低信噪比路面裂缝增强与提取方法研究
|
摘要
裂缝是最常见的路面损坏,在路面裂缝演变成坑槽之前进行修补,可以大大节约路面维护的成本。传统的基于影像的路面裂缝检测方法通常假设路面裂缝具有较高的对比度和较好的连续性,但这种假设在实践中往往不成立。这是因为,1)路面影像常常含有路面阴影造成亮度不均匀,2)路面颗粒纹理带来大量的点状噪声,3)路面裂缝由于车轮载重碾压、风化等作用发生退化造成其对比度下降、连续性降低,以及4)裂缝的成像效果对光照方向的高敏感性造成裂缝不连续。以上原因,使得裂缝在路面影像中表现为低信噪比的线状目标,给裂缝的自动化识别带来了巨大挑战。本文针对低信噪比路面裂缝的增强与提取,开展了以下研究：
(1)路面阴影不仅造成路面影像的亮度不均匀,而且破坏了路面裂缝的亮度一致性,极大地增加了路面裂缝识别的难度。准确界定并消除路面影像阴影,对路面裂缝识别非常关键。本文针对路面阴影由于半影区巨大而难以界定的难题,提出了基于亮度高程划分的阴影区域界定方法,实现对阴影区及半影区的准确界定。针对传统的加性亮度补偿不能均衡纹理细节的问题,提出了乘性亮度补偿方法,可以实现亮度补偿的同时,将阴影区的方差提高到非阴影区的水平,从而实现阴影区和非阴影区纹理细节的均衡。以上两者结合,得到了基于亮度高程模型的阴影消除算法(GSR),不仅能自动界定路面阴影区域,而且在保持裂缝的同时实现亮度和纹理细节的同步均衡。
(2)由于路面材料的颗粒纹理特性,二值路面影像常含有大量的噪声面元,造成路面裂缝信号受到噪声的严重干扰,裂缝目标与路面背景之间的信噪比非常低。考虑到张量表达点状目标的优势,以及投票过程中融入的Gestalt性法则具有潜在的提取线性显著性的功能,本文研究了针对路面裂缝增强的张量投票算法,它首先通过球投票获取每一个目标点的方向,然后运用棒投票实现目标点之间的软连接,并通过矩阵的特征分解实现线状显著性的提取,进而依据线性显著性对裂缝进行增强。
(3)针对路面裂缝由于受车轮载重碾压、自然风化等作用发生退化,导致裂缝与路面背景之间的对比度极低,甚至造成裂缝不连续的问题,研究了基于最小代价路径搜索的裂缝增强算法。在研究针对格状图最小代价路径搜索的F*算法的基础上,设计了具有较高运算效率的多尺度F*算法用于路面裂缝跟踪。在此基础上,提出了基于F*的种子生长算法——FoS,解决了F*路径跟踪起点和终点的自动选择的问题。接着,设计了自动获取裂缝种子点的算法流程,以及基于FoS的裂缝增强算法。最后,通过实验分析了种子生长半径对FoS算法效率的影响。
(4)针对从含有强噪声的目标点集合中提取具有线状结构特征的点子集的问题,提出了目标点最小生成树算法(T-MST)。T-MST首先用图模型对目标点进行描述,然后根据Gestalt法则的邻近性,计算具有最小边权总和的最小生成树,接着根据Gestalt法则的连续性设计了树的修剪算法,得到线状目标。结合T-MST算法,提出了裂缝提取的FoSA方法和CrackTree方法。FoSA方法利用F*种子生长的方式获取裂缝目标点,CrackTree利用采样的方式获取裂缝目标点。设计了针对性实验,验证了FoSA方法从路面影像中提取对比度低、连续性差的复杂裂缝具有较高的效率和可靠性。同时,采用大量路面影像进行对比实验验证了CrackTree方法比分割后处理方法、边缘检测方法具有更高的裂缝提取精度。
Cracks are the most common distresses on the road pavement. Fixing a crack beforeits deterioration can greatly reduce the cost of pavement maintenance. Most traditionalimage-based approaches for pavement crack detection implicitly assume that pavementcracks in images are with high contrast and good continuity. However, this assumptiondoes not hold in practice due to1) uneven illuminance caused by pavement shadows,2)speckle noise brought by grain-like texture of pavement,3) low contrast between cracksand the surrounding pavement and intensity inhomogeneity along the cracks caused bycrack degradation and4) bad continuity of cracks incurred by the high sensitivity ofcrack-imaging results to the direction of illumination. In the above conditions, pavementcracks show their linear structures in a low-SNR manner, which brings great challengesto the automatic detection of pavement cracks. To address these problems, this paperconducts the following research.
(1) Pavement shadows not only create uneven illuminance for pavement images, butalso undermine the intensity homogeneity of pavement cracks, which greatly increasethe difculty of identifcation of pavement cracks. To locate and remove pavement shad-ows is critical to the detection of pavement cracks. Considering that pavement shadowstypically hold a big penumbra area, we propose an intensity-based geodesic model tolocate the shadow area, as well as its penumbra area. Moreover, since traditional ad-ditive illuminance-compensation algorithm can not balance the texture detail betweenthe shadow area and the non-shadow area, we propose a multiplicative illuminance-compensation algorithm, which can improve the contrast of the shadow area to the levelof the non-shadow area by adjusting the variance. Then, a novel shadow removal al-gorihtm, i.e., GSR, is formed by integration of the above two components. GSR canautomatically locate the shadow and balance both the intensity and texture betweenthe shadow area and non-shadow area, and meanwhile preserve the cracks.
(2) Due to the particle texture of pavement materials, the binary pavement imagesoften contain a lot of speckle noise, which results in low SNR of pavement cracks againstthe pavement background. Note that the tensor is ft for describing the point target,and the Gestalt laws embedded into the voting process can potentially infer out the linear saliency. We exploit a tensor-voting-based method for crack enhancement, whichfrst uses a ball voting to form the orientation at each token, and then applies a stickvoting to softly connect the neighboring tokens, and at last, conduct an eigen-featureanalysis to extract the linear saliency.
(3) Since pavement cracks constantly sufer from the rolling of loaded wheels andthe weathering, crack degradation often exists and hence makes a low contrast betweenthe cracks and the pavement background, a bad continuity of the cracks as well. Toenhance these cracks, we exploit a method based on minimum-cost-path searching. First,we present a multi-scale F*algorithm for crack tracking in pavement images, which ismuch efcient than the original F*algorithm. Based on that, we propose an F*seed-growing algorithm, i.e., FoS, which achieves automatic selection of the tracking startand the tracking end. We develop an algorithm to automatically collect the crack seedsand subsequently apply a FoS process to enhance the cracks. We also experimentallystudy how the radius of seed growing impacts the enhancement results.
(4) To extract linear structures from a set of spatial points, we propose target-point minimum spanning tree, i.e., T-MST. T-MST inputs the target points into agraph model, and then compute the minimum spanning tree by considering the Gestaltlaw of proximity. Since a crack is a linear structure in a macro perspective, T-MSTembeds the Gestalt law of continuity into a priming algorithm and extract the fnal linecurves. Based on T-MST, we proposed the FoSA approach and CrackTree approachfor pavement crack extraction. The former acquires the target crack points by an F*seed-growing algorithm, while the later adopts a sampling strategy to collect the targetpoints. A range of experiments demonstrate that FoSA is efective and efcient inextracting complex cracks featured with low contrast and bad continuity. Meanwhile,experiments on large-scale dataset show that the proposed CrackTree achieves a muchbetter performance than several existing methods.
