MACHINE VISION FOR AUTOMATICVISUAL INSPECTION OF WOODENRAILWAY SLEEPERS USING UNSUPERVISED NEURAL NETWORKS

The motivation for this thesis work is the need for improving reliability of equipment and quality of service to railway passengers as well as a requirement for cost-effective and efficient condition maintenance management for rail transportation. This thesis work develops a fusion of various machine vision analysis methods to achieve high performance in automation of wooden rail track inspection.The condition monitoring in rail transport is done manually by a human operator where people rely on inference systems and assumptions to develop conclusions. The use of conditional monitoring allows maintenance to be scheduled, or other actions to be taken to avoid the consequences of failure, before the failure occurs. Manual or automated condition monitoring of materials in fields of public transportation like railway, aerial navigation, traffic safety, etc, where safety is of prior importance needs non-destructive testing (NDT).In general, wooden railway sleeper inspection is done manually by a human operator, by moving along the rail sleeper and gathering information by visual and sound analysis for examining the presence of cracks. Human inspectors working on lines visually inspect wooden rails to judge the quality of rail sleeper. In this project work the machine vision system is developed based on the manual visual analysis system, which uses digital cameras and image processing software to perform similar manual inspections. As the manual inspection requires much effort and is expected to be error prone sometimes and also appears difficult to discriminate even for a human operator by the frequent changes in inspected material. The machine vision system developed classifies the condition of material by examining individual pixels of images, processing them and attempting to develop conclusions with the assistance of knowledge bases and features.A pattern recognition approach is developed based on the methodological knowledge from manual procedure. The pattern recognition approach for this thesis work was developed and achieved by a non destructive testing method to identify the flaws in manually done condition monitoring of sleepers.In this method, a test vehicle is designed to capture sleeper images similar to visual inspection by human operator and the raw data for pattern recognition approach is provided from the captured images of the wooden sleepers. The data from the NDT method were further processed and appropriate features were extracted.The collection of data by the NDT method is to achieve high accuracy in reliable classification results. A key idea is to use the non supervised classifier based on the features extracted from the method to discriminate the condition of wooden sleepers in to either good or bad. Self organising map is used as classifier for the wooden sleeper classification.In order to achieve greater integration, the data collected by the machine vision system was made to interface with one another by a strategy called fusion. Data fusion was looked in at two different levels namely sensor-level fusion, feature- level fusion. As the goal was to reduce the accuracy of the human error on the rail sleeper classification as good or bad the results obtained by the feature-level fusion compared to that of the results of actual classification were satisfactory.

Road and Traffic Signs Recognition using Vector Machines

Intelligent Transportation System (ITS) is a system that builds a safe, effective and integrated transportation environment based on advanced technologies. Road signs detection and recognition is an important part of ITS, which offer ways to collect the real time traffic data for processing at a central facility.This project is to implement a road sign recognition model based on AI and image analysis technologies, which applies a machine learning method, Support Vector Machines, to recognize road signs. We focus on recognizing seven categories of road sign shapes and five categories of speed limit signs. Two kinds of features, binary image and Zernike moments, are used for representing the data to the SVM for training and test. We compared and analyzed the performances of SVM recognition model using different features and different kernels. Moreover, the performances using different recognition models, SVM and Fuzzy ARTMAP, are observed.

Carers in the welfare state : on informal care and support for carers in Sweden

  The general aim of this dissertation is to describe and analyse patterns of informal care and support for carers in Sweden. One specific aim is to study patterns of informal care from a broad population perspective in terms of types of care and types of carer. A typology of four different care categories based on what carers do revealed that women were much more likely than men to be involved at the ‘heavy end’ of caring, i.e. providing personal care in combination with a variety of other caring tasks. Men were more likely than women to provide some kind of practical help (Study I). Another aim is to investigate which support services are received by which types of informal caregiver. Relatively few informal caregivers in any care category were found to be receiving any kind of support from municipalities or voluntary organizations, for example training or financial assistance (Study II). The same study also examines which kinds of help care recipients receive in addition to that provided by informal carers. It appears that people in receipt of personal care from an informal caregiver quite often also receive help from the public care system, in this case mostly municipal services. However, the majority of those receiving personal, informal care did not receive any help from the public care system or from voluntary organizations or for-profit agencies (Study II). The empirical material in studies I and II comprises survey data from telephone interviews with a random sample of residents in the County of Stockholm aged between 18 and 84. In a number of countries there is a growing interest among social scientists and social policymakers in examining the types of support services that might be needed by people who provide informal care for older people and others. A further aim of the present dissertation is therefore to describe and analyse the carer support that is provided by municipalities and voluntary organizations in Sweden. The dissertation examines whether this support is aimed directly or indirectly at caregivers and discusses whether the Swedish government’s special financial investment in help for carers actually led to any changes in the support provided by municipalities and voluntary organisations. The main types of carer support offered by the municipalities were payment for care-giving, relief services and day care. The chief forms of carer support provided by the voluntary organizations were support groups, training groups, and a number of services aimed primarily at the elderly care recipients (Study III). Patterns of change in municipal carer support could be discerned fairly soon. The Swedish government’s special allocation to municipalities and voluntary organisations appears to have led to an increase in the number of municipalities providing direct support for carers, such as training, information material and professional caregiver consultants. On the other hand, only minor changes could be discerned in the pattern of carer support services provided by the voluntary organizations. This demonstrates stability and the relatively low impact that policy initiatives seem to have on voluntary organizations as providers (Study IV). In studies III and IV the empirical material consists of survey data from mail questionnaires sent to municipalities and voluntary organizations in the County of Stockholm. In the fields of social planning and social work there appears to be a need to clarify the aims of support services for informal carers. Should the support be direct or indirect? Should it be used to supplement or substitute caregivers? In this process of reappraisal it will be important to take the needs of both caregivers and care recipients into account when developing existing and new forms of support. How informal caregivers and care recipients interact with the care system as a whole is undeniably a fertile field for further research.