傳統的船舶感測設備存在諸如成本高和精度差的問題。另外，用於目標跟踪的算法還受到光源，環境和視點變化的影響，這使得效果較差。這項研究提出了一種適用於無人水面載具的情報，監視和偵察方法，該方法可以實現三個目的：檢測可疑目標，跟踪可疑目標以及警告危險目標。本文使用孿生網絡作為主要的神經網絡架構來實現目標跟踪。此外通過自製的無人水面載具系統，它可以檢測外部環境並在跟踪時避開障礙物，然後發出警告。本研究中提出的方法將通過指標（準確性，精確度，召回率，P-R曲線，F1分數）進行評估。本研究提出的方法不僅可以解決當今海軍艦艇所需的智能管理和控制信息，而且可以為無人水面載具提供新的硬體設計模型和追踪網絡架構。

Traditional ship sensing devices have problems such as high cost and poor accuracy. In addition, the algorithm used for target tracking is also affected by the light source, environment, and viewpoint changes, which makes the effect poor. This research proposes an intelligence, surveillance and reconnaissance method applied to unmanned surface vehicles, which can achieve three purposes: detect suspicious targets, track suspicious targets, and warn of dangerous targets. This thesis uses Siamese Network as the main neural network architecture to achieve target tracking. Two power sources are used in the unmanned surface vehicle: the four-helix wind kinetic energy of the unmanned aerial vehicle and the hydraulic kinetic energy of the double-propeller. In addition, through the self-made unmanned surface vehicle system, it can detect the outside environment and avoid obstacles while tracking, and then warn. The method proposed in this study will be evaluated by indicators (accuracy, precision, recall, P-R curve, F1 score). The method proposed in this research can solve the intelligent management and control information required by naval warships today and provide a new hardware design model and tracking network architecture in unmanned surface vehicles.

[1] N. Suzuki ,H. Kitajima and H. Kaba “An experiment of real-time data transmission of sonar images from cruising UUV to distant support vessel via USV: Development of underwater real-time communication system (URCS) by parallel cruising,” in Proc. OCEANS 2015 - Genova, Genova, Italy, 2015, pp. 1-6.
[2] E. Simetti, A. Turetta, G. Casalino and M. Cresta, “Towards the use of a team of USVs for civilian harbour protection: The problem of intercepting detected menaces,” in Proc. OCEANS'10 IEEE SYDNEY, Sydney, NSW, Australia, 2010, pp. 1-7.
[3] B. M. Kent and R. A. Ehret, “Rethinking Intelligence, Surveillance, and Reconnaissance in a wireless connected world,” in Proc. IEEE International Symposium on Antennas and Propagation, Chicago, IL, USA, 2012, pp. 1-2.
[4] L. Duan, B. Luo, Q. Li and G. Yu, “Research on intelligence, surveillance and reconnaissance mission planning model and method for naval fleet,” in Proc. Chinese Control and Decision Conference, Yinchuan, China, 2016, pp. 2419-2424.
[5] A.I. N. Alshbatat, S. Alhameli, S. Almazrouei, S. Alhameli and W. Almarar, “Automated Vision-based Surveillance System to Detect Drowning Incidents in Swimming Pools,” in Proc. Advances in Science and Engineering Technology International Conferences, Dubai, United Arab Emirates, 2020, pp. 1-5.
[6] S. S. Uz, N. Memarsadeghi and T. Ames, “Supporting Aquaculture in the Chesapeake Bay Using Artificial Intelligence to Detect Poor Water Quality with Remote Sensing,” in Proc. IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA, 2020, pp. 3629-3632.
[7] T. P. Lambrou, C. C. Anastasiou, C. G. Panayiotou and M. M. Polycarpou, “A Low-Cost Sensor Network for Real-Time Monitoring and Contamination Detection in Drinking Water Distribution Systems,” IEEE Sensors Journal., vol. 14, no. 8, pp. 2765-2772, Aug. 2014.
[8] F. Yunsheng, S. Yutong, and W. Guofeng, “On model parameter identification and trajectory tracking control for USV based on backstepping,” in Proc. 36th Chinese Control Conference, Dalian, China, 2017, pp. 4757-4761.
[9] P. Wang and J. Wang, “A Tracking Method Based on Target Classification and Recognition,” in Proc. IEEE Advanced Information Technology, Electronic and Automation Control Conference, Chengdu, China, 2019, pp. 255-259.
[10] Y. Xu, K. Xu, J. Wan, Z. Xiong, and Y. Li, “Research on Particle Filter Tracking Method Based on Kalman Filter,” in Proc. IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, Xi'an, China, 2018, pp. 1564-1568.
[11] E. Gundogdu and A. A. Alatan, “Method for learning deep features for correlation based visual tracking,” in Proc. Signal Processing and Communications Applications Conference, Antalya, Turkey, 2017, pp. 1-4.
[12] Y. Ge, L. Zhong and Z. J. Qiang, “Research on Underactuated USV Path Following Algorithm,” in Proc. Information Technology, Networking, Electronic and Automation Control Conference, Chongqing, China, 2020, pp. 2141-2145.
[13] Y. Ge, L. Zhong and Z. J. Qiang, “Research on USV Heading Control Method Based on Kalman Filter Sliding Mode Control,” in Proc. Cambridge Crystallographic Data Centre, Hefei, China, 2020, pp. 1547-1551.
[14] J. Han, Y. Cho and J. Kim, “Coastal SLAM with Marine Radar for USV Operation in GPS-Restricted Situations,” IEEE Journal of Oceanic Engineering., vol. 44, no. 2, pp. 300-309, April. 2019.
[15] X. Zhou, P. Wu, H. Zhang, W. Guo, “Learn to Navigate: Cooperative Path Planning for Unmanned Surface Vehicles Using Deep Reinforcement Learning,” IEEE Access., vol. 7, pp. 165262-165278, November. 2019.
[16] S. Mane and S. Mangale, “Moving Object Detection and Tracking Using Convolutional Neural Networks,” in Proc. International Confederation of Contamination Control Societies, Madurai, India, 2018, pp. 1809-1813.
[17] Y. Inoue, T. Ono , and K. Inouer, “Situation-Based Dynamic Frame-Rate Control for on-Line Object Tracking,” in Proc. International Japan-Africa Conference on Electronics, Communications and Computations, Alexandria, Egypt, 2018, pp. 119-122.
[18] B. J. Koskowich, M. Rahnemoonfai , and M. Starek, “Virtualot — A Framework Enabling Real-Time Coordinate Transformation & Occlusion Sensitive Tracking Using UAS Products, Deep Learning Object Detection & Traditional Object Tracking Techniques,” in Proc. IEEE International Symposium on Geoscience and Remote Sensing, Valencia, Spain, 2018, pp. 6416-6419.
[19] Y. Liu, Z. Meng, Y. Zou , and M. Cao, “Visual Object Tracking and Servoing Control of a Nano-Scale Quadrotor: System, Algorithms, and Experiments,” in Proc. IEEE/CAA Journal of Automatica Sinica., vol. 8, no. 2, pp. 344-360, February. 2021.
[20] Y. Zhou, T. Wang, R. Hu and H. Su, “Multiple Kernelized Correlation Filters (MKCF) for Extended Object Tracking Using X-Band Marine Radar Data,” IEEE Transactions on Signal Processing., vol. 67, no. 14, pp. 3676-3688, July. 2019.
[21] A. Varfolomieiev and O. Lysenko, “Modification of the KCF tracking method for implementation on embedded hardware platforms,” in Proc. International Conference Radio Electronics & Info Communications, Kiev, Ukraine, 2016, pp. 1-5.
[22] Z. Kalal, K. Mikolajczyk , and J. Matas, “Tracking-Learning-Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence., vol. 34, no. 7, pp. 1409-1422, July 2012.
[23] Dattathreya, S. Han, M. Kim, V. Maik , and J. Paik, “Keypoint-based object tracking using modified median flow,” in Proc. IEEE International Conference on Consumer Electronics-Asia, Seoul, Korea (South), 2016, pp. 1-2.
[24] J. Jiu-cai, Z. Jie and S. Feng, “Modelling, manoeuvring analysis and course following for two unmanned surface vehicles driven by a single propeller and double propellers,” in Proc. The 27th Chinese Control and Decision Conference, Qingdao, China, 2015, pp. 4932-4937.
[25] S. Sun, N. Wang, Y. Liu and B. Dai, “Fuzzy heading control of a rotary electric propulsion ship with double propellers,” in Proc. Proceedings of the 33rd Chinese Control Conference, Nanjing, China, 2014, pp. 4598-4602 10.1109/ChiCC.2014.6895713.
[26] F. M. Raimondi, M. Trapanese, V. Franzitta, A. Viola and A. Colucci, “A innovative semi-immergible USV (SI-USV) drone for marine and lakes operations with instrumental telemetry and acoustic data acquisition capability,” in Proc. OCEANS 2015 - Genova, Genova, Italy, 2015, pp. 1-10.
[27] Q. Zhu, “Design of control system of USV based on double propellers,” in Proc. IEEE International Conference of IEEE Region 10 (TENCON 2013), Xi'an, China, 2013, pp. 1-4.
[28] R. Nuari, E. Utami and S. Raharjo, “Comparison of Scale Invariant Feature Transform and Speed Up Robust Feature for Image Forgery Detection Copy Move,” in Proc. International Conference on Information Technology, Information Systems and Electrical Engineering, Yogyakarta, Indonesia, 2019, pp. 107-112.
[29] M. Z. Uddin, W. Khaksar and J. Torresen, "Activity Recognition Using Deep Recurrent Neural Network on Translation and Scale-Invariant Features,” in Proc. IEEE International Conference on Image Processing, Yogyakarta, Indonesia, 2018, pp. 475-479.
[30] A. Al-Shuibi, A. Aldarawani, H. Al-Homaidi and M. Al-Soswa, “Survey on Image Retrieval Based on Rotation, Translation and Scaling Invariant Features,” in Proc. First International Conference of Intelligent Computing and Engineering, Hadhramout, Yemen, 2019, pp. 1-11.
[31] W. Hou, D. Li, C. Xu, H. Zhang and T. Li, “An Advanced k Nearest Neighbor Classification Algorithm Based on KD-tree,” in Proc. IEEE International Conference of Safety Produce Informatization, Chongqing, China, 2018, pp. 902-905.
[32] J. Zhang and H. Shi, “Kd-Tree Based Efficient Ensemble Classification Algorithm for Imbalanced Learning,” in Proc. International Conference on Machine Learning, Big Data and Business Intelligence, Taiyuan, China, 2019, pp. 203-207.
[33] L. Wei, M. Ding and X. Zhang, "Single Target Tracking Using Reliability Evaluation and Feature Selection," in Proc. International Symposium on Computational Intelligence and Design, Hangzhou, China, 2019, pp. 228-231.
[34] A. E. Mitchell, G. E. Smith, K. L. Bell and M. Rangaswamy, “Single target tracking with distributed cognitive radar,” in Proc. IEEE Radar Conference, Seattle, WA, USA ,2017, pp. 285-288.
[35] B. Li, J. Yan, W. Wu, Z. Zhu, and X. Hu, “High Performance Visual Tracking with Siamese Region Proposal Network,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 8971-8980.
[36] H. Zhou and B. Ni, “Tracking of drone flight by neural network Siamese-RPN,” in Proc. International Conference on Engineering, Applied Sciences and Technology, Chiang Mai, Thailand, 2020, pp. 1-3.
[37] H. Fan and H. Ling, “Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 7944-7953.
[38] F. Huang, L. Yu, T. Shen and L. Jin, “Chinese Herbal Medicine Leaves Classification Based on Improved AlexNet Convolutional Neural Network,” in Proc. IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference, Chengdu, China, 2019, pp. 1006-1011.
[39] Y. Beeharry and V. Bassoo, “Performance of ANN and AlexNet for weed detection using UAV-based images,” in Proc. International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering, Réduit, Republic of Mauritius, 2020, pp. 163-167.
[40] S. Fairuz, M. H. Habaebi and E. M. A. Elsheikh, “Finger Vein Identification Based on Transfer Learning of AlexNet,” in Proc. International Conference on Computer and Communication Engineering, Hyderabad, India, 2018, pp. 465-469.
[41] K. -H. Shih, C. -T. Chiu, J. -A. Lin and Y. -Y. Bu, “Real-Time Object Detection with Reduced Region Proposal Network via Multi-Feature Concatenation,” IEEE Transactions on Neural Networks and Learning Systems., vol. 31, no. 6, pp. 2164-2173, June. 2020.