Fast Single Image Dehazing Through Edge-Guided Interpolated Filter
文献类型：会议论文
| 作者 | X. Zhu; Y. Li; Yu Qiao |
| 出版日期 | 2015 |
| 会议名称 | 2015 14th IAPR International Conference on Machine Vision Applications (MVA) |
| 会议地点 | 日本东京 |
| 英文摘要 | Images and videos taken in foggy weather often suffer from low visibility. Recent studies demonstrate the effectiveness of dark channel prior [3] and guided filter [4] based approaches for image dehazing. However, these methods require high computational cost which makes them infeasible for realtime and embedding systems. In this paper, we propose Edge-Guided Interpolated Filter (EGIF) for fast image and video dehazing. The main contributions are twofold. Firstly, we develop Guided Interpolated Filter (GIF) to significantly speed up the estimation of transmission map, which is the most computational cost step in previous methods. Secondly, we utilize edge map as guidance image in GIF to enhance the fine details in dehazed images. Experimental results show that GIF can largely improve the computational efficiency and achieve comparable dehazing performance as previous guided filter based methods. EGIF can further enhance the sharpness of transmission map. Our method can achieve real-time processing for image of size 1024 × 768 with single CPU core (2GHz). |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6702]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | X. Zhu,Y. Li,Yu Qiao. Fast Single Image Dehazing Through Edge-Guided Interpolated Filter[C]. 见:2015 14th IAPR International Conference on Machine Vision Applications (MVA). 日本东京. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。