基于自适应亮度高程模型的路面阴影消除算法研究
Research on road shadow removal algorithm based on adaptive brightness elevation model
-
摘要: 针对亮度高程模型的阴影消除算法GSR的关键参数需要手动设置、亮度等高区域的划分和亮度补偿方法也都存在严重缺陷的问题，提出一种基于自适应亮度高程模型的路面阴影消除算法SGRSR：首先，采用形态学膨胀运算和高斯平滑滤波消除路面裂缝和路面纹理对后续阴影区域划分的影响；然后，利用最大熵阈值分割求解出高斯平滑后路面影像阴影区域和非阴影区域的划分阈值，以此实现划分阈值的自适应确定；最后，基于改进的亮度等高区域划分模型和亮度补偿方法，实现路面阴影的消除.实验结果表明，与GSR算法相比，本算法不仅能够对路面阴影影像进行自动的阴影消除，而且在阴影消除后，路面影像的亮度过渡更加自然.Abstract: For the problems of brightness elevation model shadow removal algorithm GSR,such as the manual setting of key parameters and the defect in the division of the equal brightness regions and the luminance compensation method,an road shadow emoval algorithm SGRSR based on the adaptive brightness elevation model was proposed.Firstly,the influence of pavement crack and pavement texture for the division of the shadow region was eliminated by using morphological dilate operation and Gaussian smoothing filter.Secondly,the maximum entropy threshold segmentation algorithm was used to calculate the partition threshold value of the shaded area and the non-shaded area of the image after Gaussian smoothing.By this way,the threshold was determined automatically.Finally,the pavement shadow was eliminated by using the improvement of the equal brightness region partition model and the luminance compensation method.Experimental results showed that the SGRSA algorithm could eliminate the shadow of the pavement image automatically and had the more natural transition in the brightness of the pavement image compared with the GSR algorithm.
-
-
[1]
彭博,蒋阳升,韩世凡,等.路面裂缝图像自动识别算法综述[J].公路交通科技,2014,31(7):19.
-
[2]
邹勤.低信噪比路面裂缝增强与提取方法研究[D].武汉:武汉大学,2012.
-
[3]
LI H,ZHANG L,SHEN H.An adaptive nonlocal regularized shadow removal method for aerial remote sensing images[J].IEEE Transactions on Geoscience & Remote Sensing,2014,52(1):106.
-
[4]
WU T P,TANG C K,BROWN M S,et al.Natural shadow matting[J].ACM Transactions on Graphics,2007,26(2):8.
-
[5]
WU T P,TANG C K.A bayesian approach for shadow extraction from a single image[C]//Tenth IEEE International Conference on Computer Vision.Piscataway:IEEE,2005:480-487.
-
[6]
ARBEL E,HEL-OR H.Texture-preserving shadow removal in color images containing curved surfaces[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2007:1-8.
-
[7]
LIU F,GLEICHER M.Texture-consistent shadow removal[C]//10th European Conference on Computer Vision.Heidelberg:Springer,2008:437-450.
-
[8]
MOHAN A,TUMBLIN J,CHOUDHURY P.Editing soft shadows in a digital photograph[J].Computer Graphics & Applications IEEE,2007,27(2):23.
-
[9]
FINLAYSON G D,DREW M S,LU C.Intrinsic images by entropy minimization[M]//European Conference on Computer Vision-ECCV 2004.Heidelberg:Springer,2004:582-595.
-
[10]
FINLAYSON G D,HORDLEY S D,LU C,et al.On the removal of shadows from images[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2006,28(1):59.
-
[11]
FINLAYSON G D,HORDLEY S D,DREW M S.Removing Shadows from Images[C]//European Conference on Computer Vision.Heidelberg:Springer,2002:823-836.
-
[12]
ZHANG W,ZHANG G,WANG Y,et al.An investigation into shadow removal from traffic images[J].Transportation Research Record Journal of the Transportation Research Board,2007,2000(1):70.
-
[13]
RAMAMOORTHI R,KOUDELKA M,BELHUMEUR P.A fourier theory for cast shadows[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2005,27(2):288.
-
[14]
RAMAMOORTHI R,KOUDELKA M,BELHUMEUR P.A fourier theory for cast shadows[C]//European Conference on Computer Vision.Heidelberg:Springer,2004:146-162.
-
[15]
SALAMATI N,GERMAIN A,SⅡSSTRUNK S.Removing shadows from images using color and near-infrared[C]//IEEE International Conference on Image Processing.Piscataway:IEEE,2011:1713-1716.
-
[16]
ZOU Q,CAO Y,LI Q,et al.Crack Tree:Automatic crack detection from pavement images[J].Pattern Recognition Letters,2012,33(3):227.
-
[1]
-
点击查看大图
计量
- PDF下载量: 199
- 文章访问数: 8438
- 引证文献数: 0
下载:
