基于改进Kuwahara滤波的图像去雾算法
|
摘要
针对单幅图像去雾算法中存在运行效率低下的不足,提出改进的Kuwahara滤波细化粗糙透射率算法,引入积分图和平方积分图算法,将面积像素计算转化为目标矩形四个顶点的计算;对天空区域使用阈值透射率修正算法做进一步平滑,以提高算法执行效率,避免天空区域色彩失真。经仿真测试,对于800×600的雾图像,需10 ms即可完成去雾处理;对于大小为135 K的图像,改进Kuwahara处理速度是He的3 000倍,是Shi的2 000倍,表明算法能满足高速图像处理的实时性需求。
Concerning the shortcoming of low efficiency of the algorithm for single-image fog removal, an algorithm based on improved Kuwahara filter is proposed to detail rough transmission of foggy images. This algorithm introduces the square integral operator to transform calculation for pixel areas into calculation of four vertices of a rectangle. Amended algorithm based on threshold for transmission is used to go a step further detail the transmission for sky areas in order to increase the efficiency of the algorithm and avoid the color-cross of sky areas. Simulation test shows that it only needs 10 ms to deal with a foggy image of 800×600 pixel, and the velocity based on the improved Kuwahara is 3 000 times of He's, 2 000 times of Shi's, and could meet the real-time processing need for expressway images.
Concerning the shortcoming of low efficiency of the algorithm for single-image fog removal, an algorithm based on improved Kuwahara filter is proposed to detail rough transmission of foggy images. This algorithm introduces the square integral operator to transform calculation for pixel areas into calculation of four vertices of a rectangle. Amended algorithm based on threshold for transmission is used to go a step further detail the transmission for sky areas in order to increase the efficiency of the algorithm and avoid the color-cross of sky areas. Simulation test shows that it only needs 10 ms to deal with a foggy image of 800×600 pixel, and the velocity based on the improved Kuwahara is 3 000 times of He's, 2 000 times of Shi's, and could meet the real-time processing need for expressway images.
引文
[1]张长生,马荣国.山区高速公路交通事故分析及多发路段鉴别[J]长安大学学报,2010,30(6):76-80.Zhang C S,Ma G R.Identifying Method of Traffic Accident Black Spots on Mountain in Free Way[J].Journal of Chan’an University,2010,30(6):76-80.
[2]尹春娥,陈宽民.基于小波方程的高速公路交通事故自动检测[J].中国公路学报,2014,27(12):106-112.Yin C E,Chen K M.Automatic Detection Method for Expressway Traffic Accidents on Wavelet Equation[J].China Journal of Highway and Transport,2014,27(12):106-112.
[3]高银,云利军,石俊生,等.基于TV模型的暗原色理论雾天图像复原算法[J].中国激光,2015,42(8):273-278.Gao Y,Yun L J,Shi J S,et al.Enhancement Dark Channel Algorithm of Fog Image Based on the TV Model[J].Chinese Journal of Lasers,2015,42(8):273-278.
[4]Fattal R.Single Image Dehazing[C].ACM Transaction on Graphics,2008,27(3):3245-3247.
[5]Kaiming He,Jian Sun and Xiaoou Tang.Single Image Haze Removal using Dark Channel Prior[C].IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2009,33(12):2341-2347.
[6]石文轩,詹诗萦,李婕.一种边缘优化的暗通道去雾算法[J].计算机应用研究,2013,30(12):3854-3856.Shi W X,Zhan S Y,Li J.Dark Channel Prior Dehazing Algorithm Based on Edge Optimization[J].Application Research of Computer,2013,30(12):3854-3856.
[7]唐晓庆,范赐恩,刘鑫.基于边缘保持滤波的单幅图像快速去雾[J].西安交通大学学报,2015,49(3):144-150.Tang X Q,Fan C E,Liu X.A Fast Haze Removing Algorithm of Single Image Using Edge Preserving Filtering[J].Journal of Xi’an Jiao Tong University,2015,49(3):144-150.
[8]孙抗,汪渤,周志强,等.基于双边滤波的实时图像去雾技术研究[J].北京理工大学学报,2011,31(7):810-814.Sun K,Wang B,Zhou Z Q,et al.Real Time Image Haze Removal Using Bilateral Filter[J].Transactions of Beijing Institute of Technology,2011,31(7):810-814.
[9]贾迪,孟琭,孙劲光,等.采用积分图块间距离检测图像边缘[J].中国图象图形学报,2015,20(10):1322-1330.Jia D,Meng L,Sun J G,et al.Edge Detection Method of Block Distance Combining with Summed Area Table[J].Journal of Image and Graphics,2015,20(10):1322-1330.
