基于深度学习的四旋翼无人机单目视觉避障方法

doi:10.11772/j.issn.1001-9081.2018091952

计算机应用 ›› 2019, Vol. 39 ›› Issue (4): 1001-1005.DOI: 10.11772/j.issn.1001-9081.2018091952

基于深度学习的四旋翼无人机单目视觉避障方法

张午阳^1,2, 章伟¹, 宋芳¹, 龙林²

1. 上海工程技术大学机器人智能控制实验室, 上海 201620;
2. 上海工程技术大学机械与汽车工程学院, 上海 201620

收稿日期:2018-09-20 修回日期:2018-11-15 出版日期:2019-04-10 发布日期:2019-04-10
通讯作者: 宋芳
作者简介:张午阳(1994-),男,安徽淮北人,硕士研究生,主要研究方向:无人机避障、计算机视觉;章伟(1977-),男,安徽桐城人,副教授,博士,主要研究方向:非线性控制与观测器、鲁棒控制、无人机控制;宋芳(1980-),女,黑龙江大庆人,副教授,博士,主要研究方向:机器人、运动控制;龙林(1976-),男,安徽桐城人,硕士,主要研究方向:智能化控制、物联网。
基金资助:
国家自然科学基金资助项目（51505273）。

Monocular vision obstacle avoidance method for quadcopter based on deep learning

ZHANG Wuyang^1,2, ZHANG Wei¹, SONG Fang¹, LONG Lin²

1. Laboratory of Intelligent Control and Robotics, Shanghai University of Engineering Science, Shanghai 201620, China;
2. College of Mechanical and Automobile Engineering, Shanghai University of Engineering Science, Shanghai 201620, China

Received:2018-09-20 Revised:2018-11-15 Online:2019-04-10 Published:2019-04-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (51505273).

摘要/Abstract

摘要： 针对无人机避障问题，提出一种基于深度学习的四旋翼无人机单目视觉避障方法。首先通过目标检测框选出目标在图像中的位置，并通过计算目标选框上下边距的长度，以此来估量出障碍物到无人机之间的距离；然后通过协同计算机判断是否执行避障动作；最后使用基于Pixhawk搭建的飞行实验平台进行实验。实验结果表明，该方法可用于无人机低速飞行条件下避障。该方法所用到的传感器只有一块单目摄像头，而且相对于传统的主动式传感器避障方法，所占用无人机的体积大幅减小。该方法鲁棒性较好，能够准确识别不同姿态的人，实现对人避障。

关键词: 深度学习, 目标检测, 单目视觉, 无人机避障

Abstract: A monocular vision obstacle avoidance method for quadrotor based on deep learning was proposed to help quadrotors to avoid obstacles. Firstly, the position of object in the image was obtained by object detection, and by calculating the height of the object box in the image, the distance between quadcopter and obstacle was estimated. Then, whether performing obstacle avoidance was determined by synergetic computer. Finally, experiments were conducted on a flight test platform based on Pixhawk flight control board. The results show that the proposed method can be applied to quadcoptor obstacle avoidance with low speed. Compared with traditional active sensor methods, the proposed method greatly reduces the occupied volume with only one monocular camera as sensor. This method is robust and can identify people with different postures as obstacles.

Key words: deep learning, object detection, monocular vision, quadcopter obstacle avoidance

中图分类号:

TP242

张午阳, 章伟, 宋芳, 龙林. 基于深度学习的四旋翼无人机单目视觉避障方法[J]. 计算机应用, 2019, 39(4): 1001-1005.

ZHANG Wuyang, ZHANG Wei, SONG Fang, LONG Lin. Monocular vision obstacle avoidance method for quadcopter based on deep learning[J]. Journal of Computer Applications, 2019, 39(4): 1001-1005.

参考文献

[1] 杨秀霞, 刘小伟, 张毅. 基于时间约束的无人机避障研究[J]. 飞行力学, 2015, 33(2):125-129. (YANG X X, LIU X W, ZHANG Y. Research on obstacle avoidance of UAV based on time constraint[J]. Flight Mechanics, 2015, 33(2):125-129.)
[2] 高迪. 无人机避障雷达目标探测与跟踪算法研究[D]. 哈尔滨:哈尔滨工业大学, 2017:10-17. (GAO D. Research on target detection and tracking algorithm for UAV obstacle avoidance radar[D]. Harbin:Harbin Institute of Technology, 2017:10-17.)
[3] 朱平, 甄子洋, 覃海群,等. 基于立体视觉和光流的无人机避障算法研究[J]. 电光与控制, 2017, 24(12):31-35. (ZHU P, ZHEN Z Y, QIN H Q, el al. Research on UAV obstacle avoidance algorithm based on stereo vision and optical flow[J]. Electronics Optics & Control, 2017, 24(12):31-35.)
[4] YANG Y, WANG T T, CEHN L, et al. Stereo vision based obstacle avoidance strategy for quadcopter UAV[C]//Proceedings of the 2018 Chinese Control and Decision Conference. Piscataway, NJ:IEEE, 2018:490-494.
[5] HU Y Y, WANG Y X. Stereo vision-based fast obstacles avoidance without obstacles discrimination for indoor UAVs[C]//Proceedings of the 20112nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce. Piscataway, NJ:IEEE, 2011:4332-4337.
[6] HU J, NIU Y, WANG Z. Obstacle avoidance methods for rotor UAVs using RealSense camera[C]//Proceedings of the 2017 Chinese Automation Congress. Piscataway, NJ:IEEE, 2017:7151-7155.
[7] XU Z, WER R, ZHANG Q, et al. Obstacle avoidance algorithm for UAVs in unknown environment based on distributional perception and decision making[C]//Proceedings of the 2016 IEEE Chinese Guidance, Navigation and Control Conference. Piscataway, NJ:IEEE, 2016:1072-1075.
[8] GAGEIK N, BENZ P, MONTENEGRO S. Obstacle detection and collision avoidance for a UAV with complementary low-cost sensors[J]. IEEE Access, 2015, 3:599-609.
[9] RⅡSGAARD S, BLAS M R. SLAM for dummies:a tutorial approach to simultaneous localization and mapping[EB/OL].[2018-05-10]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.208.6289&rep=rep1&type=pdf.
[10] 陈炜楠, 刘冠峰, 李俊良, 等. 室内环境的元胞自动机SLAM算法[J]. 机器人, 2016, 38(2):169-177. (CHEN W N, LIU G F, LI J L, et al. Cellular automaton SLAM algorithm for indoor environment[J]. Robot, 2016, 38(2):169-177.)
[11] 徐伟杰, 李平, 韩波. 基于2点RANSAC的无人直升机单目视觉SLAM[J]. 机器人, 2012, 34(1):65-71. (XU W J, LI P, HAN B. Unmanned helicopter monocular vision SLAM based on 2 points RANSAC[J]. Robot, 2012, 34(1):65-71.)
[12] BAI G, XIANG X, ZHU H, et al. Research on obstacles avoidance technology for UAV based on improved PTAM algorithm[C]//Proceedings of the 2015 IEEE International Conference on Progress in Informatics and Computing. Piscataway, NJ:IEEE, 2015:543-550.
[13] CHEN Z, LUO X, DAI B. Design of obstacle avoidance system for micro-UAV based on binocular vision[C]//Proceedings of the 2017 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration. Piscataway, NJ:IEEE, 2017:67-70.
[14] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[15] ABBAS M A. Improving deep learning performance using random forest HTM cortical learning algorithm[C]//Proceedings of the 2018 First International Workshop on Deep and Representation Learning. Piscataway, NJ:IEEE, 2018:13-18.
[16] WANG Y. Cognitive foundations of knowledge science and deep knowledge learning by cognitive robots[C]//Proceedings of the 2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing. Piscataway, NJ:IEEE, 2017:5.
[17] GOODFELLOW I, BENGIO Y, COURVILLE A, et al. Deep learning[M]. Cambridge, MA:MIT Press, 2016:11-12.
[18] 杜学丹, 蔡莹皓, 鲁涛, 等. 一种基于深度学习的机械臂抓取方法[J]. 机器人, 2017, 39(6):820-828, 837. (DU X D, CAI Y H, LU T, et al. A mechanical arm grabbing method based on deep learning[J]. Robot, 2017, 39(6):820-828, 837.)
[19] ZOU J, SONG R. Microarray camera image segmentation with faster-RCNN[C]//Proceedings of the 2018 IEEE International Conference on Applied System Invention. Piscataway, NJ:IEEE, 2018:86-89.
[20] LECUN Y, KAVUKCUOGLU K, FARABET C. Convolutional networks and applications in vision[C]//Proceedings of the 2010 IEEE International Symposium on Circuits and Systems. Piscataway, NJ:IEEE, 2010:253-256.
[21] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2014:580-587.
[22] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:1440-1448.
[23] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[24] ZHENG W, XIAO J, XIN T. Integrated navigation system with monocular vision and LIDAR for indoor UAVs[C]//Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications. Piscataway, NJ:IEEE, 2017:924-929.
[25] GUANGLEI M, HAIBING P. The application of ultrasonic sensor in the obstacle avoidance of quad-rotor UAV[C]//Proceedings of the 2016 IEEE Chinese Guidance, Navigation and Control Conference. Piscataway, NJ:IEEE, 2016:976-981.
[26] DIXIT K R, KRISHNA P P, ANTONY R. Design and development of H frame quadcopter for control system with obstacle detection using ultrasound sensors[C]//Proceedings of the 2017 International Conference on Circuits, Controls, and Communications. Piscataway, NJ:IEEE, 2017:100-104.

基于深度学习的四旋翼无人机单目视觉避障方法

Monocular vision obstacle avoidance method for quadcopter based on deep learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[3]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[4]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[5]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[6]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[7]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[8]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[9]	樊玮, 李晨炫, 邢艳, 黄睿, 彭洪健. 航空发动机损伤图像的二分类到多分类递进式检测网络[J]. 计算机应用, 2021, 41(8): 2352-2357.
[10]	陈静, 毛莺池, 陈豪, 王龙宝, 王子成. 基于改进单点多盒检测器的大坝缺陷目标检测方法[J]. 计算机应用, 2021, 41(8): 2366-2372.
[11]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[12]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[13]	肖振远, 王逸涵, 罗建桥, 熊鹰, 李柏林. 基于部分加权损失函数的RefineDet[J]. 计算机应用, 2021, 41(7): 1928-1932.
[14]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[15]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.