Autonomous detection of damage to multiple steel surfaces from 360° panoramas using deep neural networks

Cai Luo, Leijian Yu, Jiaxing Yan, Zongwei Li, Peng Ren, Xiao Bai, Erfu Yang, Yonghong Liu

Research output: Contribution to journalArticlepeer-review

Abstract

Structural health assessments are essential for infrastructure. By using an autonomous panorama vision‐based inspection system, the limitations of the human cost and safety factors of previously time‐consuming tasks have been overcome. The main damage detection challenges to panorama images are (1) the lack of annotated panorama defect image data, (2) detection in high‐resolution images, and (3) the inherent distortion disturbance for panorama images. In this paper, a new PAnoramic surface damage DEtection Network (PADENet) is presented to solve the challenges by (a) using an unmanned aerial vehicle to capture panoramic images and a distorted panoramic augmentation method to expand the panoramic dataset, (b) employing the proposed multiple projection methods to process high‐resolution images, and (c) modifying the faster region‐based convolutional neural network and training via transfer learning on VGG‐16, which improves the precision for detecting multiple types of damage in distortion. The results show that the proposed method is optimal for surface damage detection.
Original languageEnglish
Number of pages15
JournalComputer-Aided Civil and Infrastructure Engineering
Early online date24 Mar 2021
DOIs
Publication statusE-pub ahead of print - 24 Mar 2021

Keywords

  • deep learning
  • damage detection
  • panoramic images

Fingerprint Dive into the research topics of 'Autonomous detection of damage to multiple steel surfaces from 360° panoramas using deep neural networks'. Together they form a unique fingerprint.

Cite this