一个基于像素编组和逐级质量控制的线段检测算子

针对现有线段提取算法存在的不足, 提出了一个点元梯度特征引导下的线段检测算子, 在编组的前、中和后三大环节进行逐级质量控制.基于梯度最优并结合邻近性、方向性等规则控制“欠提取”错误, 采用假设检验方法控制“过提取”错误.多源数据实验表明, 提出的算法在编组中不易受到弱梯度像素或噪声的干扰, 与经典的线段提取算子相比, 在线段提取的效率和稳健性都有一定的优势, 有利于实现从场景到结构的重要视觉符号描述.

Abstract

To resolve the “false negative” and “false positive” problems in the current line segment detectors, we proposed a novel line segment detector which organizes pixels under the guidance of pixels’ gradient and improves reliability by step-by-step quality control. Before organizing pixels, initial optimized seed points were extracted according to image gradient. Under organizing, in order to solve the bad performance, e.g. noise of weak gradient, pixels were grouped and connected by considering proximity, orientation and gradient optimization to control false negative. After organizing pixels, chain division and hypothesis testing for quality control were employed to avoid false positive. When compared with state-of-the-art algorithms by visible light and color infrared (CIR) images, such as Probability Hough Transform (PHT), EDlines and LSD (Line Segment Detector), the proposed algorithm has advantages in efficiency and robustness, so it is of great significance for digital photogrammetry, computer vision and remotely sensed information extraction.

参考文献

[1] LI Chang, ZHANG ZuXun, ZHANG YongJun. Evaluating the theoretical accuracy of error distribution of vanishing points[J]Acta Geodaetica et Cartographica Sinc (李畅, 张祖勋, 张永军. 灭点误差分布的理论精度评定. 测绘学报), 2011, 40(3): 393-396.

[2] LI Chang. The necessary and sufficient condition of camera calibration and attitude determination based on vanishing points with their uncertainty analysis[J].Acta Geodaetica et Cartographica Sinc(李畅. 利用灭点进行相机检校与定姿的充要条件及其不确定性分析. 测绘学报), 2012, 41(6): 851-856.

[3] LI Chang, LIU YaWen, HU Min, et al. Study on street elevation 3D reconstructionoriented straightline matching for closerange images[J]. Geomatics andInformation Science of Wuhan University(李畅, 刘亚文, 胡敏, 等. 面向街景立面三维重建的近景影像直线匹配方法研究. 武汉大学学报: 信息科学版), 2010, 35(12): 1461-1465.

[4] GAO Feng, WEN GongJian, LU JinJian. An optimal algorithm for IR/visual image registration based on mainlinepai[J] Chin J Comput(高峰, 文贡坚, 吕金建. 基于干线对的红外与可见光最优图像配准算法. 计算机学报), 2007, 30(6): 1014-1021.

[5] LI C, SHI W. The generalizedlinebased iterative transformation model for imagery registration and rectification [J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(8): 1394-8139.

[6] ZHU Dan, WANG Bin, ZHANG LiMing. Airport detection based on near parrallelity of line segment and GBVS saliency[J]. Infrared Millim.Waves(朱丹, 王斌, 张立明. 基于直线邻近平行性和 GBVS 显著性的遥感图像机场目标检测.红外与毫米波学报),2015, 34(3): 375-384.

[7] Zhang Y, Heipke C, Butenuth M, et al. Automatic extraction of wind erosion obstacles by integration of GIS data, DSM and stereo images [J]. International Journal of Remote Sensing, 2006, 27(8):1677-90.

[8] LI Chang. Researching on key technique for 3D autoreconstruction of city street elevatio[J] Acta Geodaetica et Cartographica Sinc(李畅. 城市街道立面自动重建关键技术研究. 测绘学报）, 2011, 40(2): 268-268.

[9] Illiingworth J, Kittler J. A survey of the hough transform[J]. Computer Vision, Graphics, and Image Processing, 1988, 44(1): 87-116.

[10] Nevatia R, Babu K R. Linear feature extraction and description[J]. Computer Graphics and Image Processing, 1980, 13(3):257-269.

[11] Etemadi A. Robust segmentation of edge data[C]. International Conference on Image Processing and its Applications, 1992: 311-314.

[12] Topal C, Akinlar C, Genc Y. Edge drawing: A heuristic approach to robust realtime edge detection[C]. 20th International Conference on Pattern Recognition (ICPR), 2010: 2424-2427.

[13] Akinlar C, Topal C. EDLines: A realtime line segment detector with afalse detection control[J]. Pattern Recognition Letters, 2011, 32(13): 1633-1642.

[14] Galamhos C, Matas J, Kittler J. Progressive probabilistic hough transform for line detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999.

[15] CHEN YanXin, QI FeiHu. A randomized hough transform using gradient direction informationx[J].Infrared Millim.Waves(陈燕新, 戚飞虎. 利用梯度方向信息的随机 Hough 变换. 红外与毫米波学报), 1998, 17(5): 375-380.

[16] Fernandes L A, Oliveira M M. Realtime line detection through an improved hough transform voting scheme[J]. Pattern Recognition, 2008, 41(1): 299-314.

[17] Burns J B, Hanson A R, Riseman E M. Extracting straight lines[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(4): 425-455.

[18] Kahn P, Kitchen L, Riseman M. A fast line finder for visionguided robot navigation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(11): 1098-1102.

[19] Desolneux A, Moisan L, Morel JM. Meaningful alignments[J]. International Journal of Computer Vision, 2000, 40(1):7-23.

[20] Von Gioi R G, Jakubowicz J, Morel JM, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2008,32(4): 722-732.

[21] Xu P, Liu J, Shi C. Total least squares adjustment in partial errorsinvariables models: Algorithm and statistical analysis[J]. Journal of Geodesy, 2012, 86(8): 661-675.

[22] Desolneux A, Ladjal S, Moisan L, et al. Dequantizing image orientation[J]. IEEE Transactions on Image Processing, 2002, 11(10):1129-1140.

[23] Grompone Von Gioi R, Jakubowicz J, Morel J, et al. LSD: A line segment detector[J]. Image Processing On Line, 2012, 2: 35-55.

[24] LIU JingNan, ZENG WenXan, XU PeiLiang. Overview of total least square methods[J]. Geomatics andInformation Science of Wuhan Universit（刘经南, 曾文宪, 徐培亮. 整体最小二乘估计的研究进展. 武汉大学学报: 信息科学版）, 2013, 38(5): 505-512.

[25] ZHENG NanNing, Computer Vision and Pattern Recognition[M]. National Defence Industry Press,1998.（郑南宁. 计算机视觉与模式识别. 国防工业出版社）, 1998.

[26] Gruen A. Adaptive least squares correlation. A powerful image matching technique[J]. South African Journal of Photogrammetry, Remote Sensing and Cartography, 1985, 14(3):175-187.

李畅, 魏东. 一个基于像素编组和逐级质量控制的线段检测算子[J]. 红外与毫米波学报, 2016, 35(6): 681. LI Chang, WEI Dong. A line segment detector based on pixels grouping and step-by-step quality control[J]. Journal of Infrared and Millimeter Waves, 2016, 35(6): 681.

一个基于像素编组和逐级质量控制的线段检测算子

关于本站 Cookie 的使用提示

全站搜索

一个基于像素编组和逐级质量控制的线段检测算子

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索