تشخیص به‌موقع پرنده‌های هدایت‌پذیر از دور چند بال چرخان با استفاده از الگوریتم YOLOv5 بهینه‌سازی‌شده

نوع مقاله : کامپیوتر - محاسبات نرم و هوش مصنوعی

نویسندگان

1 دانشجوی دکتری، فیزیک همدان،همدان، ایران

2 دانشگاه پدافند هوایی خاتم الانبیاء(ص)،تهران، ایران

3 دانشگاه ملایر،ملایر،ایران

چکیده

در سال‌های اخیر پیشرفت بسیار سریع فنّاوری در حوزة پهپادها (پرنده‌های هدایت‌پذیر از دور)، در کنار مزایای خود، تهدیدات جدی را در سطوح مختلف اجتماعی و امنیتی به همراه داشته است. از جملة این مشکلات، می‌توان به بحث پروازهای غیرمجاز در مناطق حفاظت‌شده و امنیتی اشاره کرد. لذا تشخیص به‌موقع این دستگاه‌ها در جهت انجام سریع اقدامات مربوطه، ضروری است. در همین راستا، در این پژوهش با بهره‌گیری از الگوریتم YOLOv5l که جزء جدیدترین نسخه الگوریتم‌های یک‌مرحله‌ای بینایی رایانه‌ای است، دو مدل با بهینه‌سازهای SGD و Adam جهت تشخیص به‌موقع پهپادها توسعه داده شده است. برای توسعة مدل‌های حاضر در این پژوهش، از یک مجموعه داده شامل 10046 عدد عکس از انواع و حالات مختلف پهپادها استفاده شده است. پردازش مدل‌ها به کمک بستر گوگل کولب انجام شده است که به‌صورت رایگان یک سیستم پردازشی قدرتمند را در اختیار توسعه‌دهندگان قرار می‌دهد. ارزیابی مدل‌ها بر روی چهار مجموعه‌آزمون 1000 عددی شامل مجموعه‌آزمون معمولی، کم‌حجم، حالت شب، خاکستری مقیاس و همچنین یک مجموعه‌آزمون شامل 100 عدد عکس از چندین پهپاد صورت‌گرفته است. طبق نتایج، مدل توسعه داده شده با بهینه‌ساز Adam نسبت به مدل توسعه داده شده با بهینه‌ساز SGD عملکرد بهتری داشته است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Real Time Detection of Multi-Rotor Unmanned Aerial Vehicle Using YOLOv5 Optimized Algorithm

نویسندگان [English]

  • Majid Amirzdeh 1
  • Seyed Ali Hosseini Moradi 2
  • Nader ghobadi 3
1 Imam Ali Officer University
2 University of Air Defense
3 Malayer University
چکیده [English]

In recent years, the very rapid development of technology in the field of UAVs (Unmanned Aerial Vehicles), along with its advantages, has brought serious threats at various social and security levels. Among these problems, the issue of unauthorized flights in protected and security area can be mentioned. Therefore, real time detection of these devices is necessary in order to quickly carry out relevant measures. In this regard, in this research, using the YOLOv5l algorithm, which is part of the latest version of one-stage computer vision algorithms, two models with SGD and Adam optimizers have been developed for the real time detection of UAVs. To develop the models in this research, a dataset containing 10046 images of different types and states of UAVs has been used. The processing of the models has been done with the Google Colab platform, which provides a free powerful processing system for developers. The models have been evaluated on four test sets of 1000 images including normal, low volume, night mode, and gray scale and also a test set including 100 images from several UAVs. According to the results, the developed model with The Adam optimizer performed better than the model developed with the SGD optimizer.

کلیدواژه‌ها [English]

  • UAV (Unmanned Aerial Vehicle)
  • Real Time Detection
  • Multi-Rotor UAV
  • YOLOv5

Smiley face

  • [1] Russell, S.; Norvig, P. “A Modern Approach”; Artif. Intell. 1995, 25. https://doi.org/10.1142/S0219843620500164.
  • [2] Sonka, M.; Hlavac, V.; Boyle, R. “Image Processing, Analysis, and Machine Vision”; Cengage Learning, 2014.
  • [3] Hu, Y.; Wu, X.; Zheng, G.; Liu, X. “Obect Detection of UAV for Anti-UAV Based on Improved YOLO v3”; Chin. Control Conf. 2019, 8386-8390. https://doi.org/23919/ ChiCC .2019.8865525.
  • [4] Kharchenko, V.; Chyrka, I. “Detection of Airplanes on The Ground Using YOLO Neural Network”; 17th IEEE Int. Conf. Math. Methods. Theory. 2018, 294-297. https://doi.org/10.1109/MMET.2018.8460392.
  • [5] Saqib, M.; Khan, S. D.; Sharma, N.; Blumenstein, M. “A Study on Detecting Drones Using Deep Convolutional Neural Networks”; 14th IEEE Int. Conf. Adv. Video. Signal Based Surveill. 2017, 1-5. https://doi.org/10.1109/ AVSS. 20178078541.
  • [6] Aker, C.; Kalkan, S. “Using Deep Networks for Drone Detection”; 14th IEEE Int. Conf. Adv. Video. Signal Based Surveill. 2017, 1-6. https://doi.org/1109/ AVSS.2017. 8078539.
  • [7] Lee, D.; La, W. G.; Kim, H. “Drone Detection and Identification System Using Artificial Intelligence”; Int. Conf. Inf. Commun. Syst. 2018, 1131-1133. https://doi.org/1109/ICTC.2018.8539442.
  • [8] Schumann, A.; Sommer, L.; Klatte, .; Schuchert, T.; Beyerer, . “Deep Cross-Domain Flying Obect Classification for Robust UAV Detection”; 14th IEEE Int. Conf. Adv. Video. Signal Based Surveill. 2017, 1-6. https://doi.org/ 1109/AVSS.2017.8078558.
  • [9] Unlu, E.; Zenou, E.; Riviere, N.; Dupouy, P.-E. “Deep Learning-Based Strategies for the Detection and Tracking of Drones Using Several Cameras”; IPS Trans. Comput. Vis. 2019,11,1-13. https://doi.org/10.1186/s41074-019-0059.
  • [10] Xun, D. T. W.; Lim, Y. L.; Srigrarom, S. “Drone Detection Using YOLOv3 with Transfer Learning on NVIDIA etson TX2”; 2th Symp. Instrum. Control. Artif. Intell. Robot. 2021, 1-6. https://doi.org/10.1109/ICA-SYMP50206.2021. 9358449.
  • [11] Amil, S.; Abbas, M. S.; Roy, A. M. “Distinguishing Malicious Drones Using Vision Transformer”; Artif. Intell. 2022, 3, 260-273. https://doi.org/10.3390/ai3020016.
  • [12] Upadhyay, M.; Murthy, K.; Ra, A. B. “Intelligent System for Real Time Detection and Classification of Aerial Targets Using CNN”; 5th Int. Conf. Intell. Comput. Inf. Control. Syst. 2021, 1676-1681. https://doi.org/10.1109/ICICCS 51141.2021.9432136.
  • [13] Samadzadegan, F.; Dadrass avan, ; Ashtari Mahini, F.; Gholamshahi, M. “Detection and Recognition of Drones Based on a Deep Convolutional Neural Network Using Visible Imagery”; IEEE Trans. Aerosp. Electron. Syst. 2022, 9, 31. https://doi.org/10.3390/aerospace9010031.
  • [14] Sharma, A.; Ain, N.; Kothari, M. “Lightweight Multi-Drone Detection and 3D-Localization via YOLO”; ArXiv.org. 2022, 09097. doi.org/10.48550/arXiv.2202.09097
  • [15] Sun, H.; Yang, j.; Shen, j.; Liang, D.; Ning-Zhong, L.; Zhou, H. “TIB-Net: Drone Detection Network with Tiny Iterative Backbone”; IEEE Access. 2020, 8, 130697-130707. https://doi.org/1109/ACCESS.2020.3009518.
  • [16] Hu, J.; Niu, H.; Carrasco, J.; Lennox, B.; Arvin, F. “Fault-Tolerant Cooperative Navigation of Networked UAV Swarms for Forest Fire Monitoring”; Aerosp. Sci. Technol. 2022,123,107494. https://doi.org/10.1016/j.ast.2022.107494.
  • [17] Vourtsis, C.; Rochel, V. C.; Serrano, F. R.; Stewart, W.; Floreano, D. “Insect Inspired Self-Righting for Fixed-Wing Drones”; IEEE Robot. Autom. Lett. 2021, 6, 6805-6812. https://doi.org/1109/LRA.2021.3096159.
  • [18] Dietterich, T. G. “Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms”; Neural Comput. 1998, 10, 1895-1923 https://doi.org/ 10.1162/089976698300017197.
  • [19] Vostrikov, A.; Chernyshev, S. “Training Sample Generation Software”; Intell. Decis. Technol. 2019, 145-151. https://doi.org/10.1007/978-981-13-8303-8_13.
  • [20] Redmon, J.; Farhadi, A. “YOLO9000: Better, Faster, Stronger”; IEEE Conf. CVPR. 2017, 7263-7271 https://doi.org/10.48550/arXiv.1804.02767.
  • [21] Redmon, J.; Farhadi, A. “Yolov3: An Incremental Improvement”; ArXiv.org. 2018, 1804-2767. https://doi.org/ 10,48550. /arXiv.180402768.
  • [22] Bochkovskiy, A.; Wang, C.-Y.; Liao, H.-Y. M. “Yolov4: Optimal Speed and Accuracy of Object Detection”; ArXiv.org. 2020, 10934. https://doi.org/45550/arXiv. 200410934.
  • [23] Jocher,G. et al. "NanoCode012, C. A., “Ultralytics/yolov5: v5. YOLOv5 - 1280 Models , AWS, Supervise.ly and YouTube integrations”; Zenodo 2021, 0-6. https://doi.org/ 1109/78.134446.
  • [24] Leung, H.; Haykin, S. “The Complex Backpropagation Algorithm”; IEEE Trans. Signal Process. 1991, 39, 2101-2104. https://doi.org/1109/78.134446.
  • [25] Falahat, S.; Karami, A. “Maize Tassel Detection and Counting Using Deep Learning Techniques”; J. Agric. Mach. 2022, 2228-6829. https://doi.org/1109/78.134446
  • [26] Zhou, F.; Zhao, H.; Nie, Z. “Safety Helmet Detection Based on YOLOv5”; IEEE Int. Conf. Power Electron. Control. Autom. 2021, 6-11. https://doi.org/1109/ICPECA51329. 2021.9362711.
  • [27] Bottou, L.; Bousquet, O. “The Tradeoffs of Large Scale Learning”; Adv. Neural Inf. Process. Syst. 2007, 20.
  • [28] Padilla, R.; Netto, S. L.; Da Silva, E. A. “A Survey on Performance Metrics for Object-Detection Algorithms”; IEEE Int. Conf. Systs. Signal. Image Process. 2020, 237-242. https://doi.org/1109/IWSSIP48289.2020.9145130.
  • [29] Reddy, A.; Indragandhi, V.; Ravi, L.; Subramaniyaswamy, V. “Detection of Cracks and Damage in Wind Turbine Blades Using Artificial Intelligence-Based Image Analytics”; Meas. 2019, 147, 106823. https://doi.org/ 10.1016/j.measurement.2019.07.051.
  • [30] Bai, L.; Lyu, Y.; Huang, X. “Roadnet-rt: High Throughput CNN Architecture and SOC Design for Real-Time Road Segmentation”; IEEE Trans. Circuits Syst. I, Reg. Papers. 2020, 68, 704-714. https://doi.org/1109/TCSI.2020. 3038139.
  • [31] Deng, W.; Mou, Y.; Kashiwa, T.; Escalera, S.; Nagai, K.; Nakayama, K.; Matsuo, Y.; Prendinger, H. “Vision Based Pixel-Level Bridge Structural Damage Detection Using a Link ASPP Network”; Autom. Constr. 2020, 110, 102973. https://doi.org/10.1016/j.autcon.2019.102973.
  • [32] Nath, N. D.; Behzadan, A. H.; Paal, S. G. “Deep Learning for Site Safety: Real-Time Detection of Personal Protective Equipment”; Autom. Constr. 2020, 112, 103085. https:// doi.org/10.1016/j.autcon.2020.103085.
  • [33] Nalamati, M.; Kapoor, A.; Saqib, M.; Sharma, N.; Blumenstein, M. “Drone Detection in Long-Range Surveillance Videos”; 16th IEEE Int. Conf. Adv. Video. Signal Based Surveill. 2019, 1-6. https://doi.org/1109/ AVSS.2019.8909830.
  • [34] Peng, J.; Zheng, C.; Lv, P.; Cui, T.; Cheng, Y.; Lingyu, S. “Using Images Rendered by PBRT to Train Faster R-CNN for UAV Detection”; Comput. Sci. Res. Notes 2018, 13-18. http://hdl.handle.net/11025/34647.