臺灣博碩士論文加值系統

小型無人飛行載具(Small Unmanned Aerial Veicle, Small UAV)常須以穩定的飛行姿態來執行地面目標的偵搜及辨識任務，為了維持穩定的飛行姿態，本研究在於開發一套適合Small UAV使用的視覺化飛控系統，此系統以天際線偵測的演算法為核心，利用偵測影像邊界的天際線端點來解決不規則天際線偵測的問題，並將已偵測的天際線轉換為控制飛行器姿態的水平角及俯仰參考值。這套系統整合了攝影機、飛行載具、伺服機、傳輸與接收元件、遙控裝置及地面電腦等硬軟體設備，而比例積分控制器(Proportional Integral Controller, PI Controller)也已一併整合於飛控系統內。根據靜態實測的結果，五種不同條件的測試樣本平均準確率可達到98.62%以上，而動態的自動飛行測試也驗證了本論文研發的低價飛控系統確實能夠提供即時、抗雜訊及準確偵測天際線的能力。
另外，由於海洋資源豐富且海事活動頻繁，海面船艦成為Small UAV主要的監控標的，如何將空拍回傳的船艦影像有效率地從龐大的船艦資料庫中完成比對及辨識成為重要的課題，因此，本論文延伸發展了一套以提升比對效率為導向的船艦尺度不變特徵轉換(Scale Invariant Feature Transform, SIFT)描述子特徵資料庫辨識系統。該系統藉由模糊C均值法(Fuzzy C Mean, FCM)及索貝爾(Sobel)邊緣偵測法的結合，以先粗後細的方式完成去浪及船艦切割，切割後的船艦可以產生數量較少的SIFT關鍵點(Keypoint)；接著，以切割船艦的方向資訊來排除資料庫內不需要的比對選項，並以 SIFT關鍵點的三角比對機制來縮短比對次數及強健比對的正確率，而評分機制則用來決定出最終的比對結果，經驗證本研究提出的方法可大幅提升原來SIFT船艦資料庫全域搜尋的比對效率。

In this study, a vision-based flight control system using a skyline-detection algorithm is developed for small unmanned aerial vehicles (UAVs) The skyline-detection algorithm is able to detect straight or uneven skylines. This system integrates a remote controller, a remotely controlled airplane, a camera, a wireless transmitter/receiver, a ground control computer, and the proposed skyline-detection algorithm to achieve the flight stability of automatic control. Static and dynamic tests are conducted to validate the system performance. In the static tests, the average accuracy rate for skyline detection is 98.62%, based on five test videos. In the dynamic tests, straight and circular flight paths are used to verify lateral and longitudinal stability for the proposed flight control system. The experimental results demonstrate the performance and robustness of the algorithm and the feasibility and potential of a low-cost, vision-only flight control system. Besides, a SIFT-based ship detection and recognition system is also developed in this study. To solve the problem that the captured images may be affected under complex lighting and marine variation, the integrated segmentation and recognition algorithm is developed. According to the experimental results, the proposed system can improve the key-points matching in the database more efficiently than the global search methods.

誌謝 ii
摘要 iii
ABSTRACT iv
目錄 v
表目錄 vii
圖目錄 viii
1. 緒論 1
1.1 研究動機與目的 1
1.2 研究範圍與方法 2
1.3 研究成果與架構 4
2. 文獻探討 5
3. 飛行姿態控制系統 10
3.1 問題描述與現況分析 10
3.2 演算流程 12
3.2.1初始偵測階段 13
3.2.2追蹤偵測階段 17
3.3 系統實現 23
3.4 實驗結果與討論 28
3.4.1天際線偵測結果 28
3.4.2空中飛行姿態控制結果 40
3.5 小結 45
4. 海面船艦辨識系統 46
4.1 問題描述與現況研析 46
4.2 演算流程 47
4.2.1船艦切割演算法 48
4.2.2船艦辨識演算法 57
4.3 實驗結果與討論 67
4.3.1船艦切割結果 67
4.3.2船艦辨識結果 78
4.4 小結 81
5. 結論與未來目標 82
參考文獻 83
論文發表 89
自傳 90

[1]Yi, G. and Ferrer, C., “IMS/GPS Integration with a Novel Real-Time System Platform for Inertial Data Estimation,” Proceedings of IEEE International Conference on Computer As a Tool, Warsaw, Poland, pp. 2503-2508, 2007.
[2]Wang, J., Garratt, M., Lambert, A., Wang, J. J., Hana, S., and Sinclair, D., “Integration of GPS/INS/VISION Sensors to Navigate Unmanned Aerial Vehicles,” Proceedings of International Conference on Remote Sensing and Spatial Information Science, Beijing, China, pp. 963-970, 2008.
[3]Woodman, O. J., “An Introduction to Inertial Navigation,” Technical Report, University of Cambridge, U.K, 2007.
[4]Izadian, A., Dawson, J., and Famouri, P., “Input-Output Synchronization for Bias Drift Reduction of MEMS Gyroscopes,” Proceedings of IEEE International Conference on American Control, Washinton, U.S.A, pp. 3751-3754, 2008.
[5]Ettinger, S., Nechyba, M., Ifju, P., and Waszak, M., “Vision-Guided Flight Stability and Control for Micro Air Vehicles,” Proceedings of IEEE International Conference on Intelligent Robots and Systems, Laussanne, Switzerland, pp. 2134-2140, 2002.
[6]Ettinger, S., “Design and Implementation of Autonomous Vision-Guided Micro Air Vehicles,” M.S. Thesis, Electrical and Computer Engineering, University of Florida, California, U.S.A, 2001.
[7]Pereira, G.A.S., Iscold, P., and Torres, L.A.B., “Airplane Attitude Estimation Using Computer Vision: Simple Method and Actual Experiments,” Electro. Lett., Vol. 44, No.22, 2008.
[8]Trucheet, F., Aubreton, O., Gorria, P., and Laligant, O., “Attitude Measurement by Artificial Vision,” Meas. Sci. Techono., Vol 17, No. 1, pp.101-110, 2006.
[9]Cornal, T. and Egan, G., “Heaven and Earth: How to Tell the Difference,” Technical Report, University of Monash, Australia, 2005.
[10]Cornall, T. and Egan, G., “Measuring Horizon Angle from Video on a Small Unmanned Air Vehicle,” Proceedings of IEEE International Conference on Autonomous Robots Agents, Palmerston North, New Zealand, pp. 339-344, 2004.
[11]Webb, T. and Prazenica, R., “Vision-Based State Estimation for Autonomous Micro Air Vehicles,” Journal of Guidance Control and Dynamics, Vol. 30, No. 3, pp. 816-826, 2007.
[12]Wagter, C., Proctor, A., and Johnson, E., “Vision only Aircraft Flight Control,” Proceedings of IEEE International Conference on Digital Avionics Systems, Indianapolis, U.S.A., pp. 2-11, 2003.
[13]Guiqui, B., Zhaoying, Z., Shenshu, X., and Xiongying, Y., “Vision-Based Flight Parameter Extraction for Micro Air Vehicles,” Proceedings of IEEE International Conference on Aerospace, Montana, U.S.A., pp. 2839-2847, 2003.
[14]Edwards, B., Archibald, J., Fife, W., and Lee, D., “A Vision System for Precision MAV Targeted Landing,” Proceedings of IEEE International Conference on Robotics and Automation, Florida, U.S.A., pp. 125-130, 2007.
[15]Fowers, S., Lee, D., Tippetts, B., Lillywhite, K., Dennis, A., and Archibald, J., “Vision Aided Stabilization and the Development of a Quad-Rotor Micro UAV,” Proceedings of IEEE International Conference on Robotics and Automation, Florida, U.S.A., pp. 143-148, 2007.
[16]Proctor, A., Johnson, E., and Apker, T., “Vision-only Control and Guidance for Aircraft,” J. of Fiel. Robo., Vol. 23, No. 10, pp. 863-890, 2006.
[17]http://vimeo.com/
[18]Todorovic, S. and Nechyba, M., “A Vision System for Horizon Tracking and Object Recognition for Micro Air Vehicles,” Proceedings of International Conference on Recent Advances in Robotics, Florida, U.S.A, pp. 11-18, 2004.
[19]Todorovic, S. and Nechyba, M., “A Vision System for Intelligent Mission Profiles of Micro Air Vehicles,” IEEE Trans. Vehi. Tech., Vol. 53, No. 6, pp1713-1725, 2004.
[20]Todorovic, S. and Nechyba, M. C., “Multiresolution Linear Discriminant Analysis: Efficient Extraction of Geometrical Structures in Images,” Proceedings of IEEE International Conference on Image Processing, Barcelona, Spain, pp. 1029-1032, 2003.
[21]Todorovic, S., “Statistical Modeling and Segmentation of Sky/Ground Images,” M.S. Thesis, Electrical and Computer Engineering, University of Florida, California, 2002.
[22]Todorovic, S. and Nechyba, M., “Towards Intelligent Mission Profiles of Micro Air Vehicles: Multiscale Viterbi Classfication,” Proceedings of the Eighth European Conference on Computer Vision, Prague, Czech, pp. 178-189, 2004.
[23]Bao, G. Q., Xiong, S. S., and Zhou, Z. Y., “Vision-Based Horizon Extraction for Micro Air Vehicle Flight Control,” IEEE Trans. on Inst. and Meas., Vol 54, No 3, pp. 1067-1072, 2005.
[24]Cornall, T. D., Egan, G. K., and Price, A., “Aircraft Attitude Estimation from Horizon Video,” Electro. Lett., Vol. 42, No. 13, pp.744-745, 2006.
[25]Fefilatyev, S., Smarodzinava, V., Hall, L., and Goldgof, D., “Horizon Detection Using Machine Learning Techniques,” Proceedings of IEEE International Conference on Machine Learning and Applications, Maryland, U.S.A, pp. 17-21, 2006.
[26]Dusha, D., Boles, W., and Walker, R., “Attitude Estimation for a Fixed-Wing Aircraft Using Horizon Detection and Optical Flow,” Proceedings of International Conference on Digital Image Computing Techniques and Application, Australia, pp. 485-492, 2007.
[27]McGee, T. G., Sengupta, R., and Hedrick, K., “Obstacle Detection for Small Autonomous Aircraft Using Sky Segmentation,” Proceedings of IEEE International Conference on Robotics and Automation, pp.4679-4684, 2005.
[28]Dong, Y. F., Zhang, Y. F., Zhu, C., and Wang, A. B., “Extracting Sea-Sky-Line Based on Improved Local Complexity,” Proceedings of IEEE International Conference on Computer, Mechatronics, Control and Electronic Engineering, pp. 82-85, 2010.
[29]Yuan, H. Z., Zhang, X. Q., and Feng, Z. L.,“Horizon Detection in Foggy Aerial Images,” Proceedings of IEEE International Conference on Image Analysis and Signal Processing, pp. 191-194, Zhejiang, China, 2010.
[30]Lie, W. N., Lin, T. C. I., Lin, T. C., and Huang, K. S.,“A Robust Dynamic Programming Algorithm to Extract Skyline in Images for Navigation,” Patt. Recog. Lett., Vol. 26, No. 2 , pp. 221-230, 2005.
[31]Bhanu, B. and Richard, D. H., “Model-Based Segmentation of FLIR Images,” IEEE Trans. on Aeros. and Electro. Systems, Vol. 26, No. 1, 1990.
[32]Lu, J., Yu, W., Jin, Y., and Guo, G., “Multiscale Edge Detection for Infrared Ship Target Recognition,” Proceedings of IEEE International Conference on Aerospace and Electronics, Atlanta, U.S.A, pp. 314-319, 1995.
