留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

单目视觉融合激光投射的无人机障碍探测方法

刘峰 汪瓒 王向军

刘峰, 汪瓒, 王向军. 单目视觉融合激光投射的无人机障碍探测方法[J]. 应用光学.
引用本文: 刘峰, 汪瓒, 王向军. 单目视觉融合激光投射的无人机障碍探测方法[J]. 应用光学.
LIU Feng, WANG Zan, WANG Xiangjun. Obstacle detection method for UAV based on monocular vision and laser projection[J]. Journal of Applied Optics.
Citation: LIU Feng, WANG Zan, WANG Xiangjun. Obstacle detection method for UAV based on monocular vision and laser projection[J]. Journal of Applied Optics.

单目视觉融合激光投射的无人机障碍探测方法

详细信息
    作者简介:

    刘峰(1978—),男,博士,主要从事图像分析与计算机视觉、光电传感与探测方面的研究。E-mail:tjuliufeng@tju.edu.cn

    通讯作者:

    汪瓒(1997—),男,硕士研究生,主要从事无人机避障、视觉测量方面的研究。E-mail:sang_wang@foxmail.com

  • 中图分类号: TN206

Obstacle detection method for UAV based on monocular vision and laser projection

  • 摘要: 针对微小型无人机在飞行作业任务中的主动避障需求,本文提出一种用于微小型无人机避障的基于单目视觉与主动激光点阵投射的障碍探测方法。使用单目相机采集投射的激光点阵图案,经过图像分割、聚类、质心提取等处理过程,通过像面激光线方程约束快速排除特征一致激光点的歧义,使用激光点探测出无人机前方空间中障碍的方位信息。实验验证装置在基线距离为65 mm,工作距离为7 m的条件下,障碍探测的相对误差在1.5%以内。本文方法精度高、时间复杂度低,可满足低算力的微小型无人机对障碍探测方法的需求,为进一步的避障策略的生成提供数据支撑。
  • 图  1  九点激光图案

    Fig.  1  Laser pattern of nine points

    图  2  原始采集图像与基于L*a*b*色彩空间的图像分割结果

    Fig.  2  Image captured by the vision system and Image segmentation results based on L*a*b* color space

    图  3  激光光斑聚类和质心提取结果

    Fig.  3  Results of spot clustering and centroid extraction

    图  4  受到影响的激光图案

    Fig.  4  Affected laser pattern

    图  5  像面激光线约束

    Fig.  5  Constraint of laser line on image plane

    图  6  实验装置场景图

    Fig.  6  Scene diagram of experimental device

    图  7  深度测量的相对误差折线图

    Fig.  7  Relative error line chart of depth measurement

    表  1  相机标定参数

    Table  1  Camera calibration parameters

    [fx , fy]/ pixel[u0 , v0]/ pixelkc
    相机标定参数[4 191.52, 4 195.61][862.89, 480.09][−0.506, 0.710, 0.000, 0.000]
    下载: 导出CSV

    表  2  激光图案的空间结构参数

    Table  2  Calibration parameters of laser pattern

    激光点编号结构参数
    k1b1k2b2
    00.023 5−68.557 40.036 84.240 4
    10.015 9−66.646 9−0.009 9−1.919 5
    20.053 9−71.004 8−0.001 11.396 4
    30.072 2−64.665 60.031 40.289 7
    40.063 7−67.777 30.069 0−0.513 9
    50.030 9−66.933 50.091 3−9.387 0
    6−0.005 8−70.393 90.079 7−0.097 7
    7−0.025 4−69.783 30.044 35.823 9
    8−0.016 0−68.509 80.009 7−1.490 3
    下载: 导出CSV

    表  3  “1号”激光点的测量数据

    Table  3  Measured data of the No.1 laser point mm

    组数坐标真值坐标测量值绝对误差
    XcalibYcalibZcalibXcalYcalZcalΔXΔYΔZ
    1−47.46−15.611 257.85−55.96−15.591 244.45−8.500.01−13.39
    2−44.33−16.801 363.58−55.24−17.181 346.42−10.91−0.38−17.17
    3−37.84−19.811 832.42−51.86−21.961 820.15−14.03−2.15−12.28
    4−31.59−24.082 137.75−49.70−25.642 124.71−18.11−1.56−13.04
    5−22.51−25.962 739.65−45.42−32.262 725.98−22.91−6.30−13.67
    6−14.63−32.793 216.23−41.83−37.483 230.34−27.21−4.6914.11
    7−0.04−45.004 306.69−33.99−50.274 332.54−33.94−5.2725.86
    814.09−51.175 034.92−28.99−58.425 035.40−43.07−7.250.47
    923.30−56.395 628.52−24.64−65.515 646.03−47.94−9.1217.51
    1044.40−72.856 972.79−14.46−82.107 076.21−58.87−9.25103.43
    1181.90−104.4810 044.83−5.44−98.758 344.44−87.345.73−1 700.39
    12127.28−164.3315 144.3019.85−146.3411 898.66−107.4317.99−3 245.64
    下载: 导出CSV
  • [1] HU Tianyu, SUN Xiliang, SU Yanjun, et al. Development and performance evaluation of a very low-cost UAV-lidar system for forestry applications[J]. Remote Sensing,2020,13(1):77. doi: 10.3390/rs13010077
    [2] FAN Xuanmei, XU Qiang, ALONSO-RODRIGUEZ A, et al. Successive landsliding and damming of the Jinsha River in eastern Tibet, China: prime investigation, early warning, and emergency response[J]. Landslides,2019,16(5):1003-1020. doi: 10.1007/s10346-019-01159-x
    [3] MAES W H, STEPPE K. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture[J]. Trends in Plant Science,2019,24(2):152-164. doi: 10.1016/j.tplants.2018.11.007
    [4] MENÉNDEZ O, PÉREZ M, AUAT CHEEIN F. Visual-based positioning of aerial maintenance platforms on overhead transmission lines[J]. Applied Sciences,2019,9(1):165. doi: 10.3390/app9010165
    [5] WANG Jingjing, JIANG Chunxiao, HAN Zhu, et al. Taking drones to the next level: cooperative distributed unmanned-aerial-vehicular networks for small and mini drones[J]. IEEE Vehicular Technology Magazine,2017,12(3):73-82. doi: 10.1109/MVT.2016.2645481
    [6] ZHANG Xuejun, DU Yanshuang, GU Bo, et al. Survey of safety management approaches to unmanned aerial vehicles and enabling technologies[J]. Journal of Communications and Information Networks,2018,3(4):1-14. doi: 10.1007/s41650-018-0038-x
    [7] 王海群, 王水满, 张怡. 基于激光雷达信息的无人机避障控制研究[J]. 激光杂志,2019,40(12):76-79. doi: 10.14016/j.cnki.jgzz.2019.12.076

    WANG Haiqun, WANG Shuiman, ZHANG Yi. Control of UAV barrier avoidance based on lidar information[J]. Laser Journal,2019,40(12):76-79. doi: 10.14016/j.cnki.jgzz.2019.12.076
    [8] 吴开华, 王文杰. 植保无人机结构光视觉的障碍物检测方法[J]. 光电工程,2018,45(4):32-40.

    WU Kaihua, WANG Wenjie. Detection method of obstacle for plant protection UAV based on structured light vision[J]. Opto-Electronic Engineering,2018,45(4):32-40.
    [9] 高天禹, 马雨婷, 韩成哲, 等. 基于激光测距与单目视觉的微型无人机室内目标人物搜索方法研究[J]. 中国科学:技术科学,2020,50(7):971-982. doi: 10.1360/SST-2020-0130

    GAO Tianyu, MA Yuting, HAN Chengzhe, et al. Applying a micro-UAV for searching an indoor target person using laser ranging and monocular vision[J]. Scientia Sinica (Technologica),2020,50(7):971-982. doi: 10.1360/SST-2020-0130
    [10] 寇展, 吴健发, 王宏伦, 等. 基于深度学习的低空小型无人机障碍物视觉感知[J]. 中国科学:信息科学,2020,50(5):692-703. doi: 10.1360/N112019-00034

    KOU Zhan, WU Jianfa, WANG Honglun, et al. Obstacle visual sensing based on deep learning for low-altitude small unmanned aerial vehicles[J]. Scientia Sinica (Informationis),2020,50(5):692-703. doi: 10.1360/N112019-00034
    [11] KESELMAN L, WOODFILL J I, GRUNNET-JEPSEN A, et al. Intel(R) RealSense(TM) stereoscopic depth cameras[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu, HI, USA. IEEE, : 1267-1276.
    [12] AZETSU T, SUETAKE N. Hue-preserving image enhancement in CIELAB color space considering color gamut[J]. Optical Review,2019,26(2):283-294. doi: 10.1007/s10043-019-00499-2
    [13] ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334. doi: 10.1109/34.888718
    [14] 包建强, 张献州, 李圆, 等. 多种空间直线拟合方法应用分析[J]. 测绘科学,2020,45(5):132-139,151. doi: 10.16251/j.cnki.1009-2307.2020.05.020

    BAO Jianqiang, ZHANG Xianzhou, LI Yuan, et al. Applied analysis of various space linear fitting methods[J]. Science of Surveying and Mapping,2020,45(5):132-139,151. doi: 10.16251/j.cnki.1009-2307.2020.05.020
    [15] LI Qianwen, WEI Zhihua, ZHAO Cairong. Optimized automatic seeded region growing algorithm with application to ROI extraction[J]. International Journal of Image and Graphics,2017,17(4):1750024. doi: 10.1142/S0219467817500243
  • 加载中
图(8) / 表(3)
计量
  • 文章访问数:  18
  • HTML全文浏览量:  8
  • PDF下载量:  4
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-05-10
  • 修回日期:  2022-06-13
  • 网络出版日期:  2022-11-23

目录

    /

    返回文章
    返回