A robust algorithm for detection and identification of traffic signs in video data

DUBLIN CITY UNIVERSITY SCHOOL OF ELECTRONIC ENGINEERING A Robust Algorithm for Detection and Identification of Traffic Signs in Video Data Final Report Student: Thanh Bui Minh ID: 10212575 August 2011 MASTER OF ENGINEERING IN ELECTRONIC SYSTEMS Supervised by Dr Ovidiu Ghita Acknowledgements First, I would like to thanks my supervisor Dr Ovidiu Ghita The decision he made to be my supervisor, gave me the opportunity to the project which I am interested in I am grateful to his support, guidance and advices I would also like to thanks Dr Martin Collier and Dr David Molloy for helping me to change my old project and give me a chance to work with Dr Ovidiu Ghita in this project Finally, my personal thanks are extended to my family, friends who give me encouragement, inspiration to finish this project Declaration I hereby declare that, except where otherwise indicated, this document is entirely my own work and has not been submitted in whole or in part to any other university Signed: Date: Table of contents Page The main paper Appendix A: Literature Survey Appendix B: Traffic Signs of Interest Appendix C: Sign Detection and Classification 1–5 A1 – A20 B1 – B3 C1 – C12 Shape Measure C1 Detachment of Sign C3 Support Vector Machines C6 Sign Classification C8 Appendix D: Results D1 – D4 Appendix E: References E1 – E2 A Robust Algorithm for Detection and Identification of Traffic Signs in Video Data Student: Thanh Bui-Minh; Suppervisor: Dr Ovidiu Ghita Abstract—A traffic sign recognition system is presented in this paper The system is able to recognize circular, octagonal and triangular signs which nearly cover all important Irish and UK traffic signs There are three main stages in this system: color segmentation, sign detection and sign classification HSV and HSI color spaces are used for color segmentation to extract the candidate of traffic sign And RGB color space is used in case of achromatic (black and white) color segmentation In the second stage, shape analysis and the area of the inner of the candidates are employed to identify the traffic sign Finally, the identified sign is pre-processed and converted into attributes in order to input to SVMs for sign classification The approach is tested in about 650 images and the number of videos under many different environment conditions and it shows high robustness Index Terms—Color Segmentation, Classification, Support Vector Machines (SVMs), Tracking I INTRODUCTION T he traffic signs have primarily the role to regulate the traffic and to provide information for drivers about road quality, traffic restrictions, warnings, possible directions, etc The vast majority of the road (traffic) signs are standardized and they have distinct shapes and color patterns to facilitate their easy identification in all traffic conditions With the increased traffic congestion that was witnessed over the past decade, the correct recognition of the road signs plays an important role in preventing accidents In particular the signs that regulate the traffic at intersections are of utmost importance since their avoidance can result in collisions with extreme consequences Moreover, the human visual perception abilities depend on the individual’s physical and mental conditions These abilities can be affected by many factors such as tiredness and driving tension The availability of an automatic vision-based system that is able to provide the drivers with the approaching (incoming) traffic signs will be a useful tool that will help the drivers to prevent accidents, save lives and increase the driving performance especially in situations when they are placed in unexpected locations The detection and recognition of traffic signs may face some potential challenges due to the complex environment of roads and the scenes around them The color of the sign fades with time due to the long exposure to sunlight and the reaction of the paint with the air [1] Visibility can be affected by the local light variations such as shadows, clouds and the sun Weather conditions such as fog, rain, clouds and snow is also an obstacle to the detection of the traffic signs [1] The presence of scene objects with similar colors as the traffic signs such as vehicles or building can generate additional computations to the sign detection process Signs may be found damaged, occluded or attached together If the image is captured from a moving car, then it usually suffers from motion blur and car vibration Various methods for traffic signs recognition have been proposed, some of dominant methods are covered in references [2]-[5]-[8] Escalera et al [8] detected signs by using color thresholding to segment and analyze the image The traffic images were presented as input patterns to multilayer perceptron neural networks for the classification Traffic sign detection and recognition based on Support Vector Machines (SVMs) was proposed by MaldonadoBascó et al [2] In their system, color segmentation extracted traffic sign candidates, and the candidates were recognized by two phases: shape classification using linear SVMs and sign classification based on Gaussian-kernel SVMs using gray sign image as input attributes Fleyeh et al [5] introduced a sign detection method based on color and shape of traffic sign Binary sign image and moments such as Zernike or Legendre were inputted to the SVMs for classification Moreover, Fleyeh [3] presented color constancy method for color segmentation in case of poor light conditions The paper is organized as follows The system overview is presented in Section The system consists of three main stages, namely color segmentation, sign detection and sign classification which are described in detail in Section 3, Section and Section 5, respectively Finally, the performance evaluation of the system is presented in Section and section provides concluding remarks II SYSTEM OVERVIEW The overview of our recognition system is shown in Fig The system consists of three main blocks Input image is provided to the color segmentation block The segmentation is an important step that is applied to eliminate all background objects and irrelevant information in the image It generates a binary image containing the road signs and any other objects which are similar to the color of the road signs Subsequently, the binary image is analyzed in the sign detection block Noise and small objects are discarded to find the possible traffic sign blobs by applying connected component labeling algorithm and size filtering Then, shape analysis and the consideration of inner sign are applied for these blobs to identify the traffic sign After the traffic sign is determined, it is scaled to the same dimension and the attribute of each traffic sign is extracted to serve as the input patterns for SVMs in classification stage The sign classification block is responsible for classifying the candidate traffic sign using the attributes of the candidate and the training database based on SVMs The training database is obtained in the offline mode Finally, the classified result is then outputted via a graphic interface In this work, we chose Irish and UK traffic signs as our case study The research focused on four groups of traffic sign namely prohibitory, mandatory, warning and stop & yield as shown in Fig These signs can be classified according to color and shape as shown in Table Some out to find the thresholds as presented in Table TABLE II COLOR THRESHOLD FOR HSV METHOD Color Hue [0:179] Saturation[0:255] Value[0:255] Red Blue [0-12] & [145-179] [96-128] [35-255] [75-255] [30-250] [65-254] The second method is a modification of Escalera’s method This approach uses the information of Hue and Saturation of HSI color space So the RGB image is converted to HSI image and similarly the thresholds are used to extract the color of interest Table shows the thresholds to obtain the red and blue color using this method TABLE III COLOR THRESHOLD FOR HSI METHOD Fig The overview of our traffic sign recognition system other categories such as information signs are ignored, because comparing to those categories, the four mentioned groups of traffic signs are more important and more challenging to be classified by computers Fig Traffic signs of interest TABLE I MEANING OF THE SIGNS WITH RESPECT TO COLOR AND SHAPE Color Shape Meaning Red Red Red Red Blue Octagon Triangle downward Triangle upward Circle Circle Stop Yield Warning Prohibitory Mandatory Color Hue [0:179] Saturation[0:255] Red [0-12] & [145-179] [35-255] Blue [96-129] [75-255] The inner of sign has achromatic (black and white) colors Furthermore, the binary images generated by achromatic and white color segmentation are used in sign detection and sign classification stages, respectively Unfortunately, hue and saturation is not contained enough information to segment white color In this case, the decomposition of image’s achromatic helps to detect achromatic color as shown in equation [2] (| R − G | + | G − B | + | B − R |) f ( R, G , B ) = (1) 3D IF f(R,G,B) < then achromatic color, ELSE chromatic color Where R, G, B are the brightness of the respective color and D is the degree of extraction of an achromatic color By combining f(R,G,B) and thresholds of R, G, B, the white color can be detected The threshold of R, G, B components used in our work are 160, 150 and 140 over the range of 255, respectively We obtained the best segmentation result with D equals to 35 An example of red color segmentation is shown in Fig III COLOR SEGMENTATION The main role of this computational stage is to generate the binary image containing the road signs and objects similar to the color of road signs as well as to eliminate background and irrelevant objects Hue played the central role in the color detection because it is invariant to the variations in light conditions as its scale invariant, shift invariant and invariant under saturation changes [3] So, the hue is the component that is