Classification of defects with ensemble methods in the automated visual inspection of sewer pipes

Side scanning evaluation technology (SSET) is a visual inspection technique for sewer pipelines. It provides both frontal and 360 degree images of the interior surface of the pipe wall. Image-based pipe defect classification has been widely used for rating sewage structural conditions. The classification of defects in sewer pipe is of vital importance for maintaining the sewerage systems. Usually, a human operator identifies the defect types from the acquired images. However, the diagnosis can be easily influenced by the subjective human factors. To overcome such limitations, a reliable automated sewer pipe defect classification is highly desirable. In this paper, a sewer pipe defect classification based on ensemble methods is proposed. Due to the natural shape irregularities of pipe defects and the complexity of imaging environments, pipe defect images are highly variable. A feature extraction procedure consisting of contourlet transform and the maximum response filter bank is implemented in the proposed method. A feature vector is generated with the statistical features derived from the outputs of contourlet transform and maximum response filter bank. Four ensemble classifiers are trained to classify the feature vector to assign a defect type to the input pipe image. The best ensemble method, namely RobBoot, achieves the highest classification rates in the experiments with 239 pipe images obtained by the SSET inspection. The effectiveness and performance of the proposed method are demonstrated by comparing with other state-of-the-art techniques.