基于圆环模板和标志矩阵的角点检测算法
|
摘要
为了解决计算机视觉系统中图像边缘检测时边缘点和边缘段同时检出的问题,提出了一种基于圆环模板和角点标志矩阵表示的角点检测算法。首先通过设置较小的阈值,应用圆环模板提取较多的灰度图像的亮度变化点作为候选角点;记录角点在原图像中的位置,并将原图像中该像素值设置为1,其他像素设置为0,建立角点标志矩阵,并将矩阵按照四叉树结构分解;统计子矩阵的1的个数和所占比例,将个数和比例较低的子块的角点标记删除;对其他的子矩阵分别采用行方式和列方式进行行程编码,在编码中对连续的1序列仅保留第一个,将后续的1置为0。记录同时在行方式和列方式结果矩阵中的1元素为角点。实验结果表明,与Moravec算法、Harris算法与FAST算法相比,该算法具有角点检测准确和适用面广的优点,在一定程度上解决了减少角点数目的问题。
In order to solve the problem of simultaneous detection of edge points and edge line segments during the edge detection in computer vision system,we propose a corner detection algorithm on basis of the ring template and the corner mark matrix. At first the smaller threshold is set up. More pixels with the brightness change extracting by the ring template are treated as the candidate corner pixels. The corner locations are recorded in the original image,and the pixel value of the original image is set to 1,and the other pixels are set to 0. The corner marker matrix is established and decomposed according to the quadtree structure. The number and proportion of the 1 are calculated in the submatrices. And the corners in the subblocks are deleted from the corner marks with the lower numbers and the lower proportions. The sub matrices are coded in line and column respectively through run length coding. The first 1 element in the consecutive coding sequences is kept,and the subsequent 1 is set to 0. The 1 element in the result matrix of the row and column mode are recorded as the corner points at the same time. The experiment shows that compared with Moravec algorithm,Harris algorithm and FAST algorithm,the proposed algorithm has the advantages of the accurate corner detection and the wide application,which solves the problem of reducing the number of corner points to a certain extent.
In order to solve the problem of simultaneous detection of edge points and edge line segments during the edge detection in computer vision system,we propose a corner detection algorithm on basis of the ring template and the corner mark matrix. At first the smaller threshold is set up. More pixels with the brightness change extracting by the ring template are treated as the candidate corner pixels. The corner locations are recorded in the original image,and the pixel value of the original image is set to 1,and the other pixels are set to 0. The corner marker matrix is established and decomposed according to the quadtree structure. The number and proportion of the 1 are calculated in the submatrices. And the corners in the subblocks are deleted from the corner marks with the lower numbers and the lower proportions. The sub matrices are coded in line and column respectively through run length coding. The first 1 element in the consecutive coding sequences is kept,and the subsequent 1 is set to 0. The 1 element in the result matrix of the row and column mode are recorded as the corner points at the same time. The experiment shows that compared with Moravec algorithm,Harris algorithm and FAST algorithm,the proposed algorithm has the advantages of the accurate corner detection and the wide application,which solves the problem of reducing the number of corner points to a certain extent.
引文
[1] 章为川,孔祥楠,宋文.图像的角点检测研究综述[J].电子学报,2015,43(11):2315-2321.
[2] VAN AUDENHAEGE K V,VANHOVE C,VANDENBERGHE S,et al.The evaluation of data completeness and image quality in multiplexing multi-pinhole SPECT[J].IEEE Transactions on Medical Imaging,2015,34(2):474-486.
[3] KAZMI W,ANDERSEN H J.A comparison of interest point and region detectors on structured,range and texture images[J].Journal of Visual Communication and Image Representation,2015,32:156-169.
[4] SINGH N,ARYA R,AGRAWAL R K.A convex hull approach in conjunction with Gaussian mixture model for salient object detection[J].Digital Signal Processing,2016,55:22-31.
[5] MA Hongjin,NIE Yufeng.An edge fusion scheme for image denoising based on anisotropic diffusion models[J].Journal of Visual Communication & Image Representation,2016,40:406-417.
[6] 高华.Log-Gabor梯度方向下的角点检测[J].中国图象图形学报,2017,22(6):797-806.
[7] 刘妍,余淮,杨文,等.利用SAR-FAST角点检测的合成孔径雷达图像配准方法[J].电子与信息学报,2017,39(2):430-436.
[8] 赵亚利,章为川,李云红.图像边缘轮廓自适应阈值的角点检测算法[J].中国图象图形学报,2016,21(11):1502-1514.
[9] 刘亮,王平,孙亮.基于区域灰度变化的自适应FAST角点检测算法[J].微电子学与计算机,2017,34(3):20-24.
[10] XING Yuanxiu,ZHANG Dengyi,ZHAO Jianhui,et al.Robust fast corner detector based on filled circle and outer ring mask[J].IET Image Processing,2016,10(4):314-324.
[11] PATOOMMAKESORN K,VIGNAT F,VILLENEUVE F.A new straight line matching technique by integration of vision -based image processing[J].Procedia CIRP,2016,41:777-782.
[12] BOK Y,HA H,KWEON I S.Automated checkerboard detection and indexing using circular boundaries[J].Pattern Recognition Letters,2016,71:66-72.
