| 研究生: |
蘇郁棣 Su, Yu-Ti |
|---|---|
| 論文名稱: |
應用移動向量於影像導引視覺伺服系統 Study of Image-Guiding Visual Servo System Based on Motion Vector |
| 指導教授: |
陳添智
Chen, Tien-Chi |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 工程科學系 Department of Engineering Science |
| 論文出版年: | 2005 |
| 畢業學年度: | 93 |
| 語文別: | 英文 |
| 論文頁數: | 90 |
| 中文關鍵詞: | 視覺伺服系統 、移動向量 |
| 外文關鍵詞: | Visual Servo System, Motion Vector |
| 相關次數: | 點閱:83 下載:2 |
| 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 |
近年來,數位視訊技術及機械製程上有很大的技術突破,而兩者所結合而成的系統也因此被廣泛地應用於各種研究領域上。這種以影像回授來達到閉迴路位置控制的系統統稱為視覺伺服系統,在保全系統,無人駕駛之自走車等實用領域有非常大的發展空間。
本篇論文根據“移動向量”的主要概念,提出了一個新穎的架構,藉之以達到即時“偵測目標以及影像追縱”之目的,並將之應用於一部架設有攝影機的自走車上來達到實証。這部被稱為“影像導引視覺伺服系統”的車體利用由CMOS感應器回授回來的數位影像陣列訊號,並透過如目標偵側的影像處理流程,而得到主要目標物的移動軌跡,進而送出速度命令給予車體馬達,以達到即時追縱之目的。在本論文中,“動態估測”被用來當作運算目標物移動軌跡的演算法,其具有精準且有效率地算出移動目標的移動向量進以達到控制車體的優點。在實際應用上,整套演算法僅採用一顆數位訊號處理晶片來當作中央處理器,以達到即時影像追縱之需求。
為了要驗証本篇論文所提出的方法與架構,靜態與動態的實驗結果將會呈現出來。為求整體架構的實用性,實驗會在不同的環境,以及不同的狀況之下執行,以驗証整體架構的可行度。結合簡單的硬體需求以及所提出的演算法,系統將會達到不錯的影像追縱情形。
Recently, the technical progress in digital image technologies and mechanics has made the combination of image and mechanics system become an active research field, while the system using vision to aim for controlling is described as visual servo system. Visual servo system is broadly used in many application areas, such as security, autonomous mobile robots, etc.
This thesis presents a novel approach based on the idea of “motion vector” to perform real time “target detecting and movement tracking” task, which is able to guide an eye-on-car robot using real time image processing equipment. The image-guiding visual servo system uses the binary image features from a CMOS sensor on the mobile vehicle to handle the image processing, target detection, and provides the output information for the mobile vehicle control system. The unique motion estimation process provides a simple and useful method between the moving target and desired output for controlling the vehicle. The whole algorithms are integrated into a single DSP chip to achieve the real-time visual tracking system.
To demonstrate the advantages of the proposed approach, experiments are executed and the results will be shown as static part along with the dynamic response. Through the experiment results, different cases are adopted to evaluate the feasibility for the proposed strategy. The experimental results show that the hardware implementation with the proposed approach has good performance to achieve the visual tracking task.
[1] V. Markandey, A. Reid and S. Wang, “Motion Estimation for Moving Target Detection,” IEEE Trans. on Aerospace and Electronic Systems, Vol. 32, No. 3, pp. 866-874, July 1996.
[2] R. Kelly, “Stable Visual Servoing of Camera-in-Hand Robotic Systems,” IEEE/ASME Trans. on Mechatronics, Vol. 5, No. 1, pp. 39-48, March 2000.
[3] J. Stavnitzky and D. Capson, “Multiple Camera Model-Based 3-D Visual Servo, ” IEEE Trans. on Robotics and Automation, Vol. 16, No. 6, pp. 732-739, December 2004.
[4] K. Y. Chen, M. Y. Cheng and M. C. Tsai, “Design and Implementation of A Real-Time Pan-Tilt Visual Tracking System,” IEEE International Conference on Control Applications, pp. 736-741, September 2002.
[5] S. Yamamoto, Y. Mae, Y. Shirai, J. Miura, “Realtime Multiple Object Tracking Based on Optical Flows,” IEEE International Conference on Robotics and Automation, Proceedings, Vol. 3, pp. 2328-2333, May 1995.
[6] M. B. Ahmad and C. T. Sun, “Local Threshold and Boolean Function Based Edge Detection,” IEEE Trans. on Consumer Electronics, Vol. 45, pp. 674-679, August 1999.
[7] R. R. Rakesh, P. Chaudhuri and C. A. Murthy, “Thresholding in Edge Detection: A Statistical Approach,” IEEE Trans. On Image Processing, Vol. 13, pp. 927-936, July 2004.
[8] O. R. P. Bellon and L. Silva, “New Improvements to Range Image Segmentation by Edge Detection,” IEEE Signal Processing Letters, Vol. 9, pp. 43-45, February 2002.
[9] G. Jing, C. E. Siong and D. Rajan, “Foreground Motion Detection by Difference-Based Spatial Temporal Entropy Image,” IEEE Region 10 Conference on Tencon, Vol. A, pp. 379-382, November 2004.
[10] P. M. Ngan, “Motion Detection in Temporal Clutter,” Tech. Rep. 693, Industrial Research Limited, Auckland, New Zealand, March 1997.
[11] J. Richefeu and A. Manzanera, “A New Hybrid Differential Filter For Motion Detection,” International Conference on Computer Vision and Graphics, Vol. 4, Warsaw, Poland, September 2004.
[12] A. Broggi, M. Bertozzi, A. Fascioli and M. Sechi, “Shape-Based Pedestrian Detection,” IEEE Proceedings on Intelligent Vehicles Symposium, pp. 215-220, October 2000.
[13] Z. c ivkovi Z ′, “Motion Detection and Object Tracking in Image Sequences,” Ph.D. Thesis, ASCI dissertation No. 91, University of Twente, AE Enschede, Netherlands, June 2003.
[14] I. Ishii, Y. Nakabo and M. Ishikawa, “Target Tracking Algorithm for 1 ms Visual Feedback System Using Massively Parallel Processing,” IEEE International Conference on Robotics and Automation, Vol. 3, pp. 2309 – 2314, April 1996.
[15] K. Hatano and K. Hashimoto, “Image-Based Visual Servo Using Zoom Mechanism,” Annual Conference SICE, Vol. 3, pp. 2443 – 2446, Aug. 2003.
[16] T. H. S. Li, S. J. Chang and W. Tong, “Fuzzy Target Tracking Control of Autonomous Mobile Robots by Using Infrared Sensors,” IEEE Trans. on Fuzzy Systems, Vol. 12, pp. 491 – 501, Aug. 2004.
[17] R. C. Luo and T. M. Chen, “Autonomous Mobile Target Tracking System Based on Grey-Fuzzy Control Algorithm,” IEEE Trans. on Industrial Electronics, Vol. 47, pp. 920 – 931, Aug. 2000.
[18] J. Watkinson, The Engineer’s Guide to Motion Compensation, Copyright by Snell & Wilcox, 1994.