MaDnet: multi-task semantic segmentation of multiple types of structural materials and damage in images of civil infrast
- PDF / 3,409,556 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 98 Downloads / 229 Views
ORIGINAL PAPER
MaDnet: multi‑task semantic segmentation of multiple types of structural materials and damage in images of civil infrastructure Vedhus Hoskere1 · Yasutaka Narazaki1 · Tu A. Hoang1 · B. F. Spencer Jr.1 Received: 19 November 2019 / Accepted: 20 May 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Manual visual inspection is the most common means of assessing the condition of civil infrastructure in the United States, but can be exceedingly laborious, time-consuming, and dangerous. Research has focused on automating parts of the inspection process using unmanned aerial vehicles for image acquisition, followed by deep learning techniques for damage identification. Existing deep learning methods and datasets for inspections have typically been developed for a single damage type. However, most guidelines for inspections require the identification of multiple damage types and describe evaluating the significance of the damage based on the associated material type. Thus, the identification of material type is important in understanding the meaning of the identified damage. Training separate networks for the tasks of material and damage identification fails to incorporate this intrinsic interdependence between them. We hypothesize that a network that incorporates such interdependence directly will have a better accuracy in material and damage identification. To this end, a deep neural network, termed the material-and-damage-network (MaDnet), is proposed to simultaneously identify material type (concrete, steel, asphalt), as well as fine (cracks, exposed rebar) and coarse (spalling, corrosion) structural damage. In this approach, semantic segmentation (i.e., assignment of each pixel in the image with a material and damage label) is employed, where the interdependence between material and damage is incorporated through shared filters learned through multi-objective optimization. A new dataset with pixel-level labels identifying the material and damage type is developed and made available to the research community. Finally, the dataset is used to evaluate MaDnet and demonstrate the improvement in pixel accuracy over employing independent networks. Keywords Damage detection · Computer vision · Multi-task learning · Semantic segmentation · Structural inspections
1 Introduction Condition monitoring is an essential step in ensuring the safety and serviceability of civil infrastructure. Detailed information about the current state of a structure provides valuable insights that can be used for a number of applications ranging from prioritization of repairs to the review of design and construction procedures. In the United States, current practice for assessing structural health is predominantly reliant on manual visual inspections [1]. High-profile * Vedhus Hoskere [email protected] Tu A. Hoang [email protected] 1
Department of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61820, USA
catastrophic accidents like the I-35W bridge
Data Loading...
