Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/152036
|
| Title: | 微型無人機空域防衛之即時攔截與追捕之技術研究
Technical Research on UAV Airspace Defense by Realtime Interception and Capture |
| Authors: | 李明家
MINGCHIA, LI |
| Contributors: | 劉吉軒
Liu, Jyi-shane
李明家
MINGCHIA, LI |
| Keywords: | 無人機
空域防衛
物件偵測
物件追蹤
自主導航
單目 距離估測
UAV
airspace defense
object detection
object tracking
autonomous navigation
monocular distance estimation |
| Date: | 2023 |
| Issue Date: | 2024-07-01 12:30:27 (UTC+8) |
| Abstract: | 無人機應用於當前科技領域中進展極為快速，鑒於 2022 年烏俄戰
爭中無人機被大量地使用並且影響許多戰事，且相關事蹟廣於新聞媒
體上流傳，使得人們更加關注此項技術。事實上，無人機因其高機動
性、易於部署，不論是在軍事用途、警用消防，亦或是在民生服務、
藝術攝影等上都早已有相當大的發展，並廣受各領域人群歡迎。然而
同時，無人機的濫用及衍生問題也逐漸開始增生，例如：使用無人機
進行偷拍、跟蹤的違法行為層出不窮，已構成對當事人隱私及私人領
域的騷擾；未遵守空中管制區的規定，操控無人機至機場、航道等管
制區，對飛機起落造成極大干擾；操控無人機至軍事基地進行騷擾，
對國防安全造成嚴重影響…等等，鑒於上述現象，可得知空域防衛為
一重要課題，值得深入探討及研究。
本論文提出空域防衛之技術研究，其概念近似於空中戰機纏鬥，並
探討該技術之自動化：無人機使用鏡頭影像尋找目標機 (敵機) 並自動
鎖定及追蹤，並將其捕獲、擊落作為任務的最終目標。在技術方面，
本研究基於 Yolo 來達成對目標機 (敵機) 的物件偵測，針對目標進行追
蹤以及速度及距離估測，實作出對目標無人機的自動鎖定及追蹤，最
終完成捕捉任務。
UAV Application develops rapidly in recent years. In view of the 2022 Ukrainian-
Russian war, UAVs were frequently used in many battles, and related news were
widely spread in the social media, people consider UAV important and pay more
attention on it. In fact, due to its highly flexibility, drones have already had consid-
erable development in various fields such as military, police, EMS(Emergency Med-
ical Service), photography, art, and civilian use, etc. However, drones are abused in
many wrong purpose. For example, drones are used for photo and video sneaking
and harassment; drones are used against regulation of ATC(Air Traffic Control) and
cause interference to the airport; drones fly upon military bases and make harass-
ment, which causes severe threat to national defense. Therefore, airspace defense is
certainly an important issue and worthy of further study.
This study focuses on airspace defense. The concept is related to airspace dog-
fight. UAV will find target drone(hostile drone) with onboard camera and track it au-
tomatically, and finally hunt it down. The experiment use Yolo and computer vision
techniques to implement object detection. Several tracking methods will be com-
bined with Yolo to estimate speed, distance on target drone(hostile drone). Finally,
a drone auto-tracking system will be constructed. |
| Reference: | 參考文獻
[1] Kevin W Williams. A summary of unmanned aircraft accident/incident data: Human
factors implications. Technical report, Federal Aviation Administration Oklahoma
City Ok Civil Aeromedical Inst, 2004.
[2] Dario Cazzato, Claudio Cimarelli, Jose Luis Sanchez-Lopez, Holger Voos, and
Marco Leo. A survey of computer vision methods for 2d object detection from
unmanned aerial vehicles. Journal of Imaging, 6(8), 2020. ISSN 2313-433X. doi:
10.3390/jimaging6080078. URL https://www.mdpi.com/2313-433X/6/8/78.
[3] Payal Mittal, Raman Singh, and Akashdeep Sharma. Deep learning-based object
detection in low-altitude uav datasets: A survey. Image and Vision Computing, 104:
104046, 2020.
[4] Farzaneh Dadrass Javan, Farhad Samadzadegan, Mehrnaz Gholamshahi, and Farnaz
Ashatari Mahini. A modified yolov4 deep learning network for vision-based uav
recognition. Drones, 6(7):160, 2022.
[5] Celine Teuliere, Laurent Eck, and Eric Marchand. Chasing a moving target from a
flying uav. In 2011 IEEE/RSJ International Conference on Intelligent Robots and
Systems, pages 4929–4934. IEEE, 2011.
[6] Hajer Fradi, Lorenzo Bracco, Flavia Canino, and Jean-Luc Dugelay. Autonomous
person detection and tracking framework using unmanned aerial vehicles (uavs). In
2018 26th European Signal Processing Conference (EUSIPCO), pages 1047–1051,
2018. doi: 10.23919/EUSIPCO.2018.8553010.
[7] Shuaijun Wang, Fan Jiang, Bin Zhang, Rui Ma, and Qi Hao. Development of uav-
60based target tracking and recognition systems. IEEE Transactions on Intelligent
Transportation Systems, 21(8):3409–3422, 2020. doi: 10.1109/TITS.2019.2927838.
[8] Zhengxia Zou, Zhenwei Shi, Yuhong Guo, and Jieping Ye. Object detection in 20
years: A survey. arXiv preprint arXiv:1905.05055, 2019.
[9] Zhong-Qiu Zhao, Peng Zheng, Shou-Tao Xu, and Xindong Wu. Object detection
with deep learning: A review. IEEE Transactions on Neural Networks and Learning
Systems, 30(11):3212–3232, 2019. doi: 10.1109/TNNLS.2018.2876865.
[10] Syed Sahil Abbas Zaidi, Mohammad Samar Ansari, Asra Aslam, Nadia Kanwal,
Mamoona Asghar, and Brian Lee. A survey of modern deep learning based object
detection models. Digital Signal Processing, page 103514, 2022.
[11] Angelo Coluccia, Alessio Fascista, Arne Schumann, Lars Sommer, Anastasios Di-
mou, Dimitrios Zarpalas, Fatih Cagatay Akyon, Ogulcan Eryuksel, Kamil Anil Oz-
futtu, Sinan Onur Altinuc, Fardad Dadboud, Vaibhav Patel, Varun Mehta, Miodrag
Bolic, and Iraj Mantegh. Drone-vs-bird detection challenge at ieee avss2021. In 2021
17th IEEE International Conference on Advanced Video and Signal Based Surveil-
lance (AVSS), pages 1–8, 2021. doi: 10.1109/AVSS52988.2021.9663844.
[12] Yaowen Lv, Zhiqing Ai, Manfei Chen, Xuanrui Gong, Yuxuan Wang, and Zheng-
hai Lu. High-resolution drone detection based on background difference and sag-
yolov5s. Sensors, 22(15):5825, 2022.
[13] Belmar Garcia-Garcia, Thierry Bouwmans, and Alberto Jorge Rosales Silva. Back-
ground subtraction in real applications: Challenges, current models and future direc-
tions. Computer Science Review, 35:100204, 2020.
[14] Alper Yilmaz, Omar Javed, and Mubarak Shah. Object tracking: A survey. Acm
computing surveys (CSUR), 38(4):13–es, 2006.
[15] Gioele Ciaparrone, Francisco Luque Sánchez, Siham Tabik, Luigi Troiano, Roberto
Tagliaferri, and Francisco Herrera. Deep learning in video multi-object tracking: A
survey. Neurocomputing, 381:61–88, 2020.
61[16] Tijeni Delleji, Hèdi Fkih, Abedelaziz Kallel, and Zied Chtourou. Visual tracking of
mini-uavs using modified yolov5 and improved deepsort algorithms. In 2022 6th In-
ternational Conference on Advanced Technologies for Signal and Image Processing
(ATSIP), pages 1–6, 2022. doi: 10.1109/ATSIP55956.2022.9805923.
[17] Huaizhou Yang and Yujie Ge. Research on detecting and tracking algorithm of
uav intrusion based on yolov5+deepsort. In 2022 3rd International Conference
on Computer Vision, Image and Deep Learning International Conference on Com-
puter Engineering and Applications (CVIDL ICCEA), pages 1209–1212, 2022. doi:
10.1109/CVIDLICCEA56201.2022.9823976.
[18] Vinod Kumar Yadav, Pritaj Yadav, and Shailja Sharma. An efficient yolov7 and deep
sort are used in a deep learning model for tracking vehicle and detection.
[19] David Fernández Llorca, Antonio Hernández Martínez, and Iván García Daza.
Vision-based vehicle speed estimation: A survey. IET Intelligent Transport Systems,
15(8):987–1005, 2021.
[20] Rajesh Kannan Megalingam, Vignesh Shriram, Bommu Likhith, Gangireddy Ra-
jesh, and Sriharsha Ghanta. Monocular distance estimation using pinhole camera
approximation to avoid vehicle crash and back-over accidents. In 2016 10th Inter-
national Conference on Intelligent Systems and Control (ISCO), pages 1–5, 2016.
doi: 10.1109/ISCO.2016.7727017.
[21] Marek Vajgl, Petr Hurtik, and Tomáš Nejezchleba. Dist-yolo: Fast object detection
with distance estimation. Applied Sciences, 12(3), 2022. ISSN 2076-3417. doi:
10.3390/app12031354. URL https://www.mdpi.com/2076-3417/12/3/1354.
[22] Ying-Chih Lai and Zong-Ying Huang. Detection of a moving uav based on deep
learning-based distance estimation. Remote Sensing, 12(18):3035, 2020.
[23] Xiaoyue Zhao, Fangling Pu, Zhihang Wang, Hongyu Chen, and Zhaozhuo Xu. De-
tection, tracking, and geolocation of moving vehicle from uav using monocular cam-
era. IEEE Access, 7:101160–101170, 2019. doi: 10.1109/ACCESS.2019.2929760.
62[24] Tijeni Delleji, Hedi Fekih, and Zied Chtourou. Deep learning-based approach for
detection and classification of micro/mini drones. In 2020 4th International Confer-
ence on Advanced Systems and Emergent Technologies (ICASET), pages 332–337,
2020. doi: 10.1109/ICASET49463.2020.9318281.
[25] Kun Xiao, Shaochang Tan, Guohui Wang, Xueyan An, Xiang Wang, and Xiangke
Wang. Xtdrone: A customizable multi-rotor uavs simulation platform. In 2020 4th
International Conference on Robotics and Automation Sciences (ICRAS), pages 55–
61. IEEE, 2020. |
| Description: | 碩士
國立政治大學
資訊科學系
110753150 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0110753150 |
| Data Type: | thesis |
| Appears in Collections: | [資訊科學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 315001.pdf | | 52317Kb | Adobe PDF | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
