Bridge Deck Delamination Segmentation Based on Aerial Thermography Through Regularized Grayscale Morphological Reconstruction and Gradient Statistics

Authors

Chongsheng Cheng, University of Nebraska-LincolnFollow
Zhexiong Shang, University of Nebraska-LincolnFollow
Zhigang Shen, University of Nebraska - LincolnFollow

Date of this Version

3-21-2019

Citation

Bridge deck delamination segmentation based on aerial thermography through regularized grayscale morphological reconstruction and gradient statistics C Cheng, Z Shang, Z Shen - Infrared Physics & Technology, 2019 https://doi.org/10.1016/j.infrared.2019.03.018

Comments

© 2019 Elsevier B.V. Used by permission.

Abstract

Environmental and surface texture-induced temperature variation across the bridge deck is a major source of errors in delamination detection through thermography. This type of external noise poises a significant challenge for conventional quantitative methods such as global thresholding and k-means clustering. An iterative top-down approach is proposed for delamination segmentation based on grayscale morphological reconstruction. A weight-decay function was used to regularize the reconstruction for regional maxima extraction. The mean and coefficient of variation of temperature gradient estimated from delamination boundaries were used for discrimination. The proposed approach was tested on a lab experiment and an in-service bridge deck. The results demonstrated the improved capability of the framework to handle the non-uniform background, and thus eliminates the need of inferencing the background temperature which is often required by existing methods. That the results also suggested that the gradient statistics of the delamination boundary in the thermal image could be valid criterions to refine the segmentation under the proposed framework. Therefore, the authors concluded that the proposed method is a valid delamination segmentation approach for processing field concrete deck thermal images. The parameter selection and the limitation of this approach were also discussed. Further work will be carried out in more field cases to fine tune the parameter selection of the framework.