Segmentation of Urban Traffic Scene Based on 3D Structure

摘要：

This paper proposes an approach for image segmentation of the urban traffic scene captured from a car-mounted camera. First of all, an improved SIFT feature matching algorithm is adopted for extracting 2D keypoints of the scene. Tracking the 2D keypoints generates the 3D points clouds that can estimate the 3D world structure and motion features. And then Multiple Kernels Support Vector Machines (MKSVM) is employed for sematic segmentation based on motionderived 3D structure and SIFT features. Experiments show the efficiency and the relevancy of our approach.

关键词： image segmentation 3D structure SIFT MKSVM urban traffic

作者: Tan Lun Zheng Xia Li-min Liu Yanfei

作者单位: College of Information Science and Engineering, Central South University, Chang sha 410075 Departmen College of Information Science and Engineering, Central South University, Chang sha 410075 Department of Computer Engineering, Zhongshan Polytechnic, Zhongshan Guangdong, China 528404

会议类型: 国际会议

会议名称: 2011 International Conference on Image Analysis and Signal Processing(2011第三届图像分析与信号处理国际会议 IASP 2011)

会议地点: 武汉

会议语种:英文

页码: 240-243

在线出版日期: 2011-10-21（万方平台首次上网日期，不代表论文的发表时间）