结合SVM与图匹配的车载激光点云道路标线识别
|
摘要
本文提出一种基于SVM与图匹配相结合的车载激光点云道路标线识别方法。该方法基于标线点云分割对象,利用Hu不变矩、实心形状上下文(SSC)、最小外包矩形(MBR)面积和延展度构建形状特征向量,采用SVM进行道路标线粗分类。针对粗分类结果,构建能够精确描述空间语义信息(如局部区域内标线间的排列、方向、距离)的图结构,通过图匹配方法优化粗分类结果,完成直行箭头、人行横道预告标识线、单向转向箭头、双向转向箭头、虚线型标线、斑马线共六类道路标线的精确识别。本文实验采用4份不同场景车载激光点云数据,实验结果中6类标线分类的准确率分别达100%、100%、94.12%、100%、94.94%、99.25%,召回率分别达100%、100%、88.89%、100%、98.21%、99.00%,F_1-Measure值分别达100%、100%、91.43%、100%、96.59%、99.12%。结果表明,本文方法能实现多类标线对象的精确识别,并对形状相似标线(如直行箭头、虚线型标线与斑马线)的区分具有较强稳健性。
This paper presented a novel method for identifying road markings from mobile LiDAR point clouds by integrating Support Vector Machine(SVM) and graph matching. Firstly, the road surface point cloud was extracted using the scanline method, and then, was used to generate independent marking objects by a marking segmentation method combined with intensity correction. Next, hierarchical classification was conducted to identify smaller size markings as the basic objects for further processing. Considering the shape varieties of different types of marking objects, Hu invariant moments, Solid Shape Context(SSC), the area of Minimum Bounding Rectangle(MBR), and extensibility were extracted to construct the marking shape feature vector.Subsequently, with the shape feature vector of the above-mentioned samples, a training sample set was manually established to fit SVM model parameters. In the classification section, the SVM model was conducted for the preliminary classification, where there were situations including cross misclassification of markings with similar shapes and ambiguity between dotted marking and zebra crossing. Building upon the graph structure including certain types of interactive relationship(e.g., arrangement of road markings, direction relationship, and distance between markings in the local area) and the shape feature of markings, we used the inherent characteristics and spatial neighborhood information of objects to synthetically describe the geometric feature and spatial semantic information of road markings. Since the partial absence of markings' semantic structure, we developed an inexact graph matching method based on the graph structure of markings, which could optimize the preliminary classification result. The refined classification results of all six types of road markings included the straight arrow, the crosswalk warning line, the one-way steering arrow, the two-way steering arrow, the dotted marking,and the zebra crossing. To verify the validity of the proposed method, we conducted experiments using four test data sets acquired from different MLS systems. The verification results show that the six marking types have a respective precision of 100%, 100%, 94.12%, 100%, 94.94%, and 99.25%, and a respective recall rate of 100%,100%, 88.89%, 100%, 98.21%, and 99%, and a respective F_1-Measure value of 100%, 100%, 91.43%, 100%,96.59%, and 99.12%. The experimental results demonstrate that the proposed method could accurately identify multi-class road markings. In conclusion, our algorithm is superior and robust for extracting road markings in even complicated cases where road markings may exhibit significant shape differences or high similarity(e.g.,the straight arrow and linear marking, the dotted line and zebra crossing).
This paper presented a novel method for identifying road markings from mobile LiDAR point clouds by integrating Support Vector Machine(SVM) and graph matching. Firstly, the road surface point cloud was extracted using the scanline method, and then, was used to generate independent marking objects by a marking segmentation method combined with intensity correction. Next, hierarchical classification was conducted to identify smaller size markings as the basic objects for further processing. Considering the shape varieties of different types of marking objects, Hu invariant moments, Solid Shape Context(SSC), the area of Minimum Bounding Rectangle(MBR), and extensibility were extracted to construct the marking shape feature vector.Subsequently, with the shape feature vector of the above-mentioned samples, a training sample set was manually established to fit SVM model parameters. In the classification section, the SVM model was conducted for the preliminary classification, where there were situations including cross misclassification of markings with similar shapes and ambiguity between dotted marking and zebra crossing. Building upon the graph structure including certain types of interactive relationship(e.g., arrangement of road markings, direction relationship, and distance between markings in the local area) and the shape feature of markings, we used the inherent characteristics and spatial neighborhood information of objects to synthetically describe the geometric feature and spatial semantic information of road markings. Since the partial absence of markings' semantic structure, we developed an inexact graph matching method based on the graph structure of markings, which could optimize the preliminary classification result. The refined classification results of all six types of road markings included the straight arrow, the crosswalk warning line, the one-way steering arrow, the two-way steering arrow, the dotted marking,and the zebra crossing. To verify the validity of the proposed method, we conducted experiments using four test data sets acquired from different MLS systems. The verification results show that the six marking types have a respective precision of 100%, 100%, 94.12%, 100%, 94.94%, and 99.25%, and a respective recall rate of 100%,100%, 88.89%, 100%, 98.21%, and 99%, and a respective F_1-Measure value of 100%, 100%, 91.43%, 100%,96.59%, and 99.12%. The experimental results demonstrate that the proposed method could accurately identify multi-class road markings. In conclusion, our algorithm is superior and robust for extracting road markings in even complicated cases where road markings may exhibit significant shape differences or high similarity(e.g.,the straight arrow and linear marking, the dotted line and zebra crossing).
引文
[1]Wu T,Ranganathan A.A practical system for road marking detection and recognition[C].Intelligent Vehicles Symposium,2012:25-30.
[2]Mathibela B,Newman P,Posner I.Reading the road:Road marking classification and interpretation[J].IEEETransactions on Intelligent Transportation Systems,2015,16(4):2072-2081.
[3]Danescu R,Nedevschi S.Detection and classification of painted road objects for intersection assistance applications[C].International IEEE Conference on Intelligent Transportation Systems,2010:433-438.
[4]Guan H,Li J,Yu Y,et al.Using mobile laser scanning data for automated extraction of road markings[J].ISPRSJournal of Photogrammetry and Remote Sensing,2014,87:93-107.
[5]Guan H,Li J,Yu Y,et al.Using mobile LiDAR data for rapidly updating road markings[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(5):2457-2466.
[6]Guan H,Li J,Yu Y,et al.Automated road information extraction from mobile laser scanning data[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(1):194-205.
[7]Chen X,Kohlmeyer B,Stroila M,et al.Next generation map making:geo-referenced ground-level LIDAR point clouds for automatic retro-reflective road feature extraction[C].ACM Sigspatial International Symposium on Advances in Geographic Information Systems,Acm-Gis2009,November 4-6,2009,Seattle,Washington,Usa,Proceedings,2009:488-491.
[8]Riveiro B,González-Jorge H,Martínez-Sánchez J,et al.Automatic detection of zebra crossings from mobile LiDAR data[J].Optics&Laser Technology,2015,70:63-70.
[9]Cheng M,Zhang H,Wang C,et al.Extraction and classification of road markings using mobile laser scanning point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2017,10(3):1182-1196.
[10]Yang M,Wan Y,Liu X,et al.Laser data based automatic recognition and maintenance of road markings from MLSsystem[J].Optics&Laser Technology,2018,107:192-203.
[11]Jaakkola A,Hyypp?J,Hyypp?H,et al.Retrieval algorithms for road surface modelling using laser-based mobile mapping[J].Sensors,2008,8(9):5238.
[12]Mancini A,Frontoni E,Zingaretti P.Automatic road object extraction from Mobile Mapping Systems[C].Ieee/asme International Conference on Mechatronics and Embedded Systems and Applications,2012:281-286.
[13]Yang B,Fang L,Li Q,et al.Automated extraction of road markings from mobile LIDAR point clouds[J].Photogrammetric Engineering&Remote Sensing,2012,78(4):331-338.
[14]Yu Y,Li J,Guan H,et al.Learning hierarchical features for automated extraction of road markings from 3-D mobile LiDAR point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(2):709-726.
[15]Soilán M,Riveiro B,Martínez-Sánchez J,et al.Segmentation and classification of road markings using MLS data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,123:94-103.
[16]Hervieu A,Soheilian B,Brédif M.Road marking extraction using a model&data-Driven Rj-Mcmc[J].ISPRSJournal of Photogrammetry and Remote Sensing,2015,II-3/W4:47-54.
[17]Yang B,Fang L,Li J.Semi-automated extraction and delineation of 3D roads of street scene from mobile laser scanning point clouds[J].ISPRS Journal of Photogrammetry and Remote Sensing,2013,79:80-93.
[18]Hu M.Visual pattern recognition by moment invariants[J].Information Theory Ire Transactions on,1962,8(2):179-187.
[19]Premachandran V,Kakarala R.Perceptually motivated shape context which uses shape interiors[J].Pattern Recognition,2013,46(8):2092-2102.
[20]罗海峰,方莉娜,陈崇成.车载激光扫描数据路坎点云提取方法[J].地球信息科学学报,2017,19(7):861-871.[Luo H F,Fang L N,Chen C C.Curb point clouds extraction from vehicle-borne laser scanning data[J].Journal of Geo-information Science,2017,19(7):861-871.]
[21]彭晨,余柏蒗,吴宾,等.基于移动激光扫描点云特征图像和SVM的建筑物立面半自动提取方法[J].地球信息科学学报,2016,18(7):878-885.[Peng C,Yu B L,Wu B,et al.A method for semiautomated segmentation of building facade from mobile laser scanning point cloud based on feature images and SVM[J].Journal of Geo-information Science,2016,18(7):878-885.]
[22]熊伟成,杨必胜,董震.面向车载激光扫描数据的道路目标精细化鲁棒提取[J].地球信息科学学报,2016,18(3):376-385.[Xiong W C,Yang B C,Dong Z.Refining and robust extraction of roads from mobile laser scanning point clouds[J].Journal of Geo-information Science,2016,18(3):376-385.]
[23]Foggia P,Percannella G,Vento M.Graph matching and learning in pattern recognition in the last 10 years[J].International Journal of Pattern Recognition&Artificial Intelligence,2014,28(1):1450001.
[24]项英倬,谭菊仙,韩杰思,等.图匹配技术研究[J].计算机科学,2018,45(6):33-37,51.[Xiang Y Z,Tan J X,Han J S.Survey of graph matching algorithms[J].Computer Science,2018,45(6):33-37,51.].
[25]Hartley R,Zisserman A.Multiple view geometry in computer vision[M].UK:Gambridge University Press,2003.
[26]Szegedy C,Vanhoucke V,Ioffe S,et al.Rethinking the Inception Architecture for Computer Vision[C].Computer Vision and Pattern Recognition,2016:818-2826.
[27]Wold S.Pattern recognition by means of disjoint principal components models[J].Pattern Recognition,1976,8(3):127-139.
[28]陈占龙,周林.基于方向关系矩阵的空间方向相似性定量计算方法[J].测绘学报,2015,44(7):813-821.[Chen Z L,Zhou L,et al.A quantitative calculation method of spatial direction similarity based on direction relation matrix[J].Acta Geodaetica et Cartographica Sinica,2015,44(7):813-821.].
[29]Dekel T,Oron S,Rubinstein M,et al.Best-Buddies Similarity for robust template matching[C].Computer Vision and Pattern Recognition,2015.2021-2029.
[30]王刚,孙晓亮,尚洋,等.一种基于最佳相似点对的稳健模板匹配算法[J].光学学报,2017(3):274-280.[Wang G,Sun X L,S Y,et al.A robust template matching algorithm based on eest-buddies similarity[J].Acta Optica Sinica,2017(3):274-280.]
[31]Dangerfield J.Linear programming and its applications by J.K.Strayer[J].Mathematical Gazette,1990,74(470):402-403.
[2]Mathibela B,Newman P,Posner I.Reading the road:Road marking classification and interpretation[J].IEEETransactions on Intelligent Transportation Systems,2015,16(4):2072-2081.
[3]Danescu R,Nedevschi S.Detection and classification of painted road objects for intersection assistance applications[C].International IEEE Conference on Intelligent Transportation Systems,2010:433-438.
[4]Guan H,Li J,Yu Y,et al.Using mobile laser scanning data for automated extraction of road markings[J].ISPRSJournal of Photogrammetry and Remote Sensing,2014,87:93-107.
[5]Guan H,Li J,Yu Y,et al.Using mobile LiDAR data for rapidly updating road markings[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(5):2457-2466.
[6]Guan H,Li J,Yu Y,et al.Automated road information extraction from mobile laser scanning data[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(1):194-205.
[7]Chen X,Kohlmeyer B,Stroila M,et al.Next generation map making:geo-referenced ground-level LIDAR point clouds for automatic retro-reflective road feature extraction[C].ACM Sigspatial International Symposium on Advances in Geographic Information Systems,Acm-Gis2009,November 4-6,2009,Seattle,Washington,Usa,Proceedings,2009:488-491.
[8]Riveiro B,González-Jorge H,Martínez-Sánchez J,et al.Automatic detection of zebra crossings from mobile LiDAR data[J].Optics&Laser Technology,2015,70:63-70.
[9]Cheng M,Zhang H,Wang C,et al.Extraction and classification of road markings using mobile laser scanning point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2017,10(3):1182-1196.
[10]Yang M,Wan Y,Liu X,et al.Laser data based automatic recognition and maintenance of road markings from MLSsystem[J].Optics&Laser Technology,2018,107:192-203.
[11]Jaakkola A,Hyypp?J,Hyypp?H,et al.Retrieval algorithms for road surface modelling using laser-based mobile mapping[J].Sensors,2008,8(9):5238.
[12]Mancini A,Frontoni E,Zingaretti P.Automatic road object extraction from Mobile Mapping Systems[C].Ieee/asme International Conference on Mechatronics and Embedded Systems and Applications,2012:281-286.
[13]Yang B,Fang L,Li Q,et al.Automated extraction of road markings from mobile LIDAR point clouds[J].Photogrammetric Engineering&Remote Sensing,2012,78(4):331-338.
[14]Yu Y,Li J,Guan H,et al.Learning hierarchical features for automated extraction of road markings from 3-D mobile LiDAR point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(2):709-726.
[15]Soilán M,Riveiro B,Martínez-Sánchez J,et al.Segmentation and classification of road markings using MLS data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,123:94-103.
[16]Hervieu A,Soheilian B,Brédif M.Road marking extraction using a model&data-Driven Rj-Mcmc[J].ISPRSJournal of Photogrammetry and Remote Sensing,2015,II-3/W4:47-54.
[17]Yang B,Fang L,Li J.Semi-automated extraction and delineation of 3D roads of street scene from mobile laser scanning point clouds[J].ISPRS Journal of Photogrammetry and Remote Sensing,2013,79:80-93.
[18]Hu M.Visual pattern recognition by moment invariants[J].Information Theory Ire Transactions on,1962,8(2):179-187.
[19]Premachandran V,Kakarala R.Perceptually motivated shape context which uses shape interiors[J].Pattern Recognition,2013,46(8):2092-2102.
[20]罗海峰,方莉娜,陈崇成.车载激光扫描数据路坎点云提取方法[J].地球信息科学学报,2017,19(7):861-871.[Luo H F,Fang L N,Chen C C.Curb point clouds extraction from vehicle-borne laser scanning data[J].Journal of Geo-information Science,2017,19(7):861-871.]
[21]彭晨,余柏蒗,吴宾,等.基于移动激光扫描点云特征图像和SVM的建筑物立面半自动提取方法[J].地球信息科学学报,2016,18(7):878-885.[Peng C,Yu B L,Wu B,et al.A method for semiautomated segmentation of building facade from mobile laser scanning point cloud based on feature images and SVM[J].Journal of Geo-information Science,2016,18(7):878-885.]
[22]熊伟成,杨必胜,董震.面向车载激光扫描数据的道路目标精细化鲁棒提取[J].地球信息科学学报,2016,18(3):376-385.[Xiong W C,Yang B C,Dong Z.Refining and robust extraction of roads from mobile laser scanning point clouds[J].Journal of Geo-information Science,2016,18(3):376-385.]
[23]Foggia P,Percannella G,Vento M.Graph matching and learning in pattern recognition in the last 10 years[J].International Journal of Pattern Recognition&Artificial Intelligence,2014,28(1):1450001.
[24]项英倬,谭菊仙,韩杰思,等.图匹配技术研究[J].计算机科学,2018,45(6):33-37,51.[Xiang Y Z,Tan J X,Han J S.Survey of graph matching algorithms[J].Computer Science,2018,45(6):33-37,51.].
[25]Hartley R,Zisserman A.Multiple view geometry in computer vision[M].UK:Gambridge University Press,2003.
[26]Szegedy C,Vanhoucke V,Ioffe S,et al.Rethinking the Inception Architecture for Computer Vision[C].Computer Vision and Pattern Recognition,2016:818-2826.
[27]Wold S.Pattern recognition by means of disjoint principal components models[J].Pattern Recognition,1976,8(3):127-139.
[28]陈占龙,周林.基于方向关系矩阵的空间方向相似性定量计算方法[J].测绘学报,2015,44(7):813-821.[Chen Z L,Zhou L,et al.A quantitative calculation method of spatial direction similarity based on direction relation matrix[J].Acta Geodaetica et Cartographica Sinica,2015,44(7):813-821.].
[29]Dekel T,Oron S,Rubinstein M,et al.Best-Buddies Similarity for robust template matching[C].Computer Vision and Pattern Recognition,2015.2021-2029.
[30]王刚,孙晓亮,尚洋,等.一种基于最佳相似点对的稳健模板匹配算法[J].光学学报,2017(3):274-280.[Wang G,Sun X L,S Y,et al.A robust template matching algorithm based on eest-buddies similarity[J].Acta Optica Sinica,2017(3):274-280.]
[31]Dangerfield J.Linear programming and its applications by J.K.Strayer[J].Mathematical Gazette,1990,74(470):402-403.