| 顾及空间与光谱差异的单幅遥感影像自适应云雾去除方法 |
| |
| 引用本文： | 祁琼,张弛,袁全,李慧芳,沈焕锋,程青.顾及空间与光谱差异的单幅遥感影像自适应云雾去除方法[J].武汉大学学报(信息科学版),2019,44(9):1369-1376. |
| |
| 作者姓名： | 祁琼 张弛 袁全 李慧芳 沈焕锋 程青 |
| |
| 作者单位： | 1.湖北省国土资源研究院, 湖北 武汉, 430071 |
| |
| 基金项目： | 国家自然科学基金41631180国家自然科学基金41601357湖北省土地调查及遥感监测类业务技术服务项目HBT-17170111-170928湖北省自然科学基金2016CFB333 |
| |
| 摘 要： | 光学遥感影像经常受到云雾的干扰而导致数据质量下降。在暗原色先验理论和云雾影像模型的基础上，提出了一种顾及空间和光谱差异的单幅遥感影像自适应云雾去除方法，较好地解决了传统暗原色先验在高亮地物校正过度和部分波段云雾校正不足的问题，有效地实现了影像云雾去除。首先通过高亮地物的光谱特征构建高亮地物判别指数，辅以密度分割对其进行提取分类，在此基础上引入自适应校正函数对该区域透射率进行修正；其次在对多幅云雾遥感影像实验分析的基础上，提出了符合大气散射机制的波段透射率校正系数，实现了波段间处理强度的自适应调整。实验结果表明，该方法能有效去除不同波段的云雾干扰，并避免高亮地物的过度校正，可取得较好的复原结果。
|
| 关 键 词： | 遥感影像 暗原色先验 云雾去除 空间自适应 光谱自适应 |
| 收稿时间： | 2018-08-22 |
An Adaptive Haze Removal Method for Single Remotely Sensed Image Considering the Spatial and Spectral Varieties |
| |
| Affiliation: | 1.Hubei Institute of Land and Resources, Wuhan 430071, China2.School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, China3.Guangdong OPPO Mobile Telecommunications Co. Ltd, Shenzhen 518000, China4.School of Urban Design, Wuhan University, Wuhan 430072, China |
| |
| Abstract: | Remotely sensed images are often degraded due to the haze interference during the imaging process, which greatly reduces their utilization. In order to solve this problem, a spatial-spectral adaptive haze removal method for single remote sensing image is proposed in this paper. Based on the dark prior theory and haze image model, and taking into account the spatial and spectral varieties in the remotely sensed images, our proposed method effectively overcome the difficulties of over-correction on bright terrain and inadequate correction of haze in some wavebands.A bright object index (BOI) is constructed to extract the bright objects with the help of the density segmentation method, and an adaptive correction function is then introduced to refine the misestimated transmittance. Given the influences of atmospheric scattering are wavelength dependent among visible channels, two empirical accommodation coefficients are applied to derive the transmittance of the different channels, achieving the adaptive adjustment of processing intensity in different wavebands. Experimental results show that our proposed method can remove the haze completely and yield visually haze-free images, comparing with the other existing methods. |
| |
| Keywords: | |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《武汉大学学报(信息科学版)》浏览原始摘要信息 |
|
点击此处可从《武汉大学学报(信息科学版)》下载全文 |
|
