Title :
An efficient real time rectangle speed limit sign recognition system
Author :
Zhang Yankun ; Hong Chuyang ; Wang, Chingyue
Author_Institution :
Corp. Tech. Group (CTG), Shanghai RD Center, Shanghai, China
Abstract :
This paper present an efficient real time rectangle speed limit sign recognition system. The system design considers computation load and hardware resources for driver assistant system. First multi-scale overlapping LBP features are used to train AdaBoost cascade classifier for speed limit sign object detection. Then a simple linear prediction method is used to do tracking task. At the recognition stage, a novel efficient algorithm is used to correct rotation angle, and then integral image based adaptive threshold algorithm is adopted to segment the speed limit number. The clustering based binary tree of linear support vector machine is adopted for classification task. The system is tested on real road scene video sequences. It achieves 98.3% recognition rate with approximate 16 fps frame rate on laptop.
Keywords :
driver information systems; feature extraction; image segmentation; object detection; pattern clustering; prediction theory; support vector machines; trees (mathematics); AdaBoost cascade classifier; clustering based binary tree; computation load; driver assistant system; hardware resources; image segmentation; integral image based adaptive threshold algorithm; linear prediction method; linear support machine; multiscale overlapping LBP feature; object detection; real time rectangle speed limit sign recognition system; Binary trees; Clustering algorithms; Hardware; Image recognition; Image segmentation; Object detection; Prediction methods; Real time systems; Support vector machine classification; Support vector machines;
Conference_Titel :
Intelligent Vehicles Symposium (IV), 2010 IEEE
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-7866-8
DOI :
10.1109/IVS.2010.5548140
