Visual detection of targetball for laser tracker target tracking recovery

Bo WANG; Deng-feng DONG; Dou-dou GAO

doi:10.3788/OPE.20202802.0271

您当前的位置：

首页 >

文章列表页 >

Visual detection of targetball for laser tracker target tracking recovery

Modern Applied Optics | 更新时间：2020-07-16

- Visual detection of targetball for laser tracker target tracking recovery
- Optics and Precision Engineering Vol. 28, Issue 2, Pages: 271-282(2020)
- 作者机构：
  
  1.中国科学院微电子研究所，北京 100094
  2.中国科学院大学，北京 100049
- 作者简介：
  
  董登峰(1981-)，男，河南商丘人，博士，副研究员，硕士生导师，2004年于郑州大学获得学士学位，2012年于北京航空航天大学获得博士学位，现为中国科学院微电子研究所光电研发中心副主任，主要从事光学精密测量、AI识别方法、智能跟踪控制、视觉伺服控制系统等方面的研究。E-mail:dongdengfeng@ime.ac.cn DONG Deng-feng, E-mail:dongdengfeng@ime.ac.cn
- 基金信息：
- DOI：10.3788/OPE.20202802.0271
  CLC： TH744.5; TP391.4
- Received：07 November 2019，
  
  Revised：26 November 2019，
  
  Accepted：26 November 2019，
  
  Published：15 February 2020
- 稿件说明：
移动端阅览
Bo WANG, Deng-feng DONG, Dou-dou GAO. Visual detection of targetball for laser tracker target tracking recovery[J]. Optics and precision engineering, 2020, 28(2): 271-282.
DOI：

Bo WANG, Deng-feng DONG, Dou-dou GAO. Visual detection of targetball for laser tracker target tracking recovery[J]. Optics and precision engineering, 2020, 28(2): 271-282. DOI： 10.3788/OPE.20202802.0271.

摘要

为了实现复杂场景下激光跟踪仪跟踪恢复过程中合作目标靶球的检测，本文研究了基于深度学习的靶球检测方法。首先，分析靶球自身特点、应用环境及它在跟踪恢复过程中的作用，然后根据Faster R-CNN模型原理与跟踪恢复应用需求提出基于超特征与浅层高分辨率特征信息复用的改进方法生成新的融合特征图，并优化区域建议提取参数，协同解决图像中目标多尺度变化与小尺寸导致目标漏检率高的问题；同时提出一种基于强背景干扰的困难样本挖掘方法提高模型对外形颜色等与目标近似的干扰物识别能力，解决模型误检测率高的问题。最后，本文构建了目标靶球数据集并进行了对比训练与测试。测试实验结果表明：本文提出的基于强背景干扰困难样本挖掘方法的改进Faster R-CNN模型在目标多尺度、小尺寸检测，以及对复杂背景中相似干扰物的辨别能力都有提升，最终对测试集的检测精度达到了90.11%，能够满足激光跟踪仪跟踪恢复过程对合作目标靶球的视觉检测精度要求。

Abstract

To visually detect a target ball for a laser tracker in a complex scene

a method of target ball detection improved by deep learning was proposed. Firstly

the characteristics of the target ball

its application environment

and its effect in tracking recovery were analyzed. Subsequently

Hypernet and shallow high-resolution features were adopted

New feature maps and an optimized region proposal were added to the original network

improving the network sensitivity to enable the detection of multi-scale and small targets. Hard example mining with strong background interference was used to reduce the ratio of error recognition

which resulted from similar objects. Finally

the dataset was established and a comparative experiment was carried out. The experiment results show that the improved method proposed in this study and hard example mining with strong background interference can increase the correct recognition rate obtained by Faster R-CNN

yielding a value of 90.11% in the test and meeting the tracking recovery requirement.

关键词

Keywords

references

周虎 , 邾继贵 , 张滋黎 , 等 . 激光电子经纬仪动态跟踪引导系统的设计 . 光学精密工程 , 2011 . 19 ( 11 ): 2671 - 2678 . http://www.eope.net/CN/abstract/abstract13805.shtml http://www.eope.net/CN/abstract/abstract13805.shtml .

H ZHOU , J G ZHU , Z L ZHANG , 等 . Design of dynamic tracking and guiding system for laser-electronic theodolite . Opt. Precision Eng. , 2011 . 19 ( 11 ): 2671 - 12678 . http://www.eope.net/CN/abstract/abstract13805.shtml http://www.eope.net/CN/abstract/abstract13805.shtml .

吴斌 , 苏晓越 . 一种视觉引导经纬仪自动测量中精确引导方法 . 激光技术 , 2015 . 39 ( 4 ): 453 - 457 . http://d.old.wanfangdata.com.cn/Periodical/jgjs201504005 http://d.old.wanfangdata.com.cn/Periodical/jgjs201504005 .

B WU , X Y SU . A precise guiding method for automatic measurement with visual guiding theodolites . Laser Technology , 2015 . 39 ( 4 ): 453 - 457 . http://d.old.wanfangdata.com.cn/Periodical/jgjs201504005 http://d.old.wanfangdata.com.cn/Periodical/jgjs201504005 .

王亚丽 , 魏振忠 , 张广军 , 等 . 视觉引导激光跟踪测量系统的Cayley变换校准方法 . 红外与激光工程 , 2016 . 45 ( 5 ): 248 - 253 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201605041 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201605041 .

Y L WANG , ZH ZH WEI , G J ZHANG , 等 . Calibration method for visual-guided laser tracker measurement system based on the Cayley transformation . Infrared and Laser Engineering , 2016 . 45 ( 5 ): 248 - 253 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201605041 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201605041 .

魏振忠 , 孙文 , 张广军 , 等 . 激光跟踪视觉导引测量中靶标球球心定位方法 . 红外与激光工程 , 2012 . 41 ( 4 ): 929 - 935 . DOI: 10.3969/j.issn.1007-2276.2012.04.019 http://doi.org/10.3969/j.issn.1007-2276.2012.04.019 .

ZH ZH WEI , W SUN , G J ZHANG , 等 . Method for finding the 3D center positions of the target reflectors in laser tracking measurement system based on vision guiding . Infrared and Laser Engineering , 2012 . 41 ( 4 ): 929 - 935 . DOI: 10.3969/j.issn.1007-2276.2012.04.019 http://doi.org/10.3969/j.issn.1007-2276.2012.04.019 .

姜吉祥 , 屈玉福 , 邓湘金 , 等 . 激光跟踪仪靶标球镜面中心定位方法 . 光学技术 , 2014 . 40 ( 4 ): 362 - 366, 370 . http://d.old.wanfangdata.com.cn/Periodical/gxjs201404017 http://d.old.wanfangdata.com.cn/Periodical/gxjs201404017 .

J X JIANG , Y F QU , X J DENG , 等 . Method of locating the mirror center of laser tracker target ball . Optical Technique , 2014 . 40 ( 4 ): 362 - 366, 370 . http://d.old.wanfangdata.com.cn/Periodical/gxjs201404017 http://d.old.wanfangdata.com.cn/Periodical/gxjs201404017 .

REDMON J, FARHADI A. YOLOv3: an Incremental Improvement[EB/OL]. 2018: arXiv: 1804.02767[cs.CV] . https://arxiv.org/abs/1804.02767 https://arxiv.org/abs/1804.02767

REN S Q, HE K M, GIRSHICK R, et al .. Faster R-CNN: towards real-time object detection with region proposal networks[C]// NIPS '15: Proceedings of the 28 th International Conference on Neural Information Processing Systems , MIT Press , 2015, 12015: 91-99.

郭毓 , 苏鹏飞 , 吴益飞 , 等 . 基于Faster R-CNN的机器人目标检测及空间定位 . 华中科技大学学报:自然科学版 , 2018 . 46 ( 12 ): 55 - 59 . http://d.old.wanfangdata.com.cn/Periodical/hzlgdxxb201812010 http://d.old.wanfangdata.com.cn/Periodical/hzlgdxxb201812010 .

Y GUO , P F SU , Y F WU , 等 . Object detection and location of robot based on Faster R-CNN . Journal of Huazhong University of Science and Technology:Natural Science Edition , 2018 . 46 ( 12 ): 55 - 59 . http://d.old.wanfangdata.com.cn/Periodical/hzlgdxxb201812010 http://d.old.wanfangdata.com.cn/Periodical/hzlgdxxb201812010 .

KONG T, YAO A B, CHEN Y R, et al .. HyperNet: Towards accurate region proposal generation and joint object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 27-30 June 2016, Las Vegas , NV , USA , 2016: 845-853.

冯小雨 , 梅卫 , 胡大帅 . 基于改进Faster R-CNN的空中目标检测 . 光学学报 , 2018 . 38 ( 6 ): 250 - 258 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201806034 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201806034 .

X Y FENG , W MEI , D SH HU . Aerial target detection based on improved Faster R-CNN . Acta Optica Sinica , 2018 . 38 ( 6 ): 250 - 258 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201806034 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201806034 .

王全东 , 常天庆 , 张雷 , 等 . 面向多尺度坦克装甲车辆目标检测的改进Faster R-CNN算法 . 计算机辅助设计与图形学学报 , 2018 . 30 ( 12 ): 2278 - 2291 . http://d.old.wanfangdata.com.cn/Periodical/jsjfzsjytxxxb201812010 http://d.old.wanfangdata.com.cn/Periodical/jsjfzsjytxxxb201812010 .

Q D WANG , T Q CHANG , L ZHANG , 等 . An improved faster R-CNN algorithm for detection of multi-scale tank armored vehicle targets . Journal of Computer-Aided Design & Computer Graphics , 2018 . 30 ( 12 ): 2278 - 2291 . http://d.old.wanfangdata.com.cn/Periodical/jsjfzsjytxxxb201812010 http://d.old.wanfangdata.com.cn/Periodical/jsjfzsjytxxxb201812010 .

SHRIVASTAVA A, GUPTA A, GIRSHICK R. Training Region-based object detectors with online hard example mining[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 27-30 June 2016, Las Vegas , NV , USA , 2016: 761-769.

B Y LI , Y LIU , X G WANG . Gradient harmonized single-stage detector . Proceedings of the AAAI Conference on Artificial Intelligence , 2019 . 33 8577 - 8584 . DOI: 10.1609/aaai.v33i01.33018577 http://doi.org/10.1609/aaai.v33i01.33018577 .

ERHAN D, SZEGEDY C, TOSHEV A, et al .. Scalable object detection using deep neural networks[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition , 23-28 June 2014, Columbus , OH , USA , 2014: 2155-2162.

张烨 , 许艇 , 冯定忠 , 等 . 基于难分样本挖掘的快速区域卷积神经网络目标检测研究 . 电子与信息学报 , 2019 . 40 ( 6 ): 1496 - 1502 . http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201906031 http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201906031 .

Y ZHANG , T XU , D ZH FENG , 等 . Research on Faster RCNN object detection based on hard example mining . Journal of Electronics & Information Technology , 2019 . 40 ( 6 ): 1496 - 1502 . http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201906031 http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201906031 .

方明 , 孙腾腾 , 邵桢 . 基于改进YOLOv2的快速安全帽佩戴情况检测 . 光学精密工程 , 2019 . 27 ( 5 ): 1196 - 1205 . http://www.eope.net/CN/abstract/abstract17877.shtml http://www.eope.net/CN/abstract/abstract17877.shtml .

M FANG , T T SUN , Z SHAO . Fast helmet-wearing-condition detection based on improved YOLOv2 . Opt. Precision Eng. , 2019 . 27 ( 5 ): 1196 - 1205 . http://www.eope.net/CN/abstract/abstract17877.shtml http://www.eope.net/CN/abstract/abstract17877.shtml .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Polarized image feature fusion in power inspection

Remote sensing object detection algorithm based on ultra fusion residual marching geometric perception

High-precision attitude measurement with active aiming composite sensing for laser tracker

End-to-end recognition of nighttime wildlife based on semi-supervised learning

A self correcting low-light object detection method based on pyramid edge enhancement

Related Author

NI Mengyao

PENG Yuanlong

HU Shang

YAN Longchuan

ZHENG Jinkun

CAO Danhua

BAI Chenshuai

BAI Xiaofeng

Related Institution

School of Optical and Electronic Information， Huazhong University of Science and Technology

State Grid Information & Telecommunication Branch

State Grid JiangXi Electric Power Supply Co

School of Electronic and Information Engineering， Lanzhou Jiaotong University

Institute of Microelectronics， Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