(1)路面阴影不仅造成路面影像的亮度不均匀,而且破坏了路面裂缝的亮度一致性,极大地增加了路面裂缝识别的难度。准确界定并消除路面影像阴影,对路面裂缝识别非常关键。本文针对路面阴影由于半影区巨大而难以界定的难题,提出了基于亮度高程划分的阴影区域界定方法,实现对阴影区及半影区的准确界定。针对传统的加性亮度补偿不能均衡纹理细节的问题,提出了乘性亮度补偿方法,可以实现亮度补偿的同时,将阴影区的方差提高到非阴影区的水平,从而实现阴影区和非阴影区纹理细节的均衡。以上两者结合,得到了基于亮度高程模型的阴影消除算法(GSR),不仅能自动界定路面阴影区域,而且在保持裂缝的同时实现亮度和纹理细节的同步均衡。
(2)由于路面材料的颗粒纹理特性,二值路面影像常含有大量的噪声面元,造成路面裂缝信号受到噪声的严重干扰,裂缝目标与路面背景之间的信噪比非常低。考虑到张量表达点状目标的优势,以及投票过程中融入的Gestalt性法则具有潜在的提取线性显著性的功能,本文研究了针对路面裂缝增强的张量投票算法,它首先通过球投票获取每一个目标点的方向,然后运用棒投票实现目标点之间的软连接,并通过矩阵的特征分解实现线状显著性的提取,进而依据线性显著性对裂缝进行增强。
(3)针对路面裂缝由于受车轮载重碾压、自然风化等作用发生退化,导致裂缝与路面背景之间的对比度极低,甚至造成裂缝不连续的问题,研究了基于最小代价路径搜索的裂缝增强算法。在研究针对格状图最小代价路径搜索的F*算法的基础上,设计了具有较高运算效率的多尺度F*算法用于路面裂缝跟踪。在此基础上,提出了基于F*的种子生长算法——FoS,解决了F*路径跟踪起点和终点的自动选择的问题。接着,设计了自动获取裂缝种子点的算法流程,以及基于FoS的裂缝增强算法。最后,通过实验分析了种子生长半径对FoS算法效率的影响。
(4)针对从含有强噪声的目标点集合中提取具有线状结构特征的点子集的问题,提出了目标点最小生成树算法(T-MST)。T-MST首先用图模型对目标点进行描述,然后根据Gestalt法则的邻近性,计算具有最小边权总和的最小生成树,接着根据Gestalt法则的连续性设计了树的修剪算法,得到线状目标。结合T-MST算法,提出了裂缝提取的FoSA方法和CrackTree方法。FoSA方法利用F*种子生长的方式获取裂缝目标点,CrackTree利用采样的方式获取裂缝目标点。设计了针对性实验,验证了FoSA方法从路面影像中提取对比度低、连续性差的复杂裂缝具有较高的效率和可靠性。同时,采用大量路面影像进行对比实验验证了CrackTree方法比分割后处理方法、边缘检测方法具有更高的裂缝提取精度。
Cracks are the most common distresses on the road pavement. Fixing a crack beforeits deterioration can greatly reduce the cost of pavement maintenance. Most traditionalimage-based approaches for pavement crack detection implicitly assume that pavementcracks in images are with high contrast and good continuity. However, this assumptiondoes not hold in practice due to1) uneven illuminance caused by pavement shadows,2)speckle noise brought by grain-like texture of pavement,3) low contrast between cracksand the surrounding pavement and intensity inhomogeneity along the cracks caused bycrack degradation and4) bad continuity of cracks incurred by the high sensitivity ofcrack-imaging results to the direction of illumination. In the above conditions, pavementcracks show their linear structures in a low-SNR manner, which brings great challengesto the automatic detection of pavement cracks. To address these problems, this paperconducts the following research.
(1) Pavement shadows not only create uneven illuminance for pavement images, butalso undermine the intensity homogeneity of pavement cracks, which greatly increasethe difculty of identifcation of pavement cracks. To locate and remove pavement shad-ows is critical to the detection of pavement cracks. Considering that pavement shadowstypically hold a big penumbra area, we propose an intensity-based geodesic model tolocate the shadow area, as well as its penumbra area. Moreover, since traditional ad-ditive illuminance-compensation algorithm can not balance the texture detail betweenthe shadow area and the non-shadow area, we propose a multiplicative illuminance-compensation algorithm, which can improve the contrast of the shadow area to the levelof the non-shadow area by adjusting the variance. Then, a novel shadow removal al-gorihtm, i.e., GSR, is formed by integration of the above two components. GSR canautomatically locate the shadow and balance both the intensity and texture betweenthe shadow area and non-shadow area, and meanwhile preserve the cracks.
(2) Due to the particle texture of pavement materials, the binary pavement imagesoften contain a lot of speckle noise, which results in low SNR of pavement cracks againstthe pavement background. Note that the tensor is ft for describing the point target,and the Gestalt laws embedded into the voting process can potentially infer out the linear saliency. We exploit a tensor-voting-based method for crack enhancement, whichfrst uses a ball voting to form the orientation at each token, and then applies a stickvoting to softly connect the neighboring tokens, and at last, conduct an eigen-featureanalysis to extract the linear saliency.
(3) Since pavement cracks constantly sufer from the rolling of loaded wheels andthe weathering, crack degradation often exists and hence makes a low contrast betweenthe cracks and the pavement background, a bad continuity of the cracks as well. Toenhance these cracks, we exploit a method based on minimum-cost-path searching. First,we present a multi-scale F*algorithm for crack tracking in pavement images, which ismuch efcient than the original F*algorithm. Based on that, we propose an F*seed-growing algorithm, i.e., FoS, which achieves automatic selection of the tracking startand the tracking end. We develop an algorithm to automatically collect the crack seedsand subsequently apply a FoS process to enhance the cracks. We also experimentallystudy how the radius of seed growing impacts the enhancement results.
(4) To extract linear structures from a set of spatial points, we propose target-point minimum spanning tree, i.e., T-MST. T-MST inputs the target points into agraph model, and then compute the minimum spanning tree by considering the Gestaltlaw of proximity. Since a crack is a linear structure in a macro perspective, T-MSTembeds the Gestalt law of continuity into a priming algorithm and extract the fnal linecurves. Based on T-MST, we proposed the FoSA approach and CrackTree approachfor pavement crack extraction. The former acquires the target crack points by an F*seed-growing algorithm, while the later adopts a sampling strategy to collect the targetpoints. A range of experiments demonstrate that FoSA is efective and efcient inextracting complex cracks featured with low contrast and bad continuity. Meanwhile,experiments on large-scale dataset show that the proposed CrackTree achieves a muchbetter performance than several existing methods.
引文
[1]张娟,沙爱民,孙朝云,高怀钢.基于相位编组法的路面裂缝自动识别.中国公路学报,21(2)：39-42,2008.
[2]严蔚敏,吴伟民.数据结构(C语言版).清华大学出版社,北京,1997.
[3]辛德刚,王哲人,周晓刚.高速公路沥青路面材料与结构.人民交通出版社,北京,2002.
[4]韩刚,蒋捷,陈军,曹大元.车载导航系统中顾及道路转向限制的弧段Dijkstra算法.测绘学报,31(4)：366-368,2002.
[5]高建贞,任明武,唐振民,杨静宇.路面裂缝的自动检测与识别.计算机工程,19(2)：149-150,2003.
[6]黄克智,薛明德,陆明万.张量分析(第2版).清华大学出版社,北京,2003.
[7]李晋惠.用图像处理的方法检测公路路面裂缝类病害.长安大学学报(自然科学版),24(3)：24-29,2004.
[8]王密,潘俊.一种数字航空影像的匀光方法.中国图象图形学报,9(6)：744-748,2004.
[9]唐庆适,苗夺谦,张红云.基于主曲线的指纹细节特征提取方法.计算机科学,32(1)：187-189,2005.
[10]丁辉,付梦印.基于Finite Ridgelet变换的影像线性特征提取.计算机科学,34(3)：230233，2007.
[11]洪日昌,吴秀清,刘媛,尹东.低分辨率遥感影像中道路的全自动提取方法研究.遥感学报,12(1)：36-44,2008.
[12]于向军,马若丁,刘岩,赵登峰.基于分形理论的路面裂缝图像分割研究.微计算机信息,24(3)：302-304,2008.
[13]秦菁.张量投票算法及其应用.华东师范大学硕士学位论文,2008.
[14]郭海涛,王鑫,徐青,张保明.基于感知编组的高层建筑物立面提取方法.计算机应用,29(9)：2389-2392,2009.
[15]张娟,沙爱民,孙朝云,高怀钢.路面裂缝自动识别的图像增强技术.中外公路,29(4)：301-305,2009.
[16]刘向龙.基于影像分析的路面破损评定与分类方法研究.武汉大学博士学位论文,2009.
[17]李清泉,邹勤,毛庆洲.基于最小代价路径搜索的路面裂缝检测.中国公路学报,23(6)：28-33,2010.
[18]孙波成,邱延峻,梁世庆.基于小波的路面裂缝识别研究.重庆交通大学学报(自然科学版),29(1)：69-72,2010.
