進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0308202015064700
論文名稱(中文) 基於三維點雲之高精地圖道路元素建模技術與中心線自動產製方法
論文名稱(英文) Automated Road-Elements Modelling and Centerline Generation for High Definition Maps Utilizing 3D Point Cloud
校院名稱 成功大學
系所名稱(中) 測量及空間資訊學系
系所名稱(英) Department of Geomatics
學年度 108
學期 2
出版年 109
研究生(中文) 曾芷晴
研究生(英文) Jhih-Cing Zeng
學號 P66074010
學位類別 碩士
語文別 英文
論文頁數 105頁
口試委員 指導教授-江凱偉
口試委員-曾義星
口試委員-張智安
中文關鍵字 高精地圖  點雲  道路元素萃取  建模  中心線產製 
英文關鍵字 High Definition Maps  Point cloud  Road elements extraction  Modelling  Centerline generation 
學科別分類
中文摘要 近年來,高精地圖(High Definition Maps, HD Maps)蓬勃發展成為新一代自動駕駛技術之輔助資訊,以實現道路安全之願景,相較於傳統電子導航地圖,高精地圖的精度需求更高且富含更多道路環境資訊與道路元素,包含道路邊緣、車道線、車道中心線、交通號誌與交通標誌等,由於車載移動式雷射掃瞄系統(Mobile Laser Scanner, MLS)具備快速蒐集高精度環境資訊的能力,此系統成為現今廣為使用的資料採集模式,然而,後續地圖數化、建置等測繪任務仍仰賴人為操作,此過程需耗費大量人力與時間成本,因此本研究致力於開發自動化演算法,從獲取的點雲資料中產製高精地圖中定義之特定道路元素,包含道路邊緣、車道線與中心線。
本研究提出的演算法可分成道路元素萃取與建模兩部分,首先,為了提升演算法的效率與成果,透過萃取道路邊緣以攫取路面範圍,以濾除非路面特徵物的影響,另一方面,由於路面標記具有極高的強度值特性,可藉此設定強度值門檻值進而取得,接著,萃取的路面標記經由相關交通法規所定義之幾何條件進行分類,即可區分線型之車道線與其餘路面標記,故利用三次樣條插值(Cubic spline interpolation)演算法進行道路邊緣與車道線之擬合,便能利用建模後的車道線進一步產製車道中心線,最後所有產製之道路特徵將藉由測繪業者繪製之高精地圖進行驗證,由於此高精地圖已完成精度驗證與品質檢測,故可以作為本研究成果之參考資料以確保成果的品質與絕對精度。
此外,本研究亦將提出之演算法施行於透過低成本感測器採集之點雲資料上,以測試演算法的可行性與適用性,即便低成本感測器的表現不如高規格的移動式雷射掃瞄系統,然而,若能證明透過低成本感測器獲取的點雲資料亦能達到相同的精度品質,基於低成本感測器之數據採集可成為測繪的替代方案。另一方面,因為同一條道路的幾何屬性並非一成不變,一次處理所有實驗區之測試路段的方式較不實際,此外,也必須考量運算資料量與處理效能,因此,道路會預先被切割成特定長度的路段,進而連接對應的道路元素之擬合成果,故本研究提出的驗算法也會在分割的路段上進行測試。
研究成果顯示,儘管路面標記萃取的召回率(recall)在整體表現上較不穩定,導致召回率的成果沒有顯著的提升,但是大部分的路面標記能被正確分類且精度(precision)能高達90%,除此之外,從實驗結果得知道路元素能成功地被建模,車道線與車道中心線之三維均方根誤差於所有實驗場景下皆小於20公分,而道路邊緣於高規格感測器採集之點雲資料中的三維均方根誤差也低於20公分,整體而言,本研究不僅能萃取特定路面標記,同時將路面標記進行建模以產製能供自駕車應用之高精度且可靠的高精地圖道路元素。
英文摘要 Recently, High Definition Maps (HD Maps) become additional aiding information for autonomous vehicles to improve road safety and are under rapid development. Compared with the conventional digital navigation maps, the accuracy requirement is quite higher as well as HD Maps record more detailed road information and rich road elements including road edges, lane lines, centerlines, traffic signs, and traffic lights. Owing to the efficiency and highly accurate geospatial measurements, the commercial Mobile Laser Scanner (MLS) is competent to data acquisition of HD Maps generation. However, the subsequent process of maps generation relies on manpower. Therefore, this thesis is contributed to proposing an automated approach to generate road edge, lane line, and centerline, defined in HD Maps, from point clouds.
The proposed method can be divided into road elements extraction and modelling. Firstly, the road edges are obtained to determine the range of the road surface. On the other hand, the road markings are extracted based on intensity filtering. Subsequently, the road markings are classified by the pre-defined geometric thresholds. Next, the extracted road edges and lane lines can be modelled based on the cubic spline interpolation algorithm. Therefore, centerlines are generated pass through translating from the modelling lane lines. Finally, the results are assessed by the verified HD Maps provided by the professional surveying company to guarantee the absolute precision and quality of generated results.
Moreover, this thesis also implements the proposed approach on the point cloud collected by the low-cost sensors to validate the flexibility and usability. Although the quality and the performance of low-cost point cloud cannot be as well as MLS point cloud, the data acquisition method on the basis of using low-cost payload can be an alternative way if the accuracy can be proved to achieve the accuracy requirement. On the other hand, it is not practical to process entire experimental areas at the same time to generate HD Maps since the attribute of the same road might change and the data volume and the computing operation need to be considered. In fact, the road will be segmented into a certain length in advance and then merging the modelling results with two consecutive road sections. Thus, this thesis also evaluates the proposed method on the road scenario of road segments.
From the results exhibited in this thesis, the overall recall of road markings extraction is relatively unstable that results in insignificant performance. However, most road markings can be classified into correct categories and most precisions are more than 90%. Additionally, the experimental results illustrate that the modelling road elements and centerlines can be successfully generated. The RMSEs of modelling lane lines and lane lines in both commercial MLS point cloud and low-cost point cloud are lower than 0.2 m in 3D space, while the RMSEs of modelling road edges in MLS point cloud are also lower than 0.2 m in 3D space. In conclusion, this thesis not only identifies the road markings but also models the road markings to generate reliable and precise road elements in HD Maps for autonomous driving applications.
論文目次 中文摘要 III
Abstract V
Acknowledgements VII
Contents IX
List of Tables XII
List of Figures XIII
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Objectives of the Thesis 4
1.3 Structure of the Thesis 5
Chapter 2 Background and Related Studies 6
2.1 Research Background 6
2.1.1 Introduction of Autonomous Vehicle 6
2.1.2 Introduction of HD Maps 8
2.1.3 A Comparison of HD Maps and ADAS Maps 12
2.1.4 HD Maps Format Standard 14
2.2 Review of Road Surface Extraction Methodology 20
2.2.1 2D Feature Processing 20
2.2.2 3D Point Cloud Processing 22
2.3 Review of Road Marking Extraction Methodology 24
2.4 Review of Centerline Generation and HD Maps Modelling 26
Chapter 3 Methodology for Road-Elements Modelling and Centerline Generation 31
3.1 Study Area and Dataset 31
3.1.1 Study Area 31
3.1.2 Data Collection 34
3.2 Proposed Workflow for Road-Elements Modelling and Centerline Generation 39
3.3 Road Surface Extraction 42
3.3.1 Ground Point Detection 42
3.3.2 Road Edge Extraction and Refinement 43
3.4 Road Marking Extraction and Refinement 48
3.4.1 Road Marking Extraction 48
3.4.2 Euclidean Clustering Algorithm 50
3.4.3 Oriented Bounding Box Algorithm 53
3.4.4 Lane Line Refinement 56
3.5 Road Elements Modelling and Centerline Generation 58
3.6 Validation Methods 64
Chapter 4 Results and Analysis 66
4.1 Datasets 66
4.1.1 MLS Point Cloud 66
4.1.2 Low-cost Point Cloud 68
4.1.3 Reference Data 71
4.2 Results of Feature Extraction 72
4.2.1 Road Marking Extraction 72
4.2.2 Road Elements Refinement 77
4.2.3 Computational Time 83
4.3 Accuracy Assessment of Road Element Modelling 84
4.3.1 Accuracy Assessment of Commercial MLS Point Cloud 84
4.3.2 Accuracy Assessment of Low-cost Point Cloud 90
4.3.3 Accuracy Assessment of Segmented Road Section 93
Chapter 5 Conclusions and Future Works 97
5.1 Conclusions 97
5.2 Future Works 98
References 100

參考文獻 Autoware Community. Autoware Documentation Release 1.9.0, (2018). Retrieved from
https://buildmedia.readthedocs.org/media/pdf/autoware/feature-documentation_rtd/autoware.pdf
Althoff, M., Urban, S., & Koschi, M. Automatic conversion of road networks from opendrive to lanelets. In Proceedings of 2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), pp. 157-162, (2018).
Behringer, R., Gregory, B., Sundareswaran, V., Addison, R., Elsley, R., Guthmiller, W., … & Reinhart, C. Development of an autonomous vehicle for the DARPA Grand Challenge. In Proceedings of IFAC Symposium on Intelligent Autonomous Vehicles, Lisbon, (2004).
Bauer, S., Alkhorshid, Y., & Wanielik, G. Using high-definition maps for precise urban vehicle localization. In Proceedings of 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), pp. 492-497, (2016).
Bai, M., Mattyus, G., Homayounfar, N., Wang, S., Lakshmikanth, S. K., & Urtasun, R. Deep multi-sensor lane detection. In Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3102-3109, (2018).
Baidu. Apollo, (2020). Retrieved from http://apollo.auto/.
Chen, A., Ramanandan, A., & Farrell, J. A. High-precision lane-level road map building for vehicle navigation. In Proceedings of IEEE/ION position, location and navigation symposium, pp. 1035-1042, (2010).
Cheng, M., Zhang, H., Wang, C., & Li, J. Extraction and classification of road markings using mobile laser scanning point clouds. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(3), 1182-1196, (2016).
Cudrano, P., Mentasti, S., Matteucci, M., Bersani, M., Arrigoni, S., & Cheli, F. Advances in centerline estimation for autonomous lateral control. arXiv preprint arXiv:2002.12685, (2020).
Du, J. CAMP enhanced digital mapping project—Final report. U.S. Department of Transportation, Washington, (2004). Retrieved from
https://rosap.ntl.bts.gov/view/dot/3704
Dimitrov, D., Knauer, C., Kriegel, K., & Rote, G. On the bounding boxes obtained by principal component analysis. In Proceedings of 22nd European Workshop on Computational Geometry, pp. 193-196, (2006).
Dai, J. M., Liu, T. A. J., & Lin, H. Y. Road surface detection and recognition for route recommendation. In Proceedings of 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 121-126, (2017).
De Silva, V., Roche, J., & Kondoz, A. Fusion of LiDAR and camera sensor data for environment sensing in driverless vehicles. arXiv preprint arXiv:1710.06230, (2018).
Demuynck V. What are the differences between the TomTom ADAS and HD Maps. (2019). Retrieved from https://www.tomtom.com/blog/autonomous-driving/adas-map-vs-hd-map/
Ellum, C. & El-Sheimy, N. Land-based mobile mapping systems. Photogrammetric engineering and remote sensing, 68(1), (2002).
Gottschalk, S., Manocha, D., & Lin, M. C. Collision queries using oriented bounding boxes. Ph.D. Thesis, University of North Carolina at Chapel Hill, (2000).
Gupta, A., Alliez, P., & Pion, S. Principal component analysis in CGAL, (2008). Retrieved from https://hal.inria.fr/inria-00327027/document
Guan, H., Li, J., Yu, Y., Wang, C., Chapman, M., & Yang, B. Using mobile laser scanning data for automated extraction of road markings. ISPRS Journal of Photogrammetry and Remote Sensing, 87, 93-107, (2014).
Gwon, G. P., Hur, W. S., Kim, S. W., & Seo, S. W. Generation of a precise and efficient lane-level road map for intelligent vehicle systems. IEEE Transactions on Vehicular Technology, 66(6), 4517-4533, (2016).
Gran, C. W. HD-Maps in Autonomous Driving. Master's thesis, Norwegian University of Science and Technology, Trondheim, Norway, (2019).
Hervieu, A., & Soheilian, B. Semi-automatic road/pavement modeling using mobile laser scanning. In Proceedings of ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2, 31-36, (2013).
HERE. HERE HD Live Map, (2017). Retrieved from
https://www.here.com/sites/g/files/odxslz166/files/2018-11/HERE_HD_Live_Map_one_pager_0.pdf
Han, X. F., Jin, J. S., Wang, M. J., Jiang, W., Gao, L., & Xiao, L. A review of algorithms for filtering the 3D point cloud. Signal Processing: Image Communication, 57, 103-112, (2017).
Harsha V. HD maps: New age maps powering autonomous vehicles. Geospaial world, (2017). Retrieved from https://www.geospatialworld.net/article/hd-maps-autonomous-vehicles/
Hsu, P.C. An Automotive-grade INS/HD Maps/Odometer/GNSS Integration Scheme for Lane-level Navigation Application in Urban Area. Master’s thesis, National Cheng Kung University, Tainan, Taiwan, (2019).
Joshi, A., & James, M. R. Generation of accurate lane-level maps from coarse prior maps and lidar. IEEE Intelligent Transportation Systems Magazine, 7(1), 19-29, (2015).
Junker, M. Navigation Data Standard Open Lane Model Documentation. Open Lane Model version 1.0, (2016). Retrieved from
https://www.openlanemodel.org/news_1.php
Jiang, H. Semi-automated Generation of Road Transition Lines Using Mobile Laser Scanning Data. Master's thesis, University of Waterloo, Ontario, Canada, (2017).
Jadhav, A. Autonomous Vehicle Market Outlook – 2026, (2018). Retrieved from
https://www.alliedmarketresearch.com/autonomous-vehicle-market
Kukko, A. Mobile Laser Scanning–System development, performance and applications. Finnish Geodetic Institute, Kirkkonummi, Finland, (2013).
Kato, S., Tokunaga, S., Maruyama, Y., Maeda, S., Hirabayashi, M., Kitsukawa, Y., ... & Azumi, T. Autoware on board: Enabling autonomous vehicles with embedded systems. In Proceedings of 2018 ACM/IEEE 9th International Conference on Cyber-Physical Systems (ICCPS), pp. 287-296, (2018).
Kocić, J., Jovičić, N., & Drndarević, V. Sensors and sensor fusion in autonomous vehicle. In Proceedings of 2018 26th Telecommunications Forum (TELFOR), pp. 420-425, (2018).
Litman, T. Autonomous vehicle implementation predictions, Victoria, Canada: Victoria Transport Policy Institute, (2018). Retrieved from https://www.vtpi.org/avip.pdf
Liu, R., Wang, J., & Zhang, B. High definition map for automated driving: Overview and analysis. The Journal of Navigation, 73(2), 324-341, (2020).
Lin, S. C., Zhang, Y., Hsu, C. H., Skach, M., Haque, M. E., Tang, L., & Mars, J. The architectural implications of autonomous driving: Constraints and acceleration. In Proceedings of 23th International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 751-766, (2018).
McKinley, S., & Levine, M. Cubic spline interpolation. College of the Redwoods, 45(1), 1049-1060, (1998).
McCrae, J., & Singh, K. Sketching piecewise clothoid curves. Computers & Graphics, 33(4), 452-461, (2009).
Mnih, V., & Hinton, G. E. Learning to detect roads in high-resolution aerial images. In Proceedings of 11th European Conference on Computer Vision, pp. 210-223, (2010).
Marzbani, H., Jazar, R. N., & Fard, M. Better road design using clothoids. In Proceedings of Sustainable automotive technologies 2014: Proceedings of the 6th ICSAT, Springer, Cham, pp. 25-40, (2015).
Ma, L. Generation of Horizontally Curved Driving Lines for Autonomous Vehicles Using Mobile Laser Scanning Data. Master's thesis, University of Waterloo, Ontario, Canada, (2017).
Ma, L., Wu, T., Li, Y., Li, J., Chen, Y., & Chapman, M. Automated Extraction of Driving Lines from Mobile Laser Scanning Point Clouds. In Proceedings of 29th International Cartographic Conference (ICC 2019), 1, (2019).
National Highway Traffic Safety Administration. Retrieved from
https://www.nhtsa.gov/technology-innovation/automated-vehicles-safety
OpenDRIVE. Format Specification. Rev. 1.5, (2019). Retrieved from
http://www.opendrive.org/
Park, H., & Lee, J. H. B-spline curve fitting based on adaptive curve refinement using dominant points. Computer-Aided Design, 39(6), 439-451, (2007).
PCL. How to use KdTree to search, (2020). Retrieved from
https://pcl-tutorials.readthedocs.io/en/latest/kdtree_search.html#kdtree-search
PCL. Downsampling a PointCloud using a VoxelGrid filter, (2020). Retrieved from
https://pcl-tutorials.readthedocs.io/en/latest/voxel_grid.html#voxelgrid
Rezaee, M., & Zhang, Y. Road detection using deep neural network in high spatial resolution images. In Proceedings of 2017 Joint Urban Remote Sensing Event (JURSE), pp. 1-4, (2017).
Sokolova, M., Japkowicz, N., & Szpakowicz, S. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In Proceedings of Australasian joint conference on artificial intelligence, Springer, Berlin, Heidelberg, pp. 1015-1021, (2006).
Sokolova, M., & Lapalme, G. A systematic analysis of performance measures for classification tasks. Information processing & management, 45(4), 427-437, (2009).
Smadja, L., Ninot, J., & Gavrilovic, T. Road extraction and environment interpretation from LiDAR sensors. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 38(3A), 281-286, (2010).
Shi, H. Automatic generation of OpenDrive roads from road measurements. Master's thesis, Chalmers University of Technology, Gothenburg, Sweden, (2011).
Stayton, E. L. Driverless dreams: technological narratives and the shape of the automated car. Ph.D. Thesis, Massachusetts Institute of Technology, Massachusetts, USA, (2015).
Shimada, H., Yamaguchi, A., Takada, H., and Sato, K. Implementation and evaluation of local dynamic map in safety driving systems. Journal of Transportation Technologies, 5(02), 102, (2015).
Singh, S. Critical reasons for crashes investigated in the national motor vehicle crash causation survey. National Highway Traffic Safety Administration, Washington, DC, (2015).
Seif, H. G., & Hu, X. Autonomous driving in the iCity—HD maps as a key challenge of the automotive industry. Engineering, 2(2), 159-162, (2016).
Song, Y., Ju, Y., Du, K., Liu, W., & Song, J. Online road detection under a shadowy traffic image using a learning-based illumination-independent image. Symmetry, 10(12), 707, (2018).
TomTom. HD MAP WITH ROADDNA, (2018). Retrieved from
http://download.tomtom.com/open/banners/HD_Map_with_RoadDNA_Product_Info_Sheet.pdf
TAICS TR-0016. Verification and validation guidelines for HD Maps v0.4, (2020). Retrieved from
https://gps.moi.gov.tw/sscenter/introduce/BulletinPage_Info.aspx?ID=100
Tsai, G. J. Seamless Navigation and Mapping Using INS/GNSS/LiDAR SLAM Multi-Fusion Schemes. Ph.D. Thesis, National Cheng Kung University, Tainan, Taiwan, (2020).
Wang, B., & Frémont, V. Fast road detection from color images. In Proceedings of 2013 IEEE Intelligent Vehicles Symposium (IV), pp. 1209-1214, (2013).
Wang, H., Wang, C., Chen, Y., Yang, W., & Li, J. Extracting road surface from mobile laser scanning point clouds in large scale urban environment. In Proceedings of 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 2912-2917, (2014).
Wang, Q., Gao, J., & Yuan, Y. Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Transactions on Intelligent Transportation Systems, 19(1), 230-241, (2017).
World Health Organization. Global status report on road safety 2018. World Health Organization, (2018). Retrieved from
https://www.who.int/violence_injury_prevention/road_safety_status/2018/en/
Wen, C., Sun, X., Li, J., Wang, C., Guo, Y., & Habib, A. A deep learning framework for road marking extraction, classification and completion from mobile laser scanning point clouds. ISPRS journal of photogrammetry and remote sensing, 147, 178-192, (2019).
Xu, H., Wang, X., Huang, H., Wu, K., & Fang, Q. A fast and stable lane detection method based on B-spline curve. In Proceedings of 2009 IEEE 10th International Conference on Computer-Aided Industrial Design & Conceptual Design, pp. 1036-1040, (2009).
Yang, B., Fang, L., Li, Q., & Li, J. Automated extraction of road markings from mobile LiDAR point clouds. Photogrammetric Engineering & Remote Sensing, 78(4), 331-338, (2012).
Yu, Y., Li, J., Guan, H., Jia, F., & Wang, C. Learning hierarchical features for automated extraction of road markings from 3-D mobile LiDAR point clouds. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(2), 709-726, (2014).
Yadav, M., Lohani, B., & Singh, A. K. Road surface detection from mobile lidar data. In Proceedings of ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 4, 95-101, (2018).
Zhao, H. Recognizing features in mobile laser scanning point clouds towards 3D high-definition road maps for autonomous vehicles. Master's thesis, University of Waterloo, Ontario, Canada, (2017).
Zheng, L., Li, B., Yang, B., Song, H., & Lu, Z. Lane-Level Road Network Generation Techniques for Lane-Level Maps of Autonomous Vehicles: A Survey. Sustainability, 11(16), 4511, (2019).

論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2025-07-06起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2025-07-06起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw