Drones Autonomous Landing Scene Detection with Transfer Learning

This paper proposes an improved method for autonomous landing scene detection for drones. The study addresses challenges that occur when similar environments appear different at various altitudes. Using deep learning methods and a hybrid ensemble technique, the proposed system improves the accuracy and reliability of landing scene recognition. The proposed system achieved approximately 97.65% accuracy using transfer learning models such as ResNet50 and ResNext50 combined with a hybrid Random Forest classifier. Transfer learning techniques using ResNet50 and ResNeXt50 models are applied to the LandingScenes-7 dataset to identify safe landing locations in real time. The thresholding techniques and novelty detection module enable the system to handle unpredictable environmental conditions and provide confidence-based classification decisions. This research has significant applications in drone technology, particularly in logistics, emergency response, and surveillance. The proposed system enhances drone intelligence and improves operational safety in dynamic environments by enabling reliable autonomous landing decisions.

Landing Scene Recognition, Convolutional Neural Network (CNN), Transfer Learning

1. LI B Q, HU X H. Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach. Journal of Systems Engineering and Electronics, 2019, 30(2): 238–244. [Google Scholar] [Crossref]

2. XIA G S, BAI X, DING J, et al. DOTA: a large-scale dataset for object detection in aerial images. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 3974–3983. [Google Scholar] [Crossref]

3. CHENG G, XIE X X, HAN J W, et al. Remote sensing image scene classification meets deep learning: challenges, methods, benchmarks, and opportunities. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 3735–3756. [Google Scholar] [Crossref]

4. ANAND A K, BARMAN S, PRAKASH N S, et al. Vision based automatic landing of unmanned aerial vehicle. Proc. Of the International Conference on Information Technology and Applied Mathematics, 2019: 102–113. [Google Scholar] [Crossref]

5. TIAN C, HUANG C B. An algorithm for unmanned aerial vehicle landing scene recognition based on deep learning and computational verbs. Proc. of the IEEE International Conference on Civil Aviation Safety and Information Technology, 2019: 180–184. [Google Scholar] [Crossref]

6. LU C W, TSOUGENIS E, TANG C K. Improving object recognition with the l-channel. Pattern Recognition, 2016, 49: 187–197. [Google Scholar] [Crossref]

7. ZHOU B L, LAPEDRIZA A, KHOSLA A, et al. Places: a 10 million image database for scene recognition. IEEE Trans. On Pattern Analysis and Machine Intelligence, 2018, 40(6): 1452–1464. [Google Scholar] [Crossref]

8. XIAO J X, HAYS J, EHINGER K A, et al. SUN database: large-scale scene recognition from abbey to zoo. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2010: 3485–3492. [Google Scholar] [Crossref]

9. XIAO J X, EHINGER K A, HAYS J, et al. SUN database: exploring a large collection of scene categories. International Journal of Computer Vision, 2016, 119(1): 3–22. [Google Scholar] [Crossref]

10. PATTERSON G, XU C, SU H, et al. The SUN attribute database: beyond categories for deeper scene understanding. International Journal of Computer Vision, 2014, 108(1/2):59–81. [Google Scholar] [Crossref]

11. YANG T, LI P Q, ZHANG H M, et al. Monocular vision SLAM-based UAV autonomous landing in emergencies and unknown environments. Electronics, 2018, 7(5): 73. [Google Scholar] [Crossref]

12. HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770–778. [Google Scholar] [Crossref]

13. XIE S N, GIRSHICK R, DOLLAR P, et al. Aggregated residual transformations for deep neural networks. Proc. Of the 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017: 5987–5995. [Google Scholar] [Crossref]

14. XIE L, LEE F F, LIU L, et al. Scene recognition: a comprehensive survey. Pattern Recognition, 2020, 102: 107205. [Google Scholar] [Crossref]

15. NEYSHABUR B, SEDGHI H, ZHANG C Y. What is being transferred in transfer learning? Proc. of the 34th Conference on Neural Information Processing Systems, 2020: 512–523. [Google Scholar] [Crossref]

16. WU X Z, LIU R Z, YANG H Q, et al. An Xception based convolutional neural network for scene image classification with transfer learning. Proc. of the 2nd International Conference on Information Technology and Computer Application, 2020: 262–267. [Google Scholar] [Crossref]

17. STEGER C, UIRICH M, WIEDEMANN C. Machine vision algorithms and applications. Berlin: Wiley-VCH, 2018. [Google Scholar] [Crossref]

18. KINGMA D P, BA J L. Adam: a method for stochastic optimization. Proc. of the 3rd International Conference on Learning Representations. arXiv preprint arXiv:1412.6980, 2015. [Google Scholar] [Crossref]

19. QIAN N. On the momentum term in gradient descent learning algorithms. Neural Networks, 1999, 12(1): 145–151. [Google Scholar] [Crossref]

20. DUCHI J, HAZAN E, SINGER Y. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 2011, 12(61): 2121–2159. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet