Traffic Sign Recognition using Multi-Modal Representation for Intelligent Vehicles

Zixing Cai and Mingqin Gu


Traffic sign recognition, DT-CWT, 2DICA, Intra pictogram


A novel algorithm for traffic sign recognition was introduced here. Image segmentation based on transforming RGB color space value and shape classifier based signature feature were used to detect traffic signs in complex urban scenes. For improving recognition accuracy, two different methods were presented to classify the detected candidate regions of traffic sign. The one method was dual-tree complex wavelet transform (DT-CWT) and 2D independent component analysis (2DICA) that represented candidate regions on grayscale image and reduced feature dimension, then a nearest neighbor classifier was employed to classify traffic sign image and reject noise regions. The other method was template matching based on intra pictograms of traffic sign. The obtained different recognition results were fused by some decision rules. Experimental results showed that overall recognition rate of proposed algorithm was more than 89% and the average frame rate was up to 6.6fps. These indicated that the proposed recognition method was robust, effective, and accurate to classify traffic signs

Important Links:

Go Back