由於傳統攝影機視野狹小，利用全方位攝影機(omni-directional camera)可增加視野範圍。早期大都以傳統攝影機在靜止不動，或是只有平移的情況下才能偵測移動物體，若應用在移動式的機器人或是車輛上，其行動會因此受限。
本文假設將全方位攝影機架設在移動的平台上，且攝影機為平面運動(planar motion)的情況下，藉由全方位影像(omni-directional image)上之地面影像和亮度守?琱韏{式來估測自我運動(ego-motion)，並由地面影像來得到深度的資訊，以解決單一攝影機無法求得深度的問題。以估測到的自我運動，計算出地面上假想之光流(optical flow)，然後與影像上的光流比較兩者之方向，以偵測出移動物體。藉由深度的資訊，即使攝影機在平移和旋轉的情況下，仍可以對移動物體進行偵測。

From the viewpoint of applications, conventional cameras are usually limited in their fields of view. The omni-directional camera has a full range in all directions, which gains the complete field of view. In the past, a moving object can be detected, only when the camera is static or moving with a known speed. If those methods are employed to mobile robots or vehicles, it will be difficult to determine the motion of moving objects observed by the camera.
In this paper, we assume the omni-directional camera is mounted on a moving platform, which travels with a planar motion. The region of floor in the omni-directional image and the brightness constraint equation are applied to estimate the ego-motion. The depth information is acquired from the floor image to solve the problem that cannot be obtained by single camera systems. Using the estimated ego-motion, the optical flow caused by the floor motion can be computed. Therefore, comparing its direction with the direction of the optical flow on the image leads to detection of a moving object. Due to the depth information, even if the camera is in the condition that combining translational and rotational motions, a moving object can still be accurately identified.

目錄............................................................................................................. i
圖索引....................................................................................................... iii
表索引....................................................................................................... vi
摘要.......................................................................................................... vii
Abstract..................................................................................................viii
第一章 緒論.............................................................................................. 1
1.1 動機與目的................................................................................. 1
1.2 文獻回顧..................................................................................... 2
1.3 本文架構..................................................................................... 4
第二章 雙曲面鏡型全方位攝影機......................................................... 6
2.1 全方位影像之特性..................................................................... 6
2.2 全方位攝影機系統模型............................................................. 7
2.3 幾何投影關係式......................................................................... 9
第三章 攝影機自我運動估測…………………………………………13
3.1 平面運動................................................................................... 13
3.2 亮度守?琱韏{式....................................................................... 14
3.3 運動方程式............................................................................... 15
3.4 最小平方法............................................................................... 21
第四章 移動式攝影機偵測移動物體................................................... 24
4.1 偵測移動物體之方法............................................................... 24
4.2 地面上假想之光流................................................................... 27
4.3 門檻值....................................................................................... 30
4.4 光流演算法之探討................................................................... 31
第五章 模擬結果與分析....................................................................... 34
5.1 經校正所得之投影關係式....................................................... 34
5.2 估測自我運動........................................................................... 38
5.2.1 模擬地面影像.................................................................. 38
5.2.2 估測自我運動之結果...................................................... 40
5.3 偵測移動物體........................................................................... 43
5.3.1 模擬地面上球狀物體...................................................... 43
5.3.2 靜態物體之光流.............................................................. 44
5.3.3 偵測移動物體之結果...................................................... 44
5.3.4 物體移動方向對偵測結果之影響.................................. 48
第六章 結論與未來展望....................................................................... 54
參考文獻.................................................................................................. 56
附錄 校正結果....................................................................................... 61

