基于四轴飞行器的单目视觉避障算法

赵海; 陈星池; 王家亮; 曾若凡

doi:10.3788/OPE.20142208.2232

您当前的位置：

首页 >

文章列表页 >

基于四轴飞行器的单目视觉避障算法

信息科学 | 更新时间：2020-08-13

- 基于四轴飞行器的单目视觉避障算法
- Obstacle avoidance algorithm based on monocular vision for quad-rotor helicopter
- 光学精密工程 2014年22卷第8期页码：2232-2241
- 作者机构：
  
  东北大学信息科学与工程学院,辽宁沈阳,110819
- 作者简介：
- 基金信息：
  
  国家科技支撑计划资助项目（No.2012BAH82F04）()
- DOI：10.3788/OPE.20142208.2232
  中图分类号： TP242.62;V249
- 收稿日期：2014-01-07，
  
  修回日期：2014-01-30，
  
  纸质出版日期：2014-08-25
- 稿件说明：
移动端阅览
赵海, 陈星池*, 王家亮等. 基于四轴飞行器的单目视觉避障算法[J]. 光学精密工程, 2014,22(8): 2232-2241

ZHAO Hai, CHEN Xing-chi*, WANG Jia-liang etc. Obstacle avoidance algorithm based on monocular vision for quad-rotor helicopter[J]. Editorial Office of Optics and Precision Engineering, 2014,22(8): 2232-2241
赵海, 陈星池*, 王家亮等. 基于四轴飞行器的单目视觉避障算法[J]. 光学精密工程, 2014,22(8): 2232-2241 DOI： 10.3788/OPE.20142208.2232.

ZHAO Hai, CHEN Xing-chi*, WANG Jia-liang etc. Obstacle avoidance algorithm based on monocular vision for quad-rotor helicopter[J]. Editorial Office of Optics and Precision Engineering, 2014,22(8): 2232-2241 DOI： 10.3788/OPE.20142208.2232.

摘要

针对四轴飞行器平台上单目视觉避障算法实时性不够，准确率不高的问题，提出了一种新的基于金字塔LK（Lucas-Kanade）光流与平移光流融合的单目视觉避障算法并给出了这一方法的数学推导过程。在配有320 pixel240 pixel摄像头的ArduCopter 四轴飞行器上开发和实现了该算法，并进行了多次飞行测试验证了算法的可行性与有效性。在飞行器自主飞行过程中，采用消失点进行导航，并结合神经网络PID对其进行飞行自适应控制。与单目即时定位与地图构建（SLAM）避障算法、Horn-Schunck光流避障算法以及图像分割避障算法比较了算法的实时性和准确性，结果显示：本算法具有实时性好和准确率高的优点，可以满足实际工程中四轴飞行器的实时避障要求。

Abstract

For bad real-time ability and poor accuracy rate of the monocular obstacle avoidance algorithm for quad-rotor helicopters in practical engineering applications

a new monocular obstacle avoidance algorithm based on Pyramid Lucas-Kanade optical flow and moving optical flow was proposed and the mathematical derivation process of the algorithm was given. The algorithm was established and implemented on a ArduCopter quad-rotor helicopter equipped with a 320 pixel240 pixel camera and many experiments was done to verify the feasibility and effectiveness of the algorithm. In the process of vehicle autonomous flight

the vanishing points were used for navigation and a neural net PID was used to control flighting adaptively. As compared with the monocular Synchronous Location Mapping(SLAM) obstacle avoidance algorithm

Horn-Schunck optical flow obstacle avoidance algorithm and the image segmentation obstacle avoidance algorithm

the proposed algorithm shows better real-time ability and accuracy rate

and can meet the requirements of obstacle avoidance in real time for quad-rotor helicopters.

关键词

Keywords

references

GRZONKA S,GRISETTI G,BURGARD W.A fully autonomous indoor quad-rotor[J].IEEE Transactions On Robotics,2012,28(1):90-100.

HERISSE B,HAMEL T,MAHONY R.Russotto F-X.landing a VTOL unmanned aerial vehicle on a moving platform using optical flow[J]. IEEE Robotics and Automation Society, 2012,28(1):77 -89.

AYDIN E,LU N I,EFE MÖ. Autonomous quad-rotor flight with vision-based obstacle avoidance in virtual environment [J].Expert Systems With Applications,2012,39:894-905.

刘正东,高鹏,杨静宇. 一种用于道路避障的双目视觉图像分割方法[J]. 计算机应用研究,2005,4:249-251. LIU ZH D,GAO P,YANG J Y.Binocular image segmentation algorithm for obstacles avoidance[J].Application Research of Computers,2005,4:249-251.

KENDOUL F, FANTONI A,NONAM A. Optic flow-based vision system for autonomous 3D localization and control of small aerial vehicles [J]. Robotics and Autonomous Systems, 2009, 57 (6-7):591-602.

GRIGORESCU S M,MACESANU G,COCIAS T T,et al.. Robust camera pose and scene structure analysis for service robotics [J]. Robotics and Autonomous Systems,2011,59(11): 889-909.

陈向坚,李迪,续志军,等. 四旋翼微型飞行器的区间二型模糊神经网络自适应控制[J]. 光学精密工程,2012,20(6):1335-1341. CHEN X J,LI D,XU ZH J,et al..Adaptive control of Quad-rotor MAV using interval typr-II fuzzy neuralnetwork[J]. Opt.Precision Eng.,2012,20(6):1335-1341.(in Chinese)

陈向坚,李迪,白越,等. 模糊神经网络在自适应双轴运动控制系统中的应用[J]. 光学精密工程,2011,19(7):1643-1650. CHEN X J,LI D,BAI Y,et al..Application of type-II fuzzy neural network to adaptive double axis motion control system [J].Opt.Precision Eng.,2011,19(7):1643-1650.(in Chinese)

VIET VO,NGOC LY.An effective approach for human actions recognition based on optical flow and edge featuresÖ.ICCAIS2012.Ho Chi Minh City,2012:24-29.

DAVISON A J,REID L D,MOLTON N D,et al..MonoSLAM: Real-time single camera SLAM [J].IEEE Transactions On Pattern Analysis And Machine Intelligence,2007,29(6):1052-1067.

EINHORN E,SCHR TER CH,GROSS H M.Attention-driven monocular scene reconstruction for obstacle detection, robot navigation and map building [J].Robotics and Autonomous Systems,2011,59:296-309.

HARTLEY R, ZISSERMAN A.Multiple View Geometry in Computer Vision[M].Cambridge:Cambridge University Press,2004.

STEFANOSKI N,WANG O,LANG M,et al.. Automatic view synthesis by image-domain-warping [J]. IEEE Signal Processing Society,2013,22(9):3329-3341.

夏军营,徐小泉,熊九龙. 利用平行透视投影模型的位姿迭代估计[J]. 光学精密工程,2012,20(6):1345-1349. XIA J Y,XU X Q,XIONG J L.Iterative pose estimation using paraperspective camera model[J].Opt. Precision Eng.,2012,20(6):1345-1349.

SMITH M J,BOXERBAUM A,PETERSON G L,et al.. Lectronic image stabilization using optical flow with inertial fusion[C].IROS 2010,Taipei,2010:1146-1153.

MAHONY R, KUMAR V, CORKE P. Multirotor aerial vehicles:modeling, estimation, and control of Quadrotor[J]. IEEE Robotics & Automation Magazine,2012,19(3): 20-32.

浏览量

480

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于单目视觉的火箭回收高度测量技术研究

面向激光跟踪测量的大范围高精度姿态测量

基于深度学习和PnP模型的激光跟踪仪自动姿态测量

基于三维模型的单目车辆位姿估计

面向低分辨率单目内窥镜图像的三维多孔结构重建