视频测量影像序列椭圆形人工目标点快速识别和跟踪方法

doi:10.11947/j.AGCS.2015.20130452

测绘学报 ›› 2015, Vol. 44 ›› Issue (6): 663-669.doi: 10.11947/j.AGCS.2015.20130452

视频测量影像序列椭圆形人工目标点快速识别和跟踪方法

刘祥磊^1,2, 童小华³, 马静⁴

1. 北京建筑大学测绘与城市空间信息学院, 北京 100044;
2. 现代城市测绘国家测绘地理信息局重点实验室, 北京 100044;
3. 同济大学测绘与地理信息学院, 上海 200092;
4. 北京市地质工程勘察院, 北京 100048

收稿日期:2014-04-03 修回日期:2015-03-09 出版日期:2015-06-20 发布日期:2015-07-28
通讯作者: 童小华 E-mail: xhtong@tongji.edu.cn E-mail:xhtong@tongji.edu.cn
作者简介:刘祥磊(1982—),男,博士,研究方向为视频测量建/构筑物模型健康监测。E-mail: liuxianglei@bucea.edu.cn
基金资助:
现代城市测绘国家测绘地理信息局重点实验室开放课题(20131203NY;20131202NZ);北京建筑大学科学研究基金(00331614022)

A Systemic Algorithm of Elliptical Artificial Targets Identification and Tracking for Image Sequences from Videogrammetry

LIU Xianglei^1,2, TONG Xiaohua³, MA Jing⁴

1. School of Geomatics and Urban Information, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
2. Key Laboratory for Urban Geomatics of National Administration of Surveying, Mapping and Geoinformation, Beijing 100044, China;
3. College of Surveying and Geo-informatics, Tongji University, Shanghai 200092, China;
4. Beijing Institute of Geo-engineering and Exploration, Beijing 100048, China

Received:2014-04-03 Revised:2015-03-09 Online:2015-06-20 Published:2015-07-28
Supported by:
Foundation of Key Laboratory for Urban Geomatics of National Administration of Surveying, Mapping and Geoinformation (Nos.20131203NY;20131202NZ);Scientific Research Foundation of Beijing University of Civil Engineering and Architecture (No.00331614022)

摘要/Abstract

摘要：

针对视频测量建筑物健康监测获取海量影像序列数据快速、准确识别和跟踪目标点的需求,提出基于影像块技术的椭圆形目标点识别和跟踪完整算法。该算法采用影像分块技术降低数据处理量,实现椭圆形目标点跟踪,集成数学形态学和椭圆几何属性特征,消除图像块边缘检测的非椭圆边缘信息,实现椭圆轮廓的提取,并采用最小二乘法拟合椭圆中心实现亚像素定位,快速、准确地实现视频测量建筑物健康监测椭圆形目标点的识别与跟踪。试验结果表明该方法获取的椭圆中心点像素坐标的RMS残差优于0.025个像素,且相对于随机Hough变换和模板识别算法,跟踪效率提高5倍以上。

关键词: 视频测量, 影像块, 椭圆识别, 数学形态学, 最小二乘法

Abstract:

In order to satisfy the requirement of identification and tracking the elliptical artificial targets fast and accurately for the image sequences from videogrammetric measurement for structural health monitoring, this paper proposes a systemic algorithm to identify and track the elliptical targets using the image block technique. The proposed method extracts the image block from original images to reduce the amount of data processing for the oval targets tracking. The mathematical morphology and elliptical geometric characteristics are integrated to eliminate the non-elliptical edge information to extract the elliptical contour in the range of image block. At last, the sub-pixel center location for elliptical artificial targets is acquired by the least square algorithm. The experimental results show that RMS error of 0.025 pixel can be achieved by the proposed method, furthermore, compared with the random Hough transform and template recognition algorithm, the tracking efficiency is improved over 5 times.

Key words: videogrammetric measurement, image block, ellipse identification, mathematical morphology, least square algorithm

中图分类号:

P232

刘祥磊, 童小华, 马静. 视频测量影像序列椭圆形人工目标点快速识别和跟踪方法[J]. 测绘学报, 2015, 44(6): 663-669.

LIU Xianglei, TONG Xiaohua, MA Jing. A Systemic Algorithm of Elliptical Artificial Targets Identification and Tracking for Image Sequences from Videogrammetry[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(6): 663-669.

