Open Access. Powered by Scholars. Published by Universities.®
University of Nebraska - Lincoln
Department of Construction Engineering and Management: Faculty Publications
- Keyword
-
- Concrete Delamination; Thermography; Nondestructive Evaluation; Deep Learning; Encoder-Decoder Architecture; Semantic Segmentation; UAV (1)
- Subsurface Voids; Semi Real-time Detection; Regional Temperature Contrast; Thermographic Analysis; Non-uniform Thermal Background Estimation; NDT; and Concrete Hydration (1)
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Semi Real-Time Detection Of Subsurface Consolidation Defects During Concrete Curing Stage, Chongsheng Cheng, Zhigang Shen
Semi Real-Time Detection Of Subsurface Consolidation Defects During Concrete Curing Stage, Chongsheng Cheng, Zhigang Shen
Department of Construction Engineering and Management: Faculty Publications
Subsurface consolidation defect is a common issue in concrete pavement construction, and the hidden defects often require costly repairs after project delivery. Therefore, being able to identify this type of defect during construction will enable contractor to conduct quick repairs to avoid costly post-construction rework. In this paper a semi real-time detection approach using infrared thermography is introduced. The developed approach utilizes the hydration heat during curing time to identify the subsurface voids based on the regional temperature contrast. Experimental studies were conducted using artificial void-defect in different sizes and depths. The thermographic analysis is employed to locate the void-defects …
Automatic Delamination Segmentation For Bridge Deck Based On Encoder-Decoder Deep Learning Through Uav-Based Thermography, Chongsheng, Zhexiong Shang, Zhigang Shen
Automatic Delamination Segmentation For Bridge Deck Based On Encoder-Decoder Deep Learning Through Uav-Based Thermography, Chongsheng, Zhexiong Shang, Zhigang Shen
Department of Construction Engineering and Management: Faculty Publications
Concrete deck delamination often demonstrates strong variations in size, shape, and temperature distribution under the influences of outdoor weather conditions. The strong variations create challenges for pure analytical solutions in infrared image segmentation of delaminated areas. The recently developed supervised deep learning approach demonstrated the potentials in achieving automatic segmentation of RGB images. However, its effectiveness in segmenting thermal images remains under-explored. The main challenge lies in the development of specific models and the generation of a large range of labeled infrared images for training. To address this challenge, a customized deep learning model based on encoder-decoder architecture is proposed …