稳定运动物体视频的特征方法

邱家涛; 李玉山; 初秀琴; 刘洋; 倪乐真

doi:10.3788/OPE.20122010.2300

您当前的位置：

首页 >

文章列表页 >

稳定运动物体视频的特征方法

信息科学 | 更新时间：2020-08-12

- 稳定运动物体视频的特征方法
- Feature-based approach for stabilizing videos with moving objects
- 光学精密工程 2012年20卷第10期页码：2300-2307
- 作者机构：
  
  西安电子科技大学电路CAD研究所,陕西西安,710071
- 作者简介：
- 基金信息：
  
  国家973重点基础研究发展计划资助项目(No. 2009CB724005)();中央高校基本科研业务费专项基金资助项目(No. k50510020029)()
- DOI：10.3788/OPE.20122010.2300
  中图分类号： TN941.1
- 收稿日期：2012-05-15，
  
  修回日期：2012-07-06，
  
  纸质出版日期：2012-10-10
- 稿件说明：
移动端阅览
邱家涛, 李玉山, 初秀琴, 刘洋, 倪乐真. 稳定运动物体视频的特征方法[J]. 光学精密工程, 2012,20(10): 2300-2307

QIU Jia-tao, LI Yu-shan, CHU Xiu-qin, LIU Yang, NI Le-zhen. Feature-based approach for stabilizing videos with moving objects[J]. Editorial Office of Optics and Precision Engineering, 2012,20(10): 2300-2307
邱家涛, 李玉山, 初秀琴, 刘洋, 倪乐真. 稳定运动物体视频的特征方法[J]. 光学精密工程, 2012,20(10): 2300-2307 DOI： 10.3788/OPE.20122010.2300.

QIU Jia-tao, LI Yu-shan, CHU Xiu-qin, LIU Yang, NI Le-zhen. Feature-based approach for stabilizing videos with moving objects[J]. Editorial Office of Optics and Precision Engineering, 2012,20(10): 2300-2307 DOI： 10.3788/OPE.20122010.2300.

摘要

将背景特征块配对和直方图聚类运动矢量滤波相结合

提出了一种稳定运动物体视频的方法。用得到的全局运动参量补偿摄像机的帧间运动

运用帧差法分割出前景块和背景块

把参考帧背景上的特征块与当前帧上的特征块配对估计下一轮的帧间运动。用一块对多块的匹配策略

把参考块和以参考块为中心的搜索窗内的当前帧上的最佳匹配块配对

建立稀疏运动矢量场。然后

运用直方图聚类方法滤除矢量场中未分离出的前景块矢量和误匹配矢量。最后

用多个包含运动物体的实际视频序列对提出方法进行测试

并与其它先进稳像算法和技术仿真比较。结果表明:提出方法的全局平均帧间变换保真度可达31.05 dB

接近或优于上述先进算法和技术。提出的方法对包含运动物体的视频具有较强的鲁棒性

可以去除帧间高频抖动并有效改善视频质量。

Abstract

By combining a background feature block matching and a histogram clustering method

a new approach for stabilizing videos with moving objects was proposed. The estimated global motion parameters were used to compensate the inter-frame camera motion

and a frame differencing method was adopted to segment the foreground and background blocks

then the feature blocks on the background of reference frame were matched with that on the current frame to estimate the global motion in the next run. By using a one-block-to-multiple-block matching strategy

the reference feature block was matched with the feature blocks of the current frame in the search window centered on the reference block

thus a sparse motion vector field was built. Then

the un-removed foreground vectors and erroneous vectors in this vector field were filtered out using a histogram clustering method. The proposed approach has been tested by using many real videos with moving objects and compared with other state-of-the-art video stabilization algorithms and techniques. The results indicate that the proposed approach can achieve an inter-frame transformation fidelity value by 31.05 dB

which is as high as those of state-of-the-art algorithms and techniques. Moreover

it has a higher robustness to moving objects and can remove inter-frame high frequency jitters and improve video quality.

