根據2019年台灣公路總局的《台灣智慧停車轉型概覽報告》，過去20年中汽車和摩托車的持有比率顯著增長。車輛和城市發展的持續增加使得智慧路邊停車管理在城市中變得十分重要。多項研究表明，在尋找停車位的行為占交通量的30%，在人口密集道路狹窄的亞洲城市，發展智慧停車管理系統是十分必要且具有發展性的，以確保有限的道路空間和停車設施能夠得到高效利用。

目前台灣的戶外停車管理方法包括人工收費、地磁智能停車位和智能停車樁。地磁智能停車位仍依賴人工計費，嵌入停車位的地磁傳感器檢測車輛的進出時間，並將數據直接傳輸到收費人員的手持設備上。有助於收費人員快速定位逾期停車位。在開立罰單時，收費人員會以地磁檢測到的時間作為計費的起點。相比之下，智能停車樁具有更多功能，如車輛占用檢測、車牌識別、拍攝照片和停車資訊顯示。它們能自動記錄車輛停車和離開的時間，識別停放車輛的車牌，並以拍攝照片作為證據，每次驗證時記錄圖像。然而，不論是何種路側設施，龐大的基礎設施意味著巨大的維護費用，這在未來的車聯網（IoV）時代是不可接受的。

因此，本篇論文將提出一種相對低成本的固態光達/單目相機/慣性導航系統（INS）/全球導航衛星系統（GNSS）/高精地圖框架。此篇研究基於高精地圖更新的概念，將巡檢到的路邊停放車輛作為動態高精地圖更新的對象。運用深度學習模型在提取語意資訊上比過去更加高效，通過這種方式，所提出的方法能夠在較低的運算資源下實現創新的停車管理模式。本文的貢獻如下：

1. 本論文基於高精地圖更新概念，通過停車管理評估高精地圖動態物件更新的可能性。2. 本論文提出了一種無需基礎設施的戶外路邊停車管理概念，不同於現有的停車管理系統通常依賴路邊設備來確保定位和檢測的準確性。3. 本論文提出的硬體使用相對低成本的固態光達和單目相機作為主要外部環境感測器，以降低路邊基礎設施停車管理系統的成本。4. 本論文討論了相機與光達之間外參數的傳統率定和新穎率定差異，並進行了多種實驗場景的評估。5. 由於停車管理系統高度依賴精確的時間戳，本論文設計了不同感測器時間同步的硬體架構。6. 本論文設計了配對影像-點雲的演算法，能更新高精地圖動態圖層的語意和座標資訊。7. 本論文使用固態光達點雲和高精地圖點雲，NDT匹配可以提供定位演算法額外的坐標及航向更新，將導航性能提高到0.4公尺，且牌面定位精度誤差為 0.62 公尺，滿足路邊停車管理的允許定位誤差。

Efficient parking management is crucial in crowded Asian cities to optimize limited road space and parking facilities. The increasing vehicle ownership rates in Taiwan have intensified the demand for street parking, leading to excessive driving in search of available spots, which contributes up to 30% of traffic congestion.

Current outdoor parking management methods in Taiwan include manual charging, ground magnetic intelligent parking spaces, and smart parking meters. Ground magnetic spaces rely on manual billing, while smart parking meters offer advanced functions such as vehicle occupancy detection and license plate recognition but are significantly more expensive and costly to maintain.

This thesis proposes a low-cost, infrastructure-free solution based on the HD map update concept. Using a fusion of Solid State LiDAR, Monocular Camera, INS, GNSS, and HD Maps enhanced by 2D-based deep learning for efficient region extraction. The proposed method aims to achieve high accuracy with minimal computational resources and infrastructure costs. Contributions of this paper including: Firstly, evaluating the HD map dynamic object update through parking management examples. Secondly, proposing an infrastructure-free outdoor roadside parking management system. Thirdly, reducing costs by using low-cost Solid State LiDAR and monocular cameras. Fourth, discussing traditional and novel extrinsic calibration methods through various experiments. Fifth, designing hardware architecture for precise sensor time synchronization. Sixth, developing software algorithms for accurate image-point cloud projection to update HD map parking layers. Seventh, improving navigation performance to a 0.4 meter accuracy using NDT matching with Solid State LiDAR and HD point cloud maps and the proposed applications license plate localization mean error is about 0.62 meter.

[1] 交通部公路總局. 台灣智慧化停車推動與前瞻. https://shorturl.at/RwVLa, 2019.
[2] Cristian Roman, Ruizhi Liao, Peter Ball, Shumao Ou, and Martin de Heaver. Detecting on-street parking spaces in smart cities: Performance evaluation of fixed and mobile sensing systems. IEEE Transactions on Intelligent Transportation Systems, 19(7):2234–2245, 2018.
[3] Can Biyik, Zaheer Allam, Gabriele Pieri, Davide Moroni, Muftah O＇Fraifer, Eoin O＇Connell,Stephan Olariu, and Muhammad Khalid. Smart parking systems: Reviewing the literature,architecture and ways forward. Smart Cities, 4(2):623–642, 2021.
[4] Miguel Jaller, José Holguín-Veras, and Stacey Darville Hodge. Parking in the city: Challenges for freight traffic. Transportation Research Record, 2379(1):46–56, 2013.
[5] Mohammed Islam, Sami Azam, Bharanidharan Shanmugam, Asif Karim, Jamal El-Den, FrisoDeBoer, Mirjam Jonkman, and Amit Yadav. Smart parking management system to reduce congestion in urban area. pages 1–6, 11 2020.
[6] A. Mwebaze. The design of an intelligent parking system using wireless sensor networks and multi-protocol label switching. Master’s thesis, University of Cape Town ,Faculty of Science ,Department of Computer Science., 2009.
[7] Aezaz Ali and Zubair Bin Hamid. Smart parking system for air university. Master’s thesis, Department of Computer Science, Air University, Islamabad, May 2020.
[8] Caroline Rodier, Susan Shaheen, and Charlene Kemmerer. Smart parking management field test: A bay area rapid transit (bart) district parking demonstration; final report. Institute of Transportation Studies, UC Davis, Institute of Transportation Studies, Working Paper Series, 01 2008.
[9] Vignesh N, Manoj M, Suhaas Reddy, and Koushik Reddy. Smart parking system using iot with blynk and rfid. International Research Journal on Advanced Engineering Hub (IRJAEH), 2:814–822, 04 2024.
[10] Thanh Nam Pham, Ming-Fong Tsai, Duc Binh Nguyen, Chyi-Ren Dow, and Der-Jiunn Deng. A cloud-based smart-parking system based on internet-of-things technologies. IEEE access, 3:1581–1591, 2015.
[11] Luca Mainetti, Ivan Marasovic, Luigi Patrono, Petar Solic, Maria Laura Stefanizzi, and Roberto Vergallo. A novel iot-aware smart parking system based on the integration of rfid and wsn technologies. International Journal of RF Technologies, 7(4):175–199, 2016.
[12] Yuan-Tsung Chang and Timothy K. Shih. Rfid-based intelligent parking management system with indoor positioning and dynamic tracking. In 2017 10th International Conference on Ubi-media Computing and Workshops (Ubi-Media), pages 1–8, 2017.
[13] Yong Zhong, Wei gang Guo, and Lian ming Zeng. Visual navigational method of parkingmanagement based on indoor precise real-time location. In 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering, volume 1, pages 227–229, 2010.
[14] Deni Kristin Manase, Zahir Zainuddin, Syafruddin Syarif, and Arsan Kumala Jaya. Car detection in roadside parking for smart parking system based on image processing. In 2020 International Seminar on Intelligent Technology and Its Applications (ISITIA), pages 194–198, 2020.
[15] Di Yang, Han Xu, Zhe Feng, Linghang Meng, Chengnian Long, and Shaoliang Peng. A scheme to optimize roadside parking management by using blockchain technology. In 2020 IEEE 6th International Conference on Computer and Communications (ICCC), pages 2235–2239, 2020.
[16] Yi-Chun Kuo Yi-Ting Lin Shining Yu Christoph Mertz John Dola. Updating hd maps with videos from vehicles. https://mscvprojects.ri.cmu.edu/2020teamg/, 2020.
[17] Siyu Teng, Xuemin Hu, Peng Deng, Bai Li, Yuchen Li, Yunfeng Ai, Dongsheng Yang, Lingxi Li, Zhe Xuanyuan, Fenghua Zhu, and Long Chen. Motion planning for autonomous driving: The state of the art and future perspectives. IEEE Transactions on Intelligent Vehicles, 8(6):3692– 3711, 2023.
[18] Joshua Joy and Mario Gerla. Internet of vehicles and autonomous connected car - privacy and security issues. In 2017 26th International Conference on Computer Communication and Networks (ICCCN), pages 1–9, 2017.
[19] Ilias Leontiadis, Gustavo Marfia, David Mack, Giovanni Pau, Cecilia Mascolo, and Mario Gerla. On the effectiveness of an opportunistic traffic management system for vehicular networks. IEEE Transactions on Intelligent Transportation Systems, 12(4):1537–1548, 2011.
[20] Jing Yang, Qinghua Ni, Guiyang Luo, Qi Cheng, Latifa Oukhellou, and Shuangshuang Han. A trustworthy internet of vehicles: The dao to safe, secure, and collaborative autonomous driving. IEEE Transactions on Intelligent Vehicles, 8(12):4678–4681, 2023.
[21] Ghadeer Abdelkader, Taghreed Alghamdi, Khalid Elgazzar, and Alaa Khamis. Hd maps for connected and automated vehicles: Enabling technologies and future directions. In 2023 IEEE International Conference on Smart Mobility (SM), pages 91–97, 2023.
[22] Kai-Wei Chiang, Surachet Srinara, Syun Tsai, Cheng-Xian Lin, and Meng-Lun Tsai. High- definition-map-based lidar localization through dynamic time-synchronized normal distribution transform scan matching. IEEE Transactions on Vehicular Technology, 72(6):7011–7023, 2023.
[23] K.W. Chiang, G.J. Tsai, H.W. Chang, C. Joly, and N. EI-Sheimy. Seamless navigation and mapping using an ins/gnss/grid-based slam semi-tightly coupled integration scheme. Information Fusion, 50:181–196, 2019.
[24] Andre Braga Reis, Susana Sargento, and Ozan K. Tonguz. Smarter cities with parked cars as roadside units. IEEE Transactions on Intelligent Transportation Systems, 19(7):2338–2352, 2018.
[25] Moez Jerbi, Sidi-Mohammed Senouci, Tinku Rasheed, and Yacine Ghamri-Doudane. infrastructure-free traffic information system for vehicular networks.
An In 2007 IEEE 66th Vehicular Technology Conference, pages 2086–2090, 2007.
[26] Justyna Zander. New Ability to Update HD Maps Lets DRIVE Mapping Chart Safer Course for Autonomous Driving — blogs.nvidia.com, howpublished = https://blogs.nvidia.com/blog/drive-mapping-hd-map-update/, year = 2019,.
[27] Anis Boubakri, Sonia METTALI Gammar, Mohamed BEN Brahim, and Fethi Filali. High definition map update for autonomous and connected vehicles: A survey. In 2022 International Wireless Communications and Mobile Computing (IWCMC), pages 1148–1153, 2022.
[28] Dingrui Xue, Nan Yang, Xiangmo Zhao, and Zhen Wang. Point-cloud map update for connected and autonomous vehicles based on vehicle infrastructure cooperation: Framework and field experiments. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pages 2062–2067, 2021.
[29] Chansoo Kim, Sungjin Cho, Myoungho Sunwoo, Paulo Resende, Benazouz Bradaï, and Kichun Jo. Updating point cloud layer of high definition (hd) map based on crowd-sourcing of multiple vehicles installed lidar. IEEE Access, 9:8028–8046, 2021.
[30] Hideki Shimada, Akihiro Yamaguchi, Hiroaki Takada, Kenya Sato, et al. Implementation and evaluation of local dynamic map in safety driving systems. Journal of Transportation Technologies, 5(02):102, 2015.
[31] Leica Geosystem. https://leica-geosystems.com/. [Accessed 02-07-2024].
[32] Mostafa Elhashash, Hessah Albanwan, and Rongjun Qin. A review of mobile mapping systems: From sensors to applications. Sensors, 22(11):4262, 2022.
[33] Hexagon. Calgary parkplus program. Technical report, Velocity Magazine; Velocity 2014, 2014.
[34] Zhihui Chen, Hao Xu, Junxuan Zhao, and Hongchao Liu. Curbside parking monitoring with roadside lidar. Transportation Research Record, 2677(10):824–838, 2023.
[35] Jingrong Chen, Sheng Tian, Hao Xu, Rui Yue, Yuan Sun, and Yuepeng Cui. Architecture of vehicle trajectories extraction with roadside lidar serving connected vehicles. IEEE Access, 7:100406–100415, 2019.
[36] https://www.facebook.com/olivertublog. 智慧停車的差別? 地磁智慧停車格與智慧停車柱 - 電腦王阿達 — kocpc.com.tw. https://www.kocpc.com.tw/archives/536977, 2024-03-04.
[37] Le Chang, Xiaoji Niu, Tianyi Liu, Jian Tang, and Chuang Qian. Gnss/ins/lidar-slam integrated navigation system based on graph optimization. Remote Sensing, 11(9):1009, 2019.
[38] Livox.Livox hap(ux)user manual. https://terra-1-g.djicdn.com/65c028cd298f4669a7f0e40e50ba1131/Download/HAP/HAP%20(TX)_User%20Manual.pdf,2022.07.
[39] Bernhard Hofmann-Wellenhof, Herbert Lichtenegger, and Elmar Wasle.GNSS —Global Navigation Satellite Systems: GPS, GLONASS, Galileo, and more. Springer Science & Business Media, 2007.
[40] University of Southern Queensland. Gnss signals. https://usq.pressbooks.pub/gpsandgnss/chapter/3-4-gnss-signals, 2023.
[41] Malek Karaim, Mohamed Elsheikh, Aboelmagd Noureldin, and RB Rustamov. Gnss error sources. Multifunctional operation and application of GPS, 32:137–144, 2018.
[42] Jon Otegui, Alfonso Bahillo, Iban Lopetegi, and Luis Enrique Díez. Performance evaluation of different grade imus for diagnosis applications in land vehicular multi-sensor architectures. IEEE Sensors Journal, 21(3):2658–2668, 2021.
[43] D. Titterton, J.L. Weston, Institution of Electrical Engineers, American Institute of Aeronautics, and Astronautics. Strapdown Inertial Navigation Technology. IEE Radar Series. Institution of Engineering and Technology, 2004.
[44] Eun-Hwan Shin and N El-Sheimy. Accuracy improvement of low cost ins. GPS for Land Applications, 2001.
[45] Kai-Wei Chiang. INS/GPS integration using neural networks for land vehicular navigation applications. Number NR-04589 UMI. University of Calgary Canada, 2004.
[46] J. Gao, M.G. Petovello, and Cannon M.E. Gps/low-cost imu/onboard vehicle sensors integrated land vehicle positioning system. J Embedded Systems 2007, 2007.
[47] D. Gebre-Egziabher and S. Gleason. GNSS Applications and Methods. GNSS technology and applications series. Artech House, 2009.
[48] Paul D Groves. Principles of gnss, inertial, and multisensor integrated navigation systems, [book review]. IEEE Aerospace and Electronic Systems Magazine, 30(2):26–27, 2015.
[49] Z. Zhang. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11):1330–1334, 2000.
[50] Eung-Su Kim and Soon-Yong Park. Extrinsic calibration of a camera-lidar multi sensor system using a planar chessboard. In 2019 Eleventh International Conference on Ubiquitous and Future Networks (ICUFN), pages 89–91, 2019.
[51] Subodh Mishra, Gaurav Pandey, and Srikanth Saripalli. Extrinsic calibration of a 3d-lidar and a camera. In 2020 IEEE Intelligent Vehicles Symposium (IV), pages 1765–1770, 2020.
[52] Yujian Cai, Yinwei Zhan, and Wanting Deng. A novel extrinsic calibration method of a camera-and-lidar system. In 2021 IEEE 7th International Conference on Virtual Reality (ICVR), pages 109–116, 2021.
[53] Chenghao Shi, Kaihong Huang, Qinghua Yu, Junhao Xiao, Huimin Lu, and Chenggang Xie. Extrinsic calibration and odometry for camera-lidar systems. IEEE Access, 7:120106–120116, 2019.
[54] W. Zhang and D. Xu. Extrinsic calibration of lidar-camera based on deep convolutional network. IEEE Access, China Automation Congress (CAC), Xiamen, China:2949–2954, 2022.
[55] Chongjian Yuan, Xiyuan Liu, Xiaoping Hong, and Fu Zhang. Pixel-level extrinsic self calibration of high resolution lidar and camera in targetless environments, 2021.
[56] Ki Young Koo, David Hester, and Sehoon Kim. Time synchronization for wireless sensors using low-cost gps module and arduino. Frontiers in Built Environment, 4, 01 2019.
[57] Liang Li, Haotian Li, Xiyuan Liu, Dongjiao He, Ziliang Miao, Fanze Kong, Rundong Li, Zheng Liu, and Fu Zhang. Joint intrinsic and extrinsic lidar-camera calibration in targetless environments using plane-constrained bundle adjustment, 2023.
[58] Y.-E. Lu, K.-W. Chiang, M.-L. Tsai, Y.-T. Chiu, S. Srinara, T.-C. Wu, and N. El-Sheimy. An evaluation of solid-state lidar for localization and hd point cloud mapping. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLVIII-1/W2-2023:841–847, 2023.
[59] Naoki Akai, Luis Yoichi Morales, Eijiro Takeuchi, Yuki Yoshihara, and Yoshiki Ninomiya. Robust localization using 3d ndt scan matching with experimentally determined uncertainty and road marker matching. In 2017 IEEE Intelligent Vehicles Symposium (IV), pages 1356–1363, 2017.
[60] Rayson Laroca, Evair Severo, Luiz A. Zanlorensi, Luiz S. Oliveira, Gabriel Resende Gonçalves, William Robson Schwartz, and David Menotti. A robust real-time automatic license plate 126recognition based on the yolo detector. In 2018 International Joint Conference on Neural Networks (IJCNN), pages 1–10, 2018.
[61] Rayson Laroca, Evair Severo, Luiz A Zanlorensi, Luiz S Oliveira, Gabriel Resende Gonçalves, William Robson Schwartz, and David Menotti. A robust real-time automatic license plate recognition based on the yolo detector. In 2018 international joint conference on neural networks (ijcnn), pages 1–10. IEEE, 2018.
[62] Weidong Min, Xiangpeng Li, Qi Wang, Qingpeng Zeng, and Yanqiu Liao. New approach to vehicle license plate location based on new model yolo-l and plate pre-identification. IET ImageProcessing, 13(7):1041–1049, 2019.
[63] Se-Ho Park, Saet-Byeol Yu, Jeong-Ah Kim, and Hyoseok Yoon. An all-in-one vehicle type and license plate recognition system using yolov4. Sensors, 22(3), 2022.
[64] Kiran Wadare, Mr Sharma, Mrs.Sheetal Patil, Mrs. Mrunal Bewoor, Avinash Pawar, Amol Kadam, and Suhas Patil. Vehicle number plate detection using yolov8 and easyocr. 10 2023.
[65] D.R. Vedhaviyassh, R. Sudhan, G. Saranya, M. Safa, and D. Arun. Comparative analysis of easyocr and tesseractocr for automatic license plate recognition using deep learning algorithm. In 2022 6th International Conference on Electronics, Communication and Aerospace Technology, pages 966–971, 2022.
[66] Ajay Kumar Singh and Souvik Roy. Anpr indian system using surveillance cameras. 2015 Eighth International Conference on Contemporary Computing (IC3), pages 291–294, 2015.
[67] Shyang-Lih Chang, Li-Shien Chen, Yun-Chung Chung, and Sei-Wan Chen. Automatic license plate recognition. IEEE Transactions on Intelligent Transportation Systems, 5(1):42–53, 2004.
[68] Chun-Cheng Lin, Mao-Huan Hsu, and Cheng-Yu Yeh. License plate recognition system for taiwanese vehicles using cascade of yolov4 detectors. Sensors and Materials, 35:2129, 06 2023.
[69] Elgasim Elamin Elnima. A solution for exterior and relative orientation in photogrammetry, a genetic evolution approach. Journal of King Saud University - Engineering Sciences, 27(1):108–113, 2015.
[70] Mohammed O. Aqel, Mohammad H. Marhaban, M. Iqbal Saripan, and Nasrul B. Ismail. Review of visual odometry: types, approaches, challenges, and applications. SpringerPlus, 5(1):1897, 2016.
[71] Kichun Jo, Chansoo Kim, and Myoungho Sunwoo. Simultaneous localization and map change update for the high definition map-based autonomous driving car. Sensors, 18(9):3145, 2018.