Tracking and recognition of projective spots for cooperation targets in vehicle simulation test

HUO Ju; YANG Ning; YANG Ming

doi:10.3788/OPE.20152308.2134

您当前的位置：

首页 >

文章列表页 >

Tracking and recognition of projective spots for cooperation targets in vehicle simulation test

更新时间：2020-08-12

- Tracking and recognition of projective spots for cooperation targets in vehicle simulation test
- Optics and Precision Engineering Vol. 23, Issue 8, Pages: 2134-2142(2015)
- 作者机构：
  
  1. 哈尔滨工业大学电气工程系, 黑龙江哈尔滨 150001
  2. <br /> 2. 哈尔滨工业大学控制与仿真中心,黑龙江哈尔滨,150080
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152308.2134
  CLC： V557;V448.2
- Received：21 January 2015，
  
  Revised：20 March 2015，
  
  Published：25 August 2015
- 稿件说明：
移动端阅览
霍炬, 杨宁, 杨明. 飞行器仿真测试中合作目标投影光斑的跟踪识别[J]. 光学精密工程, 2015,23(8): 2134-2142

HUO Ju, YANG Ning, YANG Ming. Tracking and recognition of projective spots for cooperation targets in vehicle simulation test[J]. Editorial Office of Optics and Precision Engineering, 2015,23(8): 2134-2142
霍炬, 杨宁, 杨明. 飞行器仿真测试中合作目标投影光斑的跟踪识别[J]. 光学精密工程, 2015,23(8): 2134-2142 DOI： 10.3788/OPE.20152308.2134.

HUO Ju, YANG Ning, YANG Ming. Tracking and recognition of projective spots for cooperation targets in vehicle simulation test[J]. Editorial Office of Optics and Precision Engineering, 2015,23(8): 2134-2142 DOI： 10.3788/OPE.20152308.2134.

摘要

针对飞行器仿真测试中合作目标投影光斑的跟踪识别问题

提出了一种投影光斑跟踪识别新方法

该方法主要由预测、识别及修正3个阶段组成。预测阶段主要结合投影光斑运动特点对传统卡尔曼滤波进行改进

提高投影光斑的位置预测精度。识别阶段则根据投影光斑位置的预测值

分两种情况对光斑进行处理:如果下一时刻投影光斑在视场内

则根据相应的判别准则和匹配策略在下一时刻图像中快速搜索投影光斑的最优匹配光斑;如果下一时刻投影光斑在视场外

则根据测量系统相关信息

对视场外投影光斑在图像平面上的位置进行求解

并将求解结果加入相应的运动轨迹

实现对视场外投影光斑的跟踪识别。在完成投影光斑的跟踪识别后

根据跟踪识别结果对投影光斑相关参数进行修正。仿真实验和实际实验结果表明

本文方法能够有效跟踪识别飞行器仿真测试中合作目标的投影光斑

其最大跟踪识别误差不超过2.5pixel

即使跟踪识别过程中存在投影光斑进出视场的情况也不受影响。

Abstract

To track and recognize the projective spots of a cooperation target in the vehicle simulation test

a tracking and recognition method is proposed by combining the advantages of statistical methods and heuristic methods. This method tracks and recognizes the projective spots in a "prediction-recognition-modification" loop. In the prediction phase

the traditional Kalman filter is improved based on the movement characteristics of projective spots so as to precisely predict the projective spot positions. According to the predicted positions

the recognition of the projective spots in the recognition phase is divided into two parts. If a projective spot is in the field-of-view at next time instance

its optimal matching spot in the image will be rapidly searched with the gain function and matching strategy. If the projective spot is out of the field-of-view at next time instance

its position on the image plane will be calculated with the measuring system information

and the calculated position will be added into the corresponding trajectory. Once the recognition of the projective spots is completed

the parameters related to projective spots are modified with the recognition results. Simulation and real experimental results indicate that the proposed method can effectively track and recognize the projective spots

whose maximum error is no more than 2.5 pixel

even if the projective spots exit and enter the scene during the measurement.

关键词

Keywords

references

赵玉华, 袁峰, 丁振良, 等. 基于合作目标的姿态测量系统建模及精度的蒙特卡洛估计[J]. 仪器仪表学报, 2010, 31(8): 1873-1877. ZHAO Y H, YUAN F, DING ZH L, et al.. Modeling of the attitude measurement system based on cooperation target and its accuracy estimation with Monte-Carlo simulation[J]. Chinese Journal of Scientific Instrument, 2010, 31(8):1873-1877. (in Chinese)

[2] 李晶, 袁峰, 胡英辉. 基于多点合作目标的多线阵CCD空间物体姿态测量[J]. 光学精密工程, 2013, 21(6): 1635-1641. LI J, YUAN F, HU Y H. Attitude measurements of space objects based on multi-linear CCD and multi-point cooperation target[J]. Optics and Precision Engineering, 2013, 21(6): 1635-1641. (in Chinese)

[3] 仲小清, 霍炬, 杨明. 基于直线的运动目标相对位置姿态光学测量方法[J]. 光学技术, 2008, 34(6): 862-869. ZHONG X Q, HUO J, YANG M. Method for relative attitude and position measurement of moving target based on lines[J]. Optical Technique, 2008, 34(6):862-869. (in Chinese)

[4] 蒋良卫. 图像序列中目标跟踪技术研究[D]. 武汉: 华中科技大学, 2013. JIANG L W. Research on Object Tracking Algorithms in Image Sequence[D]. Wuhan: Huazhong University of Science and Technology, 2013. (in Chinese)

[5] 刘洁. 基于特征点的目标检测与跟踪方法研究[D]. 成都: 电子科技大学, 2008. LIU J. Study of Object Detection and Tracking Algorithms Based on Feature Points[D]. Chengdu: University of Electronic Science and Technology of China, 2008. (in Chinese)

[6] FORTMANN T E, BAR-SHALOM Y, SCHEFFE M. Sonar tracking of multiple targets using joint probabilistic data association[J]. IEEE J. Oceanic Eng., 1983, 8(3): 173-184.

[7] REID D B. An algorithm for tracking multiple targets[J]. IEEE Trans. Automatic Control, 1979, 24(6): 843-854.

[8] STALDER S, GRABNER H, VAN GOOL L. Cascaded confidence filtering for improved tracking-by-detection[C]. Proceedings of European Conference on Computer Vision, Crete, Greece, 2010: 369-382.

[9] COR J V, MARCEL J R, ERIC B. Resolving motion correspondence for densely moving points[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2001, 23(1): 54-72.

[10] KHURRAM S, MUBARAK S. A noniterative greedy algorithm for multiframe point correspondence[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2005, 27(1): 51-65.

[11] 赵其杰, 屠大维, 高健, 等. 基于Kalman滤波的视觉预测目标跟踪及其应用[J]. 光学精密工程, 2008, 16(5): 937-942. ZHAO Q J, TU D W, GAO J, et al.. Kalman filter based vision predicting and object tracking method and its application[J]. Opt. Precision Eng., 2008, 16(5): 937-942. (in Chinese)

[12] 孔军, 汤心溢, 蒋敏, 等. 基于多尺度特征提取的Kalman滤波跟踪[J]. 红外与毫米波学报, 2011, 30(5): 446-450. KONG J, TANG X Y, JIANG M, et al.. Target tracking based on multi-scale feature extraction Kalman filter[J]. J. Infrared Millim. Waves, 2011, 30(5):446-450. (in Chinese)

[13] 李红昕, 王帅, 刘钊. 卡尔曼跟踪滤波器的一种改进的运动模型[J]. 信号处理, 2004, 20(6): 559-562. LI H X, WANG SH, LIU ZH. An improved motion model for Kalman trackers[J]. Signal Processing, 2004, 20(6): 559-562. (in Chinese)

[14] SETHI I K, JAIN R. Finding trajectories of feature points in a monocular image sequence[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1987, 9(1): 56-73.

Views

475

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Vision measurement of pitch and profile deviations for small modulus gears with unknown parameters

Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network

Calibration of binocular vision measurement system

Automatic camera calibration based on coded marker

Real-time global search for point targets in vision measurement

Related Author

Jie TANG

Xiao-bing LIU

Rui LI

Xue-song FU

Jian-lin WANG

Li-qiang ZHAO

Ru-tong WANG

Yong-qi GUO

Related Institution

Beijing Engineering Research Center of Precision Measurement Technology and Instruments， Beijing University of Technology

College of Information Science and Technology, Beijing University of Chemical Technology

Key Laboratory for Precision and Non-traditional Machining Technology of the Ministry of Education, Dalian University of Technology

Equipment Academy of the Chinese People's Liberation Army, Beijing 101416, China

School of Electrical Engineering and Automation, Harbin Institute of Technology

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