基于非局部全變分正則化優(yōu)化的單幅霧天圖像恢復(fù)新方法
doi: 10.11999/JEIT160208
-
2.
(西北工業(yè)大學(xué)電子信息學(xué)院陜西省信息獲取與處理重點(diǎn)實(shí)驗(yàn)室 西安 710129) ②(悉尼大學(xué)信息技術(shù)學(xué)院 悉尼 2006)
基金項(xiàng)目:
國家自然科學(xué)基金(61420106007)，陜西省科技統(tǒng)籌創(chuàng)新項(xiàng)目
Novel Single Hazy Image Restoration Method Based on Nonlocal Total Variation Regularization Optimization
-
2.
(Shaanxi Key Laboratory of Information Acquisition and Processing, The School of Electronics and Information, Northwestern Polytechnical University, Xi&rsquo
Funds:
The National Natural Science Foundation of China (61420106007), Shaanxi Science Technology Co-ordination Innovation Project
-
摘要: 該文針對(duì)無霧圖像具有高灰度對(duì)比度且大氣遮罩局部平滑的特性，提出一種基于非局部全變分正則化優(yōu)化的單幅霧天圖像恢復(fù)新方法。先構(gòu)建一種基于非局部全變分正則化的有約束優(yōu)化算法對(duì)大氣遮罩進(jìn)行估計(jì)，然后通過優(yōu)化Bregman分離迭代法求解非局部Rudin-Osher-Fatemi模型獲得準(zhǔn)確的大氣遮罩，進(jìn)而從霧天場景圖像恢復(fù)出場景圖像。實(shí)驗(yàn)結(jié)果表明，所提新方法可以有效地對(duì)霧天降質(zhì)圖像進(jìn)行復(fù)原，對(duì)多紋理復(fù)雜區(qū)域的恢復(fù)效果也較好。
-
關(guān)鍵詞:
- 圖像處理 /
- 圖像去霧 /
- 對(duì)比度增強(qiáng) /
- 正則化優(yōu)化
Abstract: Based on the property that the scene radiance is of high contrast and the atmospheric veil is locally smooth, a novel single hazy image restoration method based on nonlocal total variation regularization optimization is proposed in this paper. In order to obtain the atmospheric veil of a hazy image, a constrained nonlocal total variation regularization is firstly applied. Then, the accurate atmospheric veil is estimated using a nonlocal Rudin- Osher-Fatemi model, which is solved by a modified split Bregman method. Experimental results demonstrate that the proposed approach is capable of recovering the scene radiance from a single hazy image effectively, especially for the regions with multi-texture.-
Key words:
- Image processing /
- Image dehazing /
- Contrast enhancement /
- Regularization optimization
-
HE Kaiming, SUN Jian, and TANG Xiaoou. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353. doi: 10.1109/TPAMI.2010.168. 畢篤彥, 葛淵, 李權(quán)合, 等. 單幅圖像去霧方法研究[J]. 空軍工程大學(xué)學(xué)報(bào): 自然科學(xué)版, 2013, 14(6): 46-53. doi: 10.3969/j.issn.1009-3516.2013.06.012. BI Duyan, GE Yuan, LI Quanheng, et al. A research on defogging methods with single image[J]. Journal of Air Force Engineering University: Natural Science Edition, 2013, 14(6): 46-53. doi: 10.3969/j.issn.1009-3516.2013.06.012. MI Z, ZHOU H, ZHENG Y, et al. Single image dehazing via multi-scale gradient domain contrast enhancement[J]. IET Image Processing, 2016, 3(10): 206-214. doi: 10.1049/iet-ipr. 2015.0112. HE R, WANG Z, FAN Y, et al. Combined constraint for single image dehazing[J]. IET Electronics Letters, 2015, 51(22): 1776-1778. doi: 10.1049/el.2015.0707. WANG Dan and ZHU Jubo. Fast smoothing technique with edge preservation for single image dehazing[J]. IET Computer Vision, 2015, 9(6): 950-959. doi: 10.1049/iet-cvi.2015.0063. WANG Jinbao, HE Ning, ZHANG Lulu, et al. Single image dehazing with a physical model and dark channel prior[J]. Elsevier Neurocomputing, 2015, 149(PB): 718-728. doi: 10.1016/j.neucom.2014.08.005. WANG Zhongliang and FENG Yan. Fast single haze image enhancement[J]. Elsevier Computers Electrical Engineering, 2014, 40(3): 785-795. doi: 10.1016/j.compeleceng.2013.06. 009. NARASIMHAN S and NAYAR S. Vision and the atmosphere[J]. International Journal of Computer Vision, 2002, 48(3): 233-254. doi: 10.1023/A:1016328200723. TAN R. Visibility in bad weather from a single image[C]. IEEE Conference on Computer Vision and Pattern Recognition, Alaska, USA, 2008: 1-8. FATTAL R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 1-9. doi: 10.1145/1399504.1360671. TAREL J and HAUTIERE N. Fast visibility restoration from a single color or gray level image[C]. IEEE International Conference on Computer Vision, Kyoto, Japan, 2009: 2201-2208. RUDIN L, OSHER S, and FATEMI E. Nonlinear total variation based noise removal algorithms[J]. Physica D: Nonlinear Phenomena, 1992, 60(1): 259-268. doi: 10.1016/ 0167-2789(92)90242-F. 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. doi: 10.16383/j.aas.2015.c131137. WU Di and ZHU Qingsong. The latest research progress of image dehazing[J]. Acta Automatica Sinica, 2015, 41(2): 221-239. doi: 10.16383/j.aas.2015.c131137. SULAMI M, GELTZER I, FATTAL R, et al. Automatic recovery of the atmospheric light in hazy images[C]. IEEE International Conference on Computational Photography, Santa Clara, USA, 2014: 1-11. MITTAL A, MOORTHY A, and BOVIK A. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12): 4695-4708. doi: 10.1109/TIP.2012.2214050. HAUTIERE N, TAREL J, and AUBERT D. Blind contrast enhancement assessment by gradient ratioing at visible edges[J]. Image Analysis Stereology Journal, 2008, 27(2): 87-95. doi: 10.5566/ias.v27.p87-95. -
計(jì)量
- 文章訪問數(shù): 1665
- HTML全文瀏覽量: 206
- PDF下載量: 473
- 被引次數(shù): 0
下載:
