Light Equalization Algorithm for Highway Tunnel Lining Image

Dan Xue, Weiqi Yuan

Abstract


When a high-speed tunnel detection vehicle capturing tunnel lining images, it is necessary to add a high-brightness light, which causes uneven illumination in the captured images and makes it difficult to detect lining defects. Therefore, this paper proposes a light equalization algorithm for fitting illumination curve distribution based on multiple filtering. Firstly, the improved mean filtering is adopted to eliminate small fluctuation noise. Secondly, the Gaussian filtering is used to fit the light distribution curve of the image, and the difference is made with the compressed image of the pyramid. Then, removing the brightness noise, the light equalization is achieved. The algorithm was tested on the images captured on the site of Tanglingshan Tunnel in Liaoning Province. Its results show that the algorithm can achieve light equalization, eliminate some noise and enhance the details to some extent.

Keywords


tunnel lining, uneven illumination, filtering


DOI
10.12783/dtetr/mcaee2020/35012

Full Text:

PDF

Refbacks

  • There are currently no refbacks.