invariant to shadow and highlights [3] Two color segmentation methods have been developed our work which are referred to Shadow and Highlight Color Segmentation Algorithm [3] and modification of Escalera method [8] In the first method, RGB image is converted to HSV image to takes advantage of the characteristic of hue component The thresholds of H, S, V components are used to determine the image areas that are predominantly red and blue Histogram analysis and an exhausted testing are carried Fig Red color segmentation of traffic sign image IV SIGN DETECTION This stage plays an important role in the whole recognition system It implements connected component labeling to form candidate blobs, size filtering to discard noisy and small objects, shape and sign’s inner analysis to identify traffic signs A Connected Component Labeling Algorithm The objects are identified by using component-labeling algorithm that employs contour tracing technique [9] This method scans a binary image only once and traces each contour pixel no more than a constant number of times The method is proved to outperform other methods in term of computational speed, so it is effective in the development of real time applications B Size filtering Size filtering is the process of selecting of labeled objects based on the size of the object The size of the object is calculated by the number of white pixels in the binary image The noise objects, very small or very big traffic signs corresponding to very close or very far signs and the background are eliminated by using the MIN and MAX thresholds The size filtering process improves a lot of time in real time processing as un-important objects are not processed in the image for traffic sign recognition C Shape analysis and sign’s inner consideration There are three types of traffic sign shape: octagon, triangle and circle Three types of shape measures are used to decide the shape of the sign They are ellipticity, triangularity and rectangularity In our experiment, we discovered that the octagonal shape is easily confused with the circular one at medium and high distances, so octagonal signs are included in circular signs class and then using the sign’s inner to identify it Ellipticity can be obtained by applying an affine transform to a circle The simplest way is using the Affine Moment Invariant (I1) [6]: I1 = where µ 20 , moments, and µ20 µ02 − µ112 µ004 and µ11 are the µ02 µ00 is (2) Since the shape measures are computed using the Affine Moment Invariant method which is invariant to general affine transformation, the approach is invariant to rotation, scaling and translation TABLE IV SHAPE MEASURE VALUE FOR CIRCLE AND TRIANGLE SHAPE Shape Ellipticity (E) Triangularity (T) Rectangularity (T) Circle Triangle 0.99 < E < 1.03 E< 0.8 T > 1.43 0.99< T< 1.17 R > 0.69 0.49< R< 0.7 A problem occurs in case of clustered signs, that is the groups of signs share the same pole and they are often attached or partly occluded to one another When the image is color segmented, the signs become attached to each other and hence connected component labeling creates a single object Obviously, this new object does not belong to any of the expected sign shapes which the algorithm deals with The Hough circle transform is primarily used to solve this problem, however it has two disadvantages: only detect the circle signs and it fails to recognize the circle signs when the sign is rotated and/or damaged A more robust method is developed in this thesis The method uses the inner of the sign to identify the shape of the sign The reason is that when the traffic sign has a triangular or circle shape, the inner of the sign also has similar shape with some exceptions The advantage of this approach is that the inner of clustered signs are always detached and it is illustrated in Figure second order central the zero order central moment The ellipticity (E) and triangularity (T) are measured using equation (3) and (4), respectively [6]: 16π I1 if I1 ≤ 16π  (3) E= otherwise  16π I  108 I1  T =  1108 I  if I1 ≤ 108 (4) otherwise Perfect elliptic has ellipticity E of Similarly, perfect triangle has triangularity T of The rectangularity R is measured by the calculating the area of the region under considering to the area of its minimum bounding rectangle (MBR) The three shape measures assume that the object is homogeneous (does not contain any holes) Since traffic signs have two different colors, one for the rim and the other for the inner, the rim color is used for the segmentation and then the holes are filled with the same grey level In case the object under analysis is occluded by another object, the convex hull of the object is calculated to generate a homogenous object Table shows the value of E, T, R to classify the shapes In order to increase the accuracy of traffic sign detection, the interior of sign (sign’s inner) is evaluated by calculating the ratio of white area of the sign’s inner and the whole area of the sign For instance, if the object has