Sewer pipe defects diagnosis assessment using multivariate analysis on CCTV video imagery

Abstract

Closed circuit television (CCTV) technology has been commonly used to inspect underground pipe defects, and high CCTV image quality is a prerequisite for accurate defect diagnosis. An acceptance criterion for CCTV inspection videos is critical for ensuring accurate diagnosis and preventing disputes between employers and contractors. This paper used multivariate statistical methods to evaluate the overall quality of CCTV images and to define an acceptance criterion for CCTV videos. Numerous CCTV images from a sewer inspection project were assessed and their quality, consisting of similarity in luminance and contrast distortions, was calculated by comparing a set of ideal images. Principal component analysis (PCA) and redundancy analysis (RDA) grouped the CCTV videos into homogeneous segments with similar image quality and provided a visual acceptance criterion for CCTV inspection videos. Furthermore, RDA triplot indicated that the contrast improvement of CCTV images can effectively enhance image quality and increase the diagnosis efficiency.

Keywords:

• Closed circuit television (CCTV)
• image quality
• luminance
• contrast
• principal components analysis (PCA)
• redundancy analysis (RDA)