[1]许国梁,周航,袁良友.利用混合高斯和拓扑结构的人体“鬼影”抑制算法[J].智能系统学报,2021,16(2):294-302.[doi:10.11992/tis.201912030]
 XU Guoliang,ZHOU Hang,YUAN Liangyou.Human “ghost” suppression algorithm using Gaussian mixture model and topology[J].CAAI Transactions on Intelligent Systems,2021,16(2):294-302.[doi:10.11992/tis.201912030]
点击复制

利用混合高斯和拓扑结构的人体“鬼影”抑制算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年2期
页码:
294-302
栏目:
学术论文—机器感知与模式识别
出版日期:
2021-03-05

文章信息/Info

Title:
Human “ghost” suppression algorithm using Gaussian mixture model and topology
作者:
许国梁 周航 袁良友
北京交通大学 电子信息工程学院,北京 100044
Author(s):
XU Guoliang ZHOU Hang YUAN Liangyou
School of Electronic and Information engineering, Beijing Jiaotong University, Beijing 100044, China
关键词:
人体检测背景建模“鬼影”混合高斯模型网状拓扑均值漂移背景差分法像素邻域
Keywords:
human body detectionbackground modeling“ghost”Gaussian mixture modelmesh topologyMeanshiftbackground difference methodpixel neighborhood
分类号:
TP391
DOI:
10.11992/tis.201912030
摘要:
若在建模时存在目标,部分目标像素会进入背景模型,会在检测时产生“鬼影”。为了有效抑制“鬼影”,提出一种利用混合高斯和拓扑结构(Gaussian mixture model and topological structure,GMMT)的人体“鬼影”抑制算法。算法分为两个阶段,背景建模阶段采用双通道建模,通道一利用混合高斯模型进行预检测,接着利用拓扑结构将分散的人体目标连接获得完整的目标并取其外接矩形,然后将矩形外的像素加入背景模型,经过多帧的建模得到空背景;通道二使用多帧平均法计算背景模型。通过设置建模帧数的阈值T选择建模方式,若建模帧数小于T则使用通道一建模,否则使用双通道联合建模。目标检测阶段利用改进的背景差分法实现人体分割并进一步消除 “鬼影”。经过测试,GMMT在建模阶段存在目标的情况下可有效地抑制 “鬼影”。
Abstract:
When modeling, if a target is present, some of its pixels will appear in the background model, which produces a “ghost” during detection. To effectively suppress this “ghost,” we propose a human “ghost” suppression algorithm that uses a Gaussian mixture model and a topological structure (GMMT). The proposed algorithm contains two main stages: a background modeling stage and a target detection stage. In the background modeling stage, the GMMT algorithm adopts double-channel modeling. A Gaussian mixture model is used in channel 1 for pre-detection. Then, scattered human objects are connected by a topological structure to obtain the complete target and its bounding box. Pixels outside the bounding box are added to the background model, and the background is obtained by multi-frame modeling. The multi-frame averaging method is used in channel 2 to calculate the background model. The modeling method is selected by setting the threshold T of the modeling frames. Channel 1 modeling is used when the modeling frame number is less than T, otherwise double-channel joint modeling is used. In the target detection stage, the improved background difference method is used to realize segmentation of the human body and eliminate the “ghost” during modeling. Test results prove that the GMMT algorithm can effectively suppress a “ghost” if a target is present when modeling.

参考文献/References:

[1] 昝孟恩, 周航, 韩丹, 等. 粒子滤波目标跟踪算法综述[J]. 计算机工程与应用, 2019, 55(5):8-17
ZAN Mengen, ZHOU Hang, HAN Dan, et al. Survey of particle filter target tracking algorithms[J]. Computer engineering and applications, 2019, 55(5):8-17
[2] 李明杰, 刘小飞, 张福泉, 等. 基于粒子滤波和背景减除的多目标检测与跟踪算法[J]. 计算机应用研究, 2018, 35(8):2506-2509
LI Mingjie, LIU Xiaofei, ZHANG Fuquan, et al. Multi target detection and tracking algorithm based on particle filtering and background subtraction[J]. Application research of computers, 2018, 35(8):2506-2509
[3] 杜鹃, 吴芬芬. 高斯混合模型的运动目标检测与跟踪算法[J]. 南京理工大学学报, 2017, 41(1):41-46
DU Juan, WU Fenfen. Movement target tracking algorithm by using Gaussian mixture model[J]. Journal of Nanjing University of Science and Technology, 2017, 41(1):41-46
[4] 陈聪, 杨忠, 宋佳蓉, 等. 一种改进的卷积神经网络行人识别方法[J]. 应用科技, 2019, 46(3):51-57
CHEN Cong, YANG Zhong, SONG Jiarong, at al. An improved pedestrian detection method based on convolutional neural network[J]. Applied science and technology, 2019, 46(3):51-57
[5] 丁哲, 陆文总. 基于Vibe背景建模的运动目标检测算法[J]. 计算机系统应用, 2019, 28(4):187-191
DING Zhe, LU Wenzong. Moving target detection algorithm based on vibe background modeling[J]. Computer systems & applications, 2019, 28(4):187-191
[6] 左军辉, 贾振红, 杨杰. 基于改进背景减法的视频图像运动目标检测[J]. 计算机工程与设计, 2020, 44(5):1367-1372
ZUO Junhui, JIA Zhenhong, YANG Jie. Moving object detection in video image based on improved background subtraction[J]. Computer engineering and design, 2020, 44(5):1367-1372
[7] YANG Dan, ZHAO Chenqiu, ZHANG Xiaohong, at al. Background modeling by stability of adaptive features in complex scenes[J]. IEEE transactions on image processing, 2018, 27(3):1112-1125.
[8] MOUDGOLLYA R, MIDYA A, SUNANIYA A K, et al. Dynamic background modeling using intensity and orientation distribution of video sequence[J]. Multimedia tools and applications, 2019, 78(4):22537-22554.
[9] ZHOU Anran, XIE Weixin, PEI Jihong. Background modeling in the Fourier domain for maritime infrared target detection[J]. IEEE transactions on circuits and systems for video technology, 2020, 30(8):2634-2649.
[10] HUYNH-THE T, HUA C H, TU N A, et al. Locally statistical dual-mode background subtraction approach[J]. IEEE access, 2019, 7:9769-9782.
[11] DEWAN P, KUMAR R. Detection of object in motion using improvised background subtraction algorithm[C]//Proceedings of 2017 International Conference on Trends in Electronics and Informatics. Tirunelveli, India, 2017:651-656.
[12] 刘晓芳, 周航, 韩权, 等. 基于视觉的步态识别研究综述[J]. 小型微型计算机系统, 2018, 39(8):1685-1692
LIU Xiaofang, ZHOU Hang, HAN Quan, et al. Survey of vision-based gait recognition[J]. Journal of Chinese computer systems, 2018, 39(8):1685-1692
[13] 刘相锋, 周航. 步态识别技术及其在视频监控中的应用[J]. 电视技术, 2011, 35(1):119-121
LIU Xiangfeng, ZHOU Hang. Gait recognition technology and application in video surveillance[J]. Video engineering, 2011, 35(1):119-121
[14] 金静, 党建武, 王阳萍, 等. 一种基于鲁棒局部纹理特征的背景差分方法[J]. 计算机工程与科学, 2017, 39(8):1513-1519
JIN Jing, DANG Jianwu, WANG Yangping, et al. A background subtraction method based on robust local texture features[J]. Computer engineering & science, 2017, 39(8):1513-1519
[15] 孙挺, 齐迎春, 耿国华. 基于帧间差分和背景差分的运动目标检测算法[J]. 吉林大学学报(工学版), 2016, 46(4):1325-1329
SUN Ting, QI Yingchun, GENG Guohua. Moving object detection algorithm based on frame difference and background subtraction[J]. Journal of Jilin University (Engineering and Technology Edition), 2016, 46(4):1325-1329
[16] SHAHBAZ A, KURNIANGGORO L, WAHYONO, et al. Recent advances in the field of foreground detection:an overview[M]//KRóL D, NGUYEN N T, SHIRAI K. Advanced Topics in Intelligent Information and Database Systems. Cham:Springer, 2017:261-269.
[17] WREN C R, AZARBAYEJANI A, DARRELL T, et al. Pfinder:real-time tracking of the human body[J]. IEEE transactions on pattern analysis and machine intelligence, 1997, 19(7):780-785.
[18] YONG Hongwei, MENG Deyu, ZUO Wangmeng, et al. Robust online matrix factorization for dynamic background subtraction[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 40(7):1726-1740.
[19] STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking[C]//Proceedings of 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Fort Collins, USA, 1999:246-252.
[20] ZIVKOVIC Z. Improved adaptive Gaussian mixture model for background subtraction[C]//Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, UK, 2004:28-31.
[21] KIM K, CHALIDABHONGSE T H, HARWOOD D, et al. Real-time foreground-background segmentation using codebook model[J]. Real-time imaging, 2005, 11(3):172-185.
[22] BARNICH O, VAN DROOGENBROECK M. ViBE:A powerful random technique to estimate the background in video sequences[C]//2009 IEEE International Conference on Acoustics, Speech and Signal Processing. Taipei, China, 2009:945-948.
[23] BARNICH O, VAN DROOGENBROECK M. ViBe:a universal background subtraction algorithm for video sequences[J]. IEEE transactions on image processing, 2011, 20(6):1709-1724.
[24] 杨丹, 戴芳. 运动目标检测的ViBe算法改进[J]. 中国图象图形学报, 2018, 23(12):1813-1828
YANG Dan, DAI Fang. Improved ViBe algorithm for detection of moving objects[J]. Journal of image and graphics, 2018, 23(12):1813-1828
[25] LIU Shanyi. An improved ViBe moving object detection algorithm based on spatial-temporal gradient of image[C]//Proceedings of 2016 International Conference on Progress in Informatics and Computing. Shanghai, China, 2016:192-197.
[26] MIN Weidong, FAN Mengdan, GUO Xiaoguang, et al. A new approach to track multiple vehicles with the combination of robust detection and two classifiers[J]. IEEE transactions on intelligent transportation systems, 2018, 19(1):174-186.
[27] ST-CHARLES P L, BILODEAU G A, BERGEVIN R. SuBSENSE:a universal change detection method with local adaptive sensitivity[J]. IEEE transactions on image processing, 2015, 24(1):359-373.
[28] ST-CHARLES P L, BILODEAU G A, BERGEVIN R. Universal background subtraction using word consensus models[J]. IEEE transactions on image processing, 2016, 25(10):4768-4781.
[29] 朱海滨. 网络拓扑发现技术探析[J]. 网络安全技术与应用, 2017(3):26-27
ZHU Haibin. Analysis of network topology discovery technology[J]. Network security technology & application, 2017(3):26-27

相似文献/References:

[1]柳培忠,阮晓虎,田震,等.一种基于多特征融合的视频目标跟踪方法[J].智能系统学报,2014,9(03):319.[doi:10.3969/j.issn.1673-4785.201309085]
 LIU Peizhong,RUAN Xiaohu,TIAN Zhen,et al.A video tracking method based on object multi-feature fusion[J].CAAI Transactions on Intelligent Systems,2014,9(2):319.[doi:10.3969/j.issn.1673-4785.201309085]
[2]孙自飞,钱堃,马旭东,等.多传感器的移动机器人可定位性估计与自定位[J].智能系统学报,2017,12(04):443.[doi:10.11992/tis.201607007]
 SUN Zifei,QIAN Kun,MA Xudong,et al.Self-localization of mobile robot in dynamic environments based onlocalizability estimation with multi-sensor observation[J].CAAI Transactions on Intelligent Systems,2017,12(2):443.[doi:10.11992/tis.201607007]

备注/Memo

备注/Memo:
收稿日期:2019-12-24。
基金项目:国家自然科学基金面上项目(61872027,61573057);北京交通大学“北京交通大学?中建电子智能交通联合实验基地建设”项目
作者简介:许国梁,硕士研究生,主要研究方向为智能图像处理;周航,副教授,主要研究方向为智能图像处理、目标检测和跟踪、步态识别、智能交通系统的信息与控制技术。发表学术论文40余篇;袁良友,硕士研究生,主要研究方向为智能图像处理。
通讯作者:周航.E-mail:hangzhou@bjtu.edu.cn
更新日期/Last Update: 2021-04-25