跳到主要內容

臺灣博碩士論文加值系統

(100.28.2.72) 您好!臺灣時間:2024/06/16 08:59
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
: 
twitterline
研究生:卓柏揚
論文名稱:結合光學變焦與立體視覺進行視差運算
指導教授:林惠勇
指導教授(外文):LIN,HUEI-YUNG
口試委員:林文杰林維暘林惠勇王傑智吳俊霖
口試委員(外文):LIN,WEN-CHIEHLIN,WEI-YANGLIN,HUEI-YUNGWANG,CHIEH-CHIHWU,JIUNN-LIN
口試日期:2019-07-30
學位類別:碩士
校院名稱:國立中正大學
系所名稱:電機工程研究所
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:2019
畢業學年度:107
語文別:中文
論文頁數:75
中文關鍵詞:立體視覺光學變焦變焦影像
外文關鍵詞:Stereo VisionOptical ZoomZoom Image
相關次數:
  • 被引用被引用:0
  • 點閱點閱:161
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在現實中,立體視覺的應用範圍十分廣泛,從最基礎的深度感知
到後續的三維模型重建與地形重建。立體視覺這領域可以說是一個相
當成熟的項目,近幾年來,相關學者們的研究方向幾乎都是將立體視
覺中基礎的視覺資訊(影像) 與其他資訊做疊加的動作,例如更多組的
立體視覺系統或先使用其他架構從影像分析出法向量後再進行擬合,
或者嘗試在影像中萃取更多的資訊(多尺度與複數遮罩),上述方法相
對於新穎的機器學習,都可以算是傳統作法,在本研究中,將嘗試如
何將光學變焦影像與立體視覺融合。在建構的過程中將由系統的最前
端開始,先進行影像預處理將所需要的資料進行提取動作,並且為了
讓光學變焦影像與立體視覺融合需要將兩者之間的關係完整建立,並
針對這個關係來設計的代價方程式。最後在評估系統的部分使用了
Middlebury 立體視覺資料集來進行,需要注意的是此資料集僅提供單
個焦距的立體視覺影像對,所以在這部份是使用數位變焦的方式來進
行變焦影像合成,在光學變焦的部份建立了一個新的資料及來供測試
使用。
In daily life, stereo vision has a wide range of applications, from the most basic depth perception to subsequent 3D model reconstruction and terrain
reconstruction. The field of stereo vision can be said to be a fairly mature research topic. In recent years, the research direction is almost of superimposing visual information (images) based on stereo vision with other information, like a multi-baseline system or a different architecture to analyze the normal vector from the image before fitting it, or trying to extract more information (multi-scale and multi-mask) in the image.
The above method can be regarded as a traditional method compared to novel machine learning. In this study, we will integrate optical zoom images with stereo vision. In the process of construction, we start from the front end of the system, first perform image pre-processing to extract the data, and in order to integrate the optical zoom image with stereo vision, we need to establish the relationship between the two, and design our cost equation for this relationship. Finally, we used Middlebury stereo daataset to evaluate our system. It should be noted that this dataset only provides stereoscopic image pairs with a single focal length, so in this part we use digital zoom to synthesize images. It means that this method can only test our system architecture and cost. In the optical zoom part, we have built a new dataset to test our framework.
1 緒論1
1.1 研究動機. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 相關研究與應用. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2.1 基礎立體視覺演算法. . . . . . . . . . . . . . . . . . . . . . . 2
1.2.2 立體視覺演算法的其他增進手法. . . . . . . . . . . . . . . . 2
1.3 研究架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2 背景知識5
2.1 數位變焦與光學變焦. . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.3 相機校正. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.4 立體視覺. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.4.1 Block matching 與Semi-global matching . . . . . . . . . . . . . 11
2.4.2 MC-CNN fast model . . . . . . . . . . . . . . . . . . . . . . . . 13
3 架構流程15
3.1 架構概述. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.2 影像前處理. . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . 16
3.2.1 影像校正. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.2.2 視差置信度. . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3.2.3 視差候選點. . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.3 匹配點搜尋. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
3.3.1 對極幾何. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
3.3.2 單應性矩陣. . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.3 變焦校正. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
3.4 代價擬合. . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . 30
3.4.1 遮罩選擇. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
3.4.2 擬合方法. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
v
4 實驗結果37
4.1 實驗參數設置與評估方式說明. . . . . . . . . . . . . . . . . . . . . . 38
4.2 Middlebury 實驗結果. . . . . . . . . . . . . . . . . . . . . . . . . 39
4.3 實際影像實驗結果. . . . . . . . . . . . . . . .. . . . . . . . . . . . 43
5 結論與未來展望49
參考文獻51
Appendix 56
[1] K. Takita, M. A. Muquit, T. Aoki, and T. Higuchi, “A sub-pixel correspondence
search technique for computer vision applications,” IEICE transactions on fundamentals
of electronics, communications and computer sciences, vol. 87, no. 8, pp.
1913–1923, 2004.
[2] I. Haller and S. Nedevschi, “Design of interpolation functions for subpixel-accuracy
stereo-vision systems,” IEEE Transactions on image processing, vol. 21, no. 2, pp.
889–898, 2011.
[3] R. Hamzah, A. Kadmin, S. Ghani, M. Hamid, and S. Salam, “Disparity refinement
process based on ransac plane fitting for machine vision applications,” Journal of
Fundamental and Applied Sciences, vol. 9, no. 4S, pp. 226–237, 2017.
[4] H. Hirschmuller, “Stereo processing by semiglobal matching and mutual information,”
IEEE Transactions on pattern analysis and machine intelligence, vol. 30, no. 2,
pp. 328–341, 2008.
[5] J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,”
IEEE Transactions on Pattern Analysis & Machine Intelligence, no. 7, pp. 787–800,
2003.
[6] N. Mayer, E. Ilg, P. Hausser, P. Fischer, D. Cremers, A. Dosovitskiy, and T. Brox,
“A large dataset to train convolutional networks for disparity, optical flow, and scene
flow estimation,” in Proceedings of the IEEE Conference on Computer Vision and
Pattern Recognition, 2016, pp. 4040–4048.

[7] J.-R. Chang and Y.-S. Chen, “Pyramid stereo matching network,” in Proceedings of
the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5410–
5418.
[8] H. Haim, S. Elmalem, R. Giryes, A. M. Bronstein, and E. Marom, “Depth estimation
from a single image using deep learned phase coded mask,” IEEE Transactions on
Computational Imaging, vol. 4, no. 3, pp. 298–310, 2018.
[9] J. Zbontar and Y. LeCun, “Stereo matching by training a convolutional neural
network to compare image patches,” CoRR, vol. abs/1510.05970, 2015. [Online].
Available: http://arxiv.org/abs/1510.05970
[10] C. Godard, O. Mac Aodha, and G. J. Brostow, “Unsupervised monocular depth estimation
with left-right consistency,” in Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition, 2017, pp. 270–279.
[11] R. Garg, V. K. BG, G. Carneiro, and I. Reid, “Unsupervised cnn for single view depth
estimation: Geometry to the rescue,” in European Conference on Computer Vision.
Springer, 2016, pp. 740–756.
[12] M. Okutomi and T. Kanade, “A multiple-baseline stereo,” IEEE Transactions on
pattern analysis and machine intelligence, vol. 15, no. 4, pp. 353–363, 1993.
[13] S. Roy and I. J. Cox, “A maximum-flow formulation of the n-camera stereo correspondence
problem,” in Computer Vision, 1998. Sixth International Conference on.
IEEE, 1998, pp. 492–499.
[14] A. Buades and G. Facciolo, “Reliable multiscale and multiwindow stereo matching,”
SIAM Journal on Imaging Sciences, vol. 8, no. 2, pp. 888–915, 2015.
[15] K.-R. Kim and C.-S. Kim, “Adaptive smoothness constraints for efficient stereo
matching using texture and edge information,” in Image Processing (ICIP), 2016
IEEE International Conference on. IEEE, 2016, pp. 3429–3433.

[16] S. Zhang, W. Xie, G. Zhang, H. Bao, and M. Kaess, “Robust stereo matching with
surface normal prediction,” in Robotics and Automation (ICRA), 2017 IEEE International
Conference on. IEEE, 2017, pp. 2540–2547.
[17] D. Scharstein, T. Taniai, and S. N. Sinha, “Semi-global stereo matching with surface
orientation priors,” in 2017 International Conference on 3D Vision (3DV). IEEE,
2017, pp. 215–224.
[18] K. Batsos, C. Cai, and P. Mordohai, “Cbmv: A coalesced bidirectional matching volume
for disparity estimation,” in Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition, 2018, pp. 2060–2069.
[19] H.-Y. Lai, Y.-H. Tsai, and W.-C. Chiu, “Bridging stereo matching and optical flow
via spatiotemporal correspondence.”
[20] Q. Chang and T. Maruyama, “Real-time stereo vision system: a multi-block matching
on gpu,” IEEE Access, vol. 6, pp. 42 030–42 046, 2018.
[21] M. K.-p. Ng, H. Shen, S. Chaudhuri, and A. C. Yau, “Zoom-based super-resolution
reconstruction approach using prior total variation,” Optical Engineering, vol. 46,
no. 12, p. 127003, 2007.
[22] M. Mostajabi, P. Yadollahpour, and G. Shakhnarovich, “Feedforward semantic segmentation
with zoom-out features,” in Proceedings of the IEEE conference on computer
vision and pattern recognition, 2015, pp. 3376–3385.
[23] M. Gao, R. Yu, A. Li, V. I. Morariu, and L. S. Davis, “Dynamic zoom-in network
for fast object detection in large images,” in Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, 2018, pp. 6926–6935.
[24] H. Li, Y. Liu, W. Ouyang, and X. Wang, “Zoom out-and-in network with map attention
decision for region proposal and object detection,” International Journal of
Computer Vision, vol. 127, no. 3, pp. 225–238, 2019.

參考文獻54
[25] Y.-T. Chen, B.-Y. Zhuo, and H.-Y. Lin, “Stereo with zooming,” in 2018 IEEE International
Conference on Systems, Man, and Cybernetics (SMC). IEEE, 2018, pp.
2224–2229.
[26] S. R. Szeliski Daniel and H. Heiko, “Middlebury,” vision.middlebury.edu/stereo/.
[27] Z. Zhang, “A flexible new technique for camera calibration,” IEEE Transactions on
pattern analysis and machine intelligence, vol. 22, 2000.
[28] J.-Y. Bouguet, “Matlab camera calibration toolbox,” Caltech Technical Report, 2000.
[29] W. Faig, “Calibration of close-range photogrammetric systems: Mathematical formulation,”
Photogrammetric engineering and remote sensing, vol. 41, no. 12, 1975.
[30] J. Canny, “A computational approach to edge detection,” IEEE Transactions on pattern
analysis and machine intelligence, no. 6, pp. 679–698, 1986.
[31] L. Wang, H. Jin, and R. Yang, “Search space reduction for mrf stereo,” Computer
Vision–ECCV 2008, pp. 576–588, 2008.
[32] P. Fua, “Combining stereo and monocular information to compute dense depth maps
that preserve depth discontinuities.” in IJCAI, vol. 63, no. 3, 1991, pp. 1292–1298.
[33] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International
journal of computer vision, vol. 60, no. 2, pp. 91–110, 2004.
[34] M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model
fitting with applications to image analysis and automated cartography,” Communications
of the ACM, vol. 24, no. 6, pp. 381–395, 1981.
[35] M.-G. Park and K.-J. Yoon, “As-planar-as-possible depth map estimation,” Computer
Vision and Image Understanding, 2019.
[36] A. Hosni, M. Bleyer, C. Rhemann, M. Gelautz, and C. Rother, “Real-time local stereo
matching using guided image filtering,” in 2011 IEEE International Conference on
Multimedia and Expo. IEEE, 2011, pp. 1–6.

[37] R. Spangenberg, T. Langner, and R. Rojas, “Weighted semi-global matching and
center-symmetric census transform for robust driver assistance,” in International
Conference on Computer Analysis of Images and Patterns. Springer, 2013, pp.
34–41.
[38] X. Mei, X. Sun, M. Zhou, S. Jiao, H. Wang, and X. Zhang, “On building an accurate
stereo matching system on graphics hardware,” in 2011 IEEE International
Conference on Computer Vision Workshops (ICCV Workshops). IEEE, 2011, pp.
467–474.
[39] M. Humenberger, T. Engelke, and W. Kubinger, “A census-based stereo vision algorithm
using modified semi-global matching and plane fitting to improve matching
quality,” in 2010 IEEE Computer Society Conference on Computer Vision and Pattern
Recognition-Workshops. IEEE, 2010, pp. 77–84.
[40] Y. S. Heo, K. M. Lee, and S. U. Lee, “Robust stereo matching using adaptive normalized
cross-correlation,” IEEE Transactions on pattern analysis and machine intelligence,
vol. 33, no. 4, pp. 807–822, 2010.
[41] Y. Li and S. Fang, “Removal-based multi-view stereo using a window-based matching
method,” Optik, vol. 178, pp. 1318–1336, 2019.
電子全文 電子全文(網際網路公開日期:20240808)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top