[19]郑年波,陆锋,李清泉,段滢滢.顾及转向延误的时间依赖A*最短路径算法.测绘学报,39(5)：534-539,2010.
[20]张建军,胡惠灵,刘征宇,解新胜.光照不均管道内图像增强算法的研究与应用.计算机工程,37(16)：227-229,2011.
[21]章秀华,陈艳君,洪汉玉.基于加权融合纹理的路面裂缝检测.计算机与数字工程,39(10)：153-156,2011.
[22]宋蓓蓓,韦娜.基于脉冲耦合神经网络的路面裂缝提取.长安大学学报(自然科学版),31(5)：33-37,2011.
[23]于泳波,李万恒,张劲泉,聂建国.基于图像连通域的桥梁裂缝提取方法.公路交通科技,28(7)：90-93,2011.
[24]张维峰,尹冠生,刘萌,贺正权.数字图像处理技术在桥梁裂纹测量中的应用.长安大学学报(自然科学版),31(6)：50-53,2011.
[25]姚祖康.沥青路面结构设计.人民交通出版社,北京,2011.
[26]邹勤,李清泉,毛庆洲,陈龙.利用目标点最小生成树的路面裂缝检测.武汉大学学报·信息科学版,36(1)：711-715,2011.
[27]吕岩,曲仕茹.基于Beamlet变换的路面裂缝图像匀光算法.交通运输系统工程与信息,11(5)：123-128,2011.
[28]马常霞,赵春霞,狄峰,李曼先.自然环境下路面裂缝的识别.工程图学学报,4(4)：20-26,2011.
N. Almoussa. Variational retinex and shadow removal. In UCLA Technical Report,2006.
E. Arbel and H. Hel-Or. Texture-preserving shadow removal in color images containing curved surfaces. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07), pages1-8,2007.
[31]E. Arbel and H. Hel-Or. Shadow removal using intensity surfaces and texture anchor points. IEEE Transactions on Pattern Analysis and Machine Intelligence,33(6):1202-1216,2011.
[32]S. Audet. Removing shadows from images. Technical report, Department of Electrical and Computer Engineering, McGill University,2005.
[33]S. Audet and J.R. Cooperstock. Shadow removal in front projection environments using wbject tracking. In Proc. of the Workshop of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07), pages1-8,2007.
[34] R.P. Avery, G.H. Zhang, Y.H. Wang, and N. Nancy. An investigation into shadowremoval from trafc images. In Proc. of TRB2007Annual Meeting (TRB’07), pages70–77,2007.
[35] A. Ayenu-Prah and N. Attoh-Okine. Evaluating pavement cracks with bidimensionalempirical mode decomposition. EURASIP Journal on Advances in Signal Processing,2008:1–7,2008.
[36] R. Bamberger and M. Smith. A flter bank for the directional decomposition of images:theory and design. IEEE Transactions on Acoustics, Speech, and Signal Processing,40:882–893,1992.
[37] C. Barat, C. Ducottet, and M. Jourlin. Line pattern segmentation using morphologicalprobing. In Proc. of International Symposium on Image and Signal Processing, pages417–422,2003.
[38] D.J. Berndt and J. Cliford. Using dynamic time warping to fnd patterns in time series.In Proc. of the AAAI Workshop on Knowledge Discovery in Databases, pages359–370,1994.
[39] K.L. Boyer. Perceptual organization in computer vision: Status, challenges, and poten-tial. Computer Vision and Image Understanding,76(1):1–5,1999.
[40] E.J. Candes. Ridgelet: theory and applications. Ph.D Thesis, Department of Statistics,Stanford University,1998.
[41] J. Canny. A computational approach to edge detection. IEEE Transactions on PatternAnalysis and Machine Intelligence, PAMI-8:679–698,1986.
[42] M.J. Carlotto. Enhancement of low-contrast curvilinear feature in imagery. IEEE Trans-actions on Image Processing,16(1):221–228,2007.
[43] M.I. Chacon and L.E. Aguilar. A fuzzy approach to edge level detection. In Proc. ofthe10th IEEE International Conference on Fuzzy Systems, pages809–812,2001.
[44] C. Cheng, A. Koschan, D.L. Page, and M.A. Abidi. Scene image segmentation basedon perceptual organization. In Proc. of International Conference on Image Processing(ICIP’09), pages1–4,2009.
[45] H.D. Cheng, J.R. Chen, C. Glazier, and Y.G. Hu. Novel approach to pavement crack-ing detection based on fuzzy set theory. Journal of Computing in Civil Engineering,13(4):270–280,1999.
[46] H.D. Cheng, J.L. Wang, Y.G. Hu, C. Glazier, X.J. Shi, and X.W. Chen. Novel ap-proach to pavement cracking detection based on neural network. Transportation Re-search Record,1764:119–127,2001.
[47] J. Chou, W.A. O’iNeill, and H.D. Cheng. Pavement distress evaluation using fuzzy logicand moments invariants. Transportation Research Record,1505:39–46,1995.
[48] Y.Y. Chuang, D.B. Goldman, B. Curless, D.H. Salesin, and R. Szeliski. Shadow mattingand compositing. ACM Transactions on Graphics,22(3):494–500,2003.
[49] C. Copeland, G. Ravichandran, and M.M. Trivedi. Localized radon transform for shipwake detection in sar imagery. In Proc. of SPIE Automatic Object Recognition, pages1–6,1994.
[50] A. Criminisi, P. P′erez, and K. Toyama. Region flling and object removal by exemplar-based image inpainting. IEEE Transactions on Image Processing,13(9):1200–1212,2004.
[51] E.W. Dijkstra. A note on two problems in connexion with graphs. Numerische Mathe-matik,1:269271,1959.
[52] M.N. Do and M. Vetterli. The fnite ridgelet transform for image representation. IEEETransactions on Image Processing,12(1):16–28,2003.
[53] D.L. Donoho and X.M. Huo. Beamlets pyramids: A new form of multiresolution analysis,suited for extracting lines, curves, and objects from very noisy image data. In Proc. ofSPIE Wavelet Applications in Signal and Image Processing,2000.
[54] D.L. Donoho, X.M. Huo, I. Jermyn, P. Jones, G. Lerman, O. Levi, and F. Natterer.Beamlets and multiscale image analysis. In Proc. of Multiscale and MultiresolutionMethods, pages149–196. Springer,2001.
[55] M.S. Drew, G.D. Finlayson, and S.D. Hordley. Recovery of chromaticity image freefrom shadows via illumination invariance. In Proc. of the Workshop of InternationalConference on Computer Vision, pages1–8,2003.
[56] D.L. Donoho E.J. Candes. Ridgelets: A key to higher-dimensional intermittency. Philo-sophical Trans. of the Royal Society of London Series A,357(1760):2495–2509,1999.
[57] G.D. Finlayson, M. Drew, and C. Lu. Entropy minimization for shadow removal. In-ternational Journal of Computer Vision,85:35–57,2009.
[58] G.D. Finlayson, M.S. Drew, and C. Lu. Intrinsic images by entropy minimization. InProc. of Eurapean Conference on Computer Vision (ECCV’04), pages582–595,2004.
[59] G.D. Finlayson, S. Hordley, C. Lu, and M. Drew. On the removal of shadows fromimages. IEEE Transactions on Pattern Analysis and Machine Intelligence,28(1):59–68,2006.
[60] G.D. Finlayson, S.D. Hordley, and M.S. Drew. Removing shadows from images usingretinex. In Proc. of the10th Color Imaging Conference: Color Science and EngineeringSystems, Technologies, Applications.
[61] G.D. Finlayson, S.D. Hordley, and M.S. Drew. Removing shadows from images. In Proc.of the7th European Conference on Computer Vision (ECCV’02), pages823–836,2002.
[62] M.A. Fischler, J. Tenenbaum, and H. Wolf. Detection of roads and linear structuresin low-resolution aerial imagery using a multisource knowledge integration technique.Computer Graphics and Image Processing,15:201–223,1981.
[63] L.R. Ford. Network flow theory. Rand Technique Report, P-923,1956.
[64] J. Frank. Intrinsic images for shadow removal. Technical report, School of ComputerScience, McGill University,2004.
[65] C. Fredembach and G.D. Finlayson. Hamiltionian path based shadow removal. In Proc.of the British Machine Vision Conference (BMVC’05), pages1–10,2005.
