Kriminalitetens geografi : vardagsbrottslighetens spatiala fördelning i Borlänge

The aim of this thesis is to describe and analyze the geographical distribution of everyday criminality in the town of Borlänge during the year 2002 and to analyze which measures to be taken in the physical social planning to decrease this everyday criminality there. The term everyday criminality is here to be understood as those categories of crime that appear most frequently in the records of reports to the police every year. Here two kinds of crime have been in focus, thefts from cars and office burglary.In fulfilling this aim two main questions have been answered. The first one is how the everyday criminality was distributed geographically in the town of Borlänge during the year 2002. The second one is which measures to be taken in the physical social planning to decrease this everyday criminality in the town of Borlänge.In order to answer the first question a spatial autocorrelation analysis, Local Moran LISA has been used. This method is based on the measurement Moran´s I and shows the spatial autocorrelation for every single location. To answer the second question three different theories of crime prevention through environmental design have been studied and applied in the analysis. These are Jane Jacobs’ ideas about ”the living city”, Oscar Newman´s ideas about ”defensible space” and Ronald V. Clarke´s theories about crime prevention.The major conclusions that can be drawn from this thesis are that the risk of being exposed to thefts from cars, during the analyzed time period, was highest in Centrum and Hagalund and their surroundings. The lowest risk of being exposed to this type of crime was found in Domnarvet and Islingby, during the year 2002. The highest risk of being a victim of the crime office burglary was found in Hagalund and its surroundings and in the single area of Kvarnsveden. The corresponding lowest risk was found in Lergärdet and its surroundings and in Norra Backa and Kupolen. The measures that should be taken in order to decrease these types of criminality can be divided into overall changes and place-specific changes. When it comes to the crime thefts from cars a more attractive central business district, a better view of parking lots from nearby buildings, dividing of larger parking lot zones into smaller ones, migration of hidden parking lots and stronger access control to parking lots where problems with this kind of crime have occurred have been suggested as overall changes. The corresponding place-specific changes are to remove vegetation that is blocking the view, better lighting and to put up signs with information about increased risk of exposure to crime at parking lots with the most problems. To decrease the amount of office burglaries overall changes as to create a better view of the area from nearby surroundings, move bigger office compartments or divide them into smaller units, rebuild characteristic buildings and increase security by strengthening the access control to offices with these kinds of problems could be useful. Finally there are possibilities to decrease office burglary by using place-specific measures as surveillance cameras combined with signs containing information about these, high fences and better lighting around the buildings where a higher risk of being exposed to this kind of criminality is present.

Traffic and Road Sign Recognition

This thesis presents a system to recognise and classify road and traffic signs for the purpose of developing an inventory of them which could assist the highway engineers’ tasks of updating and maintaining them. It uses images taken by a camera from a moving vehicle. The system is based on three major stages: colour segmentation, recognition, and classification. Four colour segmentation algorithms are developed and tested. They are a shadow and highlight invariant, a dynamic threshold, a modification of de la Escalera’s algorithm and a Fuzzy colour segmentation algorithm. All algorithms are tested using hundreds of images and the shadow-highlight invariant algorithm is eventually chosen as the best performer. This is because it is immune to shadows and highlights. It is also robust as it was tested in different lighting conditions, weather conditions, and times of the day. Approximately 97% successful segmentation rate was achieved using this algorithm.Recognition of traffic signs is carried out using a fuzzy shape recogniser. Based on four shape measures - the rectangularity, triangularity, ellipticity, and octagonality, fuzzy rules were developed to determine the shape of the sign. Among these shape measures octangonality has been introduced in this research. The final decision of the recogniser is based on the combination of both the colour and shape of the sign. The recogniser was tested in a variety of testing conditions giving an overall performance of approximately 88%.Classification was undertaken using a Support Vector Machine (SVM) classifier. The classification is carried out in two stages: rim’s shape classification followed by the classification of interior of the sign. The classifier was trained and tested using binary images in addition to five different types of moments which are Geometric moments, Zernike moments, Legendre moments, Orthogonal Fourier-Mellin Moments, and Binary Haar features. The performance of the SVM was tested using different features, kernels, SVM types, SVM parameters, and moment’s orders. The average classification rate achieved is about 97%. Binary images show the best testing results followed by Legendre moments. Linear kernel gives the best testing results followed by RBF. C-SVM shows very good performance, but ?-SVM gives better results in some case.