A UAV-based framework for quick recognition of pipeline defects

Unmanned aerial vehicle (UAV)-based visual inspection is frequently employed for surface defect recognition. However, the recognition accuracy of UAVs is diminished by the presence of background interference and the small size of defects. To address these challenges, this paper introduces a novel framework that comprises an online image preprocessing module and the Pipe-MobileNet neural-network-based model. The preprocessing module aims to generate images without background interference, while the Pipe-MobileNet model incorporates a customized depthwise convolution operator that classifies convolution kernels, making it more efficient in defect classification. To validate the effectiveness of the proposed method, a series of experiments was conducted on two realistic DN100 and DN200 pipelines. These results underscore the method's marked improvements in recognition accuracy and computational efficiency.