مقایسة روش‌های یادگیری عمیق و طبقه‌بندی‌کنندة آبشاری در تشخیص اشیا، در فرود اتوماتیک پرنده‌های بدون سرنشین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس ارشد فتوگرامتری، دانشکدة مهندسی نقشه‌برداری، دانشگاه صنعتی خواجه نصیرالدین طوسی

2 دکتری هوافضا، دانشکده هوافضا، دانشگاه فردوسی مشهد

چکیده

فرود اتوماتیک یکی از موضوعات و چالش‌های مهم در حوزة‌ کنترل و اتوماسیون پهپادهای بدون سرنشین است. توسعة الگوریتم‌های فرود اتوماتیک نیازمند تعیین موقعیت پهپاد نسبت‌به محل فرود است که این کار، در حوزه‌های پردازش تصویر، به تشخیص دقیق و سریع محل فرود نیاز دارد. ازجمله روش‌های معمول، در این زمینه، طبقه‌بندی‌کنندة آبشاری و تناظریابی و قطعه‌بندی تصویر است که به‌نظر می‌رسد، با تغییرات آب‌و‌هوایی و مقیاس متفاوت، این الگوریتم‌ها با چالش مواجه شوند. از طرف دیگر، در سال‌های اخیر شبکه‌های کانولوشنی عمیق به‌منزلة مدل‌هایی قوی به‌منظور شناسایی و تشخیص اشیا در تصاویر به‌کار رفته‌اند؛ بااین‌حال با توجه به بار محاسباتی زیاد، این مدل‌ها هنوز در حوزة پرنده‌های بدون سرنشینی که از لحاظ سخت‌افزاری سبک‌اند و قدرت پردازش ضعیفی دارند، کاربرد جدی نیافته‌اند. هدف این مقاله مقایسة دو روش شبکه‌های عمیق کانولوشنی و طبقه‌بندی‌کنندة آبشاری برای تشخیص آنی محل فرود است. نتایج عملی‌کردن روش‌ ارائه‌شده روی یک پرندة Parrot AR Drone2.0 نشان می‌دهد که شبکه‌های کانولوشنی در مقابل دوران، مقیاس، انتقال و حتی پنهان‌شدگی پایداری بسیار زیادی دارند. دقت تشخیص در این روش 1/99 است که، در قیاس با روش طبقه‌بندی‌کنندة آبشاری، 3% بیشتر است و درعین‌حال‌ از لحاظ سرعت نیز، مناسب کاربردهای آنی است.

کلیدواژه‌ها

عنوان مقاله [English]

Comparison of Deep Learning and Cascade Classifiers Approaches for Object Detection in Autonomous UAV Landing

نویسندگان [English]

  • Behrooz Moradi 1
  • AbasAli Mehraban 2
  • Morteza Mohammadi 2
1 M.Sc. of Photogrammetry, Faculty of Geodesy and Geomatics Engineering, K.N. Tossi
2 Ph.D., Faculty of Aerospace, Ferdowsi University, Mashhad
چکیده [English]

Autonomous landing is a key challenging in the domain of UAV navigation systems. Developing an autonomous landing system requires a precise estimation of the UAV pose relative to landing marker, particularly in vision systems this involves precise Helipad recognition. It seems that traditional approaches including cascade classifiers, image matching and segmentation techniques to have major challenges in different weather conditions and scales. On the other hand, convolutional neural networks (CNNs) have been introduced as a powerful tool in the visual recognition systems in the recent years but the high computational cost of this techniques, limited their performance in the low cost and light weight UAVs. The aim of this paper is to compare the convolutional neural networks and cascade classifier for helipad detection. The results show that CNNs are invariant under translation, rotation, scaling and occlusion. The detection accuracy of this method is 99.1 % which is 3 % more than cascade classifier while its running time is suitable for real time UAV applications.
 

کلیدواژه‌ها [English]

  • Deep learning
  • Autonomous landing
  • UAV

مراجع

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S. et al., 2016, Tensorflow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, arXiv preprint arXiv: 1603.04467.
Chen, Y. & Liu, H-. L., 2016, Overview of Landmarks for Autonomous, Vision-Based Landing of Unmanned Helicopters, IEEE Aerospace and Electronic Systems Magazine, 31(5), PP. 14-27.
Chi, H., Yu, C. & Liu, L., 2013, Vision-Based Attitude Estimation and Control for Unmanned Helicopter Landing, Control Conference (CCC), 32nd Chinese.
De Oliveira, D.C., & Wehrmeister, M.A., 2016, Towards Real-Time People Recognition on Aerial Imagery Using Convolutional Neural Networks, , 19th International Symposium on Real-Time Distributed Computing (ISORC), 17-20 May.
De Oliveira, C.S., Anvar, A., Silva, M.C., Neto, A. & Mozelli, L., 2015, Comparison of Cascade Classifiers for Automatic Landing Pad Detection in Digital Images.
Fan, Y., Haiqing, S. & Hong, W., 2008, A Vision-Based Algorithm for Landing Unmanned Aerial Vehicles, International Conference on Computer Science and Software Engineering, 12-14 Dec.
Fucen, Z., Haiqing, S. & Hong, W., 2009, The Object Recognition and Adaptive Threshold Selection in the Vision System for Landing an Unmanned Aerial Vehicle, 2009 International Conference on Information and Automation, 22-24 June.
Gautam, A., Sujit, P.B. & Saripalli, S., 2014, A Survey of Autonomous Landing Techniques for UAVs, 2014 International Conference on Unmanned Aircraft Systems (ICUAS), 27-30 May.
Girshick, R., 2015, Fast R-CNN, 2015 IEEE International Conference on Computer Vision (ICCV), 7-13 Dec.
Girshick, R., Donahue, J., Darrell, T. & Malik, J., 2014, Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, 2014 IEEE Conference on Computer Vision and Pattern Recognition, 23-28 June.
Guennouni, S., Ahaitouf, A. & Mansouri, A., 2015, A Comparative Study of Multiple Object Detection Using Haar-Like Feature Selection and Local Binary Patterns in Several Platforms, Modelling and Simulation in Engineering, 2015 (ID 948960).
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S. & Lew, M.S., 2016, Deep Learning for Visual Understanding: A Review, Neurocomputing, 187(2016), PP. 27-48.
He, K., Zhang, X., Ren, S. & Sun, J., 2015, Delving Deep into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification, Proceedings of the IEEE International Conference on Computer Vision.
 
Henriques, J.F., Caseiro, R., Martins, P. & Batista, J., 2015, High-Speed Tracking with Kernelized Correlation Filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3), PP. 583-596.
IOFFE, S. & Szegedy, C., 2015, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, Proceedings of the 32nd International Conference on International Conference on Machine Learning, Vol, 37 July 2015, PP. 448-456.
Kong, W., Zhou, D., Zhang, D. & Zhang, J., 2014, Vision-Based Autonomous Landing System for Unmanned Aerial Vehicle: A Survey, 2014 International Conference on Multisensor Fusion and Information Integration for Intelligent Systems (MFI), 29 December.
Konoplich, G.V., Putin, E.O. & Filchenkovevgeniy, A.A., 2016, Application of Deep Learning to the Problem of Vehicle Detection in Uav Images, 2016 XIX IEEE International Conference on Soft Computing and Measurements (SCM), 25-27 May.
Lee, J., Wang, J., Crandall, D., Šabanović, S. & Fox, G., 2017, Real-Time Object Detection for Unmanned Aerial Vehicles Based on Cloud-Based Convolutional Neural Networks, First IEEE International Conference on Robotic Computing (IRC) Taichung, Taiwan, 10-12 April.Lin, min, qiang chen, and shuicheng yan. "Network in network." arxiv preprint arxiv: 1312.4400 (2013).
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y. & Berg, A.C., 2016, SSD: Single Shot Multibox Detector, European Conference on Computer Vision, Springer, Cham.
Miller, A., Shah, M. & Harper, D., 2008, Landing a UAV on a Runway Using Image Registration, 2008 IEEE International Conference on Robotics and Automation (ICRA), 19-23 May.
Pan, X., Ma, De-q., Jin, Li-l. & Jiang, Z-s., 2008, Vision-Based Approach Angle and Height Estimation for UAV Landing, 2008 Congress on Image and Signal Processing, 27-30 May.
Redmon, J. & Farhadi, A., 2016, Yolo9000: Better, Faster, Stronger, Conference: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Redmon, J., Divvala, S., Girshick, R. & Farhadi, A., 2016, You Only Look Once: Unified, Real-Time Object Detection, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June.
Ren, S., He, K., Girshick, R. & Sun, J., 2015, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, Advances in Neural Information Processing Systems 28 (NIPS 2015).
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C. & Fei-Fei, L., 2015, Imagenet Large Scale Visual Recognition Challenge, International Journal of Computer Vision, 115(3), PP. 211-252.
Saripalli, S., Montgomery, J.F. & Sukhatme, G.S., 2003, Visually Guided Landing of an Unmanned Aerial Vehicle, IEEE transactions on Robotics and Automation, 19(3), PP. 371-380.
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R. & LeCun, Y., 2013, Overfeat: Integrated Recognition, Localization and Detection Using Convolutional Networks, 2nd International Conference on Learning Representations, ICLR 2014 - Banff, Canada, 14-16 Apr.
Han, S., Shen, W. & Liu, Z., 2015, Deep Drone Object Detection and Tracking for Smart Drones on Embedded System, Stanford University.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguel, D., Erhan, D., Vanhoucke, V. & Rabinovich, A., 2015, Going Deeper with Convolutions, proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2015.
Tsai, A.C., Gibbens, P.W. & Stone, R.H., 2006, Terminal Phase Vision-Based Target Recognition and 3d Pose Estimation for a Tail-Sitter, Vertical Takeoff and Landing Unmanned Air Vehicle, Pacific-Rim Symposium on Image and Video Technology, Springer, Berlin, Heidelberg, 2006.
Viola, P. & Jones, M., 2001, Rapid Object Detection Using a Boosted Cascade of Simple Features, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001.
Verbandt, M., Theys, B. & De Schutter, J., 2014, Robust Marker-Tracking System for Vision-Based Autonomous Landing of Vtol Uavs, IMAV 2014: International Micro Air Vehicle Conference and Competition 2014.
Wang, R., Zhang, G-J. & Yan, P., 2007, A Hierarchical Method Based on Optical Flow for Planar 3d Motion Estimation, Optical Technique, 1(2007), P. 027.
 

فایل ها

هم رسانی

ارجاع به این مقاله

آمار