跳到主要內容

臺灣博碩士論文加值系統

(3.236.110.106) 您好!臺灣時間:2021/07/26 00:15
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:陳俊宏
研究生(外文):Jyun-Hong Chen
論文名稱:室內環境影像拼接暨其於微型飛行器之應用
論文名稱(外文):Image Stitching in the Indoor Environment and its Application on the MAV
指導教授:曹大鵬曹大鵬引用關係黃正民黃正民引用關係
口試委員:簡忠漢練光祐
口試日期:2012-07-19
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電機工程系研究所
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:2012
畢業學年度:100
語文別:中文
論文頁數:71
中文關鍵詞:微型飛行器影像拼接模糊影像偵測鬼影去除
外文關鍵詞:MAVimage stitchingblurred image detectionghosting elimination
相關次數:
  • 被引用被引用:1
  • 點閱點閱:266
  • 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
本文將影像拼接技術實行於室內環境,並藉由微型飛行器在室內環境的飛行過程中擷取影像,以影像拼接來實現室內環境的監控與觀測。由於微型飛行器的飛行姿態變化較大,容易造成在影像拍攝期間因晃動產生模糊,且在大量的連續拍攝過程中,影像的重複率及相似度較高,故須挑選出重要的影像資訊以有效地建立環境影像資訊。因此本文首先提出如何以不同尺度之邊緣影像差異,來去除因攝影機晃動拍攝到的模糊影像。接著,為了改善影像拼接時多次座標轉換所產生的累計誤差,並減少運算處理時間,我們會建立並描述影像的重要性,將此重要性作為依據,依序挑選影像來做拼接。此外,由於室內環境中對物體的近距離拍攝,將使得拍攝到的影像之間極容易產生視差並造成模糊之拼接鬼影產生。本文將透過尋找待拼接影像之邊緣一致性區域圖,來設定理想的縫合線以消除拼接鬼影區域,並結合A*演算法在拼接影像之重疊區域間尋找最佳縫合線,使產生之拼接環境影像能夠呈現出較好的品質。

This paper uses the image stitching technique to accomplish visual observation and surveillance in the indoor environment and apply it on the (Micro Aerial Vehicle, MAV). Since the camera vibration is large on the MAV during flying, the blurred image would easily occur. Besides, the continuously captured image sequence during flying would be highly repeated and similar between consecutive frames. Hence, in order to obtain the wide range image with good quality, we have to choose clear and important images to establish the mosaicking image. First, we propose the variation between the scale difference of edge to detect blurred images and remove them. Then, the important images are defined and selected to reduce the computational time and the accumulative errors from many times of the homography transformation. On the other hand, when observing in the indoor environment, the camera is close to the objects which makes the parallax and ghosting effects during stitching images. This thesis proposes the ideal seam in the edge consistency image to eliminate the ghosting region. By combining the edge consistency image with the A*search algorithm, the optimal seam can be obtained to remove the unclear region and result in the mosaicking image with high quality.

目錄
摘 要 i
ABSTRACT ii
誌 謝 iii
目錄 iii
表目錄 v
圖目錄 vi
第一章 緒論 - 1 -
1.1研究背景與目的 - 1 -
1.2相關研究 - 4 -
1.3研究方法 - 5 -
1.4研究貢獻 - 6 -
1.5論文組織架構 - 6 -
第二章 影像篩選 - 7 -
2.1模糊影像去除 - 7 -
2.1.1邊緣量的變化 - 7 -
2.1.2 Scale difference of Canny - 11 -
2.1.3區域性邊緣比較 - 12 -
2.2場景分群篩選 - 15 -
2.3最佳拼接代表篩選 - 17 -
2.3.1特徵點尋找與比對 - 17 -
2.3.2影像豐富度排序 - 19 -
2.3.3篩選最佳代表 - 22 -
第三章 消除拼接鬼影 - 25 -
3.1 相關研究 - 27 -
3.2影像邊緣不一致區域圖之建立 - 27 -
3.2.1求取影像邊緣 - 28 -
3.2.2建立障礙物地圖 - 32 -
3.3 縫合路徑規劃 - 33 -
3.3.1路徑起始點與終點 - 33 -
3.3.2理想縫合路徑 - 36 -
3.4 拼接混色 - 43 -
第四章 實驗結果 - 44 -
4.1消除鬼影結果與比較 - 44 -
4.2最佳篩選代表拼接比較 - 49 -
4.3具有模糊影像之最佳篩選拼接比較 - 59 -
4.4動態更新基準座標 - 67 -
第五章 結論與未來展望 - 68 -
5.1 結論 - 68 -
5.2 未來展望 - 68 -
參考文獻 - 69 -



