Complete Vision-Based Traffic Sign Recognition Supported by an I2V Communication System

Abstract

This paper presents a complete traffic sign recognition system based on vision sensor onboard a moving vehicle which detects and recognizes up to one hundred of the most important road signs, including circular and triangular signs. A restricted Hough transform is used as detection method from the information extracted in contour images, while the proposed recognition system is based on Support Vector Machines (SVM). A novel solution to the problem of discarding detected signs that do not pertain to the host road is proposed. For that purpose infrastructure-to-vehicle (I2V) communication and a stereo vision sensor are used. Furthermore, the outputs provided by the vision sensor and the data supplied by the CAN Bus and a GPS sensor are combined to obtain the global position of the detected traffic signs, which is used to identify a traffic sign in the I2V communication. This paper presents plenty of tests in real driving conditions, both day and night, in which an average detection rate over 95% and an average recognition rate around 93% were obtained with an average runtime of 35 ms that allows real-time performance.

Detection and Recognition of Myanmar Traffic Signs from Video

“…The processing time for all stages of their system was around 1.806 seconds. Furthermore, classifiers as support vector machines (SVM) are being used for recognition of road signs in [5]- [9]. Jiang Yanhua et al used color segmentation, shape detection and pictogram recognition algorithm to detect and recognize traffic signs [10].…”

Circular Traffic Sign Classification Using Hog Based Ring Partitioned Matching

“…The Histogram of Oriented Gradient (HOG) feature was used as the descriptors of the SVM [5][6][7]. In [8], two SVMs with Gaussian kernels were employed to detect the traffic signs.…”

“…The classifier-based methods use the machine learning classifiers, such as the Support Vector Machine (SVM) [3][4][5][6][7][8][9][10], the random forest [11], the Artificial Neural Network (ANN) [12][13][14], [18], [19], and the AdaBoost algorithm [15]. The template-based methods use the cross-correlation algorithm [16] and the histogram matching [17].…”

“…The aim of DAS is to provide a safety driving to the driver, such as to monitor the driver fatigue [1], detect the road lane [2], and recognize the traffic signs [3][4][5][6][7][8][9][10][11][12][13][14][15][16]. Traffic sign recognition (TSR) system is one of the popular and challenging topics in the DAS.…”

“…Traffic sign recognition (TSR) system is one of the popular and challenging topics in the DAS. Basically, TSR consists of two steps [3][4][5][6][7][8][9][10][11][12][13][14][15][16]: traffic sign detection and classification. Traffic sign detection is used to detect the appearance of the traffic sign on an image.…”