Deep Learning Based Automatic Crack Detection and Segmentation for Unmanned Aerial Vehicle Inspections

Abstract

Automatic crack detection and segmentation plays a significant role in the whole system of unmanned aerial vehicle inspections. In this paper, we have implemented a deep learning framework for crack detection based on classical network architectures including Alexnet, VGG and Resnet. Moreover, inspired by the feature pyramid network architecture, a hierarchical convolutional neural network (CNN) deep learning framework which is efficient in crack segmentation is also proposed, and the performance of it is compared with other state of the art network architecture. We have summarized the existing crack detection and segmentation datasets and established the largest existing benchmark-dataset on the internet for crack detection and segmentation, which is open-sourced for the research community. Our feature pyramid crack segmentation network is tested on the benchmark-dataset and gives satisfactory segmentation results. A framework for automatic unmanned aerial vehicle inspections is also proposed for the crack inspection tasks of various concrete structures.