[66] C. Fredembach and G.D. Finlayson. Simple shadow removal. In Proc. of the18th Inter-national Conference on Pattern Recognition (ICPR’06), pages832–835. IEEE ComputerSociety,2006.
[67] W.T. Freeman and E.H. Adelson. The design and use of steerable flters. IEEE Trans-actions on Pattern Analysis and Machine Intelligence,13(9):891–905,1991.
[68] D. Geman and B. Jedynak. An active testing model for tracking roads in satellite images.IEEE Transactions on Pattern Analysis and Machine Intelligence,18(1):1–14,1996.
[69] A.V. Goldberg and C. Harrelson. Computing the shortest path: A*search meets graphtheory. Technique Report, Microsoft Research, MSR-TR-2004-24,2003.
[70] A.V. Goldberg, H. Kaplan, and R.F. Werneck. Reach for A*: Efcient point-to-pointshortest path algorithms. In Proc. of SIAM Workshop on Algorithms Engineering andExperimentation, pages1–15,2006.
[71] A. Gruen and H.H. Li. Semi-automatic linear feature extraction by dynamic program-ming and lsb-snakes. Photogrammetry Engineering and Remote Sensing,63(8):985–995,1997.
[72] X. Gu, D. Yu, and L. Zhang. Image shadow removal using pulse coupled neural network.IEEE Transactions on Neural Networks,16(3):692–698,2005.
[73] G. Guy and G. Medioni. Inferring of surfaces,3d curves, and junctions from sparse, noisy,3d data. IEEE Transactions on Pattern Analysis and Machine Intelligence,19(11):1265–1277,1997.
[74] A. Hassani and H.G. Tehrani. Crack detection and classifcation in asphalt pavementusing image processing. In Proc. of the International Conference on Cracking in Pave-ments, pages891–896,2008.
[75] C.J. Hilditch. Linear skeletons from square cupboards. Machine Intelligence,4:403–420,1969.
[76] V. Hough. Methods and means for recognizing complex patterns. US, Patent,3069654,1962.
[77] S. Hsia and P. Tsai. Efcient light balancing techniques for text images in video pre-sentation systems. IEEE Transactions on Circuits and Systems for Video Technology,15(8):1026–1031,2005.
[78] Q.W. Hu and Q.Q. Li. A cloud change detection algorithm in modis image based onmask. In Proc. of2008Congress on Image and Signal Processing, pages249–253. IEEEComputer Society,2008.
[79] Y. Hu and C. Zhao. A local bineray pattern based methods for pavement crack detection.Journal of Pattern Recognition Research,1:140–147,2010.
[80] Y.X. Huang and B.G. Xu. Automatic inspection of pavement cracking distress. Journalof Electronic Imaging,15(1):013017.1–013017.6,2006.
[81] K.R. Kirschke and S.A. Velinsky. Histogram-based approach for automated pavement-crack sensing. Journal of Transportation Engineering,118(5):700–710,1992.
[82] J.L. Landabaso, M. Pardas, and L.Q. Xu. Shadow removal with morphological recon-struction. In Proc. of the Jornades de Recerca en Automatica, Visio i Robotica (AVR’04),pages1–5,2004.
[83] M.D. Levine and J. Bhattacharyya. Removing shadows. Pattern Recognition Letters,26:251–265,2005.
[84] Q.Q. Li and X.L. Liu. Novel approach to pavement image segmentation based on neigh-boring diference histogram method. In Proc. of International Congress on Image andSignal Processing, pages792–796,2008.
[85] Q.Q. Li, Q. Zou, D.Q. Zhang, and Q.Z. Mao. Fosa: F*seed-growing approach for crack-line detection from pavement images. Image and Vision Computing,29(12):861–872,2011.
[86] Y. Li, P. Gong, and T. Sasagawa. Integrated shadow removal based on photogrammetryand image analysis. International Journal of Remote Sensing,26(18):3911–3929,2005.
[87] F. Liu and M. Gleicher. Texture-consistent shadow removal. In Proc. of the10th Euro-pean Conference on Computer Vision (ECCV’08), pages437–450,2008.
[88] F.F. Liu, G.A. Xu, Y.X. Yang, X.X. Niu, and Y.L. Pan. Novel approach to pavementcracking automatic detection based on segment extending. In Proc. of InternationalSymposium on Knowledge Acquisition and Modeling, pages610–614,2008.
[89] L. Liu, D. Zhang, and J. You. Detecting wide lines using isotropic nonlinear flter. IEEETransactions on Image Processing,16(6):1584–1595,2007.
[90] H.J. Ma, Q.M. Qin, and X.Y. Shen. Shadow segmentation and compensation in highresolution satellite images. In Proc. of the IEEE International Symposium on Geoscienceand Remote Sensing (IGARSS’08), pages1036–1039,2008.
[91] R. Marikhu, M.N. Dailey, S. Makhanov, and K. Honda. A family of quadratic snakes forroad extraction. In Proc. of Asian Conference on Computer Vision (ACCV’07), pages85–94,2007.
[92] D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented naturalimages and its application to evaluating segmentation algorithms and measuring eco-logical statistics. In Proc. of International Conference on Computer Vision (ICCV’01),pages416–423,2001.
[93] G. Medioni, M. Lee, and C. Tang. A computational framework for segmentation andgrouping. Elsevier Sicence, Netherlands,2000.
[94] G. Medioni, C. Tang, and M. Lee. Tensor voting: theory and applications. In Proc. ofRFIA, pages1–10,2000.
[95] N. Merlet and J. Zerubia. Classical mechanics and road detection in spot images. JointResearch Report, INRIA/Hebrew University,1889,1993.
[96] N. Merlet and J. Zerubia. New prospects in line detection by dynamic programming.IEEE Transactions on Pattern Analysis and Machine Intelligence,18(4):426–431,1996.
[97] D. Miyazaki, Y. Matsushita, and K. Ikeuchi. Interactive shadow removal from a singleimage using hierarchical graph cut. In Proc. of the Asian Conference on ComputerVision (ACCV’09), pages234–245,2009.
[98] A. Mohan, J. Tumblin, and P. Choudhury. Editing soft shadows in a digital photograph.IEEE Computer Graphics and Applications,27(2):23–31,2007.
[99] P. Mordohai and G. Medioni. Tensor voting: a perceptual organization approach tocomputer vision and machine learning. Springer, New York, USA,2006.
[100] A.T. Nghiem, F. Bremond, and M. Thonnat. Shadow removal in indoor scenes. InProc. IEEE International Conference on Advanced Video and Signal Based Surveillance(AVSS’08), pages291–298. IEEE Computer Society,2008.
[101] T.S. Nguyen, M. Avila, and S. Begot. Automatic detection and classifcation of defecton road pavement using anisotropy measure. In Proc. of European Signal ProcessingConference (EUSIPCO’09), pages617–621,2009.
[102] M. Nielsen and C.B. Madsen. Graph cut based segmentation of soft shadows for seamlessremoval and augmentation. In Proc. of the15th Scandinavian conference on Imageanalysis (SCIA’07), pages918–927,2007.
[103] H. Oh, N.W. Garrick, and L.E.K. Achenie. Segmentation algorithm using iteratedclipping for processing noisy pavement images. In Proc. of International Conference onImaging Technologies: Techniques and Applications in Civil Engineering, pages138–147,1997.
[104] H. Oliveira and P.L. Correia. Identifying and retrieving distress images from road pave-ment surveys. In Proc. of International Conference on Image Processing, pages57–60,2008.
[105] H. Oliveira and P.L. Correia. Supervised strategies for crack detection in images ofroad pavement flexible surfaces. In Proc. of European Signal Processing Conference(EUSIPCO’08), pages25–29,2008.
[106] H. Oliveira and P.L. Correia. Automatic road crack segmentation using entropy andimage dynamic thresholding. In Proc. of European Signal Processing Conference (EU-SIPCO’09), pages622–626,2009.
[107] N. Otsu. A threshold selection method from gray-level histogram. IEEE Transactionson Systems, Man, and Cybernetics,9(1):62–66,1979.
[108] S.K. Pal and R.A. King. Image enhancement using smoothing with fuzzy. IEEE Trans-actions on System, Man and Cybernics,11(7):494–501,1981.
[109] J. Pan, M. Wang, D.R. Li, and J.L. Li. A network-based radiometric equalizationapproach for digital aerial orthoimages. IEEE Geoscience and Remote Sensing Letters,7(2):401–405,2010.
