[1]李晓峰,邢金明.基于条件随机场的视频运动目标可靠性检测方法[J].计算机技术与发展,2020,30(07):60-65.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 014]
　LI Xiao-feng,XING Jin-ming.Reliability Detection Method of Video Moving Target Based on Conditional Random Field[J].,2020,30(07):60-65.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 014]
点击复制

基于条件随机场的视频运动目标可靠性检测方法()
分享到：

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

卷:
30
期数:
2020年07期
页码:
60-65
栏目:
智能、算法、系统工程
出版日期:
2020-07-10

文章信息/Info

Title:
Reliability Detection Method of Video Moving Target Based on Conditional Random Field
文章编号:
1673-629X(2020)07-0060-06
作者:
李晓峰1 ; 邢金明2
1. 黑龙江外国语学院 信息工程系,黑龙江 哈尔滨 150025; 2. 东北师范大学,吉林 长春 130024
Author(s):
LI Xiao-feng1 ; XING Jin-ming2
1. Department of Information Engineering,Heilongjiang International University,Harbin 150025,China; 2. Northeast Normal University,Changchun 130024,China
关键词:
条件随机场模型; 视频; 运动目标; 可靠性; 检测
Keywords:
conditional random field model; video; moving target; reliability; detection
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 07. 014
摘要:
针对当前视频运动目标检测方法受到环境随机场因素的影响,存在检测性能不佳的问题,主要由视频运动特征分布散乱,跟踪效果差所导致,提出基于条件随机场模型的视频运动目标可靠性检测方法。 首先,采用模板匹配方法构建视频运动目标的像素特征点块匹配结构模型,获取目标统计特征量,划分统计特征量中的关键帧频带;其次,根据关键帧频带划分结果,构建帧内编码函数,跟踪目标运动轨迹;再次,依据跟踪结果构建目标图像的条件随机场分布模型;最后,依据运动目标的边缘轮廓特征分布,对目标进行粗重构,并增加图像特征,实现目标的高分辨视觉重建,以此完成视频运动目标可靠性检测。 实验结果表明,采用该方法进行视频运动目标检测的检测准确率、跟踪精度均较高,且检测时间较少,检测分辨率较高,具有一定的可靠性。
Abstract:
Aiming at the problem that the current video moving target detection methods are affected by the environmental random field factors and have poor detection performance, which is mainly caused by the scattered distribution of video moving features and poor tracking effect,we propose a video moving target reliability detection method based on conditional random field model. Firstly,the pixel feature block matching structure model of video moving target is constructed by the template matching method to obtain the statistical feature of the target and divide the key frame frequency band of the statistical feature. Secondly,according to the result of the key frame frequency band division,the intra-frame coding function is constructed to track the target motion track. Thirdly,according to the tracking knot,the conditional random field distribution model of the target image is constructed. Finally,according to the edge contour feature distribution of the moving target,the target is roughly reconstructed,and the image features are added to realize the high-resolution visual reconstruction of the target, so as to complete the reliability detection of the moving target in video. The experiment shows that the proposed method has higher detection accuracy and tracking accuracy,less detection time,higher detection resolution and certain reliability.

相似文献/References:

[1]熊爱平[] 周经野 刘东华[].AVS—M解码在Symbian平台上的实现[J].计算机技术与发展,2008,(02):133.
　XIONG Ai-ping,ZHOU Jing-ye,LIU Dong-hua.Implementation of AVS- M Decoder on Symbian Platform[J].,2008,(07):133.
[2]伊力哈木·亚尔买买提 哈力旦·A.基于Matlab GUI的维吾尔文字符识别系统的设计[J].计算机技术与发展,2010,(11):92.
　Yilihamu Yaermaimaiti,Halidan A.Designs of Uygur Character Identify System Based on Matlab GUI[J].,2010,(07):92.
[3]彭小玲 傅秀芬 吕占德 曾传军.基于IMS的交互式语音及视频应答系统的研究[J].计算机技术与发展,2011,(02):207.
　PENG Xiao-ling,FU Xiu-fen,LU Zhan-de,et al.Research of an Interactive Voice-Video Response System Based on IMS[J].,2011,(07):207.
[4]钱小红 李小艳.基于DirectShow实现局域网实时视频传输[J].计算机技术与发展,2011,(10):218.
　QIAN Xiao-hong,LI Xiao-yan.Realization of LAN Real-Time Video Transmission Based on DirectShow[J].,2011,(07):218.
[5]张良 周长胜.基于概念本体的视频内容分析框架[J].计算机技术与发展,2011,(12):116.
　ZHANG Liang,ZHOU Chang-sheng.Video Content Analysis Framework Based on Concept Ontology[J].,2011,(07):116.
[6]黄景星,吴伟隆,龙楚君,等.基于OpenCV的视频运动目标检测及其应用研究[J].计算机技术与发展,2014,24(03):15.
　HUANG Jing-xing,WU Wei-long,Long Chu-jun,et al.Study of Moving Object Detection in Video and Its Application Based on OpenCV[J].,2014,24(07):15.
[7]宋燕燕,秦军.基于FFMPEG 的视频水印系统设计[J].计算机技术与发展,2018,28(04):144.[doi:10.3969/ j. issn.1673-629X.2018.04.030]
　SONG Yan-yan,QIN Jun.Design of Video Watermarking System Based on FFMPEG[J].,2018,28(07):144.[doi:10.3969/ j. issn.1673-629X.2018.04.030]
[8]俞文静,张明军,王影.面向视频超分辨率重建的混合粒子群优化算法[J].计算机技术与发展,2018,28(11):75.[doi:10.3969/ j. issn.1673-629X.2018.11.017]
　YU Wen-jing,ZHANG Ming-jun,WANG Ying.A Hybrid Particle Swarm Optimization Algorithm for Image/ Video Super-resolution Reconstructio[J].,2018,28(07):75.[doi:10.3969/ j. issn.1673-629X.2018.11.017]
[9]库瓦特拜克·马木提.基于机器学习方法的哈萨克语词干切分研究[J].计算机技术与发展,2020,30(04):182.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 035]
　Kuwatebaike·MAMUTI.Research on Kazakh Stemming Based on Machine Learning[J].,2020,30(07):182.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 035]
[10]张石清,张星楠,赵小明.基于音视频信息的深度多模态抑郁症识别综述[J].计算机技术与发展,2023,33(07):1.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 001]
　ZHANG Shi-qing,ZHANG Xing-nan,ZHAO Xiao-ming.A Survey of Deep Multimodal Depression Recognition Based on Audio-visual Cues[J].,2023,33(07):1.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 001]

更新日期/Last Update: 2020-07-10