[33]Withagena, P., Schuttea, K., Vossepoelb, A., and Breuers, M., “Automatic Classification of Ships from Infrared Images,” Proceedings of SPIE Conference on Signal Processing, Sensor Fusion, and Target Recognition, Orlando, U.S.A, pp. 180-187, 1999.
[34]Gouaillier, V. and Gagnon, L., “Ship Silhouette Recognition Using Principal Components Analysis,” Proceedings of SPIE Conference on Applications of Digital Image Processing, San Diego, U.S.A, pp. 59-69, 1997.
[35]Gagnon, L. and Klepko, R., “Hierarchical Classifier Design for Airborne SAR Images of Ships,” Proceedings of SPIE Conference on Automatic Target Recognition, Orlando, U.S.A, pp. 38-49, 1998.
[36]Chen, L. and Meek, A., “Likelihood Ratio Test Polarimetric SAR Ship Detection Application,” DRDC Technical Memorandum, Ottawa, Canada, pp. 23-35, 2005.
[37]Osman, H. and Blostein, S. D., “Probabilistic Winner-Take-All Segmentation of Images with Application to Ship Detection,” IEEE Trans. Syst., Man, Cybern. B, Cybern., Vol. 30, No. 3, pp. 485-490, 2000.
[38]Liao, M., Wang, C., Wang, Y., and Jiang, L., “Using SAR Images to Detect Ships From Sea Clutter,” IEEE Geosci. and Remote Sens. Lett., Vol. 5, No. 2, pp. 194-198, 2008.
[39]Bon, N., Hajduch, G., Khenchaf, A., Garella, R., and Quellec, J. M., “Recent Developments in Detection, Imaging and Classification for Airborne Maritime Surveillance,” IET Sign. Proce., Vol. 2, No. 3, pp.192-203, 2008.
[40]Pastina, D. and Spina, C., “Multi-Feature Based Automatic Recognition of Shiptargets in ISAR,” IET Rad., Son. and Navi., Vol. 3, No. 4, pp. 406-423, 2009.
[41]Zhu, C., Zhou, H., Wang, R., and Guo, J., “A Novel Hierarchical Method of Ship Detection from Spaceborne Optical Image Based on Shape and Texture Features,” IEEE Geosci. and Remote Sens., Vol. 48, No. 9, pp. 3464-3456, 2010.
[42]Otsu N., “A Threshold Selection Method from Gray Level Histograms,” IEEE Trans. on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 62-66, 1979.
[43]Chiu, C. C., Hsieh, C. H., Chao, C. W., and Lu, P. C., “New Fuzzy Clustering Algorithms for Vector Quantization of Images,” Proceedings of IEEE International Conference on Consumer Electronics, Illinois, U.S.A, pp. 216-217, 1993.
[44]Bezdek, J. C., Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum Press, New York, pp. 68-79, 1981.
[45]Lowe, D., “Distinctive Image Features from Scale-Invariant Keypoints,” Inter. J. of Comp. Vis., Vol. 60, No. 2, pp. 91-100, 2004.
[46]Gonzalez, R. C. and Woods, R. E., Digital Image Processing, Pearson Education, New Jersey, pp. 519-560, 2002.
[47]Zabidi, M. M. A., Mustapa, J., Mokji M. M., and Marsono, M. N., Shaameri A. Z., “Embedded Vision Systems for Ship Recognition,” Proceedings of TENCON Conference on Signal Processing, Singapor, pp. 1-5, 2009.
[48]Luo Q., Khoshgoftaar T. M., and Folleco A., “Classification of Ships in Surveillance Video,” Proceedings of IEEE International Conference on Information Reuse and Integration, Waikoloa Village, HI, pp. 432-437, 2006.
[49]Feineigle A. P., Morris D. D., and Snyder F. D., “Ship Recognition Using Optical Imagery for Harbor Surveillance,” Proceedings of Association for Unmanned Vehicle Systems International (AUVSI), Washington, DC, 2007.