关键词

Keywords

references

赵跃进,连铜淑. 会聚光路中的三轴稳像棱镜组[J]. 光学学报,1992,12(8):749-754. ZHAO Y J, LIAN T SH. Three-axis image stabilizing reflecting prism assembly in convergent light [J]. Acta Optica Sinica, 1992, 12(8):749-754. (in Chinese)[2] 赵红颖, 金宏, 熊经武. 电子稳像技术概述[J]. 光学精密工程, 2001, 9(4):353-359. ZHAO H Y, JIN H, XIONG J W. A brief description of electronic image stabilization techniques [J]. Opt. Precision Eng., 2001, 9(4):353-359. (in Chinese)[3] LEE J, LEE S, PAIK J. Digital image stabilization based on statistical selection of feasible regions [J]. IEEE Transactions on Consumer Electronics,2009,55(4):1748-1755.[4] BATTIATO S, BRUNA A R, PUGLISI G. A robust block based image/video registration approach for mobile imaging devices [J]. IEEE Transactions on Multimedia,2010,12(7):622-635.[5] 邱家涛, 李玉山, 王彩玲,等. 一种基于检测块动态选择的稳像算法[J]. 光子学报,2010,39(s1):23-28. QIU J T, LI Y S, WAN C L, et al.. A dynamic detection blocks selection-based image stabilization algorithm [J]. Acta Photonica Sinica,2010,39(s1):23-28.(in Chinese)[6] 孙辉. 快速灰度投影算法及其在电子稳像中的应用[J]. 光学精密工程,2007, 15(3):412-416. SUN H. Fast gray projection algorithm and its application to electronic image stabilization [J]. Opt. Precision Eng., 2007, 15(3):412-416. (in Chinese)[7] QI B, GHAZAL M, AMER A. Robust global motion estimation oriented to video object segmentation [J]. IEEE Transactions on Image Processing, 2008,17(6):958-967.[8] WANG C, KIM J H, BYUN K Y, et al.. Robust digital image stabilization using the Kalman filter [J]. IEEE Transactions on Consumer Electronics,2009, 55(1):6-14.[9] HUANG K Y, TSAI Y M, TSAI C C, et al.. Video stabilization for vehicular applications using SURF-Like descriptor and KD-tree. Proceedings of IEEE International Conference on Image Processing, 2010:3517-3520.[10] BATTIATO S, GALLO G, PUGLISI G, et al.. Sift features tracking for video stabilization. Proceedings of the 14th International Conference on Image Analysis and Processing, 2007:825-830. [11] FISCHLER M A, BOLLES R C. Random sample consensus: A paradigm model fitting with applications to image analysis and automated cartography [J]. Commun. ACM,1981, 24(6):381-395.[12] CHEN H, LIANG C K,PENG Y C, et al.. Intergration of digital stabilizer with video codec for digital video cameras [J]. IEEE Transactions on Circuits Syst. Video Technol., 2007, 17(7):801-813.[13] HARRIS C, STEPHENS M. A combined corner and edge detector. In Alvey Vision Conference, 1988:147-151.[14] 姜永林,屈桢深,王常虹. 基于纹理及统计特征的视频背景提取[J]. 光学精密工程,2008, 16(1):172-177. JIANG Y L, QU ZH SH, WANG CH H. Video background extraction based on texture and statistical features [J]. Opt. Precision Eng., 2008, 16(1):172-177. (in Chinese)[15] NG H F. Automatic thresholding for defect detection [J]. Pattern Recognition Letters, 2006, 27(14):1644-1649.

浏览量

312

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进运动矢量估计法的视频稳像

快速灰度投影算法及其在电子稳像中的应用

场景切换感知的地基成像系统电子稳像技术

基于视觉系统分层的小目标运动检测

耦合扰动下船载成像系统的复合稳像