3-Dimension Traffic Reconstruction by Automatic Camera Calibration under Homogenous Fog

摘要：

　　A novel algorithm for 3-Dimension traffic reconstruction by automatic and dynamic camera calibration based on dark channel prior in homogenous fog weather condition is presented in this article.Camera fixed in the middle of road is calibrated by scene distance information implicated in homogenous fog weather condition.Unlike other works in 3-D traffic scene reconstruction,this proposed algorithm is executed by camera calibration and the traffic model that only includes road plane and vehicles in motion.Priori information(prior distance information marked by manual in traffic scene and vehicle length)is not available here.Painted lines are not neglected in the proposed model because sometime there are no traffic lanes in un-structured road.Four main steps compose our algorithm.At the end of this paper,calibration results and 3-D reconstruction results will be given.Comparison with other algorithm in MATLAB verifies the effectiveness of our proposed algorithm.

关键词： 3-Dimension traffic scene reconstruction camera calibration homogenous fog weather condition dark channel prior monocular

作者: SONG Hongjun GAO Yuanyuan

作者单位: College of Information Engineering,Chinese,Zhejiang A&F University,Hangzhou 311300

会议类型: 国际会议

会议名称: The 33th Chinese Control Conference第33届中国控制会议

会议地点: 南京

会议语种:英文

页码: 3356-3360

在线出版日期: 2014-07-28（万方平台首次上网日期，不代表论文的发表时间）