Salient Traffic Sign Detection Based on Multiscale Hypercomplex Fourier Transform

摘要：

The paper proposes a new approach to detect salient traffic signs, which is based on visual saliency and auto-generated strokes for image segmentation. The proposed algorithm deals with two tasks on detecting traffic signs: auto-location and auto-extraction. Firstly, inspired by recent work of visual saliency detection, we obtain the location of traffic signs in a natural image by multi-scale phase spectrum of quaternion Fourier transformation (MSPQFT). Secondly, in order to extract traffic signs, auto-generated strokes are used instead of drawing the strokes by the users, the sign board area is extracted using automatic interactive image segmentation. Extensive experiments on public datasets show that our approach outperforms state-of-the-art methods remarkably in salient traffic sign detection. Moreover, the proposed detection method has higher accurate rate and robustness to different natural scenes.

关键词： Traffic sign detection Visual saliency Quaternion Fourier Transform(QFT) Multiscale Image segmentation.

作者: Ce Li Yaling Hu

作者单位: College of Electrical and Information Engineering Lanzhou Univ. of Tech.Lanzhou, China Institute of Institute of Artificial Intelligence and Robotics Xian Jiaotong University Xian, China

会议类型: 国际会议

会议名称: 2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

会议地点: 上海

会议语种:英文

页码: 1997-2000

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）