[110] P. P′erez, M. Gangnet, and A. Blake. Poisson image editing. ACM Transactions onGraphics,22(3):313–318,2003.
[111] M. Petrou, J. Kittler, and K.Y. Song. Automatic surface crack detection on texturedmaterials. Journal of Materials Processing Technology,56:158–167,1996.
[112] A. Plaza, E. Cernadas, M.L. Dur n, P.G. Rodr guez, and M.J. Petr n. Multi-scaledetection of curvilinear structures with high contour accuracy. In Proc. of the5thIberoamerican Symposium on Pattern Recognition, pages405–412,2000.
[113] R. Ramamoorthi, M. Koudelka, and P. Belhumeur. A fourier theory for cast shadows.In Proc. of the European Conference on Computer Vision (ECCV’04), pages146–162,2004.
[114] R. Ramamoorthi, M. Koudelka, and P. Belhumeur. A fourier theory for cast shadows.IEEE Transactions on Pattern Analysis and Machine Intelligence,27(2):1–8,2005.
[115] E. Salvador, A. Cavallaro, and T. Ebrahimi. Cast shadow segmentation using invariantcolor features. Computer Vision and Image Understanding,95(2):238–259,2004.
[116] R. Samadani and J.F. Vesecky. Finding curvilinear features in speckled images. IEEETransactions on Geoscience and Remote Sensing,28(4):669–673,1990.
[117] I. Sato, Y. Sato, and K. Ikeuchi. Illumination distribution from brightness in shad-ows: adaptive estimation of illumination distribution with unknown reflectance proper-ties in shadow regions. In Proc. of the International Conference on Computer Vision(ICCV’99), pages1–8,1999.
[118] Y. Shor and D. Lischinski. The shadow meets the mask: pyramid-based shadow removal.Computer Graphics Forum,27(2):577–586,2008.
[119] K.Y. Song, M. Petrou, and J. Kittler. Texture crack detection. Machine Vision andApplications,8:63–76,1995.
[120] J.S. Stahl and S. Wang. Globally optimal grouping for symmetric closed boundaries bycombining boundary and region information. IEEE Transactions on Pattern Analysisand Machine Intelligence,30(3):395–411,2008.
[121] D.C. Stanford and A.E. Raftery. Finding curvilinear features in spatial point patterns:principal curve clustering with noise. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence,22(6):601–609,2000.
[122] Y.F. Su and H.H. Chen. A three-stage approach to shadow feld estimation from par-tial boundary information. IEEE Transactions on Image Processing,19(10):2749–2760,2010.
[123] P. Subirats, J. Dumoulin, V. Legeay, and D. Barba. Automation of pavement surfacecrack detection using the continuous wavelet transform. In Proc. of International Con-ference on Image Processing, pages3037–3040,2006.
[124] M.W. Sun and J.Q. Zhang. Dodging research for digital aerial images. In Proc. ofCongress of the International Society for Photogrammetry and Remote Sensing (IS-PRS’08), pages349–354,2008.
[125] C.K. Tang, G. Medioni, and M.S. Lee. Epipolar geometry estimation by tensor votingin8d. In Proc. of International Conference on Computer Vision (ICCV’99), pages502–509,1999.
[126] S. Tantachun, C. Pintavirooj, M. Sangworasil, and Y. Kitjaidure. Directional flterbank: An enhancement for fngerprint feature detection. In Proc. of IEEE Conferenceon Industrial Electronics and Applications, pages1–5,2006.
[127] M.F. Tappen, W.T. Freeman, and E.H. Adelson. Recovering intrinsic images from a sin-gle image. In Proc. of the Neural Information Processing Systems Conference (NIPS’02),pages1–8,2002.
[128] M.F. Tappen, W.T. Freeman, and E.H. Adelson. Recovering intrinsic images froma single image. IEEE Transactions on Pattern Analysis and Machine Intelligence,27(9):1459–1472,2005.
[129] V.J.D. Tsai. A comparative study on shadow compensation of color aerial imagesin invariant color models. IEEE Transactions on Geoscience and Remote Sensing,44(6):1661–1671,2006.
[130] Y. Tsai, V. Kaul, and R.M. Mersereau. Critical assessment of pavement distress seg-mentation methods. Journal of Transportation Engineering,136(1):11–19,2010.
[131] F. Wang and R. Newkirk. A knowledge-based system for highway network extraction.IEEE Transactions on Geoscience and Remote Sensing,26(5):525–531,1988.
[132] S. Wang, J.S. Stahl, A. Bailey, and M. Dropps. Global detection of salient convexboundaries. International Journal of Computer Vision,71(3):337–359,2007.
[133] Y. Weiss. Deriving intrinsic images from image sequences. In Proc. of the InternationalConference on Computer Vision (ICCV’01), pages1–8,2001.
[134] C. Wiedemann and H. Ebner. Automatic completion and evaluation of road networks.Machine Intelligence,33:976–986,2000.
[135] Q.S. Wu, X.L. Luo, H. Li, and P.Z. Liu. An improved multi-scale retinex algorithm forvehicle shadow elimination based on variational kimmel. In Proc. of the2010Symposiaand Workshops on Ubiquitous, Autonomic and Trusted Computing, pages31–34. IEEEComputer Society,2010.
[136] T.P. Wu and C.K. Tang. A bayesian approach for shadow extraction from a singleimage. In Proc. of the International Conference on Computer Vision (ICCV’05), pages480–487,2005.
[137] T.P. Wu, C.K. Tang, M.S. Brown, and H.Y. Shum. Natural shadow matting. ACMTransactions on Graphics,26(2):1–21,2007.
[138] L. Xu, F.H. Qi, R.J. Jiang, Y.F. Hao, and G.R. Wu. Shadow detection and removal inreal images: A survey. In SJTU-CVLAB Technical Report,2006.
[139] M.D. Yan, S.B. Bo, K. Xu, and Y.Y. He. Pavement crack detection and analysis forhigh-grade highway. In Proc. of International Conference on Electronic Measurementand Instruments, pages548–552,2007.
[140] J. Yao and Z. Zhang. Hierarchical shadow detection for color aerial images. ComputerVision and Image Understanding,102:60–69,2006.
[141] J.J. Yoon, C. Koch, and T.J. Ellis. Shadowflash: an approach for shadow removal inan active illumination environment. In Proc. of the British Machine Vision Conference(BMVC’02), pages1–10,2002.
[142] J. Zhou, P.S. Huang, and F.P. Chiang. Wavelet-based pavement distress detection andevaluation. Optical Engineering,45(2):027007.1–027007.10,2006.
[143] J.J Zhu, K.G.G. Samuel, S.Z. Masood, and M.F. Tappen. Learning to recognize shadowsin monochromatic natural images. In Proc. of the IEEE Conference on Computer Visionand Pattern Recognition (CVPR’10), pages223–230, Los Alamitos, CA, USA,2010.
[144] Q. Zou, Y. Cao, Q.Q. Li, Q.Z. Mao, and S. Wang. Cracktree: automatic crack detectionfrom pavement images. Pattern Recognition Letters,33(3):227–238,2012.
[2]严蔚敏,吴伟民.数据结构(C语言版).清华大学出版社,北京,1997.
[3]辛德刚,王哲人,周晓刚.高速公路沥青路面材料与结构.人民交通出版社,北京,2002.
[4]韩刚,蒋捷,陈军,曹大元.车载导航系统中顾及道路转向限制的弧段Dijkstra算法.测绘学报,31(4)：366-368,2002.
[5]高建贞,任明武,唐振民,杨静宇.路面裂缝的自动检测与识别.计算机工程,19(2)：149-150,2003.
[6]黄克智,薛明德,陆明万.张量分析(第2版).清华大学出版社,北京,2003.
[7]李晋惠.用图像处理的方法检测公路路面裂缝类病害.长安大学学报(自然科学版),24(3)：24-29,2004.
[8]王密,潘俊.一种数字航空影像的匀光方法.中国图象图形学报,9(6)：744-748,2004.
[9]唐庆适,苗夺谦,张红云.基于主曲线的指纹细节特征提取方法.计算机科学,32(1)：187-189,2005.
[10]丁辉,付梦印.基于Finite Ridgelet变换的影像线性特征提取.计算机科学,34(3)：230233，2007.
[11]洪日昌,吴秀清,刘媛,尹东.低分辨率遥感影像中道路的全自动提取方法研究.遥感学报,12(1)：36-44,2008.
[12]于向军,马若丁,刘岩,赵登峰.基于分形理论的路面裂缝图像分割研究.微计算机信息,24(3)：302-304,2008.
[13]秦菁.张量投票算法及其应用.华东师范大学硕士学位论文,2008.
[14]郭海涛,王鑫,徐青,张保明.基于感知编组的高层建筑物立面提取方法.计算机应用,29(9)：2389-2392,2009.
[15]张娟,沙爱民,孙朝云,高怀钢.路面裂缝自动识别的图像增强技术.中外公路,29(4)：301-305,2009.
[16]刘向龙.基于影像分析的路面破损评定与分类方法研究.武汉大学博士学位论文,2009.
[17]李清泉,邹勤,毛庆洲.基于最小代价路径搜索的路面裂缝检测.中国公路学报,23(6)：28-33,2010.
[18]孙波成,邱延峻,梁世庆.基于小波的路面裂缝识别研究.重庆交通大学学报(自然科学版),29(1)：69-72,2010.
[19]郑年波,陆锋,李清泉,段滢滢.顾及转向延误的时间依赖A*最短路径算法.测绘学报,39(5)：534-539,2010.
[20]张建军,胡惠灵,刘征宇,解新胜.光照不均管道内图像增强算法的研究与应用.计算机工程,37(16)：227-229,2011.
[21]章秀华,陈艳君,洪汉玉.基于加权融合纹理的路面裂缝检测.计算机与数字工程,39(10)：153-156,2011.
[22]宋蓓蓓,韦娜.基于脉冲耦合神经网络的路面裂缝提取.长安大学学报(自然科学版),31(5)：33-37,2011.
[23]于泳波,李万恒,张劲泉,聂建国.基于图像连通域的桥梁裂缝提取方法.公路交通科技,28(7)：90-93,2011.
[24]张维峰,尹冠生,刘萌,贺正权.数字图像处理技术在桥梁裂纹测量中的应用.长安大学学报(自然科学版),31(6)：50-53,2011.
[25]姚祖康.沥青路面结构设计.人民交通出版社,北京,2011.
[26]邹勤,李清泉,毛庆洲,陈龙.利用目标点最小生成树的路面裂缝检测.武汉大学学报·信息科学版,36(1)：711-715,2011.
[27]吕岩,曲仕茹.基于Beamlet变换的路面裂缝图像匀光算法.交通运输系统工程与信息,11(5)：123-128,2011.
[28]马常霞,赵春霞,狄峰,李曼先.自然环境下路面裂缝的识别.工程图学学报,4(4)：20-26,2011.
N. Almoussa. Variational retinex and shadow removal. In UCLA Technical Report,2006.
E. Arbel and H. Hel-Or. Texture-preserving shadow removal in color images containing curved surfaces. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07), pages1-8,2007.
[31]E. Arbel and H. Hel-Or. Shadow removal using intensity surfaces and texture anchor points. IEEE Transactions on Pattern Analysis and Machine Intelligence,33(6):1202-1216,2011.
[32]S. Audet. Removing shadows from images. Technical report, Department of Electrical and Computer Engineering, McGill University,2005.
[33]S. Audet and J.R. Cooperstock. Shadow removal in front projection environments using wbject tracking. In Proc. of the Workshop of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07), pages1-8,2007.
[34] R.P. Avery, G.H. Zhang, Y.H. Wang, and N. Nancy. An investigation into shadowremoval from trafc images. In Proc. of TRB2007Annual Meeting (TRB’07), pages70–77,2007.
[35] A. Ayenu-Prah and N. Attoh-Okine. Evaluating pavement cracks with bidimensionalempirical mode decomposition. EURASIP Journal on Advances in Signal Processing,2008:1–7,2008.
[36] R. Bamberger and M. Smith. A flter bank for the directional decomposition of images:theory and design. IEEE Transactions on Acoustics, Speech, and Signal Processing,40:882–893,1992.
[37] C. Barat, C. Ducottet, and M. Jourlin. Line pattern segmentation using morphologicalprobing. In Proc. of International Symposium on Image and Signal Processing, pages417–422,2003.
[38] D.J. Berndt and J. Cliford. Using dynamic time warping to fnd patterns in time series.In Proc. of the AAAI Workshop on Knowledge Discovery in Databases, pages359–370,1994.
[39] K.L. Boyer. Perceptual organization in computer vision: Status, challenges, and poten-tial. Computer Vision and Image Understanding,76(1):1–5,1999.
[40] E.J. Candes. Ridgelet: theory and applications. Ph.D Thesis, Department of Statistics,Stanford University,1998.
[41] J. Canny. A computational approach to edge detection. IEEE Transactions on PatternAnalysis and Machine Intelligence, PAMI-8:679–698,1986.
[42] M.J. Carlotto. Enhancement of low-contrast curvilinear feature in imagery. IEEE Trans-actions on Image Processing,16(1):221–228,2007.
[43] M.I. Chacon and L.E. Aguilar. A fuzzy approach to edge level detection. In Proc. ofthe10th IEEE International Conference on Fuzzy Systems, pages809–812,2001.
[44] C. Cheng, A. Koschan, D.L. Page, and M.A. Abidi. Scene image segmentation basedon perceptual organization. In Proc. of International Conference on Image Processing(ICIP’09), pages1–4,2009.
[45] H.D. Cheng, J.R. Chen, C. Glazier, and Y.G. Hu. Novel approach to pavement crack-ing detection based on fuzzy set theory. Journal of Computing in Civil Engineering,13(4):270–280,1999.
[46] H.D. Cheng, J.L. Wang, Y.G. Hu, C. Glazier, X.J. Shi, and X.W. Chen. Novel ap-proach to pavement cracking detection based on neural network. Transportation Re-search Record,1764:119–127,2001.
[47] J. Chou, W.A. O’iNeill, and H.D. Cheng. Pavement distress evaluation using fuzzy logicand moments invariants. Transportation Research Record,1505:39–46,1995.
[48] Y.Y. Chuang, D.B. Goldman, B. Curless, D.H. Salesin, and R. Szeliski. Shadow mattingand compositing. ACM Transactions on Graphics,22(3):494–500,2003.
[49] C. Copeland, G. Ravichandran, and M.M. Trivedi. Localized radon transform for shipwake detection in sar imagery. In Proc. of SPIE Automatic Object Recognition, pages1–6,1994.
[50] A. Criminisi, P. P′erez, and K. Toyama. Region flling and object removal by exemplar-based image inpainting. IEEE Transactions on Image Processing,13(9):1200–1212,2004.
[51] E.W. Dijkstra. A note on two problems in connexion with graphs. Numerische Mathe-matik,1:269271,1959.
[52] M.N. Do and M. Vetterli. The fnite ridgelet transform for image representation. IEEETransactions on Image Processing,12(1):16–28,2003.
[53] D.L. Donoho and X.M. Huo. Beamlets pyramids: A new form of multiresolution analysis,suited for extracting lines, curves, and objects from very noisy image data. In Proc. ofSPIE Wavelet Applications in Signal and Image Processing,2000.
[54] D.L. Donoho, X.M. Huo, I. Jermyn, P. Jones, G. Lerman, O. Levi, and F. Natterer.Beamlets and multiscale image analysis. In Proc. of Multiscale and MultiresolutionMethods, pages149–196. Springer,2001.
[55] M.S. Drew, G.D. Finlayson, and S.D. Hordley. Recovery of chromaticity image freefrom shadows via illumination invariance. In Proc. of the Workshop of InternationalConference on Computer Vision, pages1–8,2003.
[56] D.L. Donoho E.J. Candes. Ridgelets: A key to higher-dimensional intermittency. Philo-sophical Trans. of the Royal Society of London Series A,357(1760):2495–2509,1999.
[57] G.D. Finlayson, M. Drew, and C. Lu. Entropy minimization for shadow removal. In-ternational Journal of Computer Vision,85:35–57,2009.
[58] G.D. Finlayson, M.S. Drew, and C. Lu. Intrinsic images by entropy minimization. InProc. of Eurapean Conference on Computer Vision (ECCV’04), pages582–595,2004.
[59] G.D. Finlayson, S. Hordley, C. Lu, and M. Drew. On the removal of shadows fromimages. IEEE Transactions on Pattern Analysis and Machine Intelligence,28(1):59–68,2006.
[60] G.D. Finlayson, S.D. Hordley, and M.S. Drew. Removing shadows from images usingretinex. In Proc. of the10th Color Imaging Conference: Color Science and EngineeringSystems, Technologies, Applications.
[61] G.D. Finlayson, S.D. Hordley, and M.S. Drew. Removing shadows from images. In Proc.of the7th European Conference on Computer Vision (ECCV’02), pages823–836,2002.
[62] M.A. Fischler, J. Tenenbaum, and H. Wolf. Detection of roads and linear structuresin low-resolution aerial imagery using a multisource knowledge integration technique.Computer Graphics and Image Processing,15:201–223,1981.
[63] L.R. Ford. Network flow theory. Rand Technique Report, P-923,1956.
[64] J. Frank. Intrinsic images for shadow removal. Technical report, School of ComputerScience, McGill University,2004.
[65] C. Fredembach and G.D. Finlayson. Hamiltionian path based shadow removal. In Proc.of the British Machine Vision Conference (BMVC’05), pages1–10,2005.
[66] C. Fredembach and G.D. Finlayson. Simple shadow removal. In Proc. of the18th Inter-national Conference on Pattern Recognition (ICPR’06), pages832–835. IEEE ComputerSociety,2006.
[67] W.T. Freeman and E.H. Adelson. The design and use of steerable flters. IEEE Trans-actions on Pattern Analysis and Machine Intelligence,13(9):891–905,1991.
[68] D. Geman and B. Jedynak. An active testing model for tracking roads in satellite images.IEEE Transactions on Pattern Analysis and Machine Intelligence,18(1):1–14,1996.
[69] A.V. Goldberg and C. Harrelson. Computing the shortest path: A*search meets graphtheory. Technique Report, Microsoft Research, MSR-TR-2004-24,2003.
[70] A.V. Goldberg, H. Kaplan, and R.F. Werneck. Reach for A*: Efcient point-to-pointshortest path algorithms. In Proc. of SIAM Workshop on Algorithms Engineering andExperimentation, pages1–15,2006.
[71] A. Gruen and H.H. Li. Semi-automatic linear feature extraction by dynamic program-ming and lsb-snakes. Photogrammetry Engineering and Remote Sensing,63(8):985–995,1997.
[72] X. Gu, D. Yu, and L. Zhang. Image shadow removal using pulse coupled neural network.IEEE Transactions on Neural Networks,16(3):692–698,2005.
[73] G. Guy and G. Medioni. Inferring of surfaces,3d curves, and junctions from sparse, noisy,3d data. IEEE Transactions on Pattern Analysis and Machine Intelligence,19(11):1265–1277,1997.
[74] A. Hassani and H.G. Tehrani. Crack detection and classifcation in asphalt pavementusing image processing. In Proc. of the International Conference on Cracking in Pave-ments, pages891–896,2008.
[75] C.J. Hilditch. Linear skeletons from square cupboards. Machine Intelligence,4:403–420,1969.
[76] V. Hough. Methods and means for recognizing complex patterns. US, Patent,3069654,1962.
[77] S. Hsia and P. Tsai. Efcient light balancing techniques for text images in video pre-sentation systems. IEEE Transactions on Circuits and Systems for Video Technology,15(8):1026–1031,2005.
[78] Q.W. Hu and Q.Q. Li. A cloud change detection algorithm in modis image based onmask. In Proc. of2008Congress on Image and Signal Processing, pages249–253. IEEEComputer Society,2008.
[79] Y. Hu and C. Zhao. A local bineray pattern based methods for pavement crack detection.Journal of Pattern Recognition Research,1:140–147,2010.
[80] Y.X. Huang and B.G. Xu. Automatic inspection of pavement cracking distress. Journalof Electronic Imaging,15(1):013017.1–013017.6,2006.
[81] K.R. Kirschke and S.A. Velinsky. Histogram-based approach for automated pavement-crack sensing. Journal of Transportation Engineering,118(5):700–710,1992.
[82] J.L. Landabaso, M. Pardas, and L.Q. Xu. Shadow removal with morphological recon-struction. In Proc. of the Jornades de Recerca en Automatica, Visio i Robotica (AVR’04),pages1–5,2004.
[83] M.D. Levine and J. Bhattacharyya. Removing shadows. Pattern Recognition Letters,26:251–265,2005.
[84] Q.Q. Li and X.L. Liu. Novel approach to pavement image segmentation based on neigh-boring diference histogram method. In Proc. of International Congress on Image andSignal Processing, pages792–796,2008.
[85] Q.Q. Li, Q. Zou, D.Q. Zhang, and Q.Z. Mao. Fosa: F*seed-growing approach for crack-line detection from pavement images. Image and Vision Computing,29(12):861–872,2011.
[86] Y. Li, P. Gong, and T. Sasagawa. Integrated shadow removal based on photogrammetryand image analysis. International Journal of Remote Sensing,26(18):3911–3929,2005.
[87] F. Liu and M. Gleicher. Texture-consistent shadow removal. In Proc. of the10th Euro-pean Conference on Computer Vision (ECCV’08), pages437–450,2008.
[88] F.F. Liu, G.A. Xu, Y.X. Yang, X.X. Niu, and Y.L. Pan. Novel approach to pavementcracking automatic detection based on segment extending. In Proc. of InternationalSymposium on Knowledge Acquisition and Modeling, pages610–614,2008.
[89] L. Liu, D. Zhang, and J. You. Detecting wide lines using isotropic nonlinear flter. IEEETransactions on Image Processing,16(6):1584–1595,2007.
[90] H.J. Ma, Q.M. Qin, and X.Y. Shen. Shadow segmentation and compensation in highresolution satellite images. In Proc. of the IEEE International Symposium on Geoscienceand Remote Sensing (IGARSS’08), pages1036–1039,2008.
[91] R. Marikhu, M.N. Dailey, S. Makhanov, and K. Honda. A family of quadratic snakes forroad extraction. In Proc. of Asian Conference on Computer Vision (ACCV’07), pages85–94,2007.
[92] D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented naturalimages and its application to evaluating segmentation algorithms and measuring eco-logical statistics. In Proc. of International Conference on Computer Vision (ICCV’01),pages416–423,2001.
[93] G. Medioni, M. Lee, and C. Tang. A computational framework for segmentation andgrouping. Elsevier Sicence, Netherlands,2000.
[94] G. Medioni, C. Tang, and M. Lee. Tensor voting: theory and applications. In Proc. ofRFIA, pages1–10,2000.
[95] N. Merlet and J. Zerubia. Classical mechanics and road detection in spot images. JointResearch Report, INRIA/Hebrew University,1889,1993.
[96] N. Merlet and J. Zerubia. New prospects in line detection by dynamic programming.IEEE Transactions on Pattern Analysis and Machine Intelligence,18(4):426–431,1996.
[97] D. Miyazaki, Y. Matsushita, and K. Ikeuchi. Interactive shadow removal from a singleimage using hierarchical graph cut. In Proc. of the Asian Conference on ComputerVision (ACCV’09), pages234–245,2009.
[98] A. Mohan, J. Tumblin, and P. Choudhury. Editing soft shadows in a digital photograph.IEEE Computer Graphics and Applications,27(2):23–31,2007.
[99] P. Mordohai and G. Medioni. Tensor voting: a perceptual organization approach tocomputer vision and machine learning. Springer, New York, USA,2006.
[100] A.T. Nghiem, F. Bremond, and M. Thonnat. Shadow removal in indoor scenes. InProc. IEEE International Conference on Advanced Video and Signal Based Surveillance(AVSS’08), pages291–298. IEEE Computer Society,2008.
[101] T.S. Nguyen, M. Avila, and S. Begot. Automatic detection and classifcation of defecton road pavement using anisotropy measure. In Proc. of European Signal ProcessingConference (EUSIPCO’09), pages617–621,2009.
[102] M. Nielsen and C.B. Madsen. Graph cut based segmentation of soft shadows for seamlessremoval and augmentation. In Proc. of the15th Scandinavian conference on Imageanalysis (SCIA’07), pages918–927,2007.
