請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/56713
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 王傑智(Chieh-Chih Wang) | |
dc.contributor.author | Ching-Hsiang Hsu | en |
dc.contributor.author | 徐慶祥 | zh_TW |
dc.date.accessioned | 2021-06-16T05:43:47Z | - |
dc.date.available | 2015-09-04 | |
dc.date.copyright | 2014-09-04 | |
dc.date.issued | 2014 | |
dc.date.submitted | 2014-08-11 | |
dc.identifier.citation | [1] Chieh-Chih Wang, Charles Thorpe, Sebastian Thrun, Martial Hebert, and Hugh Durrant-Whyte. Simultaneous localization, mapping and moving object tracking. International Journal of Robotics Research, 26(9):889–916, 2007.
[2] Joao Paulo Costeira and Takeo Kanade. A multibody factorization method for independently moving objects. International Journal of Computer Vision, 29(3):159–179, 1998. [3] Carlo Tomasi and Takeo Kanade. Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision, 9(2):137–154, 1992. [4] Jingyu Yan and Marc Pollefeys. A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In European Conference on Computer Vision, pages 94–106. Springer, 2006. [5] Konrad Schindler. Spatially consistent 3d motion segmentation. In IEEE International Conference on Image Processing, volume 3, pages III–409. IEEE, 2005. [6] Samunda Perera and Nick Barnes. Maximal cliques based rigid body motion segmentation with a rgb-d camera. In Asian Conference on Computer Vision, pages 120–133. Springer, 2013. [7] Youbing Wang and Shoudong Huang. An efficient motion segmentation algorithm for multibody rgb-d slam. In Proceedings of Australasian Conference on Robotics and Automation, 2013. [8] Simon Hadfield and Richard Bowden. Kinecting the dots: Particle based scene flow from depth sensors. In IEEE International Conference on Computer Vision, pages 2290–2295. IEEE, 2011. [9] Michael Van den Bergh and Luc Van Gool. Real-time stereo and flow-based video segmentation with superpixels. In IEEE Workshop on Applications of Computer Vision, pages 89–96. IEEE, 2012. [10] Markus Unger, Manuel Werlberger, Thomas Pock, and Horst Bischof. Joint motion estimation and segmentation of complex scenes with label costs and occlusion modelling. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1878–1885. IEEE, 2012. [11] Evan Herbst, Xiaofeng Ren, and Dieter Fox. Object segmentation from motion with dense feature matching. In IEEE International Conference on Robotics and Automation Workshop on Semantic Perception, Mapping and Exploration, 2012. [12] Manjunath Narayana, Allen Hanson, and Erik Learned-Miller. Coherent motion segmentation in moving camera videos using optical flow orientations. In IEEE International Conference on Computer Vision, pages 1577–1584. IEEE, 2013. [13] J org St uckler and Sven Behnke. Efficient dense 3d rigid-body motion segmentation in rgb-d video. In Proceedings of the British Machine Vision Conference, 2013. [14] Thomas Brox Peter Ochs, Jitendra Malik. Segmentation of moving objects by long term video analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013. [15] Steven Hickson, Stan Birchfield, Irfan Essa, and Henrik Christensen. Efficient hierarchical graph-based segmentation of rgbd videos. In IEEE Conference on Computer Vision and Pattern Recognition. IEEE, June 2014. [16] Yi Chiang. A prioritized gauss-seidel method for dense correspondence estimation and motion segmentation in crowded urban areas with a moving depth camera. Master’s thesis, National Taiwan University, 2014. [17] Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. Indoor segmentation and support inference from rgbd images. In European Conference on Computer Vision, pages 746–760. Springer, 2012. [18] Manuel Werlberger, Thomas Pock, and Horst Bischof. Motion estimation with non-local total variation regularization. In IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, June 2010. [19] Shao-Wen Yang, Chieh-Chih Wang, and Chun-Hua Chang. Ransac matching: Simultaneous registration and segmentation. In IEEE International Conference on Robotics and Automation, pages 1905–1912. IEEE, 2010. [20] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aur elien Lucchi, Pascal Fua, and Sabine S usstrunk. Slic superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis andMachine Intelligence, 34(11):2274–2282, 2012. [21] Yuri Boykov, OlgaVeksler, and Ramin Zabih. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11):1222–1239, 2001. [22] Vladimir Kolmogorov and Ramin Zabin. What energy functions can be minimized via graph cuts? IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(2):147–159, 2004. [23] Yuri Boykov and Vladimir Kolmogorov. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(9):1124–1137, 2004. [24] ManuelWerlberger,Werner Trobin, Thomas Pock, AndreasWedel, Daniel Cremers, and Horst Bischof. Anisotropic Huber-L1 optical flow. In Proceedings of the British Machine Vision Conference, London, UK, September 2009. [25] Manuel Werlberger. Convex Approaches for High Performance Video Processing. PhD thesis, Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria, June 2012. [26] Derek Hoiem, Alexei A Efros, and Martial Hebert. Recovering surface layout from an image. International Journal of Computer Vision, 75(1):151–172, 2007. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/56713 | - |
dc.description.abstract | 在計算機視覺與機器人學領域運動分割是一個重要且具有挑戰性的問題,由於其複雜性,根據環境差異性、運動物體本身的特性和所運用的感測器,這個問題可以從不同研究方向切入。透過使用 RGB-D 結構光距離感測器,我們提出一個新穎且強健的算法來完成運動分割。我們利用色彩和空間上的一致性改進隨機抽樣一致算法(RANSAC)來進行運動估測,它繼承了原有 RANSAC 範式下的計算效率與強健性,並且我們結合基於運動估測結果的內群和離群分佈和 RGB-D 影像上的色彩與深度資訊,以圖切分演算法完成運動分割,進一步,我們引入物理支持關係除了用來表示運動分割強度,並且可以用來理解所分割運動之區段的語義。相較於現有類似架構之運動分割算法,此算法在一個高度動態的環境有良好的表現。最後,我們提供了一個在擁擠都市環境下使用 Xtion Pro Livee 感測器所錄製的 RGB-D 數據集來展示我們成果。 | zh_TW |
dc.description.abstract | Motion segmentation is an important and challenging problem in computer vision and robotics. Because of its complexity, this problemcan be approached from respective angles depending on sensors, environment, andmotions themselves. By utilizing RGB-Dvideo captured by a structured light range sensor, we proposed a novel and robust algorithm to segment motions from consecutive frames. Based on a modified random sample consensus algorithm (RANSAC), we exploit the coherence of color and spatiality in the scene to estimate motion. It inherits the computational efficiency and probabilistic robustness from the RANSAC paradigm. After aligning two point clouds by the estimated transformation, we combine the output of inlier and outlier distribution with the prior knowledge of the RGB-D images to conduct segmentation by a graph-cut optimization scenario. Moreover, we introduce physical support relationships to better understand the motions in the environment. We provide a RGB-D dataset captured in a crowded urban environment to demonstrate our idea. Comparing to several motion segmentation methods in the same pipeline, we show that our approach performs well in the highly dynamic scene. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T05:43:47Z (GMT). No. of bitstreams: 1 ntu-103-R01944021-1.pdf: 42922981 bytes, checksum: ec7e27dbf8f87aeb4910ad00d85ae5f1 (MD5) Previous issue date: 2014 | en |
dc.description.tableofcontents | TABLE OF CONTENTS iii
致謝 iv 摘要 v ABSTRACT vi List of Figures vii List of Tables ix 1 Introduction 1 2 Related Work 3 3 Motion Segmentation 6 3.1 Approach Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.2 Pre-process . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.2.1 Dense Optical Flow Estimation . . . . . . . . . . . . . . . . . . 7 3.2.2 Ground Detection . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.2.3 Over Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.4 Physical Support Relationship . . . . . . . . . . . . . . . . . . . 13 3.3 Motion Estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.4 Split Segment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.5 Merge Segment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 3.6 Result Integration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4 Experiments 25 4.1 Setting of the RGB-D Camera and Crowded Urban Dataset . . . . . . . . 26 4.2 Results and Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5 Conclusion and FutureWork 37 Bibliography 39 | |
dc.language.iso | en | |
dc.title | 以圖切分演算法搭配物理支持關係在擁擠都市中完成移動式RGB-D相機之運動分割 | zh_TW |
dc.title | Graph-cut based Motion Segmentation with Physical Support Relationships in Crowded Urban Areas from a Moving RGB-D Camera | en |
dc.type | Thesis | |
dc.date.schoolyear | 102-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 傅立成(Li-Chen Fu),莊永裕(Yung-Yu Chuang),陳祝嵩(Chu-song Chen),鍾聖倫(Sheng-Luen Chung) | |
dc.subject.keyword | 運動分割,移動物體偵測,RGB-D影片,物理支持關係, | zh_TW |
dc.subject.keyword | Motion Segmentation,Moving Object Detection,RGB-D video,Physical Support Relationship, | en |
dc.relation.page | 42 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2014-08-11 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-103-1.pdf 目前未授權公開取用 | 41.92 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。