跳到主要內容

臺灣博碩士論文加值系統

(54.80.249.22) 您好!臺灣時間:2022/01/20 06:40
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:駱昭隆
研究生(外文):Chao-Lung Lou
論文名稱:動態影像中物件切割與描述之研究
論文名稱(外文):A Study of Object Segmentation and Description for Motion Sequences
指導教授:王聖智王聖智引用關係
指導教授(外文):Sheng-Jyh Wang
學位類別:碩士
校院名稱:國立交通大學
系所名稱:電子工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:102
中文關鍵詞:影像切割動態影像切割空間時間座標系動態追蹤物件外型描述
外文關鍵詞:image segmentationmotion segmentationSpatio-Temporal Domainmotion trackingobject description
相關次數:
  • 被引用被引用:4
  • 點閱點閱:687
  • 評分評分:
  • 下載下載:138
  • 收藏至我的研究室書目清單書目收藏:0
在本論文當中,我們會分成兩個主題來進行討論。第一個主題是探討如何在影像序列中進行物件的切割;第二個主題則是討論對切割後的物件進行外型上的描述。首先,我們根據實驗室學長錢威融的作法,提出進一步的改良。在之前的作法中,是將動態影像切割轉換到空間時間座標系(Spatio-Temporal Domain)當中處理,而把動態影像切割問題轉換成一個三維空間中立體影像物件的切割問題。而根據之前的作法,我們更進一步去討論如何去選取門檻值(threshold)以達到比較好的切割結果,因此我們提出了一種可變動式調整門檻值(adaptive threshold)的方法以取代舊有的固定式門檻值(constant threshold),在我們的作法中,我們會根據不同的亮度(luminance)和色彩(chroma)的特性來調整門檻值。得到影像序列中的立體影像物件的切割結果後,在第二個主題,我們提出了一套對立體影像物件所產生的物件平面(Video Object Plane)進行追蹤以及外型的描述。我們先找到物件外型的特徵點,然後建立起不同時間的物件平面中特徵點的對應關係(Feature Point Correspondence),因此可以得知物體的外型如何沿著時間軸方向上進行變化。在得到物體沿著時間軸上運動的外型後,再對每一張影像平面上進行空間域(Spatial Domain)上的外型描述。當我們把兩者的資訊結合在一起後,我們即可以得到立體影像物件在空間-時間域(Spatial-Temporal Domain)上的三維外型描述。
In this thesis, we discuss two topics. One is about object segmentation in image sequences and the other is about shape description. In the first topic, we propose an improved motion segmentation algorithm based on Chien’s approach. In Chien’s approach, an image sequence is translated into the spatial-temporal domain and the motion segmentation issue becomes a 3-D object segmentation issue in the spatial-temporal domain. Following Chien’s approach, we further discuss the selection of contrast threshold and propose an adaptive scheme, to adjust the contrast threshold according to luminance and chroma conditions. In the second topic, we propose a new approach to track and describe segmented 3-D objects. In our approach, feature points of object’s shape are extracted first and the correspondence of these feature points are established frame by frame to describe the evolution of object’s shape along the temporal axis. Then, we describe the object’s spatial shape on each frame. After combining spatial description and temporal description, the shape of objects can be efficiently described.
第一章 簡介 1
第二章 背景資料 3
2.1 動態影像切割技術 3
2.1.1 MPEG4中有關動態切割技術的討論 4
2.1.2 動態影像切割技術相關研究 4
2.1.2.1 運動估測 (Motion Estimation) 5
2.1.2.1.1 光點流動 (Optical Flow) 5
2.1.2.1.2 Lucas-Kanade方法 6
2.1.2.1.3 利用二維平面變化模擬物體運動向量 9
2.1.2.1.4 區塊比對 (Block Matching) 12
2.1.2.2 空間域上的影像切割 14
2.1.2.2.1 Mean Shift 14
2.1.2.2.2 JSEG 17
2.2 物件外型描述 (Shape Description) 19
2.2.1 找尋物體外型特徵點 (Feature Point Extraction) 21
2.2.1.1 高斯曲率 (Gaussian Curvature) 21
2.2.1.2 Jong-Wang 所採用的主曲率估測方法 22
2.2.2外型比對 (Shape Matching) 22
2.2.2.1 利用影像亮度值資訊的方法 23
2.2.2.1.1 小波轉換 23
2.2.2.1.2 Fourier-Wavelet Descriptor 24
2.2.2.2 利用物體外型的方法 25
2.2.2.2.1 Medial Axis Transform(MAT) 25
2.2.2.2.2 Curvature Scale Space(CSS) 28
2.2.2.2.3 Shape Context 31
第三章 動態影像切割技術 35
3.1 之前所研究的動態影像切割技術 35
3.1.1選擇適合的色彩空間 36
3.1.2方向性的影像邊緣偵測器 38
3.1.3定義邊界強度 (Boundary Contrast) 39
3.1.4 時間-空間域的影像切割 40
3.2 改良的部分 43
3.2.1自動調整門檻大小的機制 (Adaptive Threshold) 43
第四章 物件外型描述 51
4.1 影像物件平面 (Video Object Plane) 51
4.2 找尋物件外型的特徵點 53
4.3 特徵點增添及刪去的方法 64
4.4 特徵點的對應 67
4.5 處理破碎的物體 68
4.5.1 Multi-resolution Feature Point Searching Scheme 69
4.5.2 特徵點校正技術 74
4.6 物體外型的描述 78
第五章 結論 93
參考資料 94
[Bel02] Belongie, S.; Malik, J.; Puzicha, J.,” Shape matching and object recognition using shape contexts”, Pattern Analysis and Machine Intelligence, IEEE Transactions on , Volume: 24 Issue: 4 , April 2002
[Blum67] H.Blum, “A transformation for extracting new descriptors of shape”. In Whaten-Dunn, editor, Models for the Perception of Speech and Visual Forms, pages 362-380 ,MIT Press, 1967
[Bui99] 1999, T.D.Bui and G.Chen Fourier-Wavelet Descriptor
[Chien 01] Wei-Jung Chien and Sheng-Jyh Wang, “The Study of Spatio-Temporal Segmentation for Image Sequences”, Master Thesis, National Chiao Tung University, Hsinchu, Taiwan, ROC, 2001
[Cho 95] Jae Gark Choi, Si-Woong Lee, and Seong-Dae Kim, “Segmentation and Motion Estimation of Moving Objects for Object-Oriented Analysis-Synthesis Coding”, International Conference on Acoustics, Speech, and Signal Processing, VOL. 4, pp. 2431-2443, 1995
[Deng 99] Y. Deng and B.S. Manjunath, “An efficient low-dimensional color indexing scheme for region-based image retrieval”, Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), p. 3017-20, 1999.
[Dor99] Dorin Comaniciu and Peter Meer, “Mean shift analysis and applications”, Proc. of the seventh IEEE Intl. Conf. on computer vision, VOL.2, p. 1197-1203, 1999.
[Dru 00] Heidelberger Druckmaschinen AG, http://www.linocolor.com/search_reg/tm.htm, 2000
[Jong 98] Hsing-Haw Jong and Sheng-Jyh Wang, “The Extraction of High-Curvature Feature Point in Image Surface”, Master Thesis, National Chiao Tung University, Hsinchu, Taiwan, ROC, 1998
[Jong 81] Jong-Sen Lee, “Refined Filtering of Image Noise Using Local Statistics”, Computer Graphics and Image Processing, VOL.15, p.380-389, 1981
[Kim99] Munchurl Kim, Jae Gark Choi, Daehee Kim, Hyung Lee, Myoung Ho Lee, Chieteuk Ahn, and Yo-Sung Ho, “A VOP Generation Tool: Automatic Segmentation of Moving Objects in Image Sequences Based on Spatio-Temporal Information”, IEEE Transactions on Circuits and System for Video Technology, VOL.9 NO. 8, pp. 1216-1226, December 1999
[Ko 00] Jui-Tai Ko and Sheng-Jyh Wang, “The Study of Dynamic Representation in Image Sequences”, Master Thesis, National Chiao Tung University, Hsinchu, Taiwan, ROC, 2000
[Mei98] Thomas Meier and King N. Ngan, “Automatic Segmentation of Moving Objects for Video Object Plane Generation”, IEEE Transactions on Circuits and System for Video Technology, VOL.8 NO. 5, pp. 525-538, September 1998
[merl] http://www.merl.com/projects/video-segmentation/
[Mok98] Mokhtarian, F.; Suomela, R, “Robust image corner detection through curvature scale space”, Pattern Analysis and Machine Intelligence, IEEE Transactions on , Volume: 20 Issue: 12 , Page(s): 1376 -1381 , Dec. 1998
[Shi 94] J.Shi and C.Tomasi, “Good Features to Track”, IEEE Conference on Computer Vision and Pattern Recognition, pp.593-600, 1994
[Sim91] E P Simoncelli and E H Adelson and D J Heeger, “Probability distributions of optical flow”, IEEE Conf on Computer Vision and Pattern Recognition, Mauii, Hawaii. June 1991.
[Sti 99] C.Stiller and J.Konrad, “Estimating Motion in Image Sequences”, IEEE Signal Processing Magazine, Vol.16, Issue.4, pp.70-91, July 1999
[Wang 94] John Y. A. Wang and Edward H. Adelson, “Representing Moving Images with Layers”, IEEE Transactions on Image processing, VOL.3 NO. 5, pp. 625-638, September, 1994
[Wys 82] Gunter Wyszecki, W.S. Stiles, “ Color Sciece: Concepts and Methods, Quantitative Data and Formulae”, Johns Wiley & Sons, Inc. 1982
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top