[1]顾 扬,曾凡意,应昊然,等.一种提取抖动视频中前景目标的新方法[J].计算机技术与发展,2021,31(01):67-72.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 012]
　GU Yang,ZENG Fan-yi,YING Hao-ran,et al.A New Approach for Extracting Foreground Targets in Jitter Video[J].,2021,31(01):67-72.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 012]
点击复制

一种提取抖动视频中前景目标的新方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年01期
页码:
67-72
栏目:
图形与图像
出版日期:
2021-01-10

文章信息/Info

Title:
A New Approach for Extracting Foreground Targets in Jitter Video
文章编号:
1673-629X(2021)01-0067-06
作者:
顾 扬1; 曾凡意1; 应昊然2; 王丽平1
1. 南京航空航天大学 理学院,江苏 南京 211106; 2. 南京航空航天大学 自动化学院,江苏 南京 211106
Author(s):
GU Yang1; ZENG Fan-yi1; YING Hao-ran2; WANG Li-ping1
1. School of Science,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China;
2. School of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
在线混合高斯模型; 仿射变换; 小波变换; 去抖动; 自适应模型
Keywords:
online mixed Gaussian model; affine transform; wavelet transform; jitter removing; adaptive model
分类号:
TP39
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 01. 012
摘要:
提取视频中的前景目标信息是视频处理领域非常重要的问题,考虑到现实生活中会出现监控摄像头不可避免地会出现晃动或偏移情况,造成监控视频短暂抖动,此时背景图像灰度和纹理信息都会受到较大的影响,从而给后期进一步分析前景信息带来了巨大的困难。 为了兼顾纹理特征提取和噪声抑制两方面的要求,针对抖动视频的前景提取问题,提出了一种有效的融合小波变换和在线混合高斯模型的方案。 首先运用仿射变换在线逐帧校准,接着利用小波变换对图像去噪,并建立自适应模型迭代上述过程,最后利用在线混合高斯模型提取前景。 实验结果表明,与同类方法相比,该算法无论针对单目标还是多目标视频均可以有效去除抖动,得到较好的前景目标提取效果,具有较高的准确性和鲁棒性。
Abstract:
Extracting foreground target information in video is an important issue in the field of video processing. In consideration of the fact that surveillance cameras inevitably shake or shift in real life,which causes brief jitter of surveillance video,the background image grayscale and texture information will be greatly affected, which brings great difficulties for further on. Aiming at the foreground extraction problem of jitter video, in order to meet the requirements of texture feature extraction and noise suppression, an effective scheme of fusing wavelet? transform and online mixed Gaussian model is proposed. Firstly,the affine transformation is used to calibrate online frame-by-frame,then the image is denoised by wavelet transform,and an adaptive model to iterate the above process. Finally,the online mixed Gaussian model is used to extract the foreground. The experiment shows that compared with the similar methods, the proposed algorithm can effectively remove the jitter for both single-target and multi-target videos and obtain better foreground target extraction results with high accuracy and strong robustness.

相似文献/References:

[1]张群会 狄效儒.纹理映射与光照处理关系研究及应用[J].计算机技术与发展,2010,(01):229.
　ZHANG Qun-hui,DI Xiao-ru.Research of Relation Between Texture Mapping and Illumination Model and Its Application[J].,2010,(01):229.
[2]侯崇明,袁广林,王健.基于粒子滤波和仿射变换的鱼目标跟踪算法[J].计算机技术与发展,2014,24(04):135.
　HOU Chong-ming,YUAN Guang-lin,WANG Jian.A Fish Tracking Algorithm Based on Particle Filtering and Affine Transform[J].,2014,24(01):135.
[3]王凤娇,陈光化,周文. 基于SIFT的POCS图像超分辨率重建[J].计算机技术与发展,2014,24(11):39.
　WANG Feng-jiao,CHEN Guang-hua,ZHOU Wen. Multi-frame Image Super-resolution Reconstruction Based on SIFT[J].,2014,24(01):39.
[4]管焱然[],管有庆[]. 基于OpenCV的仿射变换研究与应用[J].计算机技术与发展,2016,26(12):58.
　GUAN Yan-ran[],GUAN You-qing[]. Research and Application of Affine Transformation Based on OpenCV[J].,2016,26(01):58.
[5]张志佳[],贾梦思[],张丹[],等. 基于AT-SBTM的交通标志检测[J].计算机技术与发展,2017,27(08):195.
　ZHANG Zhi-jia[],JIA Meng-si[],ZHANG Dan[],et al. Traffic Sign Detection with AT-SBTM[J].,2017,27(01):195.
[6]陈 轩,宋根龙,田 彤,等.基于图像边缘特征检测的单目立体视觉算法[J].计算机技术与发展,2021,31(10):76.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 013]
　CHEN Xuan,SONG Gen-long,TIAN Tong,et al.Monocular Stereo Vision Algorithm Based on Image Edge Feature Detection[J].,2021,31(01):76.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 013]

更新日期/Last Update: 2020-01-10