计算机科学 ›› 2017, Vol. 44 ›› Issue (2): 309-312.doi: 10.11896/j.issn.1002-137X.2017.02.053

• 图形图像与模式识别 • 上一篇    下一篇

一种融合ViBe与多特征提取的微动目标检测算法

杨春德,孟琦   

  1. 重庆邮电大学计算机科学与技术学院 重庆400065,重庆邮电大学计算机科学与技术学院 重庆400065
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受重庆市高校优秀成果转化资助

Algorithm of Micro-motion Object Detection Based on ViBe and Multi-feature Extraction

YANG Chun-de and MENG Qi   

  • Online:2018-11-13 Published:2018-11-13

摘要: 为实现前景微动目标的准确提取,克服提取过程中的高误检率等难题,对CbCr分量、RGB和SILTP特征建立背景模型,提出一种融合多特征的ViBe背景建模改进算法。首先引入LBSP算子,改进LBP-TOP纹理编码方式,利用得到的纹理特征计算当前帧的时/空域前景概率,从而建立起接近真实背景的CbCr背景模型;然后结合局部像素复杂度和3种特征的变化情况改进ViBe判别与更新方法,利用背景减除和形态学处理得到完整的前景目标进行背景替换。实验结果表明,所提算法能有效分割视频图像中的微动目标并实现背景替换。

关键词: ViBe,SILTP,LBP-TOP,LBSP,背景替换

Abstract: In order to realize the accurate extraction of micro-motion object and overcome problems like high false detection rate in the target extraction process,this paper etablished background model for CbCr component,RGB and SILTP feature,and proposed an improved algorithm of ViBe background modeling based on fusion of multi features.The algorithm improvs LBP-TOP texture operator encoding method by introducing LBSP operator,and generates the spatial and temporal domain foreground probability of a pixel by utilizing the improved LBP-TOP texture feature,which is used to gradually establish a CbCr background model close to the true background.It improves ViBe foreground determination and background updating method based on the local pixel complexity and the changing conditions of the three types of characteristics.Then,it gets the complete object detection and accomplishs the accurate background replacement of the video sequences.The experimental results show that the proposed algorithm can effectively segment the micro motion-object of the video sequences and realize the background replacement.

Key words: ViBe,SLITP,LBP-TOP,LBSP,Background replacement

[1] 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.
[2] LI J J,PENG Q M.Motion Object Detection Algorithm for Sudden Illumination Changes[J].Journal of Computer-Aided Design &Computer Graphics,2012,4(11):1405-1409.(in Chinese) 李加佳,彭启民.适应光照突变的运动目标检测算法[J].计算机辅助设计与图形学学报,2012,24(11):1405-1409.
[3] XU H,YU F.Improved Compressive Tracking in Surveillance Scenes[C]∥2013 Seventh International Conference on Image and Graphics (ICIG).IEEE,2013:869-873.
[4] LIZARRAGA-MORALES R A,GUO Y,ZHAO G,et al.Local spatio temporal features for dynamic texture synthesis[J].Eu-rasip Journal on Image & Video Processing,2014,2014(17):562-564.
[5] BILODEAU G A,JODON J P,SAUNIER N.Change Detection in Feature Space Using Local Binary Similarity Patterns[C]∥2013 International Conference on Computer and Robot Vision (CRV).IEEE,2013:106-112.
[6] STCHARLES P L,BILODEAU G A.Improving backgroundsubtraction using Local Binary Similarity Patterns[C]∥2014 IEEE Winter Conference on Applications of Computer Vision (WACV).IEEE Computer Society,2014:509-515.
[7] LIU P,ZHU Y.An Adaptive Cast Shadow Detection with Combined Texture and Color Models[J].International Journal of Future Computer and Communication,2014,3(2):113-118.
[8] YANG G L,ZHOU D,ZHANG J H.Moving Object Detection Algorithm Using SILTP Texture Information[J].Computer Science,2014,1(4):302-305.(in Chinese) 杨国亮,周丹,张进辉.基于SILTP纹理信息的运动目标检测算法[J].计算机科学,2014,41(4):302-305.
[9] HUANG W,KIM K,YANG Y,et al.Automatic shadow removal by illuminance in hsv color space[J].Computer Science Information Technology,2015,3(3):70-75.
[10] QU Z,MA Q W,ZHANG Q Q.Research on the Algorithm of Micro-movement Target Tracking and Extraction in Video by Multi-thread Technology[J].Computer Science,2012,9(4):265-268.(in Chinese) 瞿中,马庆伟,张庆庆.多线程下的视频微动目标检测与提取算法研究[J].计算机科学,2012,39(4):265-268.
[11] VANOGENBROECK M,PQUOT O.Background subtraction:Experiments and improvements for ViBