請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66429
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 王傑智 | |
dc.contributor.author | Chien-Chen Weng | en |
dc.contributor.author | 翁建宸 | zh_TW |
dc.date.accessioned | 2021-06-17T00:35:24Z | - |
dc.date.available | 2013-03-19 | |
dc.date.copyright | 2012-03-19 | |
dc.date.issued | 2012 | |
dc.date.submitted | 2012-02-06 | |
dc.identifier.citation | 1. Arnold, J., Shaw, S., & Pasternack, H. (1993). Efficient target tracking using dynamic programming. IEEE Transactions on Aerospace and Electronic Systems, 29.
2. Bar-Shalom, Y. & Li, X.-R. (1988). Estimation and tracking: principles, techniques, and software. Danvers, MA: YBS. 3. Blom, H. A. P. & Bar-Shalom, Y. (1988). The interacting multiple model algorithm for systems with markovian switching coefficients. IEEE Transactions on Automatic Control, 33. 4. Fortmann, T. E., Bar-Shalom, Y., & Scheffe, M. (1983). Sonar tracking of multiple targets using joint probabilistic data association. IEEE Journal of Oceanic Engineering, 8. 5. Gish, H. & Mucci, R. (1987). Target state estimation in a multi-target environments. IEEE Transactions on Aerospace and Electronic Systems, 23. 6. Konstantinova, P., Udvarev, A., & Semerdjiev, T. (2003). A study of a target tracking algorithm using global nearest neighbor approach. In Proceedings of International Conference on Computer Systems and Technologies, Sofia, Bulgaria. 7. Liu, C., Freeman, W. T., Adelson, E. H., & Weiss, Y. (2008). Human-assisted motion annotation. In Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, US. 8. Lu, F. & Milios, E. (1994). Robot pose estimation in unknown environments by matching 2d range scans. Journal of Intelligent and Robotic Systems. 9. Reid, D. B. (1979). An algorithm for tracking multiple targets. IEEE Transactions on Automatic Control, 24. 10. Rosenberg, A. & Hirschberg, J. (2007). V-measure: A conditional entropy-based external cluster evaluation measure. In Proceedings of Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, Czech Republic. 11. Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008). Labelme: a database and web-based tool for image annotation. International Journal of Computer Vision, 77. 12. Wan, K.-W., Wang, C.-C., & Ton, T. T. (2008). Weakly interacting object tracking in indoor environments. In Proceedings of International Conference on Advanced Robotics and Its Social Impacts, Taipei, Taiwan. 13. Wang, C.-C., Lo, T.-C., & Yang, S.-W. (2007). Interacting object tracking in crowded urban areas. In Proceedings of International Conference on Robotics and Automation, Roma, Italy. 14. Yang, S.-W., Wang, C.-C., & Chang, C.-H. (2010). Ransac matching: simultaneous registration and segmentation. In Proceedings of International Conference on Robotics and Automation, Anchorage, Alaska. 15. Yang, S.-W., Wang, C.-C., & Thorpe, C. (2011). The annotated laser data set for navigation in urban areas. The International Journal of Robotics Research, 30. 16. Yuen, J., Russell, B. C., Liu, C., & Torralba, A. (2009). Labelme video: building a video database with human annotations. In Proceedings of International Conference on Computer Vision, Kyoto, Japan. 17. Zhang, Q. & Pless, R. (2004). Extrinsic calibration of a camera and laser range finder (improves camera calibration). In Proceedings of International Conference on Intelligent Robots and Systems, Sendai, Japan. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66429 | - |
dc.description.abstract | 為了要讓機器人了解周遭的動態環境,成功地追蹤移動物體是不可缺少的必要條件。在過去,學者們陸續提出了許多移動物體追蹤的演算法。然而到目前為止,卻沒有足夠的、經標示過的真實資料可以用來評估、比較各個演算法的效能。面對這樣的瓶頸,我們針對基於雷射測距儀的移動物體追蹤演算法,設計了雷射資料分群與連結的標示系統。使用者可以藉由這系統標示各個移動物體在二維空間中實際代表的雷射點群,進而與演算法計算的結果相互比較。由於資料標示的工作繁重且力求精確,我們的設計著重於提升使用者標示的精準度以及減少使用者的工作負荷。經由實驗,不僅證實了我們的標示系統能確實提升使用者的標示成果,也提供了標示過的交通路口資料,可以用來評估追蹤演算法在高度動態都市環境中的表現。 | zh_TW |
dc.description.abstract | Scene understanding is one of the most important foundations for a mobile robot to operate in human-habited environments. As the real environments are typically dynamic, moving object tracking becomes an inescapable problem. While the tracking algorithm becomes more and more elaborate, however, its performance in real world still can not be guaranteed. The major reason is that so far we do not have enough real data with ground-truth to evaluate and analysis the state of the art tracking algorithms
. In this thesis, we explore the laser-based moving object tracking problem and propose an annotation system that allows the user to annotate the ground-truth of segmentation and data association with 2D laser measurements. As the annotating task is difficult and tedious, the system is designed to achieve higher accuracy and reduce the task loading in the annotation process. To prove the usefulness of our system, real data sequences are collected and annotated by multiple users in our experiments. The results shows that the annotation performance varies but the system keeps helpful across different users. In particular, the V-measure reaches to 0.995 bits and the false positive rate and the false negative rate are reduced to 0.341% and 1.239%. At last, the ground-truth data is also generated by validating the annotated data carefully and repeatedly. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T00:35:24Z (GMT). No. of bitstreams: 1 ntu-101-R97922113-1.pdf: 1014639 bytes, checksum: 59375edc5b22bcd3c37ea102ebf4ed70 (MD5) Previous issue date: 2012 | en |
dc.description.tableofcontents | CHAPTER 1. Introduction ............................... 1
CHAPTER 2. RelatedWorks ............................... 3 2.1. Laser Scan vs. Camera Image ...................... 3 2.2. Human-Assisted Motion Annotation ................. 4 2.3. LabelMe Video .................................... 6 2.4. AnyGTA ........................................... 6 CHAPTER 3. Moving Object Tracking ..................... 7 3.1. Formulation of Moving Object Tracking ............ 7 3.2. Framework of Moving Object Tracking : ............ 8 3.3. Motion Modelling ................................. 9 3.3.1. Constant Velocity Model ........................ 9 3.3.2. Constant Acceleration Model .................... 10 3.3.3. Interacting Multiple Model ..................... 11 3.4. Moving Object Detection .......................... 16 3.4.1. Track before Detect ............................ 17 3.4.2. Moving Object Map Based Detection .............. 17 3.4.3. The Background Subtraction Approach ............ 17 3.5. Segmentation ..................................... 17 3.5.1. Simple Distance Criterion ...................... 18 3.5.2. Multi-scale Method ............................. 18 3.5.3. Over Segmentation and Under Segmentation ....... 18 3.6. Data Association ................................. 19 3.6.1. Gating ......................................... 19 3.6.2. Data Association in the Cluttered .............. 20 3.6.3. Incorrect Association and Missed Association ... 21 CHAPTER 4. Ground-truth Annotation System ............. 24 4.1. Motivation ....................................... 24 4.2. System Design .................................... 25 4.3. Annotation Rule .................................. 27 Incorrect Annotation .................................. 27 Good Annotation ....................................... 29 4.4. Annotation Method ................................ 30 4.4.1. Overall Annotation Flow ........................ 30 4.4.2. Human Correction ............................... 30 CHAPTER 5. Experiments ................................ 36 5.1. Experiment Setting ............................... 36 5.2. Evaluation ....................................... 39 5.2.1. V-measure vs. Speed ............................ 39 5.2.2. False Positive Rate vs. False Negative Rate .... 42 5.3. The application of the annotated data set ........ 45 CHAPTER 6. Conclusion and Future Work ................. 46 APPENDIX A. Laser-Camera Extrinsic Calibration ........ 47 A.1. Rigid Transformation ............................. 47 A.2. Methodology ...................................... 48 A.2.1. Basic Equations ................................ 48 A.2.2. Closed-form Solution ........................... 49 A.2.3. Non-linear Optimization ........................ 49 APPENDIX B. V-measure ................................. 51 B.1. Calculation ...................................... 51 B.2. V-measure in Segmentation and Data Association ... 52 BIBLIOGRAPHY .......................................... 55 | |
dc.language.iso | en | |
dc.title | 基於雷射測距儀之多移動物體追蹤的資料分群與連結標示系統 | zh_TW |
dc.title | The Ground-Truth Annotation System for Segmentation and Data Association in Laser-based Moving Object Tracking | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 連豊力,李綱,蔡欣穆 | |
dc.subject.keyword | 實況標示,基於雷射測距儀之多移動物體追蹤,資料分群,資料連結, | zh_TW |
dc.subject.keyword | Ground-truth Annotation,Laser-based Moving Object Tracking,Segmentation,Data Association, | en |
dc.relation.page | 58 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2012-02-06 | |
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 |
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 | |
---|---|---|---|
ntu-101-1.pdf 目前未授權公開取用 | 990.86 kB | 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。