Road Sign Recognition based onInvariant Features using SupportVector Machine

Since last two decades researches have been working on developing systems that can assistsdrivers in the best way possible and make driving safe. Computer vision has played a crucialpart in design of these systems. With the introduction of vision techniques variousautonomous and robust real-time traffic automation systems have been designed such asTraffic monitoring, Traffic related parameter estimation and intelligent vehicles. Among theseautomatic detection and recognition of road signs has became an interesting research topic.The system can assist drivers about signs they don’t recognize before passing them.Aim of this research project is to present an Intelligent Road Sign Recognition System basedon state-of-the-art technique, the Support Vector Machine. The project is an extension to thework done at ITS research Platform at Dalarna University [25]. Focus of this research work ison the recognition of road signs under analysis. When classifying an image its location, sizeand orientation in the image plane are its irrelevant features and one way to get rid of thisambiguity is to extract those features which are invariant under the above mentionedtransformation. These invariant features are then used in Support Vector Machine forclassification. Support Vector Machine is a supervised learning machine that solves problemin higher dimension with the help of Kernel functions and is best know for classificationproblems.

Evaluation of Red Colour Segmentation Algorithms in Traffic Signs Detection

Colour segmentation is the most commonly used method in road signs detection. Road sign contains several basic colours such as red, yellow, blue and white which depends on countries.The objective of this thesis is to do an evaluation of the four colour segmentation algorithms. Dynamic Threshold Algorithm, A Modification of de la Escalera’s Algorithm, the Fuzzy Colour Segmentation Algorithm and Shadow and Highlight Invariant Algorithm. The processing time and segmentation success rate as criteria are used to compare the performance of the four algorithms. And red colour is selected as the target colour to complete the comparison. All the testing images are selected from the Traffic Signs Database of Dalarna University [1] randomly according to the category. These road sign images are taken from a digital camera mounted in a moving car in Sweden.Experiments show that the Fuzzy Colour Segmentation Algorithm and Shadow and Highlight Invariant Algorithm are more accurate and stable to detect red colour of road signs. And the method could also be used in other colours analysis research. The yellow colour which is chosen to evaluate the performance of the four algorithms can reference Master Thesis of Yumei Liu.

Firm relocation and firm profits : Evidence from the Swedish wholesale trade sector

This study analyses the effects of firm relocation on firm profits, using longitudinal data on Swedish limtied liability firms and employing a difference-in-differnce propensity score method in the empirical analysis. Using propensity score matching, the pre-relocalization differneces between relocating and non-relocating firms are balanced. In addition to that, a difference-in-difference estimator is employed in order to control for all time-invariant unobserved heterogeneity among firms. For matching, nearest neighbour matching, using the one-, two- and three nearest neighbours is employed. The balanacing results indicate that matching achieves a good balance, and that similar relocating and non-relocating firms are being compared. The estimated average treatment on the treatment effects indicate thats relocations has a significant effect on the profits of the relocating firms. In other words, firms taht relocate increase their profits significantly, in comparison to what the profits would be had the firms not relocated. This effect is estimated to vary between 3 to 11 percentage points, depending on the lenght of the analysed period after relocation. 

Feasible estimation of generalized linear mixed models (GLMM) with weak dependency between groups

This paper presents a two-step pseudo likelihood estimation technique for generalized linear mixed models with the random effects being correlated between groups. The core idea is to deal with the intractable integrals in the likelihood function by multivariate Taylor's approximation. The accuracy of the estimation technique is assessed in a Monte-Carlo study. An application of it with a binary response variable is presented using a real data set on credit defaults from two Swedish banks. Thanks to the use of two-step estimation technique, the proposed algorithm outperforms conventional pseudo likelihood algorithms in terms of computational time.

Essays on firm dynamics in the Swedish wholesale trade sector

This thesis consists of a summary and five self-contained papers addressing dynamics of firms in the Swedish wholesale trade sector. Paper [1] focuses upon determinants of new firm formation in the Swedish wholesale trade sector, using two definitions of firms’ relevant markets, markets defined as administrative areas, and markets based on a cost minimizing behavior of retailers. The paper shows that new entering firms tend to avoid regions with already high concentration of other firms in the same branch of wholesaling, while right-of-the-center local government and quality of the infrastructure have positive impacts upon entry of new firms. The signs of the estimated coefficients remain the same regardless which definition of relevant market is used, while the size of the coefficients is generally higher once relevant markets delineated on the cost-minimizing assumption of retailers are used. Paper [2] analyses determinant of firm relocation, distinguishing between the role of the factors in in-migration municipalities and out-migration municipalities. The results of the analysis indicate that firm-specific factors, such as profits, age and size of the firm are negatively related to the firm’s decision to relocate. Furthermore, firms seems to be avoiding municipalities with already high concentration of firms operating in the same industrial branch of wholesaling and also to be more reluctant to leave municipalities governed by right-of-the- center parties. Lastly, firms seem to avoid moving to municipalities characterized with high population density. Paper [3] addresses determinants of firm growth, adopting OLS and a quantile regression technique. The results of this paper indicate that very little of the firm growth can be explained by the firm-, industry- and region-specific factors, controlled for in the estimated models. Instead, the firm growth seems to be driven by internal characteristics of firms, factors difficult to capture in conventional statistics. This result supports Penrose’s (1959) suggestion that internal resources such as firm culture, brand loyalty, entrepreneurial skills, and so on, are important determinants of firm growth rates. Paper [4] formulates a forecasting model for firm entry into local markets and tests this model using data from the Swedish wholesale industry. The empirical analysis is based on directly estimating the profit function of wholesale firms and identification of low- and high-return local markets. The results indicate that 19 of 30 estimated models have more net entry in high-return municipalities, but the estimated parameters is only statistically significant at conventional level in one of our estimated models, and then with unexpected negative sign. Paper [5] studies effects of firm relocation on firm profits of relocating firms, employing a difference-in-difference propensity score matching. Using propensity score matching, the pre-relocalization differences between relocating and non-relocating firms are balanced, while the difference-in-difference estimator controls for all time-invariant unobserved heterogeneity among firms. The results suggest that firms that relocate increase their profits significantly, in comparison to what the profits would be had the firms not relocated. This effect is estimated to vary between 3 to 11 percentage points, depending on the length of the analyzed period. 

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.