[1] B. D. Lucas, and T. Kanade, “An iterative image registration technique with an application to stereo vision,” IJCAI ''81, pp. 674-679, 1981.
[2] M. Brown and D. G. Lowe, “Automatic panoramic image stitching using invariant features,” Intl. J. Computer Vision, vol.74, no.1, pp.59-73, 2003.
[3] D. G. Lowe, “Object recognition from local scale-invariant features,” in Proc. of the 7th International Conf. Computer Vision, pp. 1150-1157, 1999.
[4] Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool, “SURF: Speeded up robust features,” Computer Vision and Image Understanding (CVIU), Vol. 110, no. 3, pp. 346-359, 2006.
[5] T. Suzuki, Y. Amano and T. Hashizume, “Vision based localization of a small UAV for generating a large mosaic image,” in Proc.SICE Annual Conference, 2010.
[6] F. Caballero, L. Merinot, J. Ferruz, and A. Ollero, “Homography based Kalman filter for mosaic building applications to UAV position estimation,” in Proc. IEEE Conf. Robotics and Automation, pp. 10-14, Apr. 2007.
[7] Ping Hsu and Bing-Yu Chen, “Blurred image detection and classification,” Lecture Notes in Computer Science, 2008.
[8] E. Tsomko, H. J. Kim, and E. Izquierdo,“Linear Gaussian blur evolution for detection of blurry images,” Image Processing (IET), vol.4, no.4, pp.302-312, 2008.
[9] T. Hang-hang, L. Ming-jing, Z. Hang-hang, Z. Chang-shui, “Blur detection for digital images using wavelet transform,” IEEE Int. Conf. on Multimedia and Expo(ICME), pp. 17–20, 2004.
[10] Suk Hwan Lim, Jonathan Yen, Peng Wu, “Detection of Out-Of-Focus Digital Photographs,” Imaging Systems Laboratory, 2005.
[11] S. Hinterstoisser, C. Cagniart, S. Ilic, P. Sturm, N. Navab, P. Fua, and V. Lepetit, “Gradient response maps for real-time detection of textureless objects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.34, no.5, pp. 876-888, May 2012.
[12] D. K. Park, Y. S. Jeon, C. S. Won and S. J. Park, “Efficient use of local edge histogram descriptor,” in Proc of. ACM, United States, pp. 51-54, 2000.
[13] M. Brown, R. Szeliski, S. Winder, “Multi-image matching using multi-scale oriented patches,” IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2005.
[14] J. Beis and D. Lowe, “Shape indexing using approximate nearest-neighbor search in high dimensional spaces”, in Proc. of the Interational Conf. Computer Vision and Pattern Recognition (CVPR97), pp. 1000, 1997.
[15] Leen K. Soh and Costas Tsatsoulis, “Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices,” IEEE Trans. Geosci. Remote Sensing, Vol. 37, No. 2, pp. 780-795, 1999.
[16] M. Uyttendaele, A. Eden, and R. Szeliski. “Eliminating ghosting and exposure artifacts in image mosaics,” in Proc.CVPR’01, vol. 2, pp. 509-516, 2001.
[17] V. Kwatra, A. Schodl, I. Essa, G. Turk, and A. Bobick, “Graphcut textures: Image and video synthesis using graph cuts,” ACM Trans. Graphics, Proc. Int’l Conf. Computer Graphics and Interactive Techniques (SIGGRAPH ’03), vol. 22, no. 3, pp. 277-286, July 2003.
[18] Efros and W.T. Freeman, “Image quilting for texture synthesis and transfer,” in Proc. ACM SIGGRAPH ’01, pp. 341-346, Aug. 2001.
[19] J. Davis, “Mosaics of scenes with moving objects,” IEEE Conf. Computer Vision and Pattern Recognition, pp. 354, 1998.
[20] S. Avidan and A. Shamir, “Seam carving for content-aware image resizing,” ACM Trans. Graph (SIGGRAPH), vol. 26, no. 3, 2007.
[21] M. Uyttendaele, A. Eden, and R. Szeliski, “Eliminating ghosting and exposure artifacts in image mosaics,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2001.
[22] Hua Gu, Yue Yu and Weidong Sun, “A new optimal seam selection method for airborne image stitching,” IEEE Inter. Imaging Systems and Techniques (IST ''09), pp.159-163, May 2009.
[23] Jiaya Jia and Chi-Keung Tang, “Image stitching using structure deformation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 4, 2008.
[24] Yu Tang and Huiyan Jiang, “Highly efficient image stitching based on energy map,” IEEE conf. Image and Signal Processing (CISP ''09), pp. 1-5, Oct. 2009.
[25] Yu Tang, Jungpil Shin, “De-ghosting for image stitching with automatic content-awareness,” in Proc. IEEE Conf. Pattern Recognition (ICPR), pp. 2210-2213, Aug. 2010.
[26] P. Burt and E. Adelson, “A multi resolution spline with application to image mosaics,” ACM Trans. Graphics, pp. 217–236, 1983.
[27] P. Pérez, M. Gangnet, and A. Blake, “Poisson image editing,” ACM Trans. Graph, vol. 22, no. 3, pp. 313–318, 2003.
[28] Richard Szeliski, “Image alignment and stitching: A tutorial,” Foundations and Trends in Computer Graphics and Computer Vision, 2(1):1-104, 2006.
[29] T.Botterill, S. Mills, R.Green, “Real-time aerial image mosaicking,” Inter. Conf. Image and Vision Computing New Zealand (IVCNZ), pp.1-8, 2010.
[30] E. Rosten, T. Drummond, “Machine leaning for high-speed corner detection,” ECCV, 2006
[31] Beom Su Kim, Sang Hwa Lee, Nam Ik Cho,“Real-time panorama canvas of natural images," IEEE Trans. Consumer Electronics, vol.57, no.4, pp.1961-1968, November 2011.
[32] D. Wagner, A. lloni, T. anglotz, D. chmalstieg, “Real-time panoramic mapping and tracking on mobile phones,” IEEE Conf. Virtual Reality (VR), pp.211-218, 20-24 March, 2010.


電子全文 電子全文(本篇電子全文限研究生所屬學校校內系統及IP範圍內開放)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top