跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 徐凱輬
Kai-liang Hsu
論文名稱： 多重解析度光流分析與深度計算
Multiresolution Optical Flow Estimation and Range Determination
指導教授： 曾定章
Din-chang Tseng
口試委員:
學位類別： 碩士
Master
系所名稱： 資訊電機學院 - 資訊工程學系
Department of Computer Science & Information Engineering
畢業學年度： 88
語文別： 中文
論文頁數： 71
中文關鍵詞： 深度計算 、多重解析度 、光流
外文關鍵詞： Range Determination, Multiresolution, Optical Flow
相關次數： 點閱：12  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 經由一連串連續動作影像的分析來判定物體移動的速度，再藉此速度來求得物體與偵測器間的距離是本研究的目標。為了達此目標，在本論文的研究中，我們發展一個結合了光流偵測 (optical flow estimation) 與深度計算 (range determination) 的被動式距離檢知即時系統。在光流偵測中，我們採用兩個不同性質的方法來估計影像中的光流值；一是Horn-Schunck方法；二是 Lucas-Kanade方法。在Horn-Schunck方法中，我們加入多重解析度的處理以加快光流計算的收斂速度，並得以使本系統更加符合即時的要求。藉由已知的光流資訊，配合有少許動作限制的透視投影公式，我們就能夠計算出目標物與偵測器間的距離，而此項距離資訊將可應用於自動飛行導航系統和軍事戰術演習上。

    In the applications of autonomous flight navigation and tactical simulation, we need the range information acquired from the motion cues. In this study, we develop optical flow estimation methods as well as a range determination method to achieve the purpose. Two methods for estimating optical flow from image sequences are compared; one is the Horn-Schunck method and the other is the Lucas-Kanade method. Based on the motion data of optical flow and the principle of perspective transformation, the distance from the targets to the sensor is determined. In the optical flow estimation, the multiresolution strategy is utilized to speed up the process to make our system being suitable for real-time applications.

    Abstract ii Contents iii List of Figures v List of Tables vii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 System overview 2 1.2.1 Multiresolution optical flow estimation 2 1.2.2 Motion segmentation 3 1.2.3 Range determination 3 1.3 Thesis organization 4 Chapter 2 Related Works 6 2.1 Basic definitions of optical flow 6 2.2 Optical flow estimation 7 2.2.1 Gradient-based approach 7 2.2.2 Evaluation of optical flow techniques 10 2.3 Long image sequence analysis 11 2.4 Multiresolution model 12 2.5 Range determination 13 2.5.1 Binocular stereo vision methods 13 2.5.2 Monocular stereo vision methods 14 Chapter 3 Optical Flow Estimation 16 3.1 The gradient based constraint for optical flow estimation16 3.2 Smoothness constraints 17 3.2.1 Estimating the partial derivatives 18 3.2.2 Estimating the Laplacian of the flow velocities 18 3.2.3 Minimization 20 3.2.4 Choice of iterative scheme 22 3.3 First-order weighted least square approach 22 3.4 Multiresolution optical flow estimation 23 Chapter 4 Range Determination 26 4.1 Perspective transformation 26 4.2 Range determination method 28 Chapter 5 Experiments and Discussions 31 5.1 Experimental environments 31 5.2 Experimental results 31 5.2.1 Test image sequences 31 5.2.2 Terrain image sequences 37 5.2.3 Range determination 42 5.3 Discussions 43 Chapter 6 Conclusions 46 References 47

    [1]Bainbridge-Smith, A. and R. G. Lane, "Determining optical flow using a differential method," Image and Vision Computing, Vol.15, pp.11-22, 1996.
    [2]Barniv, Y., "Error analysis of the combined optical flow and stereo Passive Ranging," IEEE Trans. on Aerospace and Electronic System, Vol.28, No.4, pp.978-989, 1992.
    [3]Barron, J., D. Fleet, and S. Beauchemin, "Performance of optical flow techniques," International Journal of Computer Vision, Vol.12, No.1, pp.43-77, 1994.
    [4]Bors, A. and I. Pitas, "Optical flow estimation and moving object segmentation based on median radial basis function network," IEEE Trans. on Image Processing, Vol.7, No.5, pp.693-702, 1998.
    [5]Brandt, J. W., "Improved accuracy in gradient-based optical flow estimation," International Journal of Computer Vision, Vol.25, No.1, pp.5-22, 1997.
    [6]Chandrashekhar S. and R. Chellappa, "Passive navigation using a monocular image sequence," IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.11, No.10, pp.1101-1106, 1989.
    [7]Chang, M. M., A. M. Tekalp, and M. I. Sezan, "Simultaneous motion estimation and segmentation," IEEE Trans. on Image Processing, Vol.6, No.9, pp.1326-1333, 1997.
    [8]Denney, T. S. J. and J. L. Prince, "Optimal brightness function for optical flow estimation of deformable motion," IEEE Trans. on Image Processing, Vol.3, No.2, pp.178-191, 1994.
    [9]Elad, M. and A. Feuer, "Recursive optical flow estimation-adaptive filtering approach," Journal of Visual Communication and Image Representation, Vol.9, No.2, pp.119-138, 1998.
    [10]Ghosal, S. and R. Mehrotra, "Robust optical flow estimation using semi_invariant local features," Pattern Recognition Vol.30, No.2, pp.229-238, 1997.
    [11]Golland, P., Optical Flow Estimation using Color Images, Master Thesis, Artificial Intelligence Lab, MIT, 1995.
    [12]Gupta, S. and J. Prince, "On variable brightness optical flow for tagged MRI," in 14th Int''l Conf. on Information Processing in Medical Imaging, Dordrecht, Holland, June, 1995, pp.323-334.
    [13]Gupta, S. and J. Prince, "Stochastic models for DIV_CURL optical flow methods," IEEE Signal Processing Letters, Vol.3, No.2, pp.32-34, 1996.
    [14]Horn, B. K. P. and B. G. Schunck, "Determining optical flow," Artificial Intelligence, Vol.17, No.1, pp.185-203, 1981.
    [15]Irani, M., B. Rousso, and S. Peleg "Computing occluding and transparent motions" International Journal of Computer Vision, Vol.12, No.1, pp.5-16, 1994.
    [16]Johnson, G. E., E. R. Dowski, and W. T. Cathey, "Passive ranging for acquisition of range images: applications to longitudinal vehicle control and warning systems," IEEE Conf. Intelligent Transportation System, Aug.8, 1997, pp.655-660.
    [17]Kenner, M. and T.-C. Pong, "Motion analysis of long image sequence Flow," Pattern Recognition Letters, Vol.11, No.1, pp.123-131,1990.
    [18]Lucas, B. and T. Kanade, "Optical navigation by the method of differences" in Proc. 7th Int. Joint Conf. Artificial Intelligence, 1985, pp.981-984.
    [19]Memin, E. and P. Perez, Adaptative Multigrid and Variable Parameterization for Optical-flow Estimation, Technique Report, INRIA, 1997.
    [20]Nagel, H. H., "Displacement vectors derived from second-order intensity variations in image sequences," Computer Vision, Graphics and Image Processing, Vol.21, No.1, pp.85-117, 1983.
    [21]Niessen. W., J. Duncan and M. Nielsen, "A multiscale approach to image sequence analysis," Computer Vision and Image Understanding, Vol.65, No.2, pp.259-268, 1997.
    [22]Sim, D. and R. Park, "A two-stage algorithm for motion discontinuity-preserving optical flow estimation," Computer Vision and Image Understanding, Vol.65, No.1, pp.19-37, 1997.

    QR CODE
    :::