red color, circle shape and the ratio is greater than 0.35, then the object belongs to prohibitory sign group The thresholds to recognize the STOP and NO ENTRY signs are smaller than that of the prohibitory signs The same method is used to identify mandatory and warning sign group Fig The result of the detection of attached sign (from left to right and top to bottom: attached sign image, red color segmentation image, sign’s inner and sign identification result) V SIGN CLASSIFICATION The traffic signs are classified according to their attributes using SVMs A Support Vector Machines (SVMs) SVMs is a pattern classification and regression techniques based on mathematical foundations of statistical learning theory, which was first proposed by Vapnik in 1992 [5] The basic training principle of SVMs is to find an optimal hyperplane to linearly separate two classes The optimal hyperplane is formed in such a way to minimize the expected classification error for unseen test samples In binary classification, the training data are labeled {xi, yi}, where i = [1 n], yi Є {-1, 1}, xi ∈ ℜ d , d is the dimension of the vector, and n is the number of training vector The classification of a new pattern x can be obtained by solving the decision function f(x) as shown in equation (5), where αi are the Lagrange multipliers and b is the bias offset  n  f ( x ) = sign  ∑ yiα i ( x xi ) + b   i =1  (5) However, in many cases, the data cannot be separated by a linear function A solution is to map the input data into a φ ( x ) where the higher-dimension feature space classification can be performed by linear SVMs So the decision function is now expressed as: n f ( x ) = ∑ α i yi K ( xi , x ) + b (6) i =1 Fig Three different types of the attributes of speed limit sign where x is the input vector to be classified, K() is kernel function A kernel constructs an implicit mapping from the input space in to a feature space There are four types of kernels: Linear, Polynomial, Radial Basis Function (RBF) and Signmoid For classification problems, the optimal hyper-plane could not be able to separate the input vectors completely, so different classification types have been proposed for SVMs The most common types are C-support vector classification (C-SVC) and ν -support vector classification (ν -SVC) Appendix C-3 describes more detail about Kernel and CSVC and ν -SVC B Classification When the candidate blob of sign is identified, the gray sign image is normalized to 31x31 In order to reduce the number of attributes and discard the effect of noise (outside the sign but belong to the bounding box), only those pixels that must be part of the sign (pixel of interest, PoI) are used For example, in case of circular sign, only pixels that are inside the inscribed circle, which belong to the normalized bounding box, are computed to get the attributes to input to SVMs for classification Both training and testing are done according to the color of each candidate region So every candidate blob is only compared to those signs that have the same color as the blob to increase the accuracy and reduce the complexity of the problem Every image in the training database is 31x31 pixels and is invariant the in-plane transformations, that include scale, translation and rotation In this work, we use 12 classes for red color signs and classes for blue color signs Oneversus-all SVMs strategy are used So the number of classifiers M needed is equal to the number of classes that belong to the case considered that is 12 and classifiers for red and blue color signs, respectively The amount of training samples per class is 30 To search for the decision region, all attributes of a specific class are grouped together against all attributes corresponding to the rest of classes The traffic signs are located in outdoor, so they are often affected by the variation of illumination conditions Consequently, the gray image of original sign does not provide a robust attributes to SVMs In our work, three kinds of the attributes of the sign are used for classification: • Gray level attributes • The original gray image is pre-processed by applying histogram equalization method then the gray level attributes are extracted • Binary attributes: The attributes of the sign are extracted from the binary image which is obtained by applying white color segmentation to the original image Figure presents three different types of the attributes of 30km/h speed limit sign and some classification results are Fig Some results of sign classification shown in Figure Appendix C-4 presents more detail about the classes for classification VI RESULTS More than 650 images which were captured from many different environmental conditions are used to evaluate the performance of the system The experiments are carried out for each stage of the system, color segmentation, sign detection and sign classification A Color Segmentation As described in Section 3, two methods for color segmentation have been developed in this thesis The first method uses three components H, S, V of HSV color space and the second method uses only H, S components of HSI color space Table presents the success rate of color segmentation of signs in images taken under different light conditions and different effects of two methods The successful color segmentation means that the method generates the complete binary object of the traffic signs The overall success rate of the first method and the second methods are 91.5% and 91.8%, respectively As can be seen from the table, the second method which uses H, S components gives much better segmentation result than the first method in case of Bad lighting, High lighting and Night lighting conditions The reason is that H and S are components that are invariant to shadow and high light conditions [3] In occlusion condition when the signs are occluded by other objects, the result is not good because it highly depends on the state of occlusion For instance, the color segmentation fails when the sign is almost covered more than 20% by other objects B Sign Detection The success of the sign detection stage significantly depends on color segmentation, so the result of sign detection is evaluated based on two color segmentation methods The accuracy of sign detection in images under different conditions is illustrated in Table The overall success rates of two analyzed methods are 86.5% and 87.6%, respectively In this work, a robust method has been introduced to solve the problem of clustered signs by using the inner of the signs, the accuracy rate of this method is 90% compared to 10% when this method is not used Appendix C-2 shows more results of this method TABLE V SUCCESS RATE OF COLOR SEGMENTATION UNDER DIFFERENT CONDITIONS First method Second method Conditions No of Signs (HSV) (HSI) Clustered sign 90 95.6% 95.6% Bad lighting 107 93.5% 99.1% Blurred Signs 89 89.9% 80.9% Damaged Signs 39 84.6% 87.2% High Lighting 97 97.9% 98.9% At Night 24 87.5% 91.6% Occluded Signs 52 78.8% 84.6% Rotated Signs 53 94.3% 90.5% Snow 30 93.3% 90% Normal 90 100% 100% Overall 671 91.5% 91.8% TABLE VI SUCCESS RATE OF SIGN DETECTION UNDER DIFFERENT CONDITIONS First method Second method Conditions No of signs (HSV) (HSI) Clustered sign 90 90% 90% Bad lighting 107 91.6% 99.1% Blurred Signs 89 85.4% 76.1% Damaged Signs 39 82% 84.6% High Lighting 97 92.8% 93.8% At Night 24 87.5% 91.7% Occluded Signs 52 60% 65.6% Rotated Signs 53 92.4% 88.6% Snow 30 83.3% 86.6% Normal 90 100% 100% Overall 671 86.5% 87.6% C Sign Classification After referring from [5], [10] and carrying many experiments, we recognize that C-SVM with Linear kernel gives the best performance for sign classification The 31x31 pixels block of sign is used for both training and testing, so the number of attributes per sign is 961 As described in section 5, three types of attributes of sign are used for SVMs classification to find the highest accuracy Eight classes of red color signs are used to evaluate the performance of classification stage Table presents the result of classification corresponding to three types of input attributes TABLE VII SUCCESS RATE OF SIGN CLASSIFICATION UNDER DIFFERENT INPUT ATTRIBUTES USING C-SVM WITH LINEAR KERNEL Input Attributes Training Testing Overall Origin gray signs Sign after applying Histogram Eq Binary signs 100% 100% 100% 95.9% 98.67% 99.5% As can be seen from the table, binary attribute gives the highest accuracy rate (99.5%), followed by the attributes after applying histogram equalization (98.67%) However, in order to get binary attributes, the white color segmentation method is applied to original image as shown in detection stage, and the white color segmentation is often sensitive to the illumination of light because it used RGB color space, this is a disadvantage of binary attributes The attributes extracted from sign after applying histogram equalization to original image gives higher success rate than original gray sign The reason is that histogram equalization increases the local contrast of the image, especially when the data of the image is represented by close contrast values More result images are presented in Appendix D TABLE VIII A COMPARISON OF OUR WORK AND FLEYEH’S WORK [5] Color Sign Sign segmentation Detection Classification Fleyeh’s work 88.15% 82.3% 100% Our work 91.8% 87.6% 99.5% Table shows a comparison of our work and Fleyeh’s work [5] We get higher success rates in case of color segmentation and sign detection stages Meanwhile in sign classification stage, Fleyeh’s work used binary attributes which obtained from yellow color segmentation using HSV color, so the result is quite perfect (100%) For demonstration, 12 reds signs and blue signs are trained and classified correctly in this thesis A number of videos with traffic signs were captured to test the recognition system and a final video result has been created The whole system has been implemented in C++ language using OPENCV library version 2.2 The mean processing time of 0.27s per frame using a 2.2GHz Intel Core Duo CPU T6600 with 448x336 pixels of frame VII CONCLUSION A complete method for traffic sign recognition which takes into consideration almost difficulties regarding to object recognition in outdoor environment has been presented in this paper The system can recognize all traffic signs of interest with high accuracy A robust method has been developed to overcome the problem of clustered signs using sign’s inner In order to improve the performance of the system, tracking method using Kalman filter has been investigated The tracking helps to estimate the traffic sign position in successive frames by using the information of inter-frame However, due to shortage of time, the tracking method is listed in the future work ACKNOWLEDGMENT I would like to express my sincere thanks to Dr Ovidiu Ghita for his precious advices and helps for this thesis REFERENCES [1] [2] [3] [4] [5] [6] [7] H Fleyeh, “Traffic Sign Recognition by Fuzzy Sets”, 2008 IEEE Intelligent Vehicles Symposium Eindhoven University of Technology Eindhoven, The Netherlands, June 4-6, 2008 Saturnino Maldonado-Bascó, Sergio Lafuente-Arroyo, Pedro GilJiménez, Hilario Gómez-Moreno and Francisco López-Ferreras, “Road-Sign Detection and Recognition Based on Support Vector Machines”, IEEE Transaction on Intelligent Transportation Systems, Vol 8, No 2, June 2007 Fleyeh, H., "Shadow and Highlight Invariant Colour Segmentation Algorithm for Traffic Signs" second IEEE Conference on Cybernetics and Intelligent Systems, Bangkok, Thailand, June, 2006 S Maldonado-Bascón, J Acevedo-Rodríguez, A FernándezCaballero, F López-Ferreras, “An optimization on pictogram identification for the road-sign recognition task using SVMs”, Computer Vision and Image Understanding, 2009 H Fleyeh, “Traffic and road sign recognition”, Dalarna University, Sweden, 2008 P Rosin, "Measuring shape: ellipticity, rectangularity, and triangularity", Machine Vision and Applications, vol 14, pp 172-184, 2003 H Gómez-Moreno, S Maldonado-Bascón, P Gil-Jiménez, S Lafuente-Arroyo, “Goal Evaluation of Segmentation Algorithms for Traffic Sign Recognition”, IEEE trans on Intelligent transportation system, Dec 2010 For full references list, please refer to Appendix E Appendix A A Robust Algorithm for Detection and Identification of Traffic Signs in Video Data Literature Survey Student: Thanh Bui Minh ID: 10212575 April 2011 MASTER OF ENGINEERING IN ELECTRONIC SYSTEMS Supervised by Dr Ovidiu Ghita (a) Input image (b) Red color segmentation (d) Pictogram of signs after size adjusting (e) Result More results a) Input image b) Red color segmentation c) Invert of (b) d) Result Failure situation When the shape of sign’s inner is not similar to the shape of sign’s rim, this method cannot get expected results Following images illustrates this situation, the system cannot detect the circle sign in the input image C-4 a) Input image b) Red color segmentation c) Invert of (b) d) Result C-5 Support Vector Machines (SVMs) SVMs is a pattern classification and regression techniques based on mathematical foundations of statistical learning theory, which was first proposed by Vapnik in 1992 [5] The basic training principle of SVMs is to find an optimal hyper-plane to linearly separate two classes The optimal hyper-plane is formed in such a way to minimize the expected classification error for unseen test samples In binary classification, the training data are labeled {xi, yi}, where i = [1 n], yi Є {-1, 1}, xi ∈ ℜ d , d is the dimension of the vector, and n is the number of training vector The classification of a new pattern x can be obtained by solving the decision function f(x) as shown in equation (5), where αi is the Lagrange multipliers, b is the bias  n  f ( x ) = sign  ∑ yiα i ( x.xi ) + b   i =1  (5) However, in many cases, the data cannot be separated by a linear function A solution is to map the input data into a higher-dimension feature space φ ( x) where the classification can be performed by linear SVMs So the decision function is now expressed as: n f ( x ) = ∑ α i yi K ( xi , x) + b (6) i =1 where x is the input vector to be classified, K() is kernel function A kernel constructs an implicit mapping from the input space in to a feature space There are four types of kernels: Linear, Polynomial, Radial Basis Function (RBF) and Signmoid • Linear: K ( xi , x j ) = xiT x j • Polynomial: K ( xi , x j ) = (γ xiT x j + r )d , γ > • Radial basis function (RBF): K ( xi , x j ) = exp(−γ xi − x j ), γ > • Sigmoid K ( xi , x j ) = tanh(γ xiT x j + r ) where γ , r and d are kernel parameters For classification problems, the optimal hyper-plane could not be able to separate the input vectors completely, so different classification types have been proposed for SVMs The most common types are C-support vector classification (C-SVC) and ν -support vector classification ( ν -SVC) Given training vector xi ∈ ℜ d , C-SVC solves the following problem for binary classification yi ∈ {−1,1} : C-6 Minimizeξ ,w.b l T w w + C ∑ ξ i , where w is the optimal hyper-plane, slack variable ξ allows i =1 some data to be misclassified, and C ( C ∈ [0, ∞] ) is a priori constant A higher value of C gives a larger penalty for classification error The ν -SVC uses a parameter ν to control the number of support vectors and errors The primal form of it: Minimizeξ , w.b T l w w −νρ + ∑ ξ i , where the parameter ν ∈ (0,1] is an upper bound on the l i =1 fraction of training errors and a lower bound of the fraction of support vectors By increasingν , more training errors take place and the margin of the hyper-plane is increased C-7 Sign Classification Eight classes of red sign are used to evaluate the performance of the classification stage The following images shows a part of the gray sign of training data Red sign Classes Class Class Class Class C-8 Class Class Class Class C-9 Blue sign classes: Class Class Class Class Three types of attributes of signs for SVMs classification are shown as follows They are gray sign, gray sign after applying histogram equalization and binary sign Gray signs Gray sign after applying histogram equalization Binary sign C - 10 For demonstration, 12 reds signs and blue signs are trained and classified correctly in this thesis A number of videos with traffic signs were captured to test the recognition system and a final video result has been created The following images show the classes used for demonstration 12 red sign classes Class Sign Figure Stop Yield Double bend ahead No left turn No right turn No Straight Ahead Speed Limit 60 Speed Limit 30 Speed Limit 70 No Overtake 10 Cross Road Ahead 11 Roundabout Ahead C - 11 blue sign classes: Class Sign Keep Left Turn Left Pass Either Side Pedal Bicycle Only Turn Right C - 12 Figure APPENDIX D RESULTS A result video is created to present the classification result which includes many environmental conditions: bad lighting, occluded signs, blurred signs, raining and clustered signs Moreover, some results are shown in the following images: D-1 D-2 D-3 D-4 APENDIX E REFERENCES [1] H Fleyeh, “Traffic Sign Recognition by Fuzzy Sets”, 2008 IEEE Intelligent Vehicles Symposium Eindhoven University of Technology Eindhoven, The Netherlands, June 4-6, 2008 [2] Saturnino Maldonado-Bascó, Sergio Lafuente-Arroyo, Pedro Gil-Jiménez, Hilario GómezMoreno and Francisco López-Ferreras, “Road-Sign Detection and Recognition Based on Support Vector Machines”, IEEE Transaction on Intelligent Transportation Systems, Vol 8, No 2, June 2007 [3] Fleyeh, H., "Shadow and Highlight Invariant Colour Segmentation Algorithm for Traffic Signs" second IEEE Conference on Cybernetics and Intelligent Systems, Bangkok, Thailand, June, 2006 [4] S Maldonado-Bascón, J Acevedo-Rodríguez, A Fernández-Caballero, F López-Ferreras, “An optimization on pictogram identification for the road-sign recognition task using SVMs”, Computer Vision and Image Understanding, 2009 [5] H Fleyeh, “Traffic and road sign recognition”, Dalarna University, Sweden, 2008 [6] P Rosin, "Measuring shape: ellipticity, rectangularity, and triangularity", Machine Vision and Applications, vol 14, pp 172-184, 2003 [7] H Gómez-Moreno, S Maldonado-Bascón, P Gil-Jiménez, S Lafuente-Arroyo, “Goal Evaluation of Segmentation Algorithms for Traffic Sign Recognition”, IEEE trans on Intelligent transportation system, Dec 2010 [8] A d l Escalera, L E Moreno, M A Salichs, and J e M i Armingol, “Road Traffic Sign Detection and Classification”, IEEE Transactions on Industrial Electronics, vol 44, pp 848-859, Dec 1997 [9] Fu Chang, Chun-Jen Chen, and Chi-Jen Lu, “A Linear-Time Component-Labeling Algorithm Using Contour Tracing Technique”, Computer Vision and Image Understanding, 2004 [10] Min Shi, Haifeng Wu and Hansan Fley, “Support Vector Machines for Traffic Signs Recognition” International Joint Conf on Neural Network, 2008 [11] Tam T Le, Son T Tran, Seichii Mita, Thuc D Nguyen, “Realtime Traffic Sign Detection Using Color and Shape-Based Features", The 2nd Asian Conference on Intelligent Information and Database Systems (ACIIDS), LNAI5991, Hue, Vietnam, 2010 [12] Gary Bradski and Adrian Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, First Edition, O’relly Publisher, 2008 E-1 [13] Intel Corporation, Open Source Computer Vision Library, Reference Manual, 2001 [14] Department of Transport of Ireland, “Traffic Signs Manual” 2010 [15] Department of Transport of UK, “Traffic Signs Manual” 2004 E-2 ... classification block is responsible for classifying the candidate traffic sign using the attributes of the candidate and the training database based on SVMs The training database is obtained in the offline... diversification of data on both training and testing data A- 18 Algorithm for detection and identification of traffic signs in video Thanh Bui Minh Chapter - Conclusions and Project Schedule The traffic. .. image in the training database is 31x31 pixels and is invariant the in- plane transformations, that include scale, translation and rotation In this work, we use 12 classes for red color signs and