[103] H. Oh, N.W. Garrick, and L.E.K. Achenie. Segmentation algorithm using iteratedclipping for processing noisy pavement images. In Proc. of International Conference onImaging Technologies: Techniques and Applications in Civil Engineering, pages138–147,1997.
[104] H. Oliveira and P.L. Correia. Identifying and retrieving distress images from road pave-ment surveys. In Proc. of International Conference on Image Processing, pages57–60,2008.
[105] H. Oliveira and P.L. Correia. Supervised strategies for crack detection in images ofroad pavement flexible surfaces. In Proc. of European Signal Processing Conference(EUSIPCO’08), pages25–29,2008.
[106] H. Oliveira and P.L. Correia. Automatic road crack segmentation using entropy andimage dynamic thresholding. In Proc. of European Signal Processing Conference (EU-SIPCO’09), pages622–626,2009.
[107] N. Otsu. A threshold selection method from gray-level histogram. IEEE Transactionson Systems, Man, and Cybernetics,9(1):62–66,1979.
[108] S.K. Pal and R.A. King. Image enhancement using smoothing with fuzzy. IEEE Trans-actions on System, Man and Cybernics,11(7):494–501,1981.
[109] J. Pan, M. Wang, D.R. Li, and J.L. Li. A network-based radiometric equalizationapproach for digital aerial orthoimages. IEEE Geoscience and Remote Sensing Letters,7(2):401–405,2010.
[110] P. P′erez, M. Gangnet, and A. Blake. Poisson image editing. ACM Transactions onGraphics,22(3):313–318,2003.
[111] M. Petrou, J. Kittler, and K.Y. Song. Automatic surface crack detection on texturedmaterials. Journal of Materials Processing Technology,56:158–167,1996.
[112] A. Plaza, E. Cernadas, M.L. Dur n, P.G. Rodr guez, and M.J. Petr n. Multi-scaledetection of curvilinear structures with high contour accuracy. In Proc. of the5thIberoamerican Symposium on Pattern Recognition, pages405–412,2000.
[113] R. Ramamoorthi, M. Koudelka, and P. Belhumeur. A fourier theory for cast shadows.In Proc. of the European Conference on Computer Vision (ECCV’04), pages146–162,2004.
[114] R. Ramamoorthi, M. Koudelka, and P. Belhumeur. A fourier theory for cast shadows.IEEE Transactions on Pattern Analysis and Machine Intelligence,27(2):1–8,2005.
[115] E. Salvador, A. Cavallaro, and T. Ebrahimi. Cast shadow segmentation using invariantcolor features. Computer Vision and Image Understanding,95(2):238–259,2004.
[116] R. Samadani and J.F. Vesecky. Finding curvilinear features in speckled images. IEEETransactions on Geoscience and Remote Sensing,28(4):669–673,1990.
[117] I. Sato, Y. Sato, and K. Ikeuchi. Illumination distribution from brightness in shad-ows: adaptive estimation of illumination distribution with unknown reflectance proper-ties in shadow regions. In Proc. of the International Conference on Computer Vision(ICCV’99), pages1–8,1999.
[118] Y. Shor and D. Lischinski. The shadow meets the mask: pyramid-based shadow removal.Computer Graphics Forum,27(2):577–586,2008.
[119] K.Y. Song, M. Petrou, and J. Kittler. Texture crack detection. Machine Vision andApplications,8:63–76,1995.
[120] J.S. Stahl and S. Wang. Globally optimal grouping for symmetric closed boundaries bycombining boundary and region information. IEEE Transactions on Pattern Analysisand Machine Intelligence,30(3):395–411,2008.
[121] D.C. Stanford and A.E. Raftery. Finding curvilinear features in spatial point patterns:principal curve clustering with noise. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence,22(6):601–609,2000.
[122] Y.F. Su and H.H. Chen. A three-stage approach to shadow feld estimation from par-tial boundary information. IEEE Transactions on Image Processing,19(10):2749–2760,2010.
[123] P. Subirats, J. Dumoulin, V. Legeay, and D. Barba. Automation of pavement surfacecrack detection using the continuous wavelet transform. In Proc. of International Con-ference on Image Processing, pages3037–3040,2006.
[124] M.W. Sun and J.Q. Zhang. Dodging research for digital aerial images. In Proc. ofCongress of the International Society for Photogrammetry and Remote Sensing (IS-PRS’08), pages349–354,2008.
[125] C.K. Tang, G. Medioni, and M.S. Lee. Epipolar geometry estimation by tensor votingin8d. In Proc. of International Conference on Computer Vision (ICCV’99), pages502–509,1999.
[126] S. Tantachun, C. Pintavirooj, M. Sangworasil, and Y. Kitjaidure. Directional flterbank: An enhancement for fngerprint feature detection. In Proc. of IEEE Conferenceon Industrial Electronics and Applications, pages1–5,2006.
[127] M.F. Tappen, W.T. Freeman, and E.H. Adelson. Recovering intrinsic images from a sin-gle image. In Proc. of the Neural Information Processing Systems Conference (NIPS’02),pages1–8,2002.
[128] M.F. Tappen, W.T. Freeman, and E.H. Adelson. Recovering intrinsic images froma single image. IEEE Transactions on Pattern Analysis and Machine Intelligence,27(9):1459–1472,2005.
[129] V.J.D. Tsai. A comparative study on shadow compensation of color aerial imagesin invariant color models. IEEE Transactions on Geoscience and Remote Sensing,44(6):1661–1671,2006.
[130] Y. Tsai, V. Kaul, and R.M. Mersereau. Critical assessment of pavement distress seg-mentation methods. Journal of Transportation Engineering,136(1):11–19,2010.
[131] F. Wang and R. Newkirk. A knowledge-based system for highway network extraction.IEEE Transactions on Geoscience and Remote Sensing,26(5):525–531,1988.
[132] S. Wang, J.S. Stahl, A. Bailey, and M. Dropps. Global detection of salient convexboundaries. International Journal of Computer Vision,71(3):337–359,2007.
[133] Y. Weiss. Deriving intrinsic images from image sequences. In Proc. of the InternationalConference on Computer Vision (ICCV’01), pages1–8,2001.
[134] C. Wiedemann and H. Ebner. Automatic completion and evaluation of road networks.Machine Intelligence,33:976–986,2000.
[135] Q.S. Wu, X.L. Luo, H. Li, and P.Z. Liu. An improved multi-scale retinex algorithm forvehicle shadow elimination based on variational kimmel. In Proc. of the2010Symposiaand Workshops on Ubiquitous, Autonomic and Trusted Computing, pages31–34. IEEEComputer Society,2010.
[136] T.P. Wu and C.K. Tang. A bayesian approach for shadow extraction from a singleimage. In Proc. of the International Conference on Computer Vision (ICCV’05), pages480–487,2005.
[137] T.P. Wu, C.K. Tang, M.S. Brown, and H.Y. Shum. Natural shadow matting. ACMTransactions on Graphics,26(2):1–21,2007.
[138] L. Xu, F.H. Qi, R.J. Jiang, Y.F. Hao, and G.R. Wu. Shadow detection and removal inreal images: A survey. In SJTU-CVLAB Technical Report,2006.
[139] M.D. Yan, S.B. Bo, K. Xu, and Y.Y. He. Pavement crack detection and analysis forhigh-grade highway. In Proc. of International Conference on Electronic Measurementand Instruments, pages548–552,2007.
[140] J. Yao and Z. Zhang. Hierarchical shadow detection for color aerial images. ComputerVision and Image Understanding,102:60–69,2006.
[141] J.J. Yoon, C. Koch, and T.J. Ellis. Shadowflash: an approach for shadow removal inan active illumination environment. In Proc. of the British Machine Vision Conference(BMVC’02), pages1–10,2002.
[142] J. Zhou, P.S. Huang, and F.P. Chiang. Wavelet-based pavement distress detection andevaluation. Optical Engineering,45(2):027007.1–027007.10,2006.
[143] J.J Zhu, K.G.G. Samuel, S.Z. Masood, and M.F. Tappen. Learning to recognize shadowsin monochromatic natural images. In Proc. of the IEEE Conference on Computer Visionand Pattern Recognition (CVPR’10), pages223–230, Los Alamitos, CA, USA,2010.
[144] Q. Zou, Y. Cao, Q.Q. Li, Q.Z. Mao, and S. Wang. Cracktree: automatic crack detectionfrom pavement images. Pattern Recognition Letters,33(3):227–238,2012.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |