Systematic image quality assessment for sewer inspection

Ming Der Yang, Tung Ching Su, Nang-Fei Pan, Yeh Fen Yang

研究成果: Article同行評審

40 引文 斯高帕斯(Scopus)


Closed circuit television (CCTV) has been applied in many developing or developed counties for sewer inspection due to its low setup cost and technical requirement. Several automated diagnosis systems of sewer pipe defects had been developed to assist the technicians in interpreting or classifying sewer pipe defects. However, many researchers pointed out that good image quality is the prerequisite for accurate interpretation and diagnosis of CCTV inspection but has not a proper evaluation approach. In this paper, a CCTV image quality index considering both of the luminance distortion and the contrast distortion of a CCTV image compared by reference images is proposed and was applied to assess the image quality of the CCTV images shot for a sewer house-connection project. The experimental result indicates that rather than luminance contrast plays a more important role in the CCTV image quality that can be effectively improved by contrast enhancement. Since CCTV image quality can hardly distinguished by human eyes, the proposed image quality index can provide helpful information to efficiently assist the on-site technicians in precisely shooting better CCTV images for the pipe defection. Additionally, a sensitivity analysis of contrast stretch was implemented to quantify the CCTV image quality improvement. CCTV imaging conditions, such as pipe materials and imager status, are found as the factors affecting the CCTV image quality. In the future, a real-time CCTV image quality assessment will be developed by modifying the CCTV image quality index as an instantaneous reference for imaging adjustment that can be expected to be practicable for the on-site sewer inspection because of the extremely short computation time.

頁(從 - 到)1766-1776
期刊Expert Systems With Applications
出版狀態Published - 2011 3月 1

All Science Journal Classification (ASJC) codes

  • 工程 (全部)
  • 電腦科學應用
  • 人工智慧


深入研究「Systematic image quality assessment for sewer inspection」主題。共同形成了獨特的指紋。