請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84366完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 洪一平(YP Hung) | |
| dc.contributor.author | Sheng-Kai Huang | en |
| dc.contributor.author | 黃聲凱 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:09:32Z | - |
| dc.date.copyright | 2022-07-05 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-04-25 | |
| dc.identifier.citation | [1] Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich. Superpoint: Self supervised interest point detection and description. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 224–236, 2018. [2] Yuki Ono, Eduard Trulls, Pascal Fua, and Kwang Moo Yi. Lfnet: Learning local features from images. arXiv preprint arXiv:1805.09662, 2018. [3] MihaiDusmanu,IgnacioRocco,TomasPajdla,MarcPollefeys,JosefSivic,Akihiko Torii, and Torsten Sattler. D2net: A trainable cnn for joint description and detection of local features. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition, pages 8092–8101, 2019. [4] JeromeRevaud,PhilippeWeinzaepfel,CésarDeSouza,NoePion,GabrielaCsurka, Yohann Cabon, and Martin Humenberger. R2d2: repeatable and reliable detector and descriptor. arXiv preprint arXiv:1906.06195, 2019. [5] Yurun Tian, Bin Fan, and Fuchao Wu. L2net: Deep learning of discriminative patch descriptor in euclidean space. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 661–669, 2017. [6] Zixin Luo, Lei Zhou, Xuyang Bai, Hongkai Chen, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, and Long Quan. Aslfeat: Learning local features of accurate shape and localization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6589–6598, 2020. [7] Relja Arandjelovic, Petr Gronat, Akihiko Torii, Tomas Pajdla, and Josef Sivic. Netvlad: Cnn architecture for weakly supervised place recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5297– 5307, 2016. [8] David G Lowe. Distinctive image features from scaleinvariant keypoints. International journal of computer vision, 60(2):91–110, 2004. [9] Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool. Speededup robust features (surf). Computer vision and image understanding, 110(3):346–359, 2008. [10] Max Jaderberg, Karen Simonyan, Andrew Zisserman, et al. Spatial transformer net works. Advances in neural information processing systems, 28:2017–2025, 2015. [11] Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, and Yichen Wei. Deformable convolutional networks. In Proceedings of the IEEE international conference on computer vision, pages 764–773, 2017. [12] TorstenSattler,BastianLeibe,andLeifKobbelt.Fastimagebasedlocalizationusing direct 2dto3d matching. In 2011 International Conference on Computer Vision, pages 667–674. IEEE, 2011. [13] Pierre Moulon, Pascal Monasse, and Renaud Marlet. Global fusion of relative mo tions for robust, accurate and scalable structure from motion. In Proceedings of the IEEE International Conference on Computer Vision, pages 3248–3255, 2013. [14] Torsten Sattler, Bastian Leibe, and Leif Kobbelt. Efficient & effective prioritized matching for largescale imagebased localization. IEEE transactions on pattern analysis and machine intelligence, 39(9):1744–1756, 2016. [15] Liu Liu, Hongdong Li, and Yuchao Dai. Efficient global 2d3d matching for cam era localization in a largescale 3d map. In Proceedings of the IEEE International Conference on Computer Vision, pages 2372–2381, 2017. [16] Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, and Akihiko Torii. Inloc: Indoor visual localization with dense matching and view synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7199–7209, 2018. [17] Johannes L Schonberger and JanMichael Frahm. Structurefrommotion revisited. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4104–4113, 2016. [18] Yongyi Tang, Xing Zhang, Lin Ma, Jingwen Wang, Shaoxiang Chen, and YuGang Jiang. Nonlocal netvlad encoding for video classification. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pages 0–0, 2018. [19] Peng Tang, Xinggang Wang, Baoguang Shi, Xiang Bai, Wenyu Liu, and Zhuowen Tu. Deep fishernet for object classification. arXiv preprint arXiv:1608.00182, 2016. [20] Eric Brachmann and Carsten Rother. Learning less is more6d camera localization via 3d surface regression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4654–4662, 2018. [21] Eric Brachmann and Carsten Rother. Expert sample consensus applied to camera relocalization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7525–7534, 2019. [22] Eric Brachmann and Carsten Rother. Visual camera relocalization from rgb and rgbd images using dsac. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021. [23] XiaotianLi,ShuzheWang,YiZhao,JakobVerbeek,andJuhoKannala.Hierarchical scene coordinate classification and regression for visual localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11983–11992, 2020. [24] Jamie Shotton, Ben Glocker, Christopher Zach, Shahram Izadi, Antonio Criminisi, and Andrew Fitzgibbon. Scene coordinate regression forests for camera relocaliza tion in rgbd images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2930–2937, 2013. [25] YihongWuandZhanyiHu.Pnpproblemrevisited.JournalofMathematicalImaging and Vision, 24(1):131–141, 2006. [26] Relja Arandjelovic and Andrew Zisserman. All about vlad. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 1578–1585, 2013. [27] Vincent Lepetit, Francesc MorenoNoguer, and Pascal Fua. Epnp: An accurate o (n) solution to the pnp problem. International journal of computer vision, 81(2):155, 2009. [28] Laurent Kneip, Hongdong Li, and Yongduek Seo. Upnp: An optimal o (n) solution to the absolute pose problem with universal applicability. In European Conference on Computer Vision, pages 127–142. Springer, 2014. [29] Torsten Sattler, Will Maddern, Carl Toft, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, et al. Benchmarking 6dof outdoor visual localization in changing conditions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8601–8610, 2018. [30] Longterm visuallocalization. https://www.visuallocalization.net. Ac cessed: 20210930. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84366 | - |
| dc.description.abstract | 近年來攝影機自我定位在很多方面都有產業化的發展，比如機器人和無人駕駛車需要視覺定位來估計其位置，由此，自我定位技術之重要性可想而知。視覺定位其中最普遍的一個方法就是基於影像特徵，此篇論文就是比較傳統特徵和深度學習特徵運用在單一影像法之定位準確度之影響，並且本次實驗所選用的單一影像法是基於影像檢索。論文中會選用兩種經典的傳統特徵提取方法以及五種最近幾年比較熱門的深度學習特徵提取方法，實驗的數據集包含季節變化和照明變化（天氣變化）的影像，在不同精確範圍下比較定位準確度，分析產生性能優劣之可能性，並討論各種方法的優缺點。這將為後續的影像定位研究提供思路與改善方向，尤其是在針對具有照明變化的定位研究。 | zh_TW |
| dc.description.abstract | In recent years, camera ego-positioning has been industrialized in many aspects. For example, robots and unmanned vehicles need visual positioning to estimate their position. Therefore, the importance of ego-positioning technology can be imagined. One of the most common methods of ego-positioning is based on image features. This paper compares the performance of traditional features and deep-learning features on the localization accuracy of a single-shot localization method, and the single-shot localization method used in this experiment is based on image retrieval . In the paper, two classic traditional feature extraction methods and five deep-learning feature extraction methods that have been popular in recent years will be selected. The experimental datasets contain images of seasonal changes and lighting changes(weather changes). The localization accuracy is compared under different accuracy ranges. Analyze the possibility of performance pros and cons, and discuss the pros and cons of various methods. This will provide ideas and improvement directions for subsequent image localization research, especially for localization research with lighting changes. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:09:32Z (GMT). No. of bitstreams: 1 U0001-1810202118590100.pdf: 3570968 bytes, checksum: 2c770ff86ee13d7952339a3cbc6f4d68 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | Acknowledgements i 摘要 ii Abstract iii Contents v List of Figures viii List of Tables ix Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Feature Extraction Techniques 2 1.3 Single-Shot Camera Localization Techniques 2 Chapter 2 Related Works 4 2.1 Feature Extraction 4 2.1.1 SIFT 4 2.1.2 SURF 5 2.1.3 SuperPoint 6 2.1.4 LF-Net 7 2.1.5 D2-Net 8 2.1.6 R2D2 9 2.1.7 ASLFeat 11 2.2 Single-Shot Camera Localization 12 2.2.1 Methods Introduction 12 2.2.2 Methods Summary 13 Chapter 3 Single-Shot Camera Localization for Feature Comparison 15 3.1 Similarity-based Pairing 16 3.2 Perspective-n-Point (PnP) 17 3.3 Summary of Experimental Methods 18 Chapter 4 Experiments 19 4.1 Data 19 4.1.1 Aachen Day-Night Dataset 20 4.1.2 RobotCar Seasons Dataset 20 4.2 Setup 23 4.3 Similarity-based Pairing 23 4.4 Accuracy Comparison 23 4.4.1 Accuracy Comparison Experiment Details 23 4.4.1.1 Accuracy Comparison Results (Aachen) 24 4.4.1.2 Accuracy Comparison Results (RobotCar Seasons) 27 4.5 Time Comparison 31 4.5.1 Time Comparison Results (Aachen) 31 4.5.2 Time Comparison Results (RobotCar Seasons) 32 4.6 Summary of Comparison on Camera Localization 33 Chapter 5 Discussion 34 Chapter 6 Conclusions and Future Work 37 References 38 | |
| dc.language.iso | en | |
| dc.subject | 影像檢索 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 視覺定位 | zh_TW |
| dc.subject | 特徵提取 | zh_TW |
| dc.subject | 自我定位 | zh_TW |
| dc.subject | 單一影像法 | zh_TW |
| dc.subject | single-shot camera localization | en |
| dc.subject | visual positioning | en |
| dc.subject | image retrieval | en |
| dc.subject | deep learning | en |
| dc.subject | feature extraction | en |
| dc.subject | ego-positioning | en |
| dc.title | 使用傳統或深度學習特徵於單一影像攝影機定位法之效能 | zh_TW |
| dc.title | Performance on Single-Shot Camera Localization Using Handcrafted or Deep-Learning Features | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李明穗(MS Lee),陳冠文(Kuan-Wen Chen) | |
| dc.subject.keyword | 自我定位,特徵提取,深度學習,影像檢索,視覺定位,單一影像法, | zh_TW |
| dc.subject.keyword | ego-positioning,feature extraction,deep learning,image retrieval,visual positioning,single-shot camera localization, | en |
| dc.relation.page | 42 | |
| dc.identifier.doi | 10.6342/NTU202103840 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-04-25 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-07-05 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1810202118590100.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 3.49 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。