請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/53708
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 盧奕璋(Yi-Chang Lu) | |
dc.contributor.author | Ching-Fan Chiang | en |
dc.contributor.author | 江擎帆 | zh_TW |
dc.date.accessioned | 2021-06-16T02:28:02Z | - |
dc.date.available | 2020-09-02 | |
dc.date.copyright | 2015-09-02 | |
dc.date.issued | 2015 | |
dc.date.submitted | 2015-08-03 | |
dc.identifier.citation | [1] 施尚融. (2006) 高速攝影系統介紹與應用. 車輛測試資訊. 2-9. [2] R. C. Gonzalez and R. E. Woods, Digital Image Processing, second ed. Massachusetts: Addison-Wesley Publishing, 1987. [3] Museumof Broadcast Communication: Encyclopedia of Television. Available: http://www.museum.tv/archives/etv/C/htmlC/colorization/colorization.htm [4] A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salesin, 'Image analogies,' presented at the Proceedings of the 28th annual conference on Computer graphics and interactive techniques, 2001. [5] E. Reinhard, M. Adhikhmin, B. Gooch, and P. Shirley, 'Color transfer between images,' Computer Graphics and Applications, IEEE, vol. 21, pp. 34-41, 2001. [6] I. Kompatsiaris and M. Gerassimos Strintz, 'Spatiotemporal segmentation and tracking of objects for visualization of videoconference image sequences,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 10, pp. 1388-1402, 2000. [7] T. Welsh, M. Ashikhmin, and K. Mueller, 'Transferring color to greyscale images,' ACM Trans. Graph., vol. 21, pp. 277-280, 2002. [8] A. Levin, D. Lischinski, and Y. Weiss, 'Colorization using optimization,' presented at the ACM SIGGRAPH 2004 Papers, Los Angeles, California, 2004. [9] D. Nie, Q. Ma, L. Ma, and S. Xiao, 'Optimization based grayscale image colorization,' Pattern Recogn. Lett., vol. 28, pp. 1445-1451, 2007. [10] R. Irony, D. Cohen-Or, and D. Lischinski, 'Colorization by example,' presented at the Proceedings of the Sixteenth Eurographics conference on Rendering Techniques, Konstanz, Germany, 2005. [11] L. Yatziv and G. Sapiro, 'Fast image and video colorization using chrominance blending,' Image Processing, IEEE Transactions on, vol. 15, pp. 1120-1129, 2006. [12] Q. Luan, F. Wen, D. Cohen-Or, L. Liang, Y.-Q. Xu, and H.-Y. Shum, 'Natural image colorization,' presented at the Proceedings of the 18th Eurographics conference on Rendering Techniques, Grenoble, France, 2007. [13] X. Liu, L. Wan, Y. Qu, T.-T. Wong, S. Lin, C.-S. Leung, et al., 'Intrinsic colorization,' ACM Trans. Graph., vol. 27, pp. 1-9, 2008. [14] G. Charpiat, M. Hofmann, and B. Schölkopf, 'Automatic Image Colorization via Multimodal Predictions,' in European Conf. on Computer Vision (ECCV), 2008, pp. 126-139. [15] J. Li, P. Hao, and C. Zhang, 'Transferring Colours to Grayscale Images by Locally Linear Embedding,' in British Machine Vision Conf.(BMVC), 2008. [16] Y. Morimoto, Y. Taguchi, and T. Naemura, 'Automatic colorization of grayscale images using multiple images on the web,' presented at the SIGGRAPH '09: Posters, New Orleans, Louisiana, 2009. [17] S. Liu and X. Zhang, 'Automatic grayscale image colorization using histogram regression,' Pattern Recognition Letters, vol. 33, pp. 1673-1681, 10/1/ 2012. [18] H. Yong Seok, L. Kyoung-Mu, and L. Sang-Uk, 'Robust Stereo Matching Using Adaptive Normalized Cross-Correlation,' Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 33, pp. 807-822, 2011. [19] M. J. Hannah, 'Digital Stereo Image Matching Techniques ' International Archives of Photogrammetry and Remote Sensing, vol. 27, pp. 280-293. [20] R. Zabih and J. Woodfill, 'Non-parametric Local Transforms for Computing Visual Correspondence,' ECCV, pp. 151-158, 2004. [21] J. Banks, M. Bennamoun, and P. Corke, 'Non-parametric techniques for fast and robust stereo matching,' in TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications., Proceedings of IEEE, 1997, pp. 365-368 vol.1. [22] L. Renxiang, Z. Bing, and M. L. Liou, 'A new three-step search algorithm for block motion estimation,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 4, pp. 438-442, 1994. [23] P. Lai-Man and M. Wing-Chung, 'A novel four-step search algorithm for fast block motion estimation,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 6, pp. 313-317, 1996. [24] Z. Shan and M. Kai-Kuang, 'A new diamond search algorithm for fast block matching motion estimation,' in Information, Communications and Signal Processing, 1997. ICICS., Proceedings of 1997 International Conference on, 1997, pp. 292-296 vol.1. [25] Z. Ce, L. Xiao, and L. P. Chau, 'Hexagon-based search pattern for fast block motion estimation,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 12, pp. 349-355, 2002. [26] M. Ghanbari, 'The cross-search algorithm for motion estimation [image coding],' Communications, IEEE Transactions on, vol. 38, pp. 950-953, 1990. [27] C. Mei-Juan, C. Liang-Gee, and C. Tzi-Dar, 'One-dimensional full search motion estimation algorithm for video coding,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 4, pp. 504-509, 1994. [28] Y. Nie and M. Kai-Kuang, 'Adaptive rood pattern search for fast block-matching motion estimation,' Image Processing, IEEE Transactions on, vol. 11, pp. 1442-1449, 2002. [29] T. Wiegand, G. J. Sullivan, G. Bjontegaard, and A. Luthra, 'Overview of the H.264/AVC video coding standard,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 13, pp. 560-576, 2003. [30] C. Shao-Yi, H. Yu-Wen, H. Bing-Yu, M. Shyh-Yih, and C. Liang-Gee, 'Fast video segmentation algorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques,' Multimedia, IEEE Transactions on, vol. 6, pp. 732-748, 2004. [31] T. Meier and K. N. Ngan, 'Automatic segmentation of moving objects for video object plane generation,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 8, pp. 525-538, 1998. [32] T. Meier and K. N. Ngan, 'Video segmentation for content-based coding,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 9, pp. 1190-1203, 1999. [33] W. Demin, 'Unsupervised video segmentation based on watersheds and temporal tracking,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 8, pp. 539-546, 1998. [34] K. Munchurl, C. Jae Gark, K. Daehee, L. Hyung, L. Myoung-Ho, C. Ahn, et al., 'A VOP generation tool: automatic segmentation of moving objects in image sequences based on spatio-temporal information,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 9, pp. 1216-1226, 1999. [35] G. Ju, K. JongWon, and C. C. J. Kuo, 'Fast video object segmentation using affine motion and gradient-based color clustering,' in Multimedia Signal Processing, 1998 IEEE Second Workshop on, 1998, pp. 