臺灣博碩士論文加值系統

隨著科技的進步，影像技術的應用除了更普及之外也更加日新月異，舉凡遙測影像的變遷偵測、無人車的障礙物偵測和監視攝影機的行人偵測等皆是影像用於偵測之應用。然而像機拍攝時可能因為自然或人為因素而發生運動。此外，拍攝場景內可能發生光影變化，進而影響後續的偵測成果。為了要能在像機發生運動的情況下使用序列影像進行移動物體偵測，本研究透過解算多張影像間的相對方位，以改正像機運動對於移動物體偵測的影響。另外，為了避免因為場景內光影變化造成偵測錯誤的發生，本研究發展基於HSI色彩空間與背景相減法之移動物體偵測方法。當取得移動物體於影像上的位置，可透過影像資料所提供的資訊搭配共線條件進行三維物體追蹤。藉由假設物體是在一個高度未發生變化的地面上運動，移動物體的位置與高度皆可根據所提方法取得。實驗結果顯示，根據所提方法只需要單張影像即可完成三維物件追蹤，且精度可達公分級。本研究方法能降低當前移動物體偵測的限制，並擴展單像機的使用於更廣泛的應用。

With the rapid development of technology, the image processing technique is changing frequently and is becoming more common nowadays. There are numerous applications of this technique, such as change detection that use remote sensing image, obstacle detecting system of unmanned vehicle, and moving people detection with surveillance cameras. However, the view of camera is often changed due to natural factors or human activities. In addition, inconsistency of images with the same view may also happen as result of luminance variation. In order to correctly detect the moving objects from image sequence captured by a moving camera, the moving correction of camera has to be done firstly. This can be accomplished by acquiring the relative orientation between two image frames. Next, to avoid the detection error caused by luminance variations or shadow effect, a moving object detection approach based on the HSI color space and background subtraction algorithm is developed in this study. Once the 2D position of moving objects is available, 3D object tracking can be performed by using the information from image data and the collinearity condition. By assuming that the object is moving on the ground without changing in altitude, the location as well as the attitude of the moving objects can be obtained based on the proposed approach. The experiment results indicated that 3D object tracking of centimeter-level accuracy can be achieved with the proposed approach, in which only single image is required. Consequently, this approach is capable of reducing the limitation of current moving object detection technique and extending the usage of a single camera for further applications.

口試委員審定書...........................Ⅰ
致謝...………………………………….…………………………………………..…Ⅱ
中文摘要...………………………………………………………...…………………Ⅲ
英文摘要...……………………………………………………………….…………..Ⅳ
目錄...……………………………………………………………………………...…Ⅴ
圖目錄...…………………………………………………………….…..……………Ⅶ
表目錄...……………………………………………………….……………………..Ⅸ
第一章 前言...………………………………………………………………………..1
1.1研究背景...…………………………………………………………….….....1
1.2研究動機與目的...…………………………………………………………..2
第二章 文獻回顧.……………………………………………………………………4
2.1像機運動偵測...………………………………………………………….….5
2.1.1 特徵萃取與匹配......................5
2.1.2 特徵點分群...…………………….………………………………….8
2.1.3 像機位置與姿態確定...…………………….……………………….9
2.2 前景與背景分離...…………….…………………………………………..11
2.2.1 像機未發生運動...……………………………………………...….12
2.2.2 像機發生運動....………………………………………………...…17
2.3 物體運動追蹤...…………………………………………………………...19
2.4 單像機應用現況與問題...………………………………………….……..21
第三章 研究方法...…………………………………………………………………24
3.1 像機運動判斷...…………………………………………………..……….24
3.1.1 特徵匹配...………………………………………………...….……25
3.1.2 E-matrix...………………………………….………………………28
3.2 移動物體偵測...………………………………………………….………..33
3.2.1 移動改正...…………………………………………………………33
3.2.2 背景相減法...………………………………………….…………...35
3.2.3 前景精化...…………………………………………………………38
3.3 移動物體定位與追蹤...……………………………………………….…..41
第四章 實驗成果與分析...…………………………………………………………45
4.1 像機靜止不動...……………………………….…………………………..47
4.1.1 未發生光影變化(情境一)...……………………………………….47
4.1.2 發生光影變化(情境二)...………………………………………….52
4.2 像機發生運動...…………………………………………………………...58
4.2.1 未發生光影變化(情境三)...……………………………………….58
4.2.2 發生光影變化(情境四)...………………………………………….63
第五章 結論與未來工作...…………………………………………………………70
第六章 參考文獻...…………………………………………………………………73

Aoki media sensing lab. (2017). Moving Object Proposal by Grouping with Motion Feature, available online. http://www.aoki-medialab.jp/1_motion_feature.html(last date accessed: 21 July 2017).
Bay, H., Tuytelaars, T., & Van Gool, L. (2006). SURF: Speeded Up Robust Features . 2006 9th European Conference on Computer Vision, Graz, Austria.
Benezeth, Y., Jodoin, P.-M., Emile, B., Laurent, H., & Rosenberger, C. (2008). Review and evaluation of commonly-implemented background subtraction algorithms. 2008 19th International Conference on Pattern Recognition , Florida, USA.
Bowden, R., Mitchell, T., & Sarhadi, M. (1998). Reconstructing 3D pose and motion from a single camera view, 1998 British Machine Vision Conference, Southampton, UK.
Brutzer, S., Höferlin, B., & Heidemann, G. (2011). Evaluation of background subtraction techniques for video surveillance. 2011 IEEE Conference on Computer Vision and Pattern Recognition, Colorado, USA.
Campbell, J., Sukthankar, R., Nourbakhsh, I., & Pahwa, A. (2005). A robust visual odometry and precipice detection system using consumer-grade monocular vision, 2005 IEEE International Conference on Robotics and Automation, Barcelona, Spain.
Chiang, K. W., Tsai, M. L., & Chu, C. H. (2012). The development of an UAV borne direct georeferenced photogrammetric platform for ground control point free applications. Sensors, 12(7), 9161-9180.
Digital Art, Design, and Communication Education. (2017). HUE, VALUE, SATURATION, available online. http://learn.leighcotnoir.com/artspeak/elements-color/hue-value-saturation/(last date accessed: 10 July 2017).
Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381-395.
FIVEKO.com. (2017). Median Filter, available online. http://fiveko.com/tutorials/dip/median(last date accessed: 15 July 2017).
Fraundorfer, F., & Scaramuzza, D. (2011). Visual odometry: Part i: The first 30 years and fundamentals. IEEE Robotics and Automation Magazine, 18(4), 80-92.
GUANGCHUN. (2013). OPENCV:Feature detectors and descriptors, available online. https://guangchun.wordpress.com/2013/02/16/opencv-feature-detectors-and-descriptode/
Han, C., Yoo, S., & Choi, J. (2011). Evaluation of co-occurring terms in clinical documents using latent semantic indexing. Healthcare informatics research, 17(1), 24-28.
Jung, B., & Sukhatme, G. S. (2004). Detecting moving objects using a single camera on a mobile robot in an outdoor environment, International Conference on Intelligent Autonomous Systems, North Holland, Netherlands.
Kanungo, T., Mount, D. M., Netanyahu, N. S., Piatko, C. D., Silverman, R., & Wu, A. Y. (2002). An efficient k-means clustering algorithm: Analysis and implementation. IEEE transactions on pattern analysis and machine intelligence, 24(7), 881-892.
Karami, E., Prasad, S., & Shehata, M. (2015). Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images, IEEE Newfoundland Electrical and Computer Engineering Conference,
Newfoundland, Canada.
Kent, Allen, Madeline M. Berry, Fred U. Luehrs, Jr., and J. W. Perry. (1955). Machine literature searching VIII. Operational criteria for designing information retrieval systems. American Documentation 6(2), 93–101.
Kim, W., & Kim, Y. (2016). Background Subtraction Using Illumination-Invariant Structural Complexity. IEEE Signal Processing Letters, 23(5), 634-638.
Kneip, L., Chli, M., Siegwart, R., Siegwart, R. Y., & Siegwart, R. Y. (2011). Robust real-time visual odometry with a single camera and an imu, 2011 British Machine Vision Conference, Scotland, UK.
Kole, S., Agarwal, C., Gupta, T., & Singh, S. (2015). SURF and RANSAC: A Conglomerative Approach to Object Recognition. International Journal of Computer Applications, 109(4).
Li, L., Huang, W., Gu, I. Y., & Tian, Q. (2003). Foreground object detection from videos containing complex background. 2003 11th ACM International Conference on Multimedia, California, USA.
Lim, J. S. (1990). Two-dimensional signal and image processing. Englewood Cliffs, NJ, Prentice Hall, 1990, 710p.
Longuet-Higgins, H. C. (1981). A computer algorithm for reconstructing a scene from two projections. Nature, 293(5828), 133-135.
Lowe, D. G. (1999). Object recognition from local scale-invariant features, 1999 the seventh IEEE International Conference on Computer Vision, Kerkyra, Greece.
Mariottini, G. L., Oriolo, G., & Prattichizzo, D. (2007). Image-based visual servoing for nonholonomic mobile robots using epipolar geometry, 2007 IEEE Transactions on Robotics, 23(1), 87-100.
Micheloni, C., & Foresti, G. (2003). A robust feature tracker for active surveillance of outdoor scenes, Electronic Letters on Computer Vision and Image Analysis, 1(1), 21-34.
Migliore, D., Rigamonti, R., Marzorati, D., Matteucci, M., & Sorrenti, D. G. (2009). Use a single camera for simultaneous localization and mapping with mobile object tracking in dynamic environments, International Workshop on Safe Navigation in Open and Dynamic Environments Application to Autonomous Vehicles, Kobe, Japan.
Montemerlo, M., Thrun, S., Koller, D., & Wegbreit, B. (2002). FastSLAM: A factored solution to the simultaneous localization and mapping problem, Eighteenth National Conference on Innovative Applications of Artificial Intelligence, Alberta, Canada.
Nguyen, V.-T., Vu, H., & Tran, T.-H. (2015). An Efficient Combination of RGB and Depth for Background Subtraction. Some Current Advanced Researches on Information and Computer Science in Vietnam (pp. 49-63): Springer.
Pantech Solutions. (2013). Matlab Code for Background Subtraction, available online. https://www.pantechsolutions.net/blog/matlab-code-for-background-subtraction/ (last date accessed: 31 March 2016).
Perceiving Systems. (2016). Computer Vision Performance Evaluation, available online. https://ps.is.tue.mpg.de/research_projects/datasets(last date accessed: 12 May 2016).
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011). ORB: An efficient alternative to SIFT or SURF, 2011 International Conference on Computer Vision, Barcelona, Spain.
Sajid, H., & Cheung, S.-C. S. (2015). Background subtraction for static & moving camera. 2015 IEEE International Conference on Image Processing, Quebec City, Canada.
Scaramuzza, D., Fraundorfer, F., & Siegwart, R. (2009). Real-time monocular visual odometry for on-road vehicles with 1-point ransac, 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan.
Sheikh, Y., Javed, O., & Kanade, T. (2009). Background subtraction for freely moving cameras. 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan.
SlideShare. (2013). An In-Depth Evaluation of Multimodal Video Genre Categorization, available online. http://www.slideshare.net/ionutmironica/cbmi-2013 (last date accessed: 31 March 2016).
Swank, A. J. (2012). Localization Using Visual Odometry and a Single Downward-Pointing Camera, National Aeronautics and Space Administration, Glenn Research Center, Cleveland, Ohio, USA.
Tardif, J.-P., Pavlidis, Y., & Daniilidis, K. (2008). Monocular visual odometry in urban environments using an omnidirectional camera, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France.
Theia Vision Library. (2015). Structure from Motion (SfM), available online. http://www.theia-sfm.org/sfm.html (last date accessed: 31 March 2016).
Tomono, M. (2005). 3-D localization and mapping using a single camera based on structure-from-motion with automatic baseline selection, 2005 IEEE International Conference on Robotics and Automation, Barcelona, Spain.
Tsai, D.-M., Chiu, W.-Y., & Tseng, T.-H. (2015). Moving object detection from a mobile robot using basis image matching, 2015 IS&T/SPIE Electronic Imaging, San Francisco, USA.
Valgren, C., & Lilienthal, A. J. (2007). SIFT, SURF and Seasons: Long-term Outdoor Localization Using Local Features, 2007 3rd European Conference on Mobile Robots, Freiburg, Germany.
Van Rijsbergen C. J. (1979). Information Retrieval, 2nd edition, Butterworths. ISBN: 0-408-70929-4.
WAYMO. (2016). Journey, available online. https://waymo.com/journey/ (last date accessed: 12 May 2016).
Zhang, W., & Kosecka, J. (2006). Image based localization in urban environments, Third International Symposium on 3D Data Processing, Visualization, and Transmission, North Carolina, USA.
Zhang, Z. (1998). Determining the epipolar geometry and its uncertainty: A review. International journal of computer vision, 27(2), 161-195.
Zheng, Y., Mahabalagiri, A., & Velipasalar, S. (2013). Detection of moving people with mobile cameras by fast motion segmentation, 2013 Seventh International Conference on Distributed Smart Cameras, California, USA.
Zhou, H., Yuan, Y., & Shi, C. (2009). Object tracking using SIFT features and mean shift. Computer vision and image understanding, 113(3), 345-352.
Zhu, K., Ruan, Q., Yang, T., & Wang, H. (2008). Tracking and measuring a moving object with a binocular camera system, 2008 Ninth International Conference on Signal Processing, Beijing, China.
Zhu, Z., Oskiper, T., Samarasekera, S., Kumar, R., & Sawhney, H. S. (2007). Ten-fold improvement in visual odometry using landmark matching, 2007 IEEE Eleventh International Conference on Computer Vision, Rio de Janeiro, Brazil.
李政軒 (2012)。基於模糊線性區別分析之模糊分群法與結合空間資訊之支撐向量機，交通大學電機工程學系，博士論文，新竹市。
李昆鴻 (2013)。應用影像特徵於底拖攝影系統運動之估計，中山大學海下科技暨應用海洋物理研究所，碩士論文，高雄市。
邱明璋 (2011)。基於極線限制條件之單眼視覺式移動物體偵測與追蹤，淡江大學機械與機電工程學系，碩士論文，新北市。
謝宗倫 (2010)。單像機高速運動物體 3D 軌跡重建的新方法，亞洲大學生物資訊學系，碩士論文，台中市。
鄭傑文 (2007)。射影幾何於攝影測量之應用，臺灣大學土木工程學系，碩士論文，台北市。
蔡政芳 (2013)。基於視訊動態背景之運動物體偵測研究，中原大學資訊工程學系，碩士論文，桃園市。
蘇恕德 (2009)。兩段式背景相減法偵測移動物體，臺灣大學電機工程學系，碩士論文，台北市。
孫琬婷 (2013)。基於運動視訊中動態背景之移動物件偵測與追蹤研究，中原大學資訊工程學系，碩士論文，桃園市。
王怡翔 (2008)。利用場景中之消失點產生影像深度圖，中華大學資訊工程學系，碩士論文，新竹市。
吳究，張奇與劉銘哲 (2009)。基於尺度不變特徵點轉換之精密多元影像套合，航測及遙測學刊，14(2)，141-155。