水下無人載具在水下進行任務時，如海底電纜的維修與檢查、海底地形的探勘等，都需要有懸停的能力。懸停控制包含兩個部份，載具移動量的估測與懸停控制系統。本文提出一個估測水下無人載具移動量的單眼視覺系統，利用裝設於水下無人載具底部的攝影機所提供的海床影像，使用以特徵為基礎的影像拼嵌方法，將影像中的特徵萃取出來與目標影像作比對，估測載具的移動量。我們建立一個視覺伺服控制架構，在載具深度沒有變動的情況下，藉由不斷回授的影像誤差訊號，補償水下無人載具因海流干擾所造成的偏移，達到水下無人載具懸停的目的。

Station-Keeping is an important capability of the Unmanned Underwater Vehicle in a variety of mission , including inspection and repair of undersea pipeline , and surveillance . Station-Keeping control includes two parts : motion estimation and Station-Keeping control system . In this thesis we propose a monocular vision system for determining the motion of an Unmanned Underwater Vehicle . The vehicle is equipped with a down-looking camera , which provides images of the sea-floor . The motion of vehicle is estimated with a feature-based mosaicking method which requires the extraction and the matching of relevant features . We designed a visual servo control system for maintaining the position of vehicle relative to a visual landmark , while maintaining a fixed depth .

第一章　緒論 1
1.1前言 1
1.2文獻回顧 2
1.3研究方法 4
1.4論文架構 4
第二章　相關理論 6
2.1灰階化 6
2.2基本運算式 7
2.2.1交互相關運算 7
2.2.2迴旋積 8
2.3差分運算子 9
2.3.1一維差分運算子 9
2.3.2二維差分運算子 10
2.4濾波器 12
2.4.1空間高斯濾波器(Gaussian Filter) 12
2.4.2最大值與最小值濾波器 14
2.5特徵萃取 15
2.5.1莫拉維茨角隅偵測(Moravec Corner Detection) 15
2.5.2海利斯角隅偵測(Harris Corner Detection) 16
第三章　視覺伺服 22
3.1影像流 24
3.2特徵萃取 25
3.3特徵匹配 26
3.3.1最大相關係數 27
3.3.2刪除不適合特徵點 30
3.4移動量估測 33
第四章　控制架構 36
4.1視覺伺服控制 36
4.2視覺控制器設計 38
第五章　系統模擬與分析 41
5.1模擬裝置 41
5.2無海流干擾下模擬實驗 46
5.2.1目標追循實驗 46
5.3具海流干擾下模擬實驗 50
5.3.1目標追循實驗 50
5.3.2 懸停控制實驗 53
5.4具正弦海流干擾下模擬實驗 58
5.4.1目標追循實驗 59
5.4.2懸停控制實驗 62
5.5穩態誤差現象 66
第六章　結論與未來展望 68
參考文獻 70

[1].A. Bruss and B. Horn, “Passive Navigation,” Computer Vision, Graphics, and Image Processing, vol. 21, 1983, pp. 3-20.
[2].A. Plotnik and S. Rock, “Automatic ROV Positioning Services Tethered Ocean Moorings,” Sea Technology, vol. 48, Apr. 2007, pp. 50-54.
[3].A. Plotnik and S. Rock, “Visual Servoing of an ROV for Servicing of Tethered Ocean Moorings,” OCEANS 2006, 2006, pp. 1-6.
[4].C. Harris and M. Stephens, “A combined corner and edge detector,” Proceedings of The Fourth Alvey Vision Conference, Manchester: 1988, pp. 189-192.
[5].E. Vincent and R. Laganiere, “Matching feature points in stereo pairs:A comparative study of some matching strategies,” Machine Graphics & Vision, vol. 10, 2001, pp. 237-259.
[6].H. Moravec, “Obstacle avoidance and navigation in the real world by a seeing robot rover,” tech. report CMU-RI-TR-80-03, Robotics Institute, Carnegie Mellon University & doctoral dissertation, Stanford University: 1980.
[7].P. Smith et al., “Effective corner matching,” British Machine Vision Conference, 1998.
[8].R. Garcia et al., “Positioning an underwater vehicle through image mosaicking,” Robotics and Automation, 2001. Proceedings 2001 ICRA. IEEE International Conference on, 2001, pp. 2779-2784 vol.3.
[9].S. Negahdaripour and C. Yu, “A generalized brightness change model for computing optical flow,” Computer Vision, 1993. Proceedings., Fourth International Conference on, 1993, pp. 2-11.
[10].S. Negahdaripour, X. Xu, and L. Jin, “Direct estimation of motion from sea floor images for automatic station-keeping of submersible platforms,” Oceanic Engineering, IEEE Journal of, vol. 24, 1999, pp. 370-382.
[11].S. van der Zwaan and J. Santos-Victor, “Real-time vision-based station keeping for underwater robots,” OCEANS, 2001. MTS/IEEE Conference and Exhibition, 2001, pp. 1058-1065 vol.2.
[12].S. van der Zwaan, A. Bernardino, and J. Santos-Victor, “Visual station keeping for floating robots in unstructured environments,” Robotics and Autonomous Systems, vol. 39, Jun. 2002, pp. 145-155.
[13].S. Wasielewski and M. Aldon, “Dynamic vision for ROV stabilization,” OCEANS '96. MTS/IEEE. 'Prospects for the 21st Century'. Conference Proceedings, 1996, pp. 1082-1087 vol.3.
[14].X. Cufi, R. Garcia, and P. Ridao, “An approach to vision-based station keeping for an unmanned underwater vehicle,” Intelligent Robots and System, 2002. IEEE/RSJ International Conference on, 2002, pp. 799-804 vol.1.
[15].何忠興，平移運動影像之伺服追循系統，國立中山大學機械與機電工程學系碩士論文，中華民國九十二年六月。
[16].陳建守，海底無人小艇之光流視覺伺服控制，國立中山大學機械工程研究所論文，中華民國八十五年五月。
[17].楊武智，影像處理與辨認，全華科技圖書股份有限公司，ISBN：957-21-0788-7，中華民國八十三年十二月初版。