[13] DING Weili,WANG Wenfeng,LI Xiaoli.OTLines:a novel line-detection algorithm without the interference of smooth curves[J].Pattern Recognition,2016,53(2):238-258.
[14] ZHANG Xiaohong,LEI Ming,YANG Dan,et al.Multi-scale curvature product for robust image corner detection in curvature scale space[J].Pattern Recognition Letters,2007,28(5):545-554.
[15] LAKEMOND R,FOOKES C,SRIDHARAN S.Affine adaptation of local image features using the Hessian matrix[C]//2009 sixth IEEE international conference on advanced video and signal based surveillance.Genova,Italy:IEEE,2009:496-501.
[16] MORAVEC H P.Visual mapping by a robot rover[C]//Proceedings of the 6th international joint conference on artificial intelligence.Tokyo,Japan:Morgan Kaufmann Publishers Inc.,1979:598-600.
[17] HARRIS C,STEPHENS M.A combined corner and edge detector[C]//Proceedings of the 4th Alvey vision conference.[s.l.]:[s.n.],1988:147-151.
[18] NOBLE J A.Finding corners[J].Image & Vision Computing,1988,6(2):121-128.
[19] SMITH S M,BRADY M.SUSAN-a new approach to low level image processing[J].International Journal of Computer Vision,1997,23(1):45-78.
[20] ROSTEN E,DRUMMOND T.Machine learning for high-speed corner detection[C]//European conference on computer vision.[s.l.]:[s.n.],2006:430-443.
[21] ROSTEN E,PORTER R,DRUMMOND T.Faster and better:a machine learning approach to corner detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2009,32(1):105-119.
[2] VAN AUDENHAEGE K V,VANHOVE C,VANDENBERGHE S,et al.The evaluation of data completeness and image quality in multiplexing multi-pinhole SPECT[J].IEEE Transactions on Medical Imaging,2015,34(2):474-486.
[3] KAZMI W,ANDERSEN H J.A comparison of interest point and region detectors on structured,range and texture images[J].Journal of Visual Communication and Image Representation,2015,32:156-169.
[4] SINGH N,ARYA R,AGRAWAL R K.A convex hull approach in conjunction with Gaussian mixture model for salient object detection[J].Digital Signal Processing,2016,55:22-31.
[5] MA Hongjin,NIE Yufeng.An edge fusion scheme for image denoising based on anisotropic diffusion models[J].Journal of Visual Communication & Image Representation,2016,40:406-417.
[6] 高华.Log-Gabor梯度方向下的角点检测[J].中国图象图形学报,2017,22(6):797-806.
[7] 刘妍,余淮,杨文,等.利用SAR-FAST角点检测的合成孔径雷达图像配准方法[J].电子与信息学报,2017,39(2):430-436.
[8] 赵亚利,章为川,李云红.图像边缘轮廓自适应阈值的角点检测算法[J].中国图象图形学报,2016,21(11):1502-1514.
[9] 刘亮,王平,孙亮.基于区域灰度变化的自适应FAST角点检测算法[J].微电子学与计算机,2017,34(3):20-24.
[10] XING Yuanxiu,ZHANG Dengyi,ZHAO Jianhui,et al.Robust fast corner detector based on filled circle and outer ring mask[J].IET Image Processing,2016,10(4):314-324.
[11] PATOOMMAKESORN K,VIGNAT F,VILLENEUVE F.A new straight line matching technique by integration of vision -based image processing[J].Procedia CIRP,2016,41:777-782.
[12] BOK Y,HA H,KWEON I S.Automated checkerboard detection and indexing using circular boundaries[J].Pattern Recognition Letters,2016,71:66-72.
[13] DING Weili,WANG Wenfeng,LI Xiaoli.OTLines:a novel line-detection algorithm without the interference of smooth curves[J].Pattern Recognition,2016,53(2):238-258.
[14] ZHANG Xiaohong,LEI Ming,YANG Dan,et al.Multi-scale curvature product for robust image corner detection in curvature scale space[J].Pattern Recognition Letters,2007,28(5):545-554.
[15] LAKEMOND R,FOOKES C,SRIDHARAN S.Affine adaptation of local image features using the Hessian matrix[C]//2009 sixth IEEE international conference on advanced video and signal based surveillance.Genova,Italy:IEEE,2009:496-501.
[16] MORAVEC H P.Visual mapping by a robot rover[C]//Proceedings of the 6th international joint conference on artificial intelligence.Tokyo,Japan:Morgan Kaufmann Publishers Inc.,1979:598-600.
[17] HARRIS C,STEPHENS M.A combined corner and edge detector[C]//Proceedings of the 4th Alvey vision conference.[s.l.]:[s.n.],1988:147-151.
[18] NOBLE J A.Finding corners[J].Image & Vision Computing,1988,6(2):121-128.
[19] SMITH S M,BRADY M.SUSAN-a new approach to low level image processing[J].International Journal of Computer Vision,1997,23(1):45-78.
[20] ROSTEN E,DRUMMOND T.Machine learning for high-speed corner detection[C]//European conference on computer vision.[s.l.]:[s.n.],2006:430-443.
[21] ROSTEN E,PORTER R,DRUMMOND T.Faster and better:a machine learning approach to corner detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2009,32(1):105-119.