Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Smart Structures and Systems Volume 31, Number 4, April 2023 , pages 335-349 DOI: https://doi.org/10.12989/sss.2023.31.4.335 |
|
|
|
Ensemble-based deep learning for autonomous bridge component and damage segmentation leveraging Nested Reg-UNet |
||
Abhishek Subedi, Wen Tang, Tarutal Ghosh Mondal, Rih-Teng Wu and Mohammad R. Jahanshahi
|
||
| Abstract | ||
| Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images. | ||
| Key Words | ||
| automated bridge inspection; component segmentation; damage segmentation; smart cities; structural health monitoring | ||
| Address | ||
| (1) Abhishek Subedi, Wen Tang, Mohammad R. Jahanshahi: Lyles School of Civil Engineering, Purdue University, West Lafayette, IN, USA; (2) Tarutal Ghosh Mondal: Department of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, MO, USA; (3) Rih-Teng Wu: Department of Civil Engineering, National Taiwan University, Taipei, Taiwan; (4) Mohammad R. Jahanshahi: Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA. | ||