Moving object detection by optical flow method based on adaptive weight coefficient

LIU Hong-bin; CHANG Fa-liang

doi:10.3788/OPE.20162402.0460

您当前的位置：

首页 >

文章列表页 >

Moving object detection by optical flow method based on adaptive weight coefficient

更新时间：2020-08-13

- Moving object detection by optical flow method based on adaptive weight coefficient
- Optics and Precision Engineering Vol. 24, Issue 2, Pages: 460-468(2016)
- 作者机构：
  
  山东大学控制科学与工程学院, 山东济南 250061
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20162402.0460
  CLC： TP391.4
- Received：11 September 2015，
  
  Revised：30 November 2015，
  
  Published：25 February 2016
- 稿件说明：
移动端阅览
刘洪彬, 常发亮,. 权重系数自适应光流法运动目标检测[J]. 光学精密工程, 2016,24(2): 460-468

LIU Hong-bin, CHANG Fa-liang,. Moving object detection by optical flow method based on adaptive weight coefficient[J]. Editorial Office of Optics and Precision Engineering, 2016,24(2): 460-468
刘洪彬, 常发亮,. 权重系数自适应光流法运动目标检测[J]. 光学精密工程, 2016,24(2): 460-468 DOI： 10.3788/OPE.20162402.0460.

LIU Hong-bin, CHANG Fa-liang,. Moving object detection by optical flow method based on adaptive weight coefficient[J]. Editorial Office of Optics and Precision Engineering, 2016,24(2): 460-468 DOI： 10.3788/OPE.20162402.0460.

摘要

为了实现Horn-Schunck光流法权重系数的自适应设定与更新

研究了权重系数对Horn-Schunck光流法的影响规律

提出一种融合模糊C均值(FCM)聚类的权重系数自适应Horn-Schunck光流法。首先

统计不同权重系数下运动目标检测的光流总值变化曲线。然后

以光流总值的最优化为依据

结合两层模糊C均值(FCM)聚类寻找最优权重和基于固定迭代次数Horn-Schunck光流法的收敛点

从而自适应地获取最优权重系数

并将收敛阈值的人工设定转化为光流值的自动寻优。最后

通过标准视频序列进行测试以验证算法的有效性。实验结果表明:相比于其他权重系数值

最优权重估计的光流图像不但运动目标明显而且噪声较少。对运动目标检测的运行时间为0.1060 s

有用比为0.5969

幅度误差为0.8011

满足光流法运动目标检测的最优或次优性能。

Abstract

To set and update weight coefficients of Horn-Schunck optical flow method adaptively

the influencing rules of weight coefficients on Horn-Schunck optical flow method is researched. An optical flow method based on adaptive weight coefficients and Fuzzy C-Means(FCM) clustering is proposed. Firstly

it computes varying curves of optical flow total values with different weight coefficients. Then

by combining two levels of FCM clusterings

it finds the optimal weight and the convergence point of Horn-Schunck optical flow method based on fixed number of iterations. By which the optimal weight coefficient is obtained adaptively. Finally

the feasibility of the method is verified based on standard video sequence. The result shows that the optical flow images estimated by the optimal weight obtains evident movement targets with little noise as compared with other weight coefficients and its running time is 0.1060 s

useful ratio is 0.5956

and End-point Error is 0.8011. It achieves the best or the next-best performance.

关键词

Keywords

references

LIU C S, CHANG F L, CHEN Z X. Rapid multiclass traffic sign detection in high-resolution images[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(6):2394-2403.

武治国,李桂菊. 动态目标识别中的实时复杂巡航场景运动检测[J]. 液晶与显示,2014,5(5):844-849. WU ZH G, LI G J. Real-time complex cruise scene detection technology in target recognition[J]. Chinese Journal of Liquid Crystals and Displays, 2014,5(5):844-849.(in Chinese)

刘翔, 杨鑫, 王蕾. 改进的基于码本模型目标检测算法[J]. 液晶与显示,2014,6(6):997-1002. LIU X, YANG X, WANG L. Object detection algorithm based on improved codebook model[J]. Chinese Journal of Liquid Crystals and Displays, 2014, 6(6):997-1002.(in Chinese)

LIU Y X, CHANG F L. Detecting algorithm for moving objects based on bayesian judging criterion[J]. Journal of Computers, 2011, 6(5):849-856.

陈星明,廖娟,李勃,等. 动态背景下基于改进视觉背景提取的前景检测[J]. 光学精密工程,2014,22(9):2543-2552. CHEN M X, LIAO J, LI B, et al.. Foreground detection based on modified ViBe in dynamic background[J]. Opt. Precision Eng., 2014, 22(9):2543-2552.(in Chinese)

MEINHARDTLLOPIS E, KONDERMANN D. Horn-Schunck optical flow with a multi-scale strategy[J]. Image Processing on Line, 2013, 3(2013):151-172.

贾松敏, 王丽佳, 王爽,等. 改进的步态光流图与视角相结合的身份识别[J]. 光学精密工程,2012, 20(11):2500-2506. JIA S M, WANG L J, WANG SH, et al.. Personal identification combining modified gait flow image and view[J]. Opt. Precision Eng., 2012, 20(11):2500-2506.(in Chinese)

SUN D, ROTH S, BLACK M J. A quantitative analysis of current practices in optical flow estimation and the principles behind them[J]. International Journal of Computer Vision, 2014, 106(2):115-137.

谢剑斌,王晖,程江华,等. 基于HS约束与轮廓条件的光流场计算[J]. 系统工程与电子技术,2009,31(4):761-763. XIE J B, WANG H, CHENG J H, et al.. Optical flow computation method based on HS constraint and outline condition[J]. Systems Engineering and Electronics, 2009, 31(4):761-763.(in Chinese)

BAARIR Z E, CHARIF F. Fast modified Horn & Schunck method for the estimation of optical flow fields[C]. IEEE Workshop on Signal Processing Systems, AUB Beirut, Lebanon:SiPS, 2011:283-288.

ISHⅡ B, TANIGUCHI T, YAMAMOTO K. High frame rate optical flow system[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2012, 22(1):105-112.

QI Y, AN G. Infrared moving targets detection based on optical flow estimation[C]. IEEE Conference on Computer Science and Network Technology, Harbin, P.R. China:ICCSNT, 2011:2452-2455.

PATEL M P, PARMAR S K. Moving object detection with moving background using optic flow[C]. IEEE Conference on Recent Advances and Innovations in Engineering, Jaipur, India:ICRAIE, 2014:1-6.

屠大维,江济良. 改进的光流运动图像分析方法及其应用[J]. 光学精密工程,2011,19(5):1159-1164. TU D W, JIANG J L. Improved algorithm for motion image analysis based on optical flow and its application[J]. Opt. Precision Eng., 2011, 19(5):1159-1164.(in Chinese)

王鲁平, 张路平, 韩建涛. 采用灰度加权核函数的动态背景运动目标检测算法[J]. 红外与激光工程,2013,42(12):3453-3457. WANG L P, ZHANG L P, HAN J T. Detecting algorithm of moving target in dynamic background based on gray-weighted kernel function[J]. Infrared and Laser Engineering, 2013, 42(12):3453-3457.(in Chinese)

YU X, CHEN X, ZHANG H. Accurate motion detection in dynamic scenes based on ego-motion estimation and optical flow segmentation combined method[C]. IEEE Symposium on Photonics and Optoelectronics, Wuhan, P.R. China:SOPO, 2011:1-4.

BRUHN A, WEICHERT J, SCHNORR C. Lucas & Kanade meets Horn & Schunck:Combining local and global optic flow methods[J]. IEEE International Journal of Computer Vision, 2005, 61(3):211-231.

ZHANG K, ZHANG L, YANG M H. Fast compressive tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10):2002-2015.

MYKHAYLO A, STEFAN R, BERNT S. Monocular 3D pose estimation and tracking by detection[J]. IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, USA:CVPR, 2010:623-630.

TANG S, ANDRILUKA M, MILAN A, et al.. Learning people detectors for tracking in crowded scenes[C]. IEEE International Conference on Computer Vision, Sydney, Australia:ICCV, 2013:1049-1056.

TARAGHI B, JALALI V R. Fuzzy c-mean(FCM) clustering and Genetic Algorithm capability in predicting saturated hydraulic conductivity[C]. International Congress on Technology, Communication and Knowledge, Mashhad, Iran:ICTCK, 2014:1-6.

赵东,赵宏伟,于繁华. 动态多目标优化的运动物体图像分割[J]. 光学精密工程,2015,23(7):2109-2116. ZHAO D, ZHAO H W, YU F H. Moving object image segmentation by dynamic multi-objective optimization[J]. Opt. Precision Eng., 2015, 23(7):2109-2116.(in Chinese)

李庆辉,李艾华,苏延召,等. 结合FCM聚类与SVM的火焰检测算法[J]. 红外与激光工程, 2014,43(5):1660-1666. LI Q H, LI A H, SU Y ZH, et al.. Fire detection algorithm using FCM clustering and SVM[J]. Infrared and Laser Engineering, 2014, 43(5):1660-1666.(in Chinese)

SIMON B, DANIEL S, LEWIS J P. A database and evaluation methodology for optical flow[J]. International Journal of Computer Vision, 2011, 92(1):1-31.

SUN D Q, ROTH S, LEWIS J P, et al.. Learning optical flow[J]. Lecture Notes in Computer Science, 2008, 5304:83-97.

Views

504

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fuzzy C-means clustering algorithm based on adaptive neighbors information

An improved ViBe algorithm and its application in traffic video processing

Moving object detection in combination of CenSurE and spatial-temporal information

Moving object detection by combining SIFT and differential multiplication

Moving object detection based on variant block difference in complex scenes

Related Author

GAO Yunlong

LI Jianpeng

ZHENG Xingshen

SHAO Guifang

ZHU Qingyuan

CAO Chao

Wei-dong MIN

Xiao-guang GUO

Related Institution

Tung Sah Institute of Micro-Nano Science and Technology， Xiamen University

Department of Automation， Xiamen University

Third Institute of Oceanography， Ministry of Natural Resources

School of Information Engineering, Nanchang University

School of Computer Science and Software Engineering, Tianjin Polytechnic University

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