Water Journal : Water Journal May 2012
pipeline cleaning & maintenance refereed paper technical features 60 MAY 2012 water Some holes can be identified as pipe connections by means of a pipe connection detector that examines the dimensions and location of the defect and may compute the ellipse of best fit for the boundary of the defect in order to give a compound fuzzy membership value. Intrusive defects can be given a deterministic or fuzzy classification as either tree roots or deposits by use of a tree root detector that computes the maximum deviation between the range values of off-defect pixels and on-defect pixels in windows centred on boundary points of the defect. The remainder of this paper describes some techniques for the recognition of defects and features in pipe images. The first step in each case is to carry out segmentation of the pipe image, which results in a binary image. The connected components of this binary image are candidates for defect regions or pipe features. The large connected component extending over the full length of the pipe is referred to as the principal segmented region, and contains the pipe flow lines, the pipe joints and adjoining defects. Other connected components are candidates for corrosion defects and pipe connections. An approach is therefore needed for distinguishing between corrosion regions and pipe connections. In this research, corrosion defects and pipe connections are distinguished using a simple fuzzy approach. The principal segmented region may then be decomposed into its component flow lines region, pipe joint regions and adjoining defect regions using the techniques of mathematical morphology. The Segmentation Sub-System There are a number of approaches to colour image segmentation including thresholding, feature-based clustering, region-based approaches, edge detection approaches, fuzzy approaches and neural network approaches (Cheng et al., 2001). The main segmentation approach that we consider in this paper is described in (Mashford et al., 2007). It is a supervised method involving classification of feature vectors consisting of the H, S and B components in the HSB (hue, saturation and brightness) colour space. For the classifier we used a support vector machine (SVM). SVMs are statistical pattern recognisers that can be used for classification or regression tasks. They have certain properties that make them superior to neural networks such as requiring smaller training sets and having better generalisation ability. For generation of a training set for the SVM, a set of feature vectors for individual pixels together with their classifications must be extracted from the training data images. The approach that we have used to generate training sets for the pixel classifier is to select rectangular regions of constant classification using standard tools. Rectangular regions were selected and extracted from the unwrapped pipe image of a concrete sewer pipe. The regions were extracted from regions of corrosion and regions of good pipe. Corrosion and good pipe regions were used for both training and testing the classifier. SVMs generally require 100s or 1000s of training cases in order to be trained effectively. Since the SVMs used in this research are being used as pixel classifiers, and a single image contains many thousands of pixels, it is not necessary to use a large number of images to train an SVM for this purpose. It is just necessary to ensure that there is sufficient variability in the training data to reflect variability in practice. The SVMs were trained to detect areas of sub-critical corrosion characterised by darker areas of pipe, but other defect types such as different coloured corrosion areas could also be investigated. Detection of Corrosion Defects and Pipe Connections Segmented regions other than the principal segmented region form candidates for corrosion regions, other defect regions or pipe connections. Pipe connections may be distinguished from corrosion regions by using a simple fuzzy approach. A defect region is likely to be a pipe connection if it is located approximately laterally in the pipe and its size is within a range of suitable sizes. One may also consider requiring that its shape as measured by, for example, a goodness of fit parameter for an ellipse of best fit is in a suitable range. However, as noted by Müller and Fischer (2007) segmented regions arising from pipe connections can come in a number of shapes other than oval. One may define fuzzy membership functions associated with the conditions that the defect be laterally located and of a suitable size. Pipe connection detection by this simple fuzzy approach has been applied to the trial images under consideration, with the result of completely accurate detection except in one case where the pipe connection was on the boundary of the image. Cases such as these can be avoided by processing the full, unwrapped pipe image, or else by using overlapping windows. Defect regions, together with their classification as either corrosion or pipe connection, can be displayed by means of a GUI, as shown, for example, in Figure 5, where a pipe connection is displayed. The effectiveness of the system at finding defects or features depends on the quality of the segmentation. For the SVM segmentation the result depends on a parameter called reference_brightness. In this case the value of reference_ brightness is determined by trial and error. When the parameter is high the system under-segments, resulting in more false negatives. When the parameter is low the system over-segments, resulting in more false positives. Some values of the parameter are associated with both false positives and false negatives. Thus, as in the case of the thresholding method, Figure 5. GUI display of pipe connection.
Water Journal July 2012
Water Journal April 2012