单目视觉Tukey权因子模型室内位置测量
A monocular indoor vision position measurement method based on the Tukey model
- 2020年24卷第1期 页码:76-84
纸质出版日期: 2020-01-07
DOI: 10.11834/jrs.20208210
扫 描 看 全 文
浏览全部资源
扫码关注微信
纸质出版日期: 2020-01-07 ,
扫 描 看 全 文
刘飞,张继贤,王坚,张欣欣,丁晓波.2020.单目视觉Tukey权因子模型室内位置测量.遥感学报,24(1): 76-84
LIU Fei,ZHANG Jixian,WANG Jian,ZHANG Xinxin,Ding Xiaobo. 2020. A monocular indoor vision position measurement method based on the Tukey model. Journal of Remote Sensing(Chinese). 24(1): 76-84
面向室内导航和定位的需求,本文提出了一种基于编码图形和单目视觉传感器相结合的室内移动载体位置测量方法。首先,优化设计了一系列用于移动载体空间位置计算的编码影像,利用轮廓匹配、矩计算和映射匹配相结合的方式实现空编图形的识别与定位。其次,针对编码图形中心像方坐标观测值提取残差,构建了基于单位权和Tukey权因子模型的空间后方交会方法,基于两种权重因子分别计算了移动载体的观测值残差权重,分析了不同残差的观测值对结果的影响程度。然后,构建了4组实验环境,从不同角度获取了观测影像,并进行了数据处理与分析。最后,通过实验验证,表明基于2种权因子模型的方法均能够实现载体位置的计算,但基于Tukey权因子方法具有更高的精度,平面精度提高了29.76%—49.42%,高程精度提高了29.17%—74.07%。本文方法能够为室内空间移动载体提供高精度的导航和定位测量服务。
Localization is one of the core technologies of indoor surveying and mapping services. To achieve an accurate indoor navigation and positioning
many indoor navigation and positioning technologies have been introduced. Given that visual sensors can generate an abundant amount of information at low cost and can be easily implemented
the space navigation and positioning method based on vision sensors has become a research hotspot. This paper proposes a robust method for measuring the mobile platform position measurement based on the coding graphic images that are captured by a monocular vision sensor.
First
a series of coding graphics for the positioning of the carrier are designed. Coding graphics can be accurately identified through contour matching
and the coordinates of the center of graphics can be obtained by means of moment calculation and coding matching. However
due to the shooting angle
the coding image is deformed
thereby resulting in the residual errors of the image coordinates. Second
the Tukey weight factor model is used to calculate the weight according to the residual of the observed value. The value with a residual error of less than 1
<math id="M1"><msub><mrow><mi>s</mi></mrow><mrow><mn mathvariant="normal">0</mn></mrow></msub></math>
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165233&type=
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165229&type=
2.28600001
3.04799986
will be fully utilized
the value with a residual error ranging from 1
<math id="M2"><msub><mrow><mi>s</mi></mrow><mrow><mn mathvariant="normal">0</mn></mrow></msub></math>
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165241&type=
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165236&type=
2.28600001
3.04799986
to 2
<math id="M3"><msub><mrow><mi>s</mi></mrow><mrow><mn mathvariant="normal">0</mn></mrow></msub></math>
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165250&type=
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165246&type=
2.28600001
3.04799986
will be used with reduced weight
and the values with a residual error outside the range of 2
<math id="M4"><msub><mrow><mi>s</mi></mrow><mrow><mn mathvariant="normal">0</mn></mrow></msub></math>
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165259&type=
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=21165255&type=
2.28600001
3.04799986
will be suppressed. Third
the space resection methods based on Tukey and unit weights are adopted and used to calculate the position information of the mobile vehicle. Finally
experimental environments are then built
where 22 coding graphics are randomly pasted on the wall
and the coordinates of the coding graphics with accuracies of greater than 1 cm are measured by the total station. Four groups of images are captured
with each group having 9
12
11
and 17 available coding graphics of each group.
The experiment results indicate that the proposed methods (based on unit weight and Tukey weights can be used to calculate the position of mobile carriers in a room. The method based on Tukey weight obtained better results and improved the plane and elevation accuracies by 29.76%–49.42% and 29.17%–74.07%
respectively.
In general
the coding graphics designed in this paper can be accurately identified and positioned
the Tukey weight factor model can effectively identify the observed value residuals
and the space resection method based on the Tukey weight factor model can be used to calculate the position information of the vehicle and obtain better estimates. Therefore
the proposed method can provide high-precision navigation and positioning measurement services for indoor space mobile carriers.
室内定位编码图形单目视觉tukey权重抗差模型
indoor positioningcoding graphicsmonocular visiontukey weightrobust model
Aider O A, Hoppenot P and Colle E. 2005. A model-based method for indoor mobile robot localization using monocular vision and straight-line correspondences. Robotics and Autonomous Systems, 52(2/3): 229-246 [DOI: 10.1016/j.robot.2005.03.002http://dx.doi.org/10.1016/j.robot.2005.03.002]
Ayala V, Hayet J B, Lerasle F and Devy M. 2000. Visual localization of a mobile robot in indoor environments using planar landmarks//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Takamatsu, Japan: IEEE: 275-280 [DOI: 10.1109/IROS.2000.894617http://dx.doi.org/10.1109/IROS.2000.894617]
Bradski G and Kaehler A. 2008. Learning OpenCV. Sebastopol: O’Reilly Media, Inc
Chen Y T. 2016. Research and Application on Monocular Vision for Mobile Robot Navigation and Localization Technology. Chengdu: University of Electronic Science and Technology of China
陈易婷. 2016. 基于单目视觉的移动智能机器人的导航定位技术的研究和应用. 成都: 电子科技大学
Feng C. 2013. Research on Identification and Location of Object Based on Monocular Vision. Nanjing: Nanjing University of Aeronautics and Astronautics
冯春. 2013. 基于单目视觉的目标识别与定位研究. 南京: 南京航空航天大学
Feng W H. 2002. Close Range Photogrammetry. Wuhan: Wuhan University Press
冯文灏. 2002. 近景摄影测量——物体外形与运动状态的摄影法测定 . 武汉: 武汉大学出版社
Otsu N. 1975. A threshold selection method from gray-level histograms. Automatica, 11(285/296): 23-27
Royer E, Lhuillier M, Dhome M and Lavest J M. 2007. Monocular vision for mobile robot localization and autonomous navigation. International Journal of Computer Vision, 74(3): 237-260 [DOI: 10.1007/s11263-006-0023-yhttp://dx.doi.org/10.1007/s11263-006-0023-y]
Shen H J. 2009. Research on Camera Location based on Monocular Vision. Changchun: Jilin University
沈慧杰. 2009. 基于单目视觉的摄像机定位方法的研究. 长春: 吉林大学
Wang Z, Wu L X and Kong X Q. 2011. Mobile positioning in blind environments (I): pattern recognition algorithms for coded sequence pattern signposts. Journal of Northeastern University (Natural Science), 32(5): 732-735
王植, 吴立新, 孔祥勤. 2011. 盲环境移动定位(I): 序列编码图形路标识别算法. 东北大学学报(自然科学版), 32(5): 732-735 [DOI: 10.3969/j.issn.1005-3026.2011.05.031http://dx.doi.org/10.3969/j.issn.1005-3026.2011.05.031]
Wang Z B, Yao X and Luan X K. 2010. Automated circle target detection in close-range photogrammetry based on Hu moments. Urban Geotechnical Investigation and Surveying, (5): 93-97
王至博, 姚喜, 栾学科. 2010. 基于Hu矩的近景摄影测量圆形标志的自动检测. 城市勘测, (5): 93-97 [DOI: 10.3969/j.issn.1672-8262.2010.05.023]
Zhang J Q, Pan L and Wang S G. 2009. Photogrammetry. 2nd ed. Wuhan: Wuhan University Press
张剑清, 潘励, 王树根. 2009. 摄影测量学. 2版. 武汉: 武汉大学出版社
Zhang Z, Xu C, Ren S X and Han H L. 2014. Digital Image Process and Robot Vision. 2nd ed. Beijing: PostsandTelecom Press
张铮, 徐超, 任淑霞, 韩海玲. 2014. 数字图像处理与机器视觉——Visual C++与Matlab实现. 2版. 北京: 人民邮电出版社
Zhang Z M, Wang P and Sun C K. 2011. Position and orientation measurement method with monocular vision and digital simulation. Journal of Tianjin University, 44(5): 440-444
张子淼, 王鹏, 孙长库. 2011. 单目视觉位姿测量方法及数字仿真. 天津大学学报, 44(5): 440-444 [DOI: 10.3969/j.issn.0493-2137.2011.05.012http://dx.doi.org/10.3969/j.issn.0493-2137.2011.05.012]
Zhang Z Y. 2000. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11): 1330-1334 [DOI: 10.1109/34.888718http://dx.doi.org/10.1109/34.888718]
Zhou J W, Huang Y C and Yang Y X. 1997. Wuhan: Huazhong University of Science and Technology Press: 74-82
周江文, 黄幼才, 杨元喜. 1997. 抗差最小二乘法. 武汉: 华中理工大学出版社: 74-82
Zhou N. 2007. Research on Camera Location based on Monocular Vision. Nanjing: Nanjing University of Aeronautics and Astronautics
周娜. 2007. 基于单目视觉的摄像机定位技术研究. 南京: 南京航空航天大学
相关文章
相关作者
相关机构