…”

“…Finally, as in [8], an image composition is computed that is a linear combination betweenĨ and the maximum ratio value of its derivative response in one direction and the perpendicular one (see [8] for further details).…”

“…An example of the first type of strategy is percolation [7] which classifies a pixel depending on the outcome of a simulated percolation process in its neighborhood. An example of the second kind of approach is [8]. In this latter, maximum paths (in terms of significance) are researched through the image, so that the algorithm of [8] is able to overcome some low contrast parts of the crack in order to detect a global crack.…”

“…An example of the second kind of approach is [8]. In this latter, maximum paths (in terms of significance) are researched through the image, so that the algorithm of [8] is able to overcome some low contrast parts of the crack in order to detect a global crack. In this work, we argue that the proposed approach based on MPP models offers a robust compromise between a local decision and a global solution which may occasionally drift from a regular crack model.…”

Concrete Cracks Detection Based on Deep Learning Image Classification

“…Though the development of automated crack detection system is not entirely new, with a few deployments on UAV [5,6], but it still represents a challenging task that has been explored over the last decades. Most of the development relies on a combination or improvement of conventional digital image processing techniques such as thresholding, mathematical morphology, and edge detection, while utilising photometric (e.g., pixel value) and geometric assumptions (e.g., continuity and local orientation) about properties of crack images to detect cracks-an extensive review can be found in [7].…”