吉林大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (6): 1976-1985.doi: 10.13229/j.cnki.jdxbgxb201706041

• 论文 • 上一篇    下一篇

基于改进粒子滤波的煤矿视频监控模糊目标检测

杨超宇1, 2, 李策1, 梁胤程1, 杨峰1   

  1. 1.中国矿业大学(北京) 机电与信息工程学院,北京 100083;
    2.安徽理工大学 经济与管理学院,安徽 淮南 232001
  • 收稿日期:2016-10-13 出版日期:2017-11-20 发布日期:2017-11-20
  • 作者简介:杨超宇(1981-),男,副教授,博士.研究方向:计算机视觉,图像分析,多媒体物联网.E-mail:yangchy@aust.edu.cn
  • 基金资助:
    国家自然科学基金项目(51404007,61601466); 安徽省重大教学改革研究项目(2015zdjy074)

Blurred object detection based on improved particle filter in coal mine underground surveilance

YANG Chao-yu1, 2, LI Ce1, LIANG Yin-cheng1, YANG Feng1   

  1. 1.School of Mechanical Electronic and Information Engineering, China University of Mining and Technology(Beijing), Beijing 100083, China;
    2.School of Economics and Management, Anhui University of Science and Technology, Huainan 232001, China
  • Received:2016-10-13 Online:2017-11-20 Published:2017-11-20

RICH HTML

0   

PDF (PC)

251

摘要： 针对煤矿井下智能视频监控采集到的视频图像质量较差、干扰多、噪点多、目标检测不准确等问题,提出了一种基于改进粒子滤波的模糊目标检测方法。在标准粒子滤波理论框架下,以视频多图像帧差为基础构建非线性、非高斯多系统状态空间融合模型;在图像帧差得到的关键点区域范围内进行粒子抽样及概率密度的传播;利用加权后验样本粒子表示多系统状态空间融合模型的后验概率密度;采用样本均值方法融合估计系统后验状态;最后对系统状态空间模型进行输出,得到目标检测结果。使用三交河煤矿井下视频监控数据进行试验验证,分别釆用改进的粒子滤波、标准粒子滤波、无损卡尔曼滤波以及扩展卡尔曼滤波等方法进行对比。试验结果表明:针对煤矿井下视频模糊目标检测问题,改进的多状态空间模型及关键区域采样粒子滤波算法具有良好的目标检测效果。

关键词: 信息处理技术, 目标检测, 粒子滤波, 多状态空间, 关键区域采样

Abstract: Regarding that the videos collected by intelligent monitoring system in coal mine underground are blur, a novel algorithm for unclear video object detection based on improved particle filter is proposed. In the framework of standard particle filter, a nonlinear, non-Gaussian and multi system state space fusion model is constructed based on frame difference. First, particle sampling and probability density propagation are realized in the region of the key points obtained in the frame difference image. Then, the weighted posterior sample particles are used to represent the posterior probability density of the multi system state space fusion model. The mean of the samples is used to estimate and fuse the posteriori state of the system. Finally, the system state space model is output to fulfill the object detection. Experiments are carried out using the video data of the Sanjiaohe coal mine underground monitoring system. The performance of the proposed model is evaluated by comparison with extended Kalman filter, unscented Kalman filter and particle filter. The improved accuracy and effectiveness of the proposed method are demonstrated.

Key words: information processing technology, object detection, particle filter, multi-state space, critical region sampling

中图分类号: 