[1] Collett, T., “Insect Vision: Controlling Actions through Optical Flow,” Current Biology, Vol. 12, No. 18, pp. R615-R617, 2002.
[2] Srinivasan, M. V., “Visual Navigation: The Eyes Know Where Their Owner is Going,” Motion Vision-Computational, Neural and Ecological Constraints, Edited by Zanker, J. M. and Zeil, J., Springer-Verlag, pp. 181-186, 2001.
[3] Nayar, S. K., “Catadioptric Omnidirectional Camera,” Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 482-488, 1997.
[4] Hong, L., Wenkai, P. and Hongbin, Z., “Motion Detection for Multiple Moving Targets by Using an Omnidirectional Camera,” Proceedings of IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, Vol. 1, pp. 422-426, 2003.
[5] Yamazawa, K. and Yokoya, N., “Detecting Moving Objects from Omnidirectional Dynamic Images Based on Adaptive Background Subtraction,” Proceedings of IEEE International Conference on Image Processing, Vol. 3, pp. 953-956, 2003.
[6] Kruger, W., Enkelmann, W. and Rossle, S., “Real-time Estimation and Tracking of Optical Flow Vectors for Obstacle Detection,” Proceedings of the Intelligent Vechicles ’95 Symposium, pp. 304-309, 1995.
[7] Giachetti, A., Campani, M. and Torre, V. “The Use of Optical Flow for Road Navigation,” IEEE Transactions on Robotics and Automation, Vol. 14, No. 1, pp. 34-48, 1998.
[8] Gandhi, T. and Trivedi, M. M., “Motion Based Vehicle Surround Analysis Using an Omni-Directional Camera,” Proceedings of IEEE Intelligent Vehicles Symposium, pp. 560-565, 2004.
[9] Gandhi, T. and Trivedi, M. M., “Motion Analysis for Event Detection and Tracking with a Mobile Omnidirectional Camera,” Multimdeia Systems, Vol. 10, No. 2, pp. 131-143, 2004.
[10] Stratmann, I. and Solda, E., “Omnidirectional Vision and Inertial Clues for Robot Navigation,” Proceedings of the 11th International Conference on Advanced Robotics, Portugal, pp. 1915-1921, 2003.
[11] Prazdny, K., “Determining the Instantaneous Direction of Motion from Optical Flow Generated by a Curvilinearly Moving Observer,” Computer Graphics and Image Processing, Vol. 17, pp. 238-248, 1981.
[12] Burger, W. and Bhanu, B., “Estimating 3-D Egomotion from Perspective Image Sequences,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 11, pp. 1040-1058, 1990.
[13] Ke, Q. and Kanade, T., “Transforming Camera Geometry to a Virtual Downward-looking Camera: Robust Ego-motion Estimation and Ground-layer Detection,” Proceedings of IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 390- 397, 2003.
[14] Naqatani, K., Tachibana, S., Sofne, M. and Tanaka, Y., “Improvement of Odometry for Omnidirectional Vehicle Using Optical Flow Information,” Proceedings of IEEE/RSJ International
Conference on Intelligent Robots and Systems, Vol. 1, pp. 468-473, 2000.
[15] Gluckman, J. and Nayar, S. K., “Ego-motion and Omnidirectional Cameras,” Proceedings of the International Conference on Computer Vision, pp. 999-1005, 1998.
[16] Vassallo, R. F., Santos-Victor, J. and Schneebeli, H. J., “A General Approach for Egomotion Estimation with Omnidirectional Images,” Proceedings of the Third Workshop on Omni-directional Vision, pp. 97-103, 2002.
[17] Shakernia, O., Vidal, R. and Sastry, S., “Omnidirectional Egomotion Estimation from Back-projection Flow,” Proceedings of IEEE Workshop on Omnidirectional Vision, Vol. 7, pp. 82, 2003.
[18] Bunschoten, R., Mapping and Localization from a Panoramic Vision Sensor, Ph. D. thesis, University of Amsterdam, 2003.
[19] Ishiguro, H., “Development of Low-Cost Compact Omnidirectional Vision Sensors and Their Applications,” Proceedings of International Conference on Information Systems, Analysis and Synthesis, pp. 433-439, 1998.
[20] Yamazawa, K., Yagi, Y. and Yachida, M., “Omnidirectional Imaging with Hyperboloidal Projection,” Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol. 2, pp. 1029-1034, 1993.
[21] Yachida, M., “Omnidirectional Sensing and Combined Mutliple Sensing,” Proceedings of IEEE and ATR Workshop on Computer Vision for Virtual Reality Based Human Communications, pp. 20-27, 1998.
[22] Hoshi, Y. and Kato, M., “A Walkthrough Image Generation for Facility Guidance by Interpolating Omnidirectional Images,” Proceedings of IEEE Conference on Systems, Man, and Cybernetics, pp. 1598-1602, 2006.
[23] Stratmann, I., “Omnidirectional Imaging and Optical Flow,” Proceedings of IEEE Workshop on Omnidirectional Vision, pp. 104-111, 2002.
[24] Scaramuzza, D., Martinelli, A. and Siegwart, R., “A Flexible Technique for Accurate Omnidirectional Camera Calibration and Structure from Motion,” Proceedings of IEEE International Conference on Computer Vision Systems, pp. 45, 2006.
[25] Scaramuzza, D., Martinelli, A. and Siegwart, R., “A Toolbox for Easily Calibrating Omnidirectional Cameras,” Proceedings of IEEE International Conference on Intelligent Robots and Systems, pp. 5695-5701, 2006.
[26] Horn, B. and Schunck, B., “Determining Optical Flow,” Artificial Intelligence, Vol. 17, pp. 185-203, 1981.
[27] Barron, J. L., Fleet, D. J. and Beauchemin, S., “Performance of Optical Flow Techniques,” International Journal of Computer Vision, Vol. 12, No. 1, pp. 43-77, 1994.
[28] Anandan, P., “A Computational Framework and an Algorithm for Visual Motion,” International Journal of Computer Vision, Vol. 2, pp. 283-310, 1989.
[29] Lucas, B. and Kanade, T., “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proceedings of the 7th International Joint Conference on Artificial Intelligence, pp. 674-679, 1981.
[30] Fleet, D. J. and Jepson, A. D., “Computation of Component Image Velocity from Local Phase Information,” International Journal of Computer Vision, pp. 77-104, 1990.
[31] Daniilidis, K., Makadia, A. and Bulow, T., “Processing in Catadioptric Planes: Spatiotemporal Derivatives and Optical Flow Computation,” Proceedings of IEEE Workshop on Omnidirectional Vision, pp. 3-12, 2002.
[32] Hirunyaphisutthikul, S. and Tunwannarux, A., “Synthesizing Test Image Sequences for Omnicamera: Translating and Rotating Spheres,” Proceedings of IEEE International Symposium on
Communications and Information Technology, Vol. 1, pp. 421-426, 2004.
[33] http://asl.epfl.ch/~scaramuz/research/Davide_Scaramuzza_files/Research/OcamCalib_Tutorial.htm
[34] Demonceaux, C. and Kachi-Akkouche, D., “Optical Flow Estimation in Omnidirectional Images Using Wavelet Analysis,” Proceedings of Conference on Computer Vision and Pattern Recognition Workshop, Vol. 7, pp. 76, 2003.