(54.173.237.152) 您好!臺灣時間:2019/02/22 23:10
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:::

我願授權國圖
本論文永久網址: 
line
研究生:陳品樺
研究生(外文):Pin-Hua Chen
論文名稱:利用空間與時間軸小波轉換進行場景變換偵測
論文名稱(外文):Shot change detection using spatio-temporal wavelet transform
指導教授:王元凱王元凱引用關係
指導教授(外文):Yuan-Kai Wang
學位類別:碩士
校院名稱:輔仁大學
系所名稱:電子工程學系
學門:工程學門
學類:電資工程學類
論文出版年:2005
畢業學年度:93
語文別:中文
論文頁數:77
中文關鍵詞:分鏡小波轉換場景變換
外文關鍵詞:shot changewavelet transformspatio-temporal
相關次數:
  • 被引用被引用:0
  • 點閱點閱:452
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出一個以結合空間軸的2D影像小波轉換與時間軸的spatio-temporal wavelet transform (STWT)方法降低移動(motion)在分鏡變換偵測上的影響。本方法分成兩部份:首先,利用以STWT產生符合移動物體在空間與時間軸變化的特徵來偵測移動物體,再以STWT產生的特徵做為Bayes classifier的輸入,把所有畫面進行分鏡或非分鏡畫面的分類,而屬於有motion的畫面在Bayes classifier的規則下會被濾掉,有效的減少motion對分鏡變換偵測的影響,最後由實驗應証了利用空間與時間軸的STWT與Bayes classifier 確實能對分鏡變換偵測在物體移動的影響下有良好的改進。
We propose a novel technique for the suppression of motion effects to shot change detection based upon the integration of spatial domain and temporal domain wavelet transform (STWT). The proposed method consists of two parts. First, based on characteristics of the STWT, spatio-temporal domain structural changes conform to those characteristics of moving objects is considered as moving objects. Second, each frame is classified as a shot change frame or a non-shot change frame by the Bayes classifier in the light of the STWT features. Moreover, the motion effects can be greatly diminished on account of the Bayes decision rule. Experimental results show that the proposed method detects shot changes improvably in the motion case.
目錄
摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 導論 1
1.1 研究背景 1
1.2研究目的與動機 4
1.3國內外研究現況 4
第二章 論文架構 13
2.1特徵分析(Features Analysis) 14
2.2移動影像的建立與特徵統計(Establishing for Moving Image and Effects of Correlation) 15
2.3視訊資料分鏡切割方法 15
第三章 特徵分析 16
3.1彩色模型 16
3.2快速小波轉換原理(FWT) 18
3.2.1一維快速小波轉換(One Dimension Fast Wavelet Transform) 19
3.2.2二維快速小波轉換(Two Dimension Fast Wavelet Transform) 24
3.3 空間與時間軸快速小波轉換(STWT) 27
第四章 移動影像的建立與特徵統計 36
4.1移動影像(Moving Image)的建立 36
4.1.1合成 37
4.1.2 Thresholding 38
4.1.3 Median Filter 39
4.1.4 Morphology 39
4.2統計特徵 41
第五章 視訊資料分割 43
5.1 Thresholding法 43
5.2 Bayes classifier 45
5.3 Shot change frames與Non shot change frames的定義 47
第六章 實驗結果 50
6.1實驗環境 50
6.2實驗方法 55
6.3實驗結果 57
6.3.1 小波轉換基底 58
6.3.2 Bayes classifier參數 61
6.3.3 Bayes classifier對OM與CM的優勢 65
6.4 錯誤情形分析 66
6.4.1 Cut shot change detection的錯誤情形 67
6.4.2 Gradual shot change detection的錯誤情形 69
第七章 結論 72
參考文獻 73



表目錄
表 6- 1:實驗影片資料 50
表 6- 2:Gradual shot change detect結果 63

圖目錄
圖 1- 1:突然式分鏡變換圖例。分鏡變換發生於第4張畫面。 2
圖 1- 2:漸進式分鏡變換圖例。分鏡變換發生於第1~9張畫面。 3
圖 1- 3:利用兩個臨界值來做分鏡偵測 7
圖 1- 4:以2D影像為基礎的視訊分割法。(a) 3D轉2D示意圖 (b)分析結果圖。 9
圖 1- 5:攝影機操作之MVs型態圖。 11
圖 2- 1:鏡變換偵測架構流程圖。 13
圖 3- 1:原始影像轉換彩色模型後取出亮度值之結果圖。(a) 原始影像,(b) HSV Color Model,(c) YUV Color Model。 17
圖3- 2:Ψj,k (x) =Ψ0,0 (x) 訊號。 20
圖3- 3:Ψj,k (x) =Ψ0,2 (x) 訊號。 20
圖3- 4:Ψj,k (x) =Ψ1,0 (x) 訊號 20
圖 3- 5:J Stage多層次解析小波轉換示意圖。 22
圖 3- 6:一維FWT之轉換與反轉換示意圖。 23
圖 3- 7:2D FWT小波轉換示意圖 25
圖 3- 8:影像經過二維FWT的結果。(a) 二維FWT 示意圖,(b) 二維FWT 結果 26
圖 3- 9:2D FWT。(a)原始畫面,(b)將(a)經過DB4 2D FWT。 27
圖 3- 10:DB4 2D FWT實例。(a)原始畫面,(b)HH,(c)HL,(d)LH。 30
圖 3- 11:DB4 STWT實例。 (a)HHH,(b)HHL,(c)HLH,(d)HLL。 32
圖 3- 12:Cut shot change在第j個stage時的Recall rate和Precision rate。(a) Recall rate, (b) Precision rate。 34
圖 3- 13:Gradual shot change在第j個stage時的Recall rate和Precision rate。(a) Recall rate, (b) Precision rate。 34
圖 4- 1:建立移動影像之流程圖。 36
圖 4- 2:由圖3-10(a)所得之HCI圖。 37
圖 4- 3:Thresholding之後的二值化反相結果。 38
圖 4- 4:由二值化影像進行Median Filter後的結果。 39
圖 4- 5:Morphology的結果。 40
圖 4- 6:MI與原始畫面相對應圖。 40
圖 5 - 1:Shot change與No shot change在特徵直方圖上的機率分佈理想圖。 44
圖 6 - 1:12段測試影片的內容。(a) Bebes (b) Flamants (c) Lascaux (d) Nyangatom (e) Waste (f) Golf (g) News1(1) (h) News1(2) (i) News1(3) (j) News2(1) (k) News2(2) (l) News2(3)。 54
圖 6 - 2:訓練資料 值。 (a) (b) (c) (d) 。 56
圖 6 - 3:Cut、Gradual與一般畫面的 在四種小波基底兩兩之間的組合分佈。(a)Xi[D1,D2] (b) Xi[D1,D3] (c) Xi[D1,D4] (d) Xi[D2,D3] (e) Xi[D2,D4] (f) Xi[D3,D4] 59
圖 6 - 4:Cut、Gradual與一般畫面的 在四種小波基底三者之間的組合分佈。(a) Xi[D1,D2,D3] (b) Xi[D1,D2,D4] (c) Xi[D1,D3,D4] (d) Xi[D2,D3,D4] 60
圖 6 - 5:輸入dataT與 值得到的Recall rate 與Precision rate。 61
圖 6 - 6:Cut shot change detect結果。 62
圖 6 - 7: Cut shot change detect結果。(a) Precision rate, (b) Recall rate。 64
圖 6 - 8: Gradual shot change detect結果。(a) Precision rate, (b) Recall rate。 64
圖 6 - 9:Mahalanobis Distance 特性圖 65
圖 6 - 10:Cut分鏡變換偵測的誤判情形。(a) Waste的誤判,(b) Lascaux的誤判,(c) News1(1)的誤判,(d) News2(2)的誤判。 68
圖 6 - 11:Cut分鏡變換偵測的遺漏情形。(a) News2(2)的遺漏,(b) News1(1)的遺漏。 68
圖 6 - 12:Gradual分鏡變換偵測在影片Waste的誤判情形。 69
圖 6 - 13:Gradual分鏡變換偵測的遺漏情形。(a) Flamants的遺漏,截自第970-1017張畫面,(b) Flamants的遺漏,截自第1300-1317張畫面(c) News1(1)的遺漏。 71
參考文獻
[1]S. F. Chang, W. Chen, H. J. Meng, H. Sundaram, D. Zhong, “VideoQ: An automated content based video search system using visual cues,” Proceedings of ACM Multimedia Conference, Seattle, 1997.
[2]W. Niblack, X. Zhu, J. L. Hafner, T. Breuer, D. B. Ponceleon, D. Petkovic, M. D. Filckner, E. Upfal, S. I. Nin, S. Sull, B. E. Dom, B. L. Yeo, S. Srinivasan, D. Zivkovic, M. Penner, “Updates to the QBIC system,” Proceedings of SPIE Storage and Retrieval for Image and Video Databases VI, Vol. 3312, San Jose, CA, pp. 150-161, Jan. 1998.
[3]M. Smith and T. Kanade, “Video skimming and characterization through the combination of image and language understanding,” IEEE International Workshop Content-Based Access of Image and Video Database, Bombay, INDIA, pp. 775, Jan. 1998.
[4]S. Antani, R. Kasturi, and R. Jain, “A survey on the use of pattern recognition methods for abstraction, indexing and retrieval of images and video,” Pattern Recognition, Vol. 35, pp. 945-965, 2002.
[5]M. R. Naphade and T. S. Huang, “A probabilistic framework for semantic video indexing, filtering, and retrieval,” IEEE Transactions on Multimedia, Vol. 3, No. 1, Mar. 2001.
[6]T. Kikukawa and S. Kawafuchi, “Development of an automatic summary editing system for the audio-visual resources,” Transactions on Electronics and Information J75-A, pp. 204-212, 1992.
[7]A. Nagasaka and Y. Tanaka, “Automatic video indexing and full-video search for object appearances,” Proceedings of the IFIP TC2/WG 2.6 Second Working Conference on Visual Database Systems II, pp. 113-127, Oct. 1992.
[8]H. J. Zhang, A. Kankanhalli and S. Smoliar, “Automatic partitioning of full-motion video,” Multimedia Systems, Vol. 1, No. 1, pp. 10-28, Jun. 1993.
[9]W. Xiong, J. C. M. Lee, and M. C. Ip, “Net comparison: a fast and effective method for classifying image sequences,” Proceedings of SPIE Storage and Retrieval for Image and Video Databases III, Vol. 2420, San Jose, CA, pp. 318-328, 1995.
[10]W. Xiong and J. C. -M. Lee, “Efficient scene change detection and camera motion annotation for video classification,” Computer Vision and Image Understanding, Vol. 71, No. 2, pp. 166-181, 1998.
[11]B. Shahraray, “Scene change detection and content-based sampling of video sequences,” In Digital Video Compression: Algorithms and Technologies, Vol. 2419, pp. 2-13, Feb. 1995.
[12]R. Kasturi and R. Jain, “Dynamic vision, in Computer Vision: Principles,” IEEE Computer Society Press, Washingtion DC, pp. 469-480, 1991.
[13]M. J. Swain, “Interactive indexing into image databases,” Proceedings of SPIE Storage and Retrieval in Image and Video Databases, pp. 173-187, 1993.
[14]G. Pass, R. Zabih, “Comparing images using joint histograms,” Multimedia Systems, 1999.
[15]Y. Tonomura, “Video handling based on structured information for hypermedia systems,” Proceedings of ACM Multimedia Conference, pp. 333-344, 1991.
[16]J. S. Boreczky, L. A. Rowe, “Comparison of video shot boundary detection techniques,” Proceedings of SPIE Storage and Retrieval for Image and Video Databases VI, Vol. 2670, pp. 170-179, San Jose, Feb. 1996.
[17]U. Gargi, S. Oswald, D. Kosiba, S. Devadiga, R. Kasturi, “Evaluation of video sequence indexing and hierarchical video indexing,” Proceedings of SPIE Storage and Retrieval for Image and Video Databases, pp. 1522-1530, 1995.
[18]C. -M. Lee and D. M.-C. Ip, “A robust approach for camera break detection in color video sequences,” Proceedings in IAPR Workshop Machine Vision Application, Kawasaki, Japan, pp. 502-505, 1994.
[19]D. Swanberg, C. -F. Shu, and R. Jain, “Knowledge guided parsing in video databases,” Proceedings of SPIE Storage and Retrieval for Image and Video Databases, Vol. 1908, pp. 13-24, 1993.
[20]H. Yu, G. Bozdagi, and S. Harrington, “Feature-based hierarchical video segmentation,” IEEE International Conference on Image Processing, Santa Barbara, pp. 498-501, 1997.
[21]W. A. C. Femando, C. N. Canagarajah, and D. R. Bull, “Scene change detection algorithms for content-based video indexing and retrieval,” IEE Journal of Electronics & Communication Engineering, Vol. 13, No. 3, pp. 117-126, Jun. 2001.
[22]R. Zabih, J. Miler, and K. Mai, “A feature-based algorithm for detecting and classifying production effects,” Multimedia Systems, Vol. 7, No. 2, pp. 119-128, Mar. 1999.
[23]Silvio Jamil Ferzoli Guimarães, Michel Couprie, Arnaldo de Albuquerque Araújo and Neucimar Jerônimo Leite, “Video segmentation based on 2D image analysis,” Pattern Recognition Letters, Vol. 24, No. 7, pp. 947-957, 2003.
[24]F. Arman, A. Hsu, and M-Y Chiu, “Image processing on compressed data for large video databases,” First ACM International Conference on Multimedia, Annaheim, CA, pp. 267-272, Aug. 1993.
[25]U. Gargi, R. Kasturi, and S. Antani, “Performance characterization and comparison of video indexing algorithms,” Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998.
[26]I. Koprinska and S. Carrato, “Detecting and classifying video shot boundaries in MPEG compressed sequences,” Proceeding of the European Signal Processing Conference (EUSIPCO), special session on Multimedia Signal Processing 8-11, Island of Rhodes, Greece, pp. 1729-1732, Sep. 1998.
[27]I. Koprinska and S. Carrato, “Camera operation detection in MPEG video data by means of neural networks,” Proceeding of the COST 254 Workshop on Emerging Technologies for Communication Terminals, pp. 300-304, Toulouse, 1997.
[28]J. Meng, Y. Juan, and S.-F. Chang, “Scene change detection in a MPEG compressed video sequence,” Digital Video Compression: Algorithms and Technologies in SPIE Symposium on Electronic Imaging: Science & Technology, Vol. 2417, San Jose, pp. 14-25, Feb. 1995.
[29]N. V. Patel and I. K. Sethi, “Video shot detection and characterization for video databases,” Pattern Recognition, Vol. 30, No. 4, pp. 583-592, Apr. 1997.
[30]I. K. Sethi and N. V. Patel, “A statistical approach to scene change detection,” Proceedings of SPIE Storage and Retrieval for Image and Video Databases III, Vol. 2420, San Jose, pp. 2-11, 1995.
[31]I. K. Sethi and G. P. R. Sarvarayuda, “Hierarchical classifier design using mutual information,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 4, pp. 441-445, 1982.
[32]C. Taskiran and E. Delp, “Video scene change detection using the generalized sequence trace,” Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seattle, pp. 2961-2964, May 1998.
[33]B. Yeo and B. Liu, “Rapid scene analysis on compressed video,” IEEE Transactions on Circuits & Systems for Video Technology, Vol. 5, No. 6, pp. 533-544, 1995.
[34]H. J. Zhang, C. Y. Low, Y. H. Gong, and S. W. Smoliar, “Video parsing using compressed data,” Proceedings of IS&T/SPIE Conference on Image and Video Processing II, Bellingham, Wash, pp. 142-149, 1994.
[35]H. J. Zhang, C. Y. Low, and S. W. Smoliar, “Video parsing and browsing using compressed data,” Multimedia Tools and Applications, Kluwer Academic Publishers, Vol. 1, No. 1, pp. 89-111, Mar. 1995.
[36]A. Hampapur, R. Jain, and T. E. Weymouth, “Production model based digital video segmentation,” Multimedia Tools and Applications, Vol. 1, No. 1, pp. 9-46, 1995.
[37]J. S. Boreczky and L. D. Wilcox, “A hidden Markov model framework for video segmentation using audio and image features,” Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, Vol. 6, pp. 3741-3744, May 1998.
[38]A. Akustsu, Y. Tonomura, H. Hashimoto, Y. Ohba, “Video indexing using motion vectors,” Proceedings of SPIE: Visual Communications and Image Processing, Vol. 1818, pp. 1522-1530, Nov. 1992.
[39]B. Gunsel, A. M. Ferman, A. M. Tekalp, “Temporal video segmentation using unsupervised clustering and semantic object tracking,” Journal of Electronic Imaging, Vol. 7, No. 3, pp. 592-604, Jul. 1998.
[40]T. N. Pappas, “An adaptive clustering algorithm for image segmentation,” IEEE Transactions on Signal Processing, Vol. 40, No. 4, pp. 901-914, Apr. 1992.
[41]A. M. Ferman and A. M. Tekalp, “Efficient filtering and clustering for temporal video segmentation and visual summarization,” Journal of Visual Communication and Image Representation, Vol. 9, No. 4, pp. 336-351, Dec. 1998.
[42]S. Mallat, “A theory for multiresolution signal decomposition: The Wavelet representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 7, pp. 617-643, Jul. 1989.
[43]L. Zhang and P. Bao, “Edge detection by scale multiplication in wavelet domain,” Pattern Recognition Letters, Vol. 23, No. 14, pp. 1771-1784, Dec. 2002.
[44]S. G. Chang, B. Yu, M. Vetterli, “Adaptive wavelet thresholding for image denoising and compression,” IEEE Transactions on Image Processing, Vol. 9, No. 9, Sep. 2000.
[45]Y. K. Wang and P. H. Chen, “Shot change detection using temporal wavelet transform,” Proceedings of IPPR Conference on CVGIP’ 2004, Hwa Leing, Taiwan, R. O. C., pp. 71, 2004.
[46]Y. K. Wang and S. H. Chen, “A robust vehicle detection approach,” Proceedings of IPPR Conference on CVGIP’ 2004, Hwa Leing, Taiwan, R. O. C., pp. 46, 2004.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
1. 36. 傅朝卿〈2002〉。世界人文文化遺產概論:聯合國教科文組織世界文化遺產之概念-保存與維護概念。臺南市文化資產保護協會會刊,7,1-8。
2. 18. 林會承〈2002〉。文資無罪分類有理-現行文化資產保存法分類體系之檢討。文化視窗,37。
3. 18. 林會承〈2002〉。文資無罪分類有理-現行文化資產保存法分類體系之檢討。文化視窗,37。
4. 12. 方鳳玉、邱上嘉〈2003〉。從虛擬空間的概念探討歷史性建築之保存。設計研究,3,33-46。
5. 12. 方鳳玉、邱上嘉〈2003〉。從虛擬空間的概念探討歷史性建築之保存。設計研究,3,33-46。
6. 36. 傅朝卿〈2002〉。世界人文文化遺產概論:聯合國教科文組織世界文化遺產之概念-保存與維護概念。臺南市文化資產保護協會會刊,7,1-8。
7. 38. 張家甄〈2004〉。台灣古蹟及歷史建築再利用之探討。建築師,五月,70-79。
8. 38. 張家甄〈2004〉。台灣古蹟及歷史建築再利用之探討。建築師,五月,70-79。
9. 43. 薛琴〈1998〉。台灣都市保存與都市發展的衝突─法規、制度與民意覺醒。住都雙月刊,132,27-34。
10. 43. 薛琴〈1998〉。台灣都市保存與都市發展的衝突─法規、制度與民意覺醒。住都雙月刊,132,27-34。
11. 44. 薛琴〈2000〉。古蹟保存與歷史空間保存活用。宜蘭文獻雜誌,39,13-19。
12. 44. 薛琴〈2000〉。古蹟保存與歷史空間保存活用。宜蘭文獻雜誌,39,13-19。
 
系統版面圖檔 系統版面圖檔