Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66028Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 傅楸善 | |
| dc.contributor.author | Chih-Chun Lee | en |
| dc.contributor.author | 李知駿 | zh_TW |
| dc.date.accessioned | 2021-06-17T00:19:29Z | - |
| dc.date.available | 2017-07-16 | |
| dc.date.copyright | 2012-07-16 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-06-26 | |
| dc.identifier.citation | REFERENCE
[1] Exposureguide.com, “Focusing Basics,” http://www.exposureguide.com/focusing-basics.htm, 2012. [2] Film Alley, “What Is Single CCD and 3-CCD System,” http://www.filmalley.com/articles/1ccd%20vs%203ccd/, 2004. [3] G. Ward. “Fast, robust image registration for compositing high dynamic range photographs from handheld exposures,” Journal of Graphics Tools, vol. 8, no. 2, pp. 17-30, 2004. [4] K. Jacobs, C. Loscos, and G.Ward. “Automatic high-dynamic range image generation for dynamic scenes,” IEEE Computer Graphics and Applications, vol. 28, no. 2, pp. 84–93, 2008. [5] M. Aggarwal and N. Ahuja. “Split Aperture Imaging for High Dynamic Range,” International Journal of Computer Vision, vol. 58, pp. 7-17, 2004. [6] M. D. Grossberg and S. K. Nayer. “Determining the Camera Response from Image: What Is Knowable?,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 11, pp. 1455-1467, 2003. [7] N. Ostu. “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, pp. 62-66, Jan. 1979. [8] P. E. Debevec and J. Malik, “Recovering High Dynamic Range Radiance Maps from Photographs,” Proceeding of ACM SIGGRAPH, Los Angeles, pp. 369-378, 1997. [9] P. Burt and T. Adelson, “The Laplacian Pyramid as a Compact Image Code,” IEEE Transaction on Communication, vol. 31, no. 4, pp. 532–540, Apr. 1983. [10] S. Paris and F. Durand. “A Fast Approximation of The Bilateral Filter Using a Signal Processing Approach,” ECCV, 2006. [11] S. P. Tang, “Image Sensors (CCD and CMOS),” http://kcs.kcjh.ptc.edu.tw/~spt/computer/digital-image/CCD-CMOS.htm, 2012. [12] Shree K. Nayar, “Computer Vision Laboratory,” http://www1.cs.columbia.edu/CAVE/projects/rad_cal/images/dorfDiagram.jpg [13] T. Mertens, J. Kautz, and F. V. Reeth, “Exposure Fusion,” Conputer Graphics Forum, vol. 28, no. 1, pp. 161-171, 2009. [14] W. C. Kao, C. C. Hsu, L. Y. Chen, C. C. Kao, and S. H. Chen, “Integrating Image Fusion and Motion Stabilization for Capturing Still Images in High Dynamic Range Scenes,” IEEE Transaction Consumer Electronics, vol. 52, no. 3, pp. 735-741, 2006. [15] W. Zhang and W. K, Cham, “Gradient-Directed Composition of Multi-Exposure Images,” Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, pp. 530-536, 2010. [16] Wikipedia, “Dynamic Range,” http://en.wikipedia.org/wiki/Dynamic_range, 2012. [17] Wikipedia, “Color Filter Array,” http://en.wikipedia.org/wiki/Color_filter_array, 2012. [18] Wikipedia, “Exposure (Photography),” http://en.wikipedia.org/wiki/Exposure_(photography), 2012. [19] Wikipedia, “Aperture,” http://en.wikipedia.org/wiki/Aperture, 2012. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66028 | - |
| dc.description.abstract | 在相關的研究中，大多數的演算法藉由融合數張不同曝光的影像來生成高動態範圍影像。在本論文中，我們提出一個藉由融合長短曝光原始影像來生成高動態範圍影像的影像融合流程。有些演算法只用兩張曝光照片來產生高動態範圍影像時會出現瑕疵，我們的方法利用原始影像的特性來克服這樣瑕疵。藉由數個特性的測量像是亮度、對比和飽和度，我們測量出權重圖，然後使用多解析度混和技術融合這兩張原始影像來生成一個無縫隙的高動態範圍影像。我們也加入了影像對齊和鬼影消除的演算法來處理震動的問題和移動物體，使得最後的融合結果看起來很乾淨。 | zh_TW |
| dc.description.abstract | In related work, most algorithms generate high dynamic range image by fusing several differently exposed images. In this paper, we propose an image fusion pipeline that generates a high dynamic range image by fusing long- and short-exposure raw images. Some algorithms generating high dynamic range image with two exposure images may incur artifacts. Our method uses the property of raw image to overcome the artifact. By performing several quality measures such as brightness, contrast, and saturation, we estimate a weighting map, and then fuse the two raw images by multi-resolution blending technique to generate seamless high dynamic range image. We also combine the image alignment and ghost removal algorithm to deal with vibration problem and moving objects and make the fusion result clearer and better. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T00:19:29Z (GMT). No. of bitstreams: 1 ntu-101-R99922115-1.pdf: 3937292 bytes, checksum: 84b2906640ff2bfb10eea4adc9b900b4 (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | CONTENTS
口試委員會審定書 i 誌謝 ii 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES vii Chapter 1 Introduction 1 1.1 Raw Image 2 1.2 Exposure 5 1.2.1 Shutter Speed 6 1.2.2 Aperture 7 1.2.3 ISO Speed 8 1.3 Thesis Framework 9 Chapter 2 Related Works 10 2.1 Recovering the Radiance Map 12 2.2 Exposure Fusion 17 2.3 Gradient-Directed Multi-Exposure Composition 22 Chapter 3 Background 29 3.1 Image Alignment 29 3.2 Ghost Removal 33 Chapter 4 Our Method 36 4.1 Overview 36 4.2 Choose Exposure Images 37 4.3 Image Fusion 39 Chapter 5 Experimental Results 42 Chapter 6 Conclusion and Future Work 53 REFERENCE 54 | |
| dc.language.iso | en | |
| dc.subject | 影像融合 | zh_TW |
| dc.subject | 高動態範圍 | zh_TW |
| dc.subject | image fusion | en |
| dc.subject | high dynamic range | en |
| dc.title | 使用長短曝光照片合成高動態範圍影像 | zh_TW |
| dc.title | High Dynamic Range Image with Two Exposures | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李傑仁,林合泉 | |
| dc.subject.keyword | 高動態範圍,影像融合, | zh_TW |
| dc.subject.keyword | high dynamic range,image fusion, | en |
| dc.relation.page | 56 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2012-06-27 | |
| 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 |
| Appears in Collections: | 資訊工程學系 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-101-1.pdf Restricted Access | 3.85 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.