[10]Narasimhan S G,Nayar S K.Contrast restoration of weather degraded images[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,25(6):713-724.
[11]Sun W.A New Single-image Fog Removal Algorithm Based on Physical Model[J].Optik-International Journal for Light and Electron Optics,2013,124(21):4770-4775.
[12]Yuan Z J,Xie X D,Hu J M,et al.An Effective Method for Fog-degraded Traffic Image Enhancement[C].Proceedings of 2014IEEE International Conference on Service Operations and Logistics,and Informatics,2014:27-32.
[13]孙建召,常青.一种新型的图像噪声滤波算法研究[J].控制工程,2016,23(6):848-852.Sun J Z,Chang Q.Research on Image Noise Filtering Algorithm Based on Improved Pulse Coupled Neural Network[J].Control Engineering of China,2016,23(6):848-851.
[14]涂刚,刘华清,朱昌平.一种改进的自适应非局部均值图像去噪方法[J].控制工程,2016,23(6):839-844.Tu G,Loi H Q,Zhu C P.An Improved Adaptive Non-local Mean Image Denoising Method[J].Control Engineering of China,2016,23(6):839-843.
[2]尹春娥,陈宽民.基于小波方程的高速公路交通事故自动检测[J].中国公路学报,2014,27(12):106-112.Yin C E,Chen K M.Automatic Detection Method for Expressway Traffic Accidents on Wavelet Equation[J].China Journal of Highway and Transport,2014,27(12):106-112.
[3]高银,云利军,石俊生,等.基于TV模型的暗原色理论雾天图像复原算法[J].中国激光,2015,42(8):273-278.Gao Y,Yun L J,Shi J S,et al.Enhancement Dark Channel Algorithm of Fog Image Based on the TV Model[J].Chinese Journal of Lasers,2015,42(8):273-278.
[4]Fattal R.Single Image Dehazing[C].ACM Transaction on Graphics,2008,27(3):3245-3247.
[5]Kaiming He,Jian Sun and Xiaoou Tang.Single Image Haze Removal using Dark Channel Prior[C].IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2009,33(12):2341-2347.
[6]石文轩,詹诗萦,李婕.一种边缘优化的暗通道去雾算法[J].计算机应用研究,2013,30(12):3854-3856.Shi W X,Zhan S Y,Li J.Dark Channel Prior Dehazing Algorithm Based on Edge Optimization[J].Application Research of Computer,2013,30(12):3854-3856.
[7]唐晓庆,范赐恩,刘鑫.基于边缘保持滤波的单幅图像快速去雾[J].西安交通大学学报,2015,49(3):144-150.Tang X Q,Fan C E,Liu X.A Fast Haze Removing Algorithm of Single Image Using Edge Preserving Filtering[J].Journal of Xi’an Jiao Tong University,2015,49(3):144-150.
[8]孙抗,汪渤,周志强,等.基于双边滤波的实时图像去雾技术研究[J].北京理工大学学报,2011,31(7):810-814.Sun K,Wang B,Zhou Z Q,et al.Real Time Image Haze Removal Using Bilateral Filter[J].Transactions of Beijing Institute of Technology,2011,31(7):810-814.
[9]贾迪,孟琭,孙劲光,等.采用积分图块间距离检测图像边缘[J].中国图象图形学报,2015,20(10):1322-1330.Jia D,Meng L,Sun J G,et al.Edge Detection Method of Block Distance Combining with Summed Area Table[J].Journal of Image and Graphics,2015,20(10):1322-1330.
[10]Narasimhan S G,Nayar S K.Contrast restoration of weather degraded images[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,25(6):713-724.
[11]Sun W.A New Single-image Fog Removal Algorithm Based on Physical Model[J].Optik-International Journal for Light and Electron Optics,2013,124(21):4770-4775.
[12]Yuan Z J,Xie X D,Hu J M,et al.An Effective Method for Fog-degraded Traffic Image Enhancement[C].Proceedings of 2014IEEE International Conference on Service Operations and Logistics,and Informatics,2014:27-32.
[13]孙建召,常青.一种新型的图像噪声滤波算法研究[J].控制工程,2016,23(6):848-852.Sun J Z,Chang Q.Research on Image Noise Filtering Algorithm Based on Improved Pulse Coupled Neural Network[J].Control Engineering of China,2016,23(6):848-851.
[14]涂刚,刘华清,朱昌平.一种改进的自适应非局部均值图像去噪方法[J].控制工程,2016,23(6):839-844.Tu G,Loi H Q,Zhu C P.An Improved Adaptive Non-local Mean Image Denoising Method[J].Control Engineering of China,2016,23(6):839-843.