486-491. [36] R. Mech and M. Wollborn, 'A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera,' Signal Processing, vol. 66, 1998. [37] Z. Zhengyou, 'Flexible camera calibration by viewing a plane from unknown orientations,' in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, 1999, pp. 666-673 vol.1. [38] M. Warren, D. McKinnon, and B. Upcroft, 'Online Calibration of Stereo Rigs for Long-Term Autonomy,' presented at the International Conference on Robotics and Automation, Karlsruhe, Germany, 2013. [39] Y. Ma, J. Kosecka, S. Soatto, and S. Sastry, 'Image Formation'in An Invitation to 3-D Vision: From Images to Geometric Models, 1 ed., 2003. [40] Coarse-to-fine (CTF) stereo with accurate 3D boundaries. Available: http://www.cse.yorku.ca/~sizints/ctf_stereo/ctf_stereo_main.html [41] D. Scharstein, R. Szeliski, and R. Zabih, 'A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,' in Stereo and Multi-Baseline Vision, 2001. (SMBV 2001). Proceedings. IEEE Workshop on, 2001, pp. 131-140. [42] B. H. Friemel, L. N. Bohs, and G. E. Trahey, 'Relative performance of two-dimensional speckle-tracking techniques: normalized correlation, non-normalized correlation and sum-absolute-difference,' in Ultrasonics Symposium, 1995. Proceedings., 1995 IEEE, 1995, pp. 1481-1484 vol.2. [43] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision: Addison-Wesley Longman Publishing Co., Inc., 1992. [44] D. Scharstein and R. Szeliski, 'High-accuracy stereo depth maps using structured light,' in Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, 2003, pp. I-195-I-202 vol.1. [45] D. Scharstein and R. Szeliski, 'A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,' International Journal of Computer Vision, vol. 47, pp. 7-42, 2002/04/01 2002. [46] C. Ttofis and T. Theocharides, 'Towards accurate hardware stereo correspondence: A real-time FPGA implementation of a segmentation-based adaptive support weight algorithm,' in Design, Automation Test in Europe Conference Exhibition (DATE), 2012, 2012, pp. 703-708. [47] H. Chaur-Heh and T. P. Lin, 'VLSI architecture for block-matching motion estimation algorithm,' Circuits and Systems for Video Technology, IEEE Transactions on, vol. 2, pp. 169-175, 1992. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/53708 | - |
dc.description.abstract | 彩色高幀率攝影機的價格相對昂貴,且需要大量記憶空間儲存每秒所得的資訊,而單色之高幀率攝影機價格較低,又只有單色的資料需要儲存。如果可以將灰階之高幀率影像進行塗色,如此便可得到彩色高幀率視訊之效果,同時減少影像系統的資料傳輸量。而灰階影像著色一直是一門很重要的領域,改善影像著色品質的方法不斷被提出,但是其往往有所限制,例如是否可自動化,顏色是否準確等等的問題。 我們提出一個單色高幀率攝影彩色化系統,在單色高幀率攝影機之兩側各加上一部低幀率彩色攝影機,透過外部觸發控制三部攝影機的取像時間。低幀率彩色攝影機雖然每秒張數少,但是毎固定間隔時間可以提供單色高幀率攝影機色彩的資訊,再利用立體視覺比對,以及運動估測演算法,提出的系統可以將單色高幀率影像彩色化予以實現,這個過程是完全自動化的,而且保留了原本顏色的真實性。 最後,由於立體視覺上色與運動估測上色是相當耗時的演算法,再加上一次處理非常多的影像,整體運算量相當大,因此我們實作於硬體,硬體部分分成兩個部分,第一個部分是立體視覺比對上色硬體,上色一張影像可於22.5 ms完成,與軟體相比,加速可達 105 倍,以 TSMC90 nm製程實現,晶片尺寸為4.73 mm2 ,核心尺寸為2.94 mm2,運作頻率設計最高為100 MHz,功率消耗為327.6 mW 。第二部分是運動估測上色硬體,上色一張影像可於130ms完成,以 TSMC90 nm製程實現,晶片尺寸為1.18 mm2,核心尺寸為0.43mm2,運作頻率設計最高為100 MHz,功率消耗為13.45 mW 。 | zh_TW |
dc.description.abstract | The price of high-frame rate color cameras is relatively expensive, and it needs plenty of memory space to store captured video information. If we can generate highframe rate color video by colorizing high-frame rate monochrome video, the total cost can be greatly reduced.
We propose a high-frame rate monochrome video colorization system which is composed of one high-frame rate monochrome camera and two low-frame rate color cameras, and these three cameras are synchronized by a common external trigger signal. Although low-frame rate cameras have less information per second, it provides the color clue for the high-frame rate monochrome camera. With stereo matching and motion estimation algorithms, colorization of high-frame rate monochrome video can be realized using the proposed system. This process can be fully automated and the color quality is high. In this thesis, we implement the hardware of a stereo matching algorithm and a motion estimation algorithm to reduce the processing time. The entire process of stereo matching can be completed in 22.5 ms. Compared to software results, 105X speed-up can be achieved.The chip is implemented using TSMC 90 nm cell library.The chip area is 4.73 mm2 , and the core area is 2.94 mm2. The chip consumes 327.6 mW when operating at 100 MHz. On the other hand, the entire process of a motion estimation algorithm can be completed in 130 ms. The chip is implemented using TSMC90 nm cell library. The chip area is 1.18 mm2, and the core area is 0.43 mm. The chip consumes 13.45 mW when operating at 100 MHz. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T02:28:02Z (GMT). No. of bitstreams: 1 ntu-104-R01943001-1.pdf: 9334422 bytes, checksum: cbb5654124012f03ad7230630d011dc2 (MD5) Previous issue date: 2015 | en |
dc.description.tableofcontents | 口試委員會審定書 # 誌謝 I 中文摘要 II ABSTRACT III 目錄 IV 圖目錄 VIII 表目錄 XII Chapter 1 緒論 1 1.1 灰階影像上色技術簡介 1 1.2 立體比對法介紹 3 1.3 運動估測演算法介紹 3 1.4 視訊動態物體分群演算法介紹 5 1.5 章節概要 6 Chapter 2 高幀率單色視訊彩色化技術 7 2.1 系統整體架構 7 2.1.1 系統架設與傳輸協定 7 2.1.2 實驗資料拍攝方法 7 2.1.3 系統流程圖 8 2.2 影像前處理 9 2.2.1 未經校正的影像 9 2.2.2 相機校正 10 2.2.3 影像校正 12 2.2.4 顏色轉換 13 2.3 遮蔽區域分析 14 2.4 立體視覺匹配演算法 15 2.4.1 明亮度調整 15 2.4.2 區域性比對方法 15 2.5 適合上色使用的運動估測演算法 17 2.5.1 三步驟搜尋 19 2.5.2 四步驟搜尋 19 2.5.3 鑽石型搜尋 20 2.5.4 結合運動向量預測的鑽石型搜尋法 21 2.5.5 適合用於上色使用的運動估測法 22 2.5.6 計算目標函數的方法 22 2.6 視訊動態物體分群技術 23 2.6.1 上色之應用 23 2.6.2 視訊動態物體分群演算法 24 Chapter 3 實驗結果 27 3.1 校正的場景資料 27 3.1.1 立體視覺上色結果 27 3.1.2 適合上色使用的運動估測法上色結果 30 3.2 真實場景資料 32 3.2.1 不會形變的單一動態物體 32 3.2.2 會形變的單一動態物體 36 3.2.3 多重動態物體 37 3.3 結合動態物體分群的運動估測上色法 39 3.4 與內插方法比較 42 Chapter 4 硬體架構設計 45 4.1 整體架構 45 4.1.1 立體視覺上色之硬體架構 45 4.1.2 運動估測上色之硬體架構 46 4.2 立體視覺上色之硬體設計 47 4.2.1 資料讀入順序 47 4.2.2 目標函數計算 51 4.2.3 循環移位 52 4.2.4 絕對誤差和計算器與最佳匹配選擇器 53 4.3 立體視覺硬體模擬結果 54 4.3.1 軟體與硬體之結果比較 54 4.3.2 硬體規格與效能 55 4.4 運動估測之硬體設計 57 4.4.1 資料讀入與模組設計 57 4.4.2 目標顏色移位暫存以及最佳匹配選擇器 62 4.5 運動估測硬體模擬結果 64 4.5.1 軟體與硬體之結果比較 64 4.5.2 硬體規格與效能 65 Chapter 5 結論與未來展望 68 5.1 結論 68 5.2 展望 68 參考文獻 69 | |
dc.language.iso | zh-TW | |
dc.title | 利用同步低幀率彩色資料之高幀率單色視訊彩色化技術 | zh_TW |
dc.title | Colorization of High-Frame-Rate Monochrome Videos Using Synchronized Low-Frame-Rate Color Data | en |
dc.type | Thesis | |
dc.date.schoolyear | 103-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 王傑智(CC Wang),李佳翰,丁建均(Jian-Jiun Ding) | |
dc.subject.keyword | 高幀率影像,多相機系統,彩色化,立體視覺,運動估測, | zh_TW |
dc.subject.keyword | High-frame rate video,multiple camera system,colorization,stereo matching,motion estimation, | en |
dc.relation.page | 72 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2015-08-03 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-104-1.pdf 目前未授權公開取用 | 9.12 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。