JISP  >> Vol. 5 No. 2 (April 2016)

    基于光流法的视觉避障系统研究
    Visual Obstacle Avoidance System Based on Optical Flow Method

  • 全文下载: PDF(387KB) HTML   XML   PP.66-72   DOI: 10.12677/JISP.2016.52009  
  • 下载量: 1,388  浏览量: 3,973  

作者:  

黄宏燕,高斯文,余艳梅,何小海:四川大学电子信息学院,图像信息研究所,四川 成都

关键词:
无人机光流法金字塔LK算法视觉避障Unmanned Aerial Vehicles Optical Flow Method Pyramid LK Algorithm Visual Obstacle Avoidance

摘要:

本文针对无人机自主飞行过程中有效定位和识别障碍物的问题,研究了基于金字塔Lukas-Kanade光流法的视觉避障原理,在光流法基础上给出了障碍物检测方法及相应的避障策略。结合配有320 × 240像素摄像头的视觉模块和高性能嵌入式计算平台,构建了一套完整的实时视觉避障系统。实验表明,本文算法能够很好地识别障碍物并作出相应的避障动作,具有较好的实时性和鲁棒性。

To solve the problems of effective orientation and obstacle recognition in autonomous flight of Unmanned Aerial Vehicles, this essay has studied the visual obstacle avoidance principle based on Pyramid LK optical flow and the obstacle detection method as well as the relevant obstacle avoidance strategy with the foundation of optical flow. Combining with the 320 × 240 pixle camera- equipped visual module and high-performance embedded computing platform, we constitute a complete real-time visual obstacle avoidance system. Experiments show that the proposed algorithm can recognize obstacle well and react with relevant obstacle avoidance action, which has good real-time and robustness features.

文章引用:
黄宏燕, 高斯文, 余艳梅, 何小海. 基于光流法的视觉避障系统研究[J]. 图像与信号处理, 2016, 5(2): 66-72. http://dx.doi.org/10.12677/JISP.2016.52009

参考文献

[1] Ulrich, I. and Nourbakhsh, I.R. (2000) Appearance-Based Obstacle Detection with Monocular Color Vision. AAAI, 866-871.
[2] 苏东. 基于双目视觉的小型无人飞行器的导航与避障[D]: [硕士学位论文]. 成都: 电子科技大学, 2014.
[3] Alvarez, H., Paz, L., Sturm, J. and Cremers, D. (2016) Collision Avoidance for Quadrotors with a Monocular Camera. Experimental Robotics. Experimental Robotics, 109, 195-209. http://dx.doi.org/10.1007/978-3-319-23778-7_14
[4] Chao, H., Gu, Y. and Napolitano, M. (2013) A Survey of Optical Flow Techniques for Robotics Navigation Applications. Journal of Intelligent & Robotic Systems, 73, 710-716.
[5] Bradski, G.R. and Kaehler, A. (2008) Learning OpenCV: Computer Vision with the OpenCV Library. O’Reilly Media, Sebastopol.
[6] Bouguet, J.Y. (2001) Pyramidal Implementation of the Affine Lucas Kanade Feature Tracker Description of the Algorithm. Intel Corporation, 5, 4.
[7] Shi, J. and Tomasi, C. (1994) Good Features to Track. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, 21-23 June 1994, 593-600.
[8] Srinivasan, M.V. and Gregory, R.L. (1992) How Bees Exploit Optic Flow: Behavioural Experiments and Neural Models [and Discussion]. Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences, 337, 253-259. http://dx.doi.org/10.1098/rstb.1992.0103
[9] Souhila, K. and Karim, A. (2007) Optical Flow Based Robot Obstacle Avoidance. International Journal of Advanced Robotic Systems, 4, 13-16. http://dx.doi.org/10.5772/5715
[10] Warren, W.H. (1988) Chapter 14 Action Modes and Laws of Control for the Visual Guidance of Action. Advances in Psychology, 50, 339-379. http://dx.doi.org/10.1016/S0166-4115(08)62564-9