  • TD76
[1] 孙继平. 煤矿安全生产监控与通信技术[J]. 煤炭学报,2010,35(11):1925-1929.
Sun Ji-ping. Technologies of monitoring and communication in the coal mine[J]. Journal of China Coal Society,2010,35(11):1925-1929.
[2] 孙继平,陈伟,王福增,等. 矿井监控图像中空列车的识别[J]. 中国矿业大学学报,2007,36(5):597-602.
Sun Ji-ping, Chen Wei, Wang Fu-zeng, et al. Recognizing empty trainsin coalmine surveillance images[J]. Journal of China University of Mining & Technology,2007,36(5):597-602.
[3] 厉丹. 视频目标检测与跟踪算法及其在煤矿中应用的研究[D]. 徐州:中国矿业大学信息与控制工程学院,2011.
Li Dan. Research on object detection and tracking algorithm and its application in coal mine[D]. Xuzhou: School of Information and Control Engineering,China University of Mining and Technology,2011.
[4] 张谢华,张申,方帅,等. 煤矿智能视频监控中雾尘图像的清晰化研究[J].煤炭学报,2014,39(1):198-204.
Zhang Xie-hua, Zhang Shen, Fang Shuai, et al. Clearing research on fog and dust images in coalmine intelligent video surveillance[J]. Journal of China Coal Society,2014,39(1):198-204.
[5] 杜明本,陈立潮,潘理虎. 基于暗原色理论和自适应双边滤波的煤矿尘雾图像增强算法[J]. 计算机应用,2015,35(5):1435-1438.
Du Ming-ben, Chen Li-chao, Pan Li-hu. Enhancement algorithm for fog and dust images in coal mine based on dark channel prior theory and bilateral adaptive filter[J]. Journal of Computer Applications,2015,35(5):1435-1438.
[6] 王法胜,鲁明羽,赵清杰,等. 粒子滤波算法[J]. 计算机学报,2014,37(8):1679-1694.
Wang Fa-sheng, Lu Ming-yu, Zhao Qing-jie, et al. Particle filter algorithm[J]. Chinese Journal of Computers,2014,37(8):1679-1694.
[7] Kitagawa G. Monte Carlo filter and smoother for non-Gaussian non-linear state space models[J]. Journal of Computational and Graphical Statistics,1996,5(1):1-25.
[8] Gordon N, Salmond D. Novel approach to non-linear and non-Gaussian Bayesian state estimation[J]. Proc of Institute Electric Engineering,1993,140(2):107-113.
[9] 吴刚. 基于粒子滤波与增量学习的车辆跟踪方法硏究[D]. 南京:南京理工大学计算机学院,2014.
Wu Gang. Research of vehicle tracking methods based on particle filter and incremental learning[D]. Nanjing: College of Computer,Nanjing University of Science and Technology, 2014.
[10] Carpenter J, Clifford P. Improved particle filter for nonlinear problems[J]. IEEE Proc of Radar, Sonar and Navigation,1999,146(1):2-7.
[11] 毛晓楠. 基于粒子滤波的图像分割算法研究[D]. 上海:上海交通大学模式识别与图像处理研究所,2008.
Mao Xiao-nan. Research on image segmentation algorithm based on particle filter[D]. Shanghai: Institute of Image Processing and Pattern Recognition,Shanghai Jiao Tong University,2008.
[12] 李昱辰.基于粒子滤波的视频目标跟踪方法研究[D]. 兰州:兰州理工大学电气工程与信息工程学院,2013.
Li Yu-chen. Research of video target tracking methods based on particle filter[D]. Lanzhou: College of Electrical and Information Engineering, Lanzhou University of Technology,2013.
[13] 于金霞,汤永利,刘文静. 粒子滤波自适应机制研究综述[J]. 计算机应用研究,2010,27(2):417-422.
Yu Jin-xia, Tang Yong-li, Liu Wen-jing. A survey on adaptive mechanism of particle filter[J]. Applications Research of Computers,2010,27(2):417-422.
[14] Mikami D, Otsuka K, Yamato J. Memory-based particle filter for tracking objects with large variation in pose and appearance[C]//Proceedings of the European Conference on Computer Vision, Crete, Greece,2010:215-228.
[15] Tang Y, Bai X, Yang X, et al. Skeletonization with particle filters[J]. International Journal of Pattern Recognition and Artificial Intelligence,2010,24(4):619-634.
[16] 张苗辉,刘先省. 基于无味粒子滤波的动态场景下高机动目标跟踪[J]. 光电子激光,2010,30(6):924-929.
Zhang Miao-hui, Liu Xian-xing. Maneuverable target tracking in dynamic scene based on unscented particle filter[J]. Journal of Optoelectronics Laser,2010,30(6):924-929.
[1] 苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[2] 徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[3] 黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[4] 李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[5] 应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[6] 陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[7] 刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[8] 单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.
[9] 姚海洋, 王海燕, 张之琛, 申晓红. 双Duffing振子逆向联合信号检测模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1282-1290.
[10] 全薇, 郝晓明, 孙雅东, 柏葆华, 王禹亭. 基于实际眼结构的个性化投影式头盔物镜研制[J]. 吉林大学学报(工学版), 2018, 48(4): 1291-1297.
[11] 陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[12] 陈涛, 崔岳寒, 郭立民. 适用于单快拍的多重信号分类改进算法[J]. 吉林大学学报(工学版), 2018, 48(3): 952-956.
[13] 孟广伟, 李荣佳, 王欣, 周立明, 顾帅. 压电双材料界面裂纹的强度因子分析[J]. 吉林大学学报(工学版), 2018, 48(2): 500-506.
[14] 林金花, 王延杰, 孙宏海. 改进的自适应特征细分方法及其对Catmull-Clark曲面的实时绘制[J]. 吉林大学学报(工学版), 2018, 48(2): 625-632.
[15] 王柯, 刘富, 康冰, 霍彤彤, 周求湛. 基于沙蝎定位猎物的仿生震源定位方法[J]. 吉林大学学报(工学版), 2018, 48(2): 633-639.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发