Tung-Ching Su

Segmenting ideal morphologies of sewer pipe defects on CCTV images for automated diagnosis

Several literatures presented automated systems for detecting or classifying sewer pipe defects based on morphological features of pipe defects. In those automated systems, however, the morphologies of the darker center or some uncertain objects on CCTV images are also segmented and become noises while morphology-based pipe defect segmentation is implemented. In this paper, the morphology-based pipe defect segmentation is proposed and discussed to be an improved approach for automated diagnosis of pipe defects on CCTV images. The segmentation of pipe defect morphologies is first to implement an opening operation for gray-level CCTV images to distinguish pipe defects. Then, Otsus technique is used to segment pipe defects by determining the optimal thresholds for gray-level CCTV images of opening operation. Based on the segmentation results of CCTV images, the ideal morphologies of four typical pipe defects are defined. If the segmented CCTV images match the definition of those ideal morphologies, the pipe defects on those CCTV images can be successfully identified by a radial basis network (RBN) based diagnostic system. As for the rest CCTV images failing to match the ideal morphologies, the failure causes was discussed so to suggest a regulation for imaging conditions, such as camera pose and light source, in order to obtain CCTV images for successful segmentation.

Morphological segmentation based on edge detection for sewer pipe defects on CCTV images

The essential work of sewer rehabilitation is a sewer inspection through diagnoses of sewer pipe defects. At present, image processing and artificial intelligence techniques have been used to develop diagnostic systems to assist engineers in interpreting sewer pipe defects on CCTV images to overcome humans fatigue and subjectivity, and time-consumption. Based on the segmented morphologies on images, the diagnostic systems were proposed to diagnose sewer pipe defects. However, the environmental influence and image noise hamper the efficiency of automatic diagnosis. For example, the central area of a CCTV image, where is always darker than the surrounding due to the vanishing light and slight reflectance, causes a difficulty to segment correct morphologies. In this paper, a novel approach of morphological segmentation based on edge detection (MSED) is presented and applied to identify the morphology representatives for the sewer pipe defects on CCTV images. Compared with the performances of the opening top-hat operation, which is a popular morphological segmentation approach, MSED can generate better segmentation results. As long as the proper morphologies of sewer pipe defects on CCTV images can be segmented, the morphological features, including area, ratio of major axis length to minor axis length, and eccentricity, can be measured to effectively diagnose sewer pipe defects.

Mapping of the 26 December 2004 tsunami disaster by using FORMOSAT-2 images

The Sumatra earthquake struck South Asia on 26 December 2004 and triggered monstrous waves that turned into a tsunami hitting the ocean regions and caused the most severe natural disaster of recent decades. The devastating earthquake and tsunami changed the landscape of coastal areas in many countries around the whole Indian Ocean region. To provide real‐time information for rescue and rehabilitation plans, satellite images were applied to monitor and evaluate the damage over several devastated spots. The FORMOSAT‐2 satellite, which was launched on 21 May 2004 and operated by the National Space Organization, Taiwan, is uniquely designed to take timely and low‐cost black and white images daily with a resolution of 2 m and colour images of 8‐m resolution. FORMOSAT‐2 is expected to have many useful applications, such as natural‐disaster evaluation, land‐usage analysis, environmental monitoring, and coastal search and rescue. FORMOSAT‐2 successfully acquired several post‐tsunami images of the hazardous areas, both Puhket, Thailand and Banda Aceh, Indonesia on 28 December. A series of FORMOSAT‐2 satellite images were processed by geometric and radiometric correction, haze reduction, image enhancement, feature extraction, image classification, and image fusion to assess the damage over those devastated areas. FORMOSAT‐2 satellite images with a high‐temporal resolution and high‐spatial resolution were proved to be an efficient and useful information source for decision‐makers to make rescue and recovery plans, especially for some isolated islands hard to reach in time.

An optimization model of sewage rehabilitation

Abstract Due to low visibility, sewer systems are difficult to monitor, maintain and rehabilitate. To prevent failures, environmental pollution, and wastewater treatment overflow, regular rehabilitation of sewage is necessary. However, sewage rehabilitation usually costs an immense amount of money and is hampered by a limited budget. Thus, efficient planning of maintenance and rehabilitation for sewage upkeep is demanded. In this paper, an optimization model has been built to find an appropriate rehabilitation strategy consisting of a rehabilitation method and a substitute material for each pipe failure under a limited budget. The optimization model was designed to search for a Pareto curve (or trade‐off front) consisting of a set of optimal solutions with desirable rehabilitation effectiveness at the least cost. This paper employs genetic algorithms (GA) to obtain a Pareto curve at a low computation cost for large and complex sewer systems. This optimization model was applied to a sewer system in the 15th district of Kaohsiung City, Taiwan. Compared with the experts’ manual estimation, the optimization model saved about 20% of the rehabilitation cost for Kaohsiung City.

An efficient fitness function in genetic algorithm classifier for Landuse recognition on satellite images.

Genetic algorithm (GA) is designed to search the optimal solution via weeding out the worse gene strings based on a fitness function. GA had demonstrated effectiveness in solving the problems of unsupervised image classification, one of the optimization problems in a large domain. Many indices or hybrid algorithms as a fitness function in a GA classifier are built to improve the classification accuracy. This paper proposes a new index, DBFCMI, by integrating two common indices, DBI and FCMI, in a GA classifier to improve the accuracy and robustness of classification. For the purpose of testing and verifying DBFCMI, well-known indices such as DBI, FCMI, and PASI are employed as well for comparison. A SPOT-5 satellite image in a partial watershed of Shihmen reservoir is adopted as the examined material for landuse classification. As a result, DBFCMI acquires higher overall accuracy and robustness than the rest indices in unsupervised classification.

Priority Evaluation of Sewerage Rehabilitation By AHP

Usually the cost of sewerage rehabilitation is large but the budget is limited. Thus, a priority list for sewerage rehabilitation is necessary. This research is to establish an evaluation model to find out the cost-benefit ratio for each sewer sub-system. An evaluation model was established through an analytic hierarchy process (AHP). Initially, a comprehensive list of factors affecting the sewerage rehabilitation was established based on the result of a brainstorm meeting. Then, through an expert questionnaire, the weights for all affecting factors were estimated. Moreover, appropriate scoring rules, which convert qualitative factors into quantitative score, were set according to literatures, law and regulations, or personal experiences. By multiplying the all quantitative affecting factors and their weights, an overall score can be obtained for the cost-benefit evaluation. Finally, the authorities can set up the strategy for the sewerage rehabilitation by considering both the rehabilitation priority and budget limitation. This evaluation process was applied to a sewerage system in the 9 re-planning district which was located in east Taichung city, Taiwan. Introduction According to Taiwan EPA, there are about 27% of the streams are polluted. Moreover, the pollution rate is increasing more than 1.1% every year. Addition to controlling point-source pollution, increasing the treatment of municipal discharge is the most efficient way to improve the water quality of stream. Nowadays, the 1 Associate Professor, National Chung Hsing University, 250, Kuo Kuang Road, Taichung, Taiwan; phone 886-4-22840440ext214;mdyang@dragon.nchu.edu.tw 2 Ph.D. Candidate, National Chung Hsing University, 250, Kuo Kuang Road, Taichung, Taiwan; phone 886-4-22840440ext239;d9162404@mail.nchu.edu.tw 3 Lecturer, Da-Yeh University,112, Shan-Jeau Road, Dah-Tsuen, Changhwa, Taiwan; yp5768@yahoo.com 2 functions of sewerage, including collecting and transporting wastewater, get more attention in many developed and developing countries. Moreover, the popular rate of sewerage is considered as an important index for a modernizing city (Ostojic-Skomrlj et al., 1995). Sewer systems are buried underground so that the authorities have difficulties to maintain, monitor, and rehabilitate sewer systems. On the contrast, sewer systems are easy to get cracks and damages because of corrosive wastewater inside sewer and complex surrounding outside sewer. Serious cracks and leaks could result in exceeding the designed rate flow of the sewerage treatment plants due to the infiltration of rain or underground water. Also, the exfoliation of sewerage from detective pipes may cause a potential health hazard with the possible contamination of groundwater and soil. After sewerage infrastructure is constructed, appropriate and efficient operation and management becomes another issue. To keep sewerage in a good function, regular rehabilitation is necessary. A rehabilitation project is planned based on the many considerations, such as structure factors, critical factors, and service factors for sewerage (Water Research Centre, 1994). Therefore, an inspection work must be finished before a rehabilitation project is proposed. Under a limited budget, a rehabilitation project with a high efficiency and a low cost should be searched. Thus, the purpose of this paper is to optimize the priority of sewerage rehabilitation. To appropriately decide which sewer system in a sewerage network should be rehabilitated at the first priority, an evaluation model should be established. The priority evaluation of sewerage rehabilitation has two characters, uncertainty and multiple criteria (Webber et al., 1996; Basak, 2001). Analytic hierarchy process (AHP), which can help to easily organize the logic relationship among the complex factors, was employed to construct an analyzable hierarchy. The hierarchy can assist decision-makers in not only realizing the whole problem but also providing appropriate weights for the complex factors through the AHP model (Tummala et al., 1997; Alphonce, 1997; Handfield et al., 2002; Yu, 2002). Finally benefit/cost ratio is treated as an index to rank the priority of sewerage rehabilitation. Analytic Hierarchy Analyses of AHP model and benefit/cost ratios have been applied to many decision problems (Tummala et al., 1997; Yang et al., 2004). The analytic procedure of this paper is described as follows. First, several experts, who have abundant experiences in sewerage rehabilitation, were invited to convene a brainstorm meeting to list the possible factors that impacts the rehabilitation 3 priorities. The factors are listed based on the profession of every expert, so some of these factors are almost interdependent and similar so that we have to generalize independent and representative subcriteria for these factors (Kuo et al., 2002). Then, the subcriteria were discussed based on three criteria, economy, society, and environment, respectively. Furthermore, we classified the subcriteria of the three criteria according to two viewpoints, cost and benefit, respectively. The subcriteria of the cost viewpoint include rehabilitation costs, maintenance costs, traffic impacts, impacts on commerce or residents, construction dust, and construction noise. On the other hand, the subcriteria of the benefit viewpoint include extending cyclic lives of sewerage, improving capacities of sewerage, promoting qualities of life, increasing serviced population, controlling pollution of groundwater, and reducing pollution of soil. The analytic hierarchy is constructed as Figure 1. Next, an expert questionnaire was executed to find out the weights of the subcriteria. Scoring rules were established to calculate the scores of the subcriteria of the sewer systems. Finally, the analysis of benefit/cost ratios was calculated to rank the rehabilitation priorities (Al-Harbi, 2001). Scoring Rules Because the units of measuring the subcriteria are different, establishing a proper scoring rule for each subcriterion is essential. The appropriate scoring rules were set according to literatures, law and regulations, or personal experiences. However, related literatures, law and regulations are not enough to cover scoring rules of these subcriteria, so the rest of the scoring rules are just established by linearization as well as qualitative concept by personal experiences. The followings are the description of the scoring rules. AA1. Rehabilitation Costs. Rehabilitation costs vary with the rehabilitation approaches. The appropriate rehabilitation approaches are determined after the investigation of the failures for a sewer system through an inspection work. For example, renovations or replacements are employed if the length of crack is over 25% of a pipeline (between two manholes); else renewals are employed (Water Research Centre, 1994). To review differences among the costs of these approaches, we estimated the costs based on the cost functions of renewals, renovations, and replacements, respectively (OuYang, 2001). Replacements can be executed in both ways of excavation and trenchless. The scoring rule of rehabilitation costs is as follows. 4 Rehabilitation priority of sewerage A. Cost B. Benefit AA. Economy BA. Economy AB. Society BB. Society AC. Environment BC. Environment AA1. Rehabilitation Costs AA2. Maintenance Costs AB2. Impacts on Commerce or Residents AC1. Construction Dust AC2. Construction Noise BA1. Extending Cyclic Lives of Sewerage BA2. Improving Capacities of Sewerage BB1. Promoting Qualities of Life BB2. Increasing Serviced Population BC1. Controlling Pollution of Groundwater BC2. Reducing Pollution of Soil Sewer Subsystem I

Application of Morphological Segmentation to Leaking Defect Detection in Sewer Pipelines

As one of major underground pipelines, sewerage is an important infrastructure in any modern city. The most common problem occurring in sewerage is leaking, whose position and failure level is typically idengified through closed circuit television (CCTV) inspection in order to facilitate rehabilitation process. This paper proposes a novel method of computer vision, morphological segmentation based on edge detection (MSED), to assist inspectors in detecting pipeline defects in CCTV inspection images. In addition to MSED, other mathematical morphology-based image segmentation methods, including opening top-hat operation (OTHO) and closing bottom-hat operation (CBHO), were also applied to the defect detection in vitrified clay sewer pipelines. The CCTV inspection images of the sewer system in the 9th district, Taichung City, Taiwan were selected as the experimental materials. The segmentation results demonstrate that MSED and OTHO are useful for the detection of cracks and open joints, respectively, which are the typical leakage defects found in sewer pipelines.

Sewerage rehabilitation planning

Following the construction completion of the new infrastructures of sewerage, sewerage rehabilitation planning is the major work. This paper presents a systematic sewerage rehabilitation planning consisting of sewer inspection, diagnosis of pipe defects, grading of sewerage structural conditions, and determination of cost-effectiveness rehabilitation methods and substitution pipe materials. The main purpose of sewer inspection is to acquire closed circuit TV (CCTV) images for diagnosis of pipe defects. For diagnosis of pipe defects, a computer aided approach rather than the tradition manual interpretation is presented, and the overall diagnosis accuracies of above 90% are obtained. Also, genetic algorithm (GA) is used to design an optimization model to find out the multi-optimal sewer rehabilitation approaches. Finally, a set of optimal sewerage rehabilitation plans is searched.

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.

Optimal cluster numbers of unsupervised classification in Minkowski spaces

Unsupervised classification needs no prior knowledge of interested region and has less human interference that is suitable for processing messes of digital images acquired from earth observation satellites. A typical sequence for unsupervised classification might begin with the analyst specifying minimum and maximum numbers of categories to be generated by the classification algorithm. Usually, a larger cluster number is assigned in advance for the initial clustering. Then, several classified clusters are merged into a larger group so that the number of clusters can be reduced. The selection of an appropriate cluster number is up to the analysts experience. This paper illustrates the convergence of cluster-center optimization and the optimal cluster number varying with the dimension in Minkowski space. One of the simplest and most popular is Euclidean distance while Minkowski distance is measured in two dimensions. The experiment was executed on several digital images by a classifier employing Genetic Algorithm as a searching tool and Davies-Bouldin index as a cluster validity measure. The results show that a smaller dimension, e.g. one-, two-, and infinity dimensions, in Minkowski space derives less clusters, while the assignment of a larger dimension results in a larger cluster number with a more detailed segmentation.