Abstract
In the past decade, a lot of researches have been done on the topic of real-time obstacle avoidance of Unmanned Aerial Vehicle (UAV). For example, the use of Light Detection and Ranging (LIDAR), ultrasonic sensors, and now more popular visual sensors can effectively avoid obstacles. Although these methods are simple and effective, there are few of UAV real-time obstacle avoidance for complex environments, and most of them are used to avoid a single obstacle. When facing multiple obstacles, they cannot choose the optimal strategy, which inevitably consumes more power and time. In view of the complex environment that UAV may face multiple obstacles, in order to avoid multiple obstacles with minimum efforts in the process of real obstacle avoidance, this paper proposes a new method to detect multiple obstacles. Firstly, it extracts obstacle feature points, and then uses unsupervised clustering algorithm in machine learning to divide the feature points of different obstacles into different categories, and finally detects the obstacles represented by convex hull of same category feature points. The method is simple and effective. This paper compares the time of several popular feature point detection and unsupervised clustering algorithms through experiments and estimates the approximate relationship between the number of feature points detected and the distance when the UAV approaches the obstacle, which is a priori study for the future practical obstacle avoidance link. It summarizes which algorithm can save more time and is more suitable for real-time obstacle avoidance of multiple obstacles.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, C., Wang, J., Shen, Y., Zhang, X.: Autonomous navigation of UAVs in large-scale complex environments: a deep reinforcement learning approach. IEEE Trans. Veh. Technol. 68(3), 2124–2136 (2019)
Radmanesh, M., Kumar, M., Guentert, P.H., Sarim, M.: Overview of path-planning and obstacle avoidance algorithms for UAVs: a comparative study. Unmanned Syst. 6(2), 95–118 (2018)
Sung, T.W., Sun, L., Chang, K.C.: Multi-hop route planning based on environment information for path-following UAVs. In: Proceedings of the 2020 International Conference on Artificial Intelligence and Computer Vision (AICV), Cairo, Egypt, 8–10 Apr 2020, pp. 831–839 (2020)
Sung, T.W., Yang, C.S.: A Voronoi-based sensor handover protocol for target tracking in distributed visual sensor networks. Int. J. Distrib. Sens. Netw. 2014(AID 586210), 1–14 (2014)
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD), Portland, Oregon, USA, Aug 1996, pp. 226–231 (1996)
Pham, D.T., Dimov, S.S., Nguyen, C.D.: Selection of K in K-means clustering. Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci. 219(1), 103–119 (2005)
Pan, J.S., Kong, L., Sung, T.W., Tsai, P.W., Snasel, V.: A clustering scheme for wireless sensor networks based on genetic algorithm and dominating set. J. Internet Technol. 19(4), 1111–1118 (2018)
Peng, Y., Qu, D., Zhong, Y., Xie, S., Luo, J. Gu, J.: The obstacle detection and obstacle avoidance algorithm based on 2-D lidar. In: Proceedings of IEEE International Conference on Information and Automation (ICIA), Lijiang, China, 8–9 Aug 2015, pp. 1648–1653 (2015)
Iacono, M., Sgorbissa, A.: Path following and obstacle avoidance for an autonomous UAV using a depth camera. Robot. Auton. Syst. 106, 38–46 (2018)
Guanglei, M., Haibing, P.: The application of ultrasonic sensor in the obstacle avoidance of quad-rotor UAV. In: Proceedings of IEEE Chinese Guidance, Navigation and Control Conference (CGNCC), Nanjing, China, 12–14 Aug 2016, pp. 976–981 (2016)
Al-Kaff, A., Meng, Q., Martín, D. , De La Escalera, A., Armingol, J.M.: Monocular vision-based obstacle detection/avoidance for unmanned aerial vehicles. In: Proceedings of IEEE Intelligent Vehicles Symposium (IV), Gothenburg, Sweden, 19–22 June 2016, pp. 92–97 (2016)
Al-Kaff, A., García, F., Martín, D., De La Escalera, A., Armingol, J.M.: Obstacle detection and avoidance system based on monocular camera and size expansion algorithm for UAVs. Sensors 17(5), 1061, 1–22 (2017)
Sung, T.W., Zhao, B., Chang, K.C.: Experimental comparison of different feature detection algorithms for UAV obstacle avoidance. In: Proceedings of the 2020 International Conference on Artificial Intelligence and Computer Vision (AICV), Cairo, Egypt, 8–10 Apr 2020, pp. 840–849 (2020)
Yang, Y., Wang, T., Chen, L., Zhang, W.: Stereo vision based obstacle avoidance strategy for quadcopter UAV. In: Proceedings of Chinese Control and Decision Conference (CCDC), Shenyang, China, 9–11 June 2018, pp. 490–494 (2018)
Choi, Y., Jimenez, H., Mavris, D.N.: Two-layer obstacle collision avoidance with machine learning for more energy-efficient unmanned aircraft trajectories. Robot. Auton. Syst. 2017(98), 158–173 (2017)
Acknowledgements
This work is supported by Fujian Provincial Natural Science Foundation in China (Project Number: 2017J01730) and Fujian University of Technology (Project Number: GY-Z20016 and GY-Z18183).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhao, B., Sung, TW., Zhang, X. (2021). Image Feature Detection and Clustering for UAV Multiple Obstacles Avoidance. In: Pan, JS., Li, J., Namsrai, OE., Meng, Z., Savić, M. (eds) Advances in Intelligent Information Hiding and Multimedia Signal Processing. Smart Innovation, Systems and Technologies, vol 211. Springer, Singapore. https://doi.org/10.1007/978-981-33-6420-2_9
Download citation
DOI: https://doi.org/10.1007/978-981-33-6420-2_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6419-6
Online ISBN: 978-981-33-6420-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)