Home > Published Issues > 2020 > Volume 9, No. 1, February 2020 >

An Image Mosaicking Method for Tunnel Lining Inspection

Cuong Nguyen Kim 1, Kei Kawamura 2, Masando Shiozaki 3 and Amir Tarighat 4
1. Mien Truong University of Civil Engineering, Phu Yen, Vietnam
2. Graduate School of Science Technology Innovation of Yamaguchi University, Ube, Yamaguchi, Japan
3. Sumitomo Mitsui Construction Co., Ltd., Tokyo, Japan
4. Department of Civil Engineering, Shahid Rajaee Teacher Training University, Iran

Abstract—The paper proposes an image mosaicking method for tunnel lining inspection. The conventional methods only used the cost value of the pixel being processed based on similarity metric to estimate an image-matching location. To improve the image-mosaicking efficiency, the curvatures of the cost curve at candidate matching points are adapted. Moreover, experimental results for an actual tunnel demonstrate that the curvature measurement can select the precise matching points accurately for assisting defect inspection.

Index Terms—tunnel lining inspection, image mosaicking, curvature metrics

Cite: Cuong Nguyen Kim, Kei Kawamura, Masando Shiozaki, and Amir Tarighat, "An Image Mosaicking Method for Tunnel Lining Inspection," International Journal of Structural and Civil Engineering Research, Vol. 9, No. 1, pp. 101-105, February 2020. doi: 10.18178/ijscer.9.1.101-105