Complete vision-based traffic sign recognition supported by an I2V communication system

• Published in: Sensors (Basel, Switzerland) Vol. 12; no. 2; pp. 1148 - 1169
• Main Authors: García-Garrido, Miguel A, Ocaña, Manuel, Llorca, David F, Arroyo, Estefanía, Pozuelo, Jorge, Gavilán, Miguel
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.02.2012; Molecular Diversity Preservation International (MDPI)
• Subjects: advanced driver assistance systems; Artificial Intelligence; Automobile Driving; Communications systems; computer vision; Driving conditions; Equipment Design; Equipment Failure Analysis; I2V; Image Interpretation, Computer-Assisted - instrumentation; Location Directories and Signs; Pattern Recognition, Automated - methods; Recognition; Roads; Roads & highways; Sensors; Street signs; Support vector machines; traffic sign recognition; Traffic signs; Travel; User-Computer Interface; Vision; Wireless Technology - instrumentation; Spain; traffic sign recognition; I2V; advanced driver assistance systems; computer vision
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s120201148

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.