New concept for corrosion inspection of urban pipeline networks by digital image processing

摘要

Closed-circuit television (CCTV) is currently used in many inspection applications, such as the inspection of non accessible pipe surfaces. This human-oriented approach based on offline analysis of the raw images is highly subjective and prone to error because of the exorbitant amount of data to be assessed. This paper describes a methodology for automatic analysis of the inner surface of pipelines by means of digital image processing (DIP). The whole platform consists of an inspection mobile robot that carries a Line-Laser and a CCTV camera to recognize defects of the inner pipeline structure that is not easily accessible for human inspectors. A simple algorithm is presented that is able to detect cracks in the inner surface of the pipes with approximately 80 percent accuracy in final result, representing the main purpose of vision systems and the use of DIP technique. Experiments illustrate that the same set of results are achieved when the inner pipe is not illuminated.