Bayesian Outdoor Defect Detection
This work addresses a domain-specific problem for outdoor inspection using drones, offering an incremental improvement in defect detection accuracy.
The paper tackles defect detection in motion-blurred images on rough surfaces by introducing a Bayesian detector with reflected non-local priors, resulting in enhanced accuracy in identifying defects like hail damage in drone images.
We introduce a Bayesian defect detector to facilitate the defect detection on the motion blurred images on rough texture surfaces. To enhance the accuracy of Bayesian detection on removing non-defect pixels, we develop a class of reflected non-local prior distributions, which is constructed by using the mode of a distribution to subtract its density. The reflected non-local priors forces the Bayesian detector to approach 0 at the non-defect locations. We conduct experiments studies to demonstrate the superior performance of the Bayesian detector in eliminating the non-defect points. We implement the Bayesian detector in the motion blurred drone images, in which the detector successfully identifies the hail damages on the rough surface and substantially enhances the accuracy of the entire defect detection pipeline.