Embedded Vision System for Automated Drone Landing Site Detection
This paper presents an embedded video subsystem used to classify the terrain, based on an image from a camera located under the drone, for the purpose of an automatic landing system. Colour and texture features, as well as decision trees and support vector machine classifiers were analysed and evaluated. The algorithm was supported with a shadow detection module. It was evaluated on 100 test cases and achieved over 80% performance. The designed video system was implemented on two embedded platforms – a Zynq SoC (System on Chip – Field Programmable Gate Array + ARM processor system) and a Jetson GPU (Graphic Processing Unit + ARM processor system). The performance achieved on both architectures is compared and discussed.
KeywordsUnmanned Aerial Vehicle (UAV) Safe landing site detection Decision Trees (DT) Support Vector Machine (SVM) Machine learning Digital image processing FPGA Zynq GPU
The work presented in this paper was partially supported by the National Science Centre project no. 2016/23/D/ST6/01389 and Fundação para a Ciencia e a Tecnologia under the grant SFRH/BSAB/135037/2017.
- 2.Din, A., et al.: Embedded low power controller for autonomous landing of UAV using artificial neural network. In: 10th International Conference on Frontiers of Information Technology, Islamabad, pp. 196–203 (2012)Google Scholar
- 3.Fitzgerald, D., Walker, R., Campbell, D.: A vision based emergency forced landing system for an autonomous UAV. In: Proceedings Australian International Aerospace Congress Conference, Melbourne, Australia (2005)Google Scholar
- 6.Mejias, L., Fitzgerald, D.: A multi-layered approach for site detection in UAS emergency landing scenarios using geometry-based image segmentation. In: 2013 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 366–372. IEEE (2013)Google Scholar
- 7.Mestre, D., Fonseca, J., Mora A.: Monitoring of in-vitro plant cultures using digital image processing and random forests. In: ICPRS - IET 8th International Conference on Pattern Recognition Systems (2017)Google Scholar
- 8.Mora, A.D., et al.: A fuzzy multicriteria approach for data fusion. In: Fourati, H. (ed.) Multisensor Data Fusion From Algorithms and Architectural Design to Applications, pp. 109–126. CRC Press, Boca Raton (2015)Google Scholar
- 10.Mukadam, K., Sinh, A., Karani, R.: Detection of landing areas for unmanned aerial vehicles. In: 2016 International Conference on Computing Communication Control and automation (ICCUBEA), pp. 1–5. IEEE (2016)Google Scholar
- 12.Paglieroni, D.: Distance transforms: properties and machine vision applications. Comput. Vis. Graph. Image Process. Graph. Model. Image Process. 54(1), 57–58 (1992)Google Scholar
- 15.Simoes, L., Bourdarias, C., Ribeiro, R.: Real-time planetary landing site selection-a non-exhaustive approach. Acta Futur. 5, 39–52 (2012)Google Scholar