Single Image Haze Removal Based on Priori Image Geometry and Edge-Preserving Filtering

摘要：

　　Images captured in foggy weather conditions often suffer from bad visibility.Therefore,in this paper,we propose an efficient and automatic method to remove hazes from a single input image.Our method benefits much from an exploration on the priori image geometry on the transmission function.This prior,combined with an edge-preserving texture-smoothing filtering,is applied to estimate the unknown transmission map.Next,the restored image is obtained by taking the estimated transmission map and the atmospheric light into the image degradation model to recover the scene radiance.The proposed method is controlled by just a few parameters and can restore a high-quality haze-free image with fine image details.The experimental results demonstrate that our method shows competitive performance against other methods.

关键词： Single image Haze removal Priori image geometry Edge-preserving filtering Image degradation model

作者: Fan Guo Changjun Zhu

作者单位: School of Information Science and Engineering,Central South University,Changsha 410083,Hunan,China Powder Metallurgy Research Institute of Central South University,Changsha 410083,Hunan,China

会议类型: 国际会议

会议名称: 第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)

会议地点: 成都

会议语种:英文

页码: 26-41

在线出版日期: 2016-11-03（万方平台首次上网日期，不代表论文的发表时间）