参考文献

[1] HILLEBRAND M,STEVANOVIC N,HOSTICKA B J,et al. High Speed Camera System Using a CMOS Image Sensor[C]//Proceedings of the IEEE Intelligent Vehicles Symposium. Dearborn:IEEE,2000:656-661.
[2] MUEHLMANN U,RIBO M,LANG P,et al.A New High Speed CMOS Camera for Real-time Tracking Applications[C]//Proceedings of the 2004 IEEE International Conference on Robotics and Automation. New Orleans:IEEE,2004,5:5195-5200.
[3] REMONDINO F.Videogrammetry for Human Movement Analysis[C]//Proceedings of the 9th International Symposium on 3D Analysis of Human Movement. Zurich:Institute of Geodesy and Photogrammetry, 2006:25-33.
[4] WANG J B,ZHANG Y,YANG M G,et al.Observation of Arc Discharging Process of Nanocomposite Ag-SnO₂ and La-doped Ag-SnO₂ Contact with A High-speed Camera[J].Materials Science and Engineering:B,2006,131(1-3):230-234.
[5] FRASER C S,RIEDEL B.Monitoring the Thermal Deformation of Steel Beams via Vision Metrology[J].ISPRS Journal of Photogrammetry and Remote Sensing,2000,55(4):268-276.
[6] LEIFER J,WEEMS B J,KIENLE S C,et al.Three-dimensional Acceleration Measurement Using Videogrammetry Tracking Data[J].Experimental Mechanics,2011,51(2):199-217.
[7] FU G K,MOOSA A G.An Optical Approach to Structural Displacement Measurement and Its Application[J].Journal of Engineering Mechanics,2002,128(5):511-520.
[8] LEE J J, FUKUDA Y, SHINOZUKA M, et al.Development and Application of A Vision-based Displacement Measurement System for Structural Health Monitoring of Civil Structures[J].Smart Structures and Systems, 2007, 3(3):373-384.
[9] LIN S Y,MILLS J P,GOSLING P D.Videogrammetric Monitoring of As-built Membrane Roof Structures[J].The Photogrammetric Record,2008,23(122):128-147.
[10] YAN Bei,WANG Bin,LI Yuan.Optimal Ellipse Fitting Method Based on Least-square Principle[J].Journal of Beijing University of Aeronautics and Astronautics,2008,34(3):295-298.(闫蓓,王斌,李媛.基于最小二乘法的椭圆拟合改进算法[J].北京航空航天大学学报,2008,34(3):295-298.)
[11] LIU Shenghao,ZENG Libo,WU Qiongshui,et al. A Novel Cervical Cell Segmentation Method Based on Ellipse Deformable Template Technology[J].Chinese Journal of Scientific Instrument,2004,25(2):222-225.(刘生浩,曾立波,吴琼水,等.一种基于椭圆可变形模板技术的宫颈细胞图像分割方法[J].仪器仪表学报,2004,25(2):222-225.)
[12] HOUGH V,PAUL C.Method and Means for Recognizing Complex Patterns:US,069654[P/OL].1962-12-18.
[13] NIU X, HU Z,YANG S.Hierarchical Ellipse Detection Algorithm Based on Local PCA Hough Transform with Parameter Restraint[J].Journal of Computer Applications, 2009, 29(5):1365-1368.
[14] ZHOU T H,PAPANIKOLOPOULOS N.Enhancing the Randomized Hough Transform with k-means Clustering to Detect Mutually-Occluded Ellipses[C]//Proceedings of the 19th Mediterranean Conference on Control & Automation. Corfu:IEEE,2011:327-332.
[15] LIU R,SUN H M,WEI J,et al.Ellipse Detection and Fitting Based on RANSAC[J].Journal of Beijing Institute of Clothing Technology:Natural Science Edition, 2012,32(4):74-78.
[16] DOHI K,HATANAKA Y,NEGI K.Deep-pipelined FPGA Implementation of Ellipse Estimation for Eye Tracking[C]//Proceedings of the 22nd International Conference on Field Programmable Logic and Application.Oslo:IEEE,2012:458-463.
[17] LI Chang, Researching on Key Technique for 3D Auto-Reconstruction of City Street Elevation[J]. Acta Geodaetica et Cartographic Sinica, 2011, 40(2): 268-268.(李畅. 城市街道立面自动重建关键技术研究[J]. 测绘学报, 2011, 40(2): 268-268.)
[18] XUE Ting,SUN Mei,ZHANG Tao,et al.Complete Approach to Automatic Identification and Sub-pixel Center Location for Ellipse Feature[J].Journal of Optoelectronics·Laser,2008,19(8):1076-1078.(薛婷,孙梅,张涛,等. 类椭圆特征自动识别及亚像素提取的完整实现[J].光电子·激光,2008,19(8):1076-1078.)
[19] QIAO Y,ONG S H.Arc-based Evaluation and Detection of Ellipse[J].Pattern Recognition,2007,40(7):1990-2003.
[20] LI Liangfu,FENG Zuren,HE Kailiang.An Improved Algorithm for Ellipses Detection Based on Randomized Hough Transform[J].Pattern Recognition and Artificial Intelligence,2005,18(4):459-464.(李良福,冯祖仁,贺凯良.一种基于随机Hough变换的椭圆检测算法研究[J]. 模式识别与人工智能.2005,18(4):459-464.)
[21] PANG Yongjie,LIU Wei.Improved K-RANSAC Method for Ellipse Detection[J].Journal of Harbin Engineering University,2003,24(5):487-490.(庞永杰,刘维. 改进的K-RANSAC椭圆检测方法[J].哈尔滨工程大学学报,2003,24(5):487-490.)
[22] XIA Fei, ZHU Qianghua, JIN Guoqing. Accelerating RNA Secondary Structure Prediction Application Based on CPU+GPU Hybrid Platform[J]. Journal of National University of Defense Technology, 2013, 35(6):138-146. (夏飞,朱强华,金国庆.基于CPU+GPU混合计算平台的 RNA二级结构预测算法并行化研究[J]. 国防科技大学学报,2013,35(6):138-146.)
[23] QU Y D,CUI C S,CHEN S B,et al.A Fast Sub-pixel Edge Detection Method Using Sobel-zernike Moments Operator[J].Image and Vision Computing,2005,23(1):11 -17.
[24] FANG Liuyang, WANG Mi, LI Deren. A CPU-GPU Co-processing Orthographic Rectification Approach for Optical Satellite Imagery[J], Acta Geodaetica et Cartographic Sinica,2013, 42(5): 668-675. (方留杨,王密,李德仁.基于CPU和GPU协同处理的光学卫星遥感影像正射校正方法[J]. 测绘学报, 2013, 42(5): 668-675.)
[25] KANG Xiaochen, LIU Jiping, LIN Xiangguo. Parallel Filter of Progressive TIN Densification for Airborne LiDAR Point Clouds Using Multi-core CPU[J], Acta Geodaetica et Cartographic Sinica,2013, 42(3): 331-336. (亢晓琛,刘纪平,林祥国.基于多核CPU的机载LiDAR点云并行三角网渐进加密滤波方法[J]. 测绘学报, 2013, 42(3): 331-336.)

视频测量影像序列椭圆形人工目标点快速识别和跟踪方法

A Systemic Algorithm of Elliptical Artificial Targets Identification and Tracking for Image Sequences from Videogrammetry

PDF

可视化

被引次数

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

本文评价

[1]	闫凤池, 王振杰, 赵爽, 聂志喜, 孙振, 李伟嘉. 顾及双程声径的常梯度声线跟踪水下定位算法[J]. 测绘学报, 2022, 51(1): 31-40.
[2]	徐君, 王彩玲, 王丽. 采用PPI算法改进的一种数学形态学端元提取方法[J]. 测绘学报, 2019, 48(8): 996-1003.
[3]	刘晓刚, 孙中苗, 管斌, 范昊鹏. 航空重力测量数据向下延拓的改进Poisson积分迭代法[J]. 测绘学报, 2018, 47(9): 1188-1195.
[4]	方兴, 黄李雄, 曾文宪, 吴云. 稳健估计的一种改进迭代算法[J]. 测绘学报, 2018, 47(10): 1301-1306.
[5]	王丽娜, 李响, 江南, 杨振凯, 杨飞. 中心型时间地图的构建方法与实现[J]. 测绘学报, 2018, 47(1): 123-132.
[6]	林祥国, 张继贤. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用[J]. 测绘学报, 2017, 46(6): 724-733.
[7]	李忠美, 边少锋, 瞿勇. 多像空间前方交会的抗差总体最小二乘估计[J]. 测绘学报, 2017, 46(5): 593-604.
[8]	詹银虎, 郑勇, 张超. 测日定位中病态问题的有偏估计及精度分析[J]. 测绘学报, 2016, 45(8): 911-918.
[9]	鲁铁定. 几种粗差估值方法的比较[J]. 测绘学报, 2016, 45(6): 656-662.
[10]	王燚, 姜效典, 李德勇. 多源重力数据球冠谐模型抗差融合法[J]. 测绘学报, 2015, 44(9): 952-957.
[11]	边少锋, 刘强, 李忠美, 李厚朴. 斜轴变形椭球高斯投影方法[J]. 测绘学报, 2015, 44(10): 1071-1077.
[12]	林旭罗志才姚朝龙. 常加速度模型的简化自协方差最小二乘法[J]. 测绘学报, 2014, 43(11): 1144-1150.
[13]	隋立春,杨耘. 基于Car(p,q)模型和数学形态学理论的LiDAR点云数据滤波[J]. 测绘学报, 2012, 41(2): 219-224.
[14]	徐新禹,李建成,邹贤才,王正涛. 基于空域最小二乘法求解GOCE卫星重力场的模拟研究[J]. 测绘学报, 2011, 40(6): 697-702,.
[15]	隋立春. 基于改进的数学形态学算法的LiDAR点云数据滤波[J]. 测绘学报, 2010, 39(4): 0-440.