基于場(chǎng)景傳輸漸進(jìn)估計(jì)的單幅圖像能見(jiàn)度快速?gòu)?fù)原
doi: 10.11999/JEIT150515 cstr: 32379.14.JEIT150515
-
2.
(湖北大學(xué)計(jì)算機(jī)與信息工程學(xué)院 武漢 430062) ②(武漢大學(xué)計(jì)算機(jī)學(xué)院 武漢 430072)
基金項(xiàng)目:
國(guó)家自然科學(xué)基金 (61300125)
Fast Visibility Restoration of Single Image by Progressive Scene Transmission Estimation
-
1.
(School of Computer Science and Information Engineering, Hubei University, Wuhan 430062, China)
-
2.
(School of Computer Science and Information Engineering, Hubei University, Wuhan 430062, China)
Funds:
The National Natural Science Foundation of China (61300125)
-
摘要: 該文提出一種基于場(chǎng)景傳輸漸進(jìn)估計(jì)的單幅圖像能見(jiàn)度快速?gòu)?fù)原方法。利用場(chǎng)景輻射的邊界條件，結(jié)合大氣散射模型估計(jì)場(chǎng)景傳輸?shù)某跏贾?，并采用遞歸雙邊濾波對(duì)其精化。通過(guò)梯度域遞歸雙邊濾波分解復(fù)原結(jié)果，對(duì)得到的基層和細(xì)節(jié)層分別進(jìn)行色調(diào)調(diào)整和增強(qiáng)，獲取高質(zhì)量的清晰圖像。利用高斯KD樹(shù)對(duì)原始圖像的高維特征空間進(jìn)行自適應(yīng)剖分，獲取其高斯采樣以加速?gòu)?fù)原計(jì)算。與相關(guān)工作比較，所提方法能夠保持邊緣和細(xì)節(jié)，有效避免光暈效應(yīng)。采用客觀(guān)指標(biāo)評(píng)價(jià)復(fù)原結(jié)果。實(shí)驗(yàn)結(jié)果表明，該方法有效易行，復(fù)原結(jié)果更加符合真實(shí)場(chǎng)景。
-
關(guān)鍵詞:
- 圖像處理 /
- 能見(jiàn)度復(fù)原 /
- 遞歸雙邊濾波 /
- 自適應(yīng)采樣
Abstract: A fast visibility restoration method of single image by progressive scene transmission estimation is proposed. Based on the boundary conditions of scene radiance and the atmosphere scattering model, the initial value of the scene transmission is estimated and refined with recursive bilateral filtering. The restoration result is decomposed into a base layer and a detail layer by gradient domain recursive bilateral filtering. The high visibility?restoration result is obtained with tone mapping of the base layer and detail enhancement. Utilizing Gaussian KD tree, the high dimensional feature space of the original image is subdivided adaptively to obtain the Gaussian sampling and accelerate the restoration computing. Compared with related work, the proposed method preserves edges and details, avoiding the halo effectively. The objective indicators are applied to evaluate the restoration results. The experiment results show that the proposed method is effective and feasible, and the restoration results accord with the real scene better. -
TAREL J P, HAUTIERE N, CORD A, et al.. Improved visibility of road scene images under heterogeneous fog[C]. 2010 IEEE Intelligent Vehicles Symposium (IV), San Diego, 2010: 478-485. 南棟, 畢篤彥, 查宇飛, 等. 基于參數(shù)估計(jì)的無(wú)參考型圖像質(zhì)量評(píng)價(jià)算法[J]. 電子與信息學(xué)報(bào), 2013, 35(9): 2066-2072. doi: 10.3724/SP.J.1146.2012.01652. NAN Dong, BI Duyan, ZHA Yufei, et al. A no-reference image quality assessment method based on parameter estimation[J]. Journal of Electronics Information Technology, 2013, 35(9): 2066-2072. doi: 10.3724/SP.J.1146. 2012.01652. 吳煒, 李勃, 楊嫻, 等. 基于路面視亮度差平方最優(yōu)化的視頻能見(jiàn)度檢測(cè)算法[J]. 電子與信息學(xué)報(bào), 2014, 36(10): 2412-2418. doi: 10.3724/SP.J.1146.2013.01743. WU Wei, LI Bo, YANG Xian, et al. Visibility detection algorithm based on optimization of squared differences upon apparent luminance of roads[J]. Journal of Electronics Information Technology, 2014, 36(10): 2412-2418. doi: 10.3724/SP.J.1146.2013.01743. HE K, SUN J, and TANG X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409. 褚宏莉, 李元祥, 周則明, 等. 基于黑色通道的圖像快速去霧優(yōu)化算法[J]. 電子學(xué)報(bào), 2013, 41(4): 791-797. CHU Hongli, LI Yuanxiang, ZHOU Zeming, et al. Optimized fast dehazing method based on dark channel prior[J]. Acta Electronica Sinica, 2013, 41(4): 791-797. 薛模根, 周浦城, 張洪坤. 利用方向延伸專(zhuān)家場(chǎng)的單幅霧天圖像復(fù)原[J]. 計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào), 2014, 26(5): 782-787. XUE mogen, ZHOU Pucheng, and ZHANG Hongkun. Single foggy image restoration using orientation extended fields of experts[J]. Journal of Computer Aided Design Graphics, 2014, 26(5): 782-787. 郭璠, 唐琎, 蔡自興. 基于融合策略的單幅圖像去霧算法[J]. 通信學(xué)報(bào), 2014, 35(7): 199-207. GUO Fan, TANG Jin, and CAI Zixing. Single image defogging based on fusion strategy[J]. Journal on Communications, 2014, 35(7): 199-207. 吳迪, 朱青松. 圖像去霧的最新研究進(jìn)展[J]. 自動(dòng)化學(xué)報(bào), 2015, 41(2): 221-239. WU Di and ZHU Qingsong. The latest research progress of image dehazing[J]. Acta Automatica Sinica, 2015, 41(2): 221-239. McCann J J. Retinex at 40[J]. Journal of Electronic Imaging, 2004, 13(1): 6-7. FATTAL R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 1-9. HE K, SUN J, and TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353. TAREL J P and HAUTIERE N. Fast visibility restoration from a single color or gray level image[C]. 2009 IEEE 12th International Conference on Computer Vision, Kyoto, 2009: 2201-2208. TAN R T. Visibility in bad weather from a single image[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Alaska, 2008: 1-8. YANG Q. Recursive bilateral filtering[C]. European Conference on Computer VisionECCV, Springer Berlin Heidelberg, 2012: 399-413. DRAGO F, MYSZKOWSKI K, ANNEN T, et al.. Adaptive logarithmic mapping for displaying high contrast scenes[J]. Computer Graphics Forum, 2003, 22(3): 419-426. 郭璠, 蔡自興. 圖像去霧算法清晰化效果客觀(guān)評(píng)價(jià)方法[J]. 自動(dòng)化學(xué)報(bào), 2012, 38(9): 1410-1419. GUO Fan and CAI Zixing. Objective assessment method for the clearness effect of image defogging algorithm[J]. Acta Automatica Sinica, 2012, 38(9): 1410-1419. -
計(jì)量
- 文章訪(fǎng)問(wèn)數(shù): 1282
- HTML全文瀏覽量: 177
- PDF下載量: 460
- 被引次數(shù): 0
下載:
