基于自适应大气光校正的图像去雾方法
|
摘要
针对暗通道先验去雾算法的不足,提出一种自适应大气光校正的改进算法。利用四叉树算法粗略估计大气光,利用提出的自适应大气光校正方法校正粗略估计的大气光;利用均值滤波代替最小值滤波得到暗通道,进而得到平滑的透射率,该透射率不需细化;使用一种自适应透射率补偿方法对天空等明亮区域的透射率进行动态修正;根据大气散射模型复原出无雾图像,并对无雾图像进行色调调整,用来得到清晰明亮的输出图像。实验结果表明,该算法具有较快的处理速度,同时所恢复出的图像细节突出,具有较好的视觉效果。
To overcome the shortcomings of dark channel prior dehazing algorithm, this paper proposed an improved adaptive atmospheric light correction algorithm. We used quad-tree algorithm to estimate atmospheric light roughly, and the proposed adaptive atmospheric light correction method was adopted to correct the roughly estimated atmospheric light. The mean filter was used instead of minimum filter to get dark channel, and then smooth transmittance was obtained, which need not be refined. We used an adaptive transmittance compensation method to dynamically modify the transmittance of bright areas such as the sky. According to the atmospheric scattering model, the haze-free image was restored, and the color of the haze-free image was adjusted to obtain a clear and bright output image. The experimental results show that the algorithm has faster processing speed, and provide more detailed restored image with good visual effects.
To overcome the shortcomings of dark channel prior dehazing algorithm, this paper proposed an improved adaptive atmospheric light correction algorithm. We used quad-tree algorithm to estimate atmospheric light roughly, and the proposed adaptive atmospheric light correction method was adopted to correct the roughly estimated atmospheric light. The mean filter was used instead of minimum filter to get dark channel, and then smooth transmittance was obtained, which need not be refined. We used an adaptive transmittance compensation method to dynamically modify the transmittance of bright areas such as the sky. According to the atmospheric scattering model, the haze-free image was restored, and the color of the haze-free image was adjusted to obtain a clear and bright output image. The experimental results show that the algorithm has faster processing speed, and provide more detailed restored image with good visual effects.
引文
[1] 吴迪, 朱青松. 图像去雾的最新研究进展[J]. 自动化学报, 2015, 41(2): 221-239.
[2] 吴成茂. 直方图均衡化的数学模型研究[J]. 电子学报, 2013, 41(03): 598-602.
[3] Provenzi E, Fierro M, Rizzi A, et al. Random spray Retinex: a new Retinex implementation to investigate the local properties of the model[J]. IEEE Trans Image Process, 2007, 16(1):162-171.
[4] Hautiére N, Tarel J P, Lavenant J, et al. Automatic fog detection and estimation of visibility distance through use of an onboard camera[J]. Machine Vision and Applications, 2006, 17(1): 1-26.
[5] Tan R T . Visibility in bad weather from a single image[C]// 2008 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2008.
[6] Kim J H, Jang W D, Sim J Y, et al. Optimized contrast enhancement for real-time image and video dehazing[J]. Journal of Visual Communication & Image Representation, 2013, 24(3):410-425.
[7] Fattal R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 1-9.
[8] Tarel J P, Hautière N. Fast visibility restoration from a single color or gray level image[C]// IEEE, International Conference on Computer Vision. IEEE, 2009: 2201-2208.
[9] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[10] He K M, Sun J, Tang X O. Guided image filtering[J]. IEEE Trans Pattern Anal Mach Intelligence, 2013, 35(6): 1397-1409.
[11] 胡妍, 王柯俨, 许宁, 等. 利用分割中值滤波和透射率补偿的图像去雾[J]. 西安电子科技大学学报(自然科学版), 2018, 45(4): 99-105.
[12] 陈俊君, 徐冰. 雾霾天气条件下的机器视觉图像清晰化研究[J]. 计算机工程, 2017, 43(2): 280-285.
[13] 沈逸云, 刘春晓, 张金栋, 等.鲁棒图像去雾的大气光校正与透射率优化算法[J]. 计算机辅助设计与图形学学报, 2017, 29(9): 1604-1612.
[14] 尹芳, 陈田田, 付自如,等.暗原色先验图像去雾改进新方法[J]. 计算机科学与探索, 2017, 11(7): 1131-1139.
[15] 曾浩, 尚媛园, 丁辉, 等. 基于暗原色先验的图像快速去雾[J]. 中国图象图形学报, 2015, 20(7): 914-921.
[16] 刘春辉, 齐越, 丁文锐. 基于大气光鲁棒估计的无人机图像去雾方法[J]. 北京航空航天大学学报, 2017, 43(6): 1105-1111.
[17] Hautière N, Tarel J P, Aubert D, et al. Blind contrast enhancement assessment by gradient ratioing at visible edges[J]. Image Analysis and Stereology Journal, 2008, 27(2): 87-95.
[18] 郭璠, 蔡自兴. 图像去雾算法清晰化效果客观评价方法[J]. 自动化学报, 2012, 38(9): 1410-1419.
[2] 吴成茂. 直方图均衡化的数学模型研究[J]. 电子学报, 2013, 41(03): 598-602.
[3] Provenzi E, Fierro M, Rizzi A, et al. Random spray Retinex: a new Retinex implementation to investigate the local properties of the model[J]. IEEE Trans Image Process, 2007, 16(1):162-171.
[4] Hautiére N, Tarel J P, Lavenant J, et al. Automatic fog detection and estimation of visibility distance through use of an onboard camera[J]. Machine Vision and Applications, 2006, 17(1): 1-26.
[5] Tan R T . Visibility in bad weather from a single image[C]// 2008 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2008.
[6] Kim J H, Jang W D, Sim J Y, et al. Optimized contrast enhancement for real-time image and video dehazing[J]. Journal of Visual Communication & Image Representation, 2013, 24(3):410-425.
[7] Fattal R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 1-9.
[8] Tarel J P, Hautière N. Fast visibility restoration from a single color or gray level image[C]// IEEE, International Conference on Computer Vision. IEEE, 2009: 2201-2208.
[9] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[10] He K M, Sun J, Tang X O. Guided image filtering[J]. IEEE Trans Pattern Anal Mach Intelligence, 2013, 35(6): 1397-1409.
[11] 胡妍, 王柯俨, 许宁, 等. 利用分割中值滤波和透射率补偿的图像去雾[J]. 西安电子科技大学学报(自然科学版), 2018, 45(4): 99-105.
[12] 陈俊君, 徐冰. 雾霾天气条件下的机器视觉图像清晰化研究[J]. 计算机工程, 2017, 43(2): 280-285.
[13] 沈逸云, 刘春晓, 张金栋, 等.鲁棒图像去雾的大气光校正与透射率优化算法[J]. 计算机辅助设计与图形学学报, 2017, 29(9): 1604-1612.
[14] 尹芳, 陈田田, 付自如,等.暗原色先验图像去雾改进新方法[J]. 计算机科学与探索, 2017, 11(7): 1131-1139.
[15] 曾浩, 尚媛园, 丁辉, 等. 基于暗原色先验的图像快速去雾[J]. 中国图象图形学报, 2015, 20(7): 914-921.
[16] 刘春辉, 齐越, 丁文锐. 基于大气光鲁棒估计的无人机图像去雾方法[J]. 北京航空航天大学学报, 2017, 43(6): 1105-1111.
[17] Hautière N, Tarel J P, Aubert D, et al. Blind contrast enhancement assessment by gradient ratioing at visible edges[J]. Image Analysis and Stereology Journal, 2008, 27(2): 87-95.
[18] 郭璠, 蔡自兴. 图像去雾算法清晰化效果客观评价方法[J]. 自动化学报, 2012, 38(9): 1410-1419.