本研究主要提出透過影像處理技術進行水下目標物之追蹤控制系統，此系統由水下環境、目標特徵和動態屬性組成，搭配輔助光源進行視覺技術的處理，用於自主式水下載具(Autonomous Underwater Vehicle, AUV)。在影像處理由於檢測範圍有限與能見度較差，針對水下圖像進行雜訊處理，圖像處理包括色彩空間轉換、二值化進行目標物與背景分離、中值濾波器去除雜訊、影像形態學使影像辨識結果更加完整。得到水下目標物影像資訊後，計算出影像之面積與座標點作為PID控制器的輸入值，再加入MATLAB模擬之PID TUNER控制器內得出最佳增益值，且透過影像資訊定義伺服舵機轉動角度與螺槳轉速，以上實驗皆由穩定性能水槽完成。最後於拖航水槽進行PID控制器與加入卡爾曼濾波器實驗比較，而卡爾曼濾波器為透過原始目標物座標進行新座標預測，由兩種方式作為導航之參考依據，觀察舵板的角度變化與推進速度之效果。

This study mainly develops an image navigation system of an Autonomous Underwater Vehicle (AUV) for tracking underwater objects through image processing technology. This system is composed of underwater environment, target characteristics and dynamic attributes, which are combined with auxiliary light source for visual processing in AUV. Due to the limited detection range and poor visibility in image processing, noise processing is carried out for underwater images. Image processing includes color space conversion, binarization for target object and background separation, median filter for noise removal, and image morphology to make image identification results more complete. After obtaining the underwater target image information, the area of the image and the reference point of the image were calculated as the input values of the PID controller. Subsequently, the PID TUNER controller simulated by MATLAB was added to obtain the optimal gain value. The rudder angle and propeller speed were defined through the image information. At last, the PID controller was compared with the experimental results by including the Kalman filter in the towing tank. The Kalman filter was used to predict the new coordinates through the original target coordinates. The two methods are used as the reference for navigation to observe the effect of the variations of the rudder plates and the thruster speed.

1. Widditsch, H., SPURV-The first decade. 1973, WASHINGTON UNIV SEATTLE APPLIED PHYSICS LAB.
2. Allen, B., et al. REMUS: a small, low cost AUV; system description, field trials and performance results. in Oceans' 97. MTS/IEEE Conference Proceedings. 1997. IEEE.
3. Kumagai, M., et al. New AUV designed for lake environment monitoring. in Proceedings of the 2000 International Symposium on Underwater Technology (Cat. No. 00EX418). 2000. IEEE.
4. Yoerger, D.R., A.M. Bradley, and B.B. Walden. The autonomous benthic explorer (ABE): An AUV optimized for deep seafloor studies. in Proceedings of the seventh international symposium on unmanned untethered submersible technology (UUST91). 1991.
5. Petillot, Y., S. Reed, and J.M. Bell. Real time AUV pipeline detection and tracking using side scan sonar and multi-beam echo-sounder. in OCEANS'02 MTS/IEEE. 2002. IEEE.
6. Purcell, M., et al. Use of REMUS 6000 AUVs in the search for the Air France Flight 447. in OCEANS'11 MTS/IEEE KONA. 2011. IEEE.
7. Vaneck, T.W., et al., Automated bathymetry using an autonomous surface craft. Navigation, 1996. 43(4): p. 407-419.
8. Jacobi, M. and D. Karimanzira. Underwater pipeline and cable inspection using autonomous underwater vehicles. in 2013 MTS/IEEE OCEANS-Bergen. 2013. IEEE.
9. Park, J.-Y., et al., Experiments on vision guided docking of an autonomous underwater vehicle using one camera. Ocean Engineering, 2009. 36(1): p. 48-61.
10. Sahu, B.K. and B. Subudhi, Adaptive tracking control of an autonomous underwater vehicle. International Journal of Automation and Computing, 2014. 11(3): p. 299-307.
11. Hagen, P.E., O. Midtgaard, and O. Hasvold. Making AUVs truly autonomous. in OCEANS 2007. 2007. IEEE.
12. Leonard, J.J. and A. Bahr, Autonomous underwater vehicle navigation, in Springer Handbook of Ocean Engineering. 2016, Springer. p. 341-358.
13. Papanikolopoulos, N.P. and P.K. Khosla, Adaptive robotic visual tracking: Theory and experiments. IEEE Transactions on Automatic Control, 1993. 38(3): p. 429-445.
14. Balasuriya, B., et al. Vision based autonomous underwater vehicle navigation: underwater cable tracking. in Oceans' 97. MTS/IEEE Conference Proceedings. 1997. IEEE.
15. Bazeille, S., I. Quidu, and L. Jaulin, Color-based underwater object recognition using water light attenuation. Intelligent service robotics, 2012. 5(2): p. 109-118.
16. Yu, S.-C., et al. Navigation of autonomous underwater vehicles based on artificial underwater landmarks. in MTS/IEEE Oceans 2001. An Ocean Odyssey. Conference Proceedings (IEEE Cat. No. 01CH37295). 2001. IEEE.
17. Jalving, B., The NDRE-AUV flight control system. IEEE Journal of Oceanic Engineering, 1994. 19(4): p. 497-501.
18. Hitam, M.S., et al. Mixture contrast limited adaptive histogram equalization for underwater image enhancement. in 2013 International conference on computer applications technology (ICCAT). 2013. IEEE.
19. Pramunendar, R.A., et al., Auto level color correction for underwater image matching optimization. Int. J. Comput. Sci. Netw. Secur., 2013. 13(1): p. 18-23.
20. Kalman, R.E., A new approach to linear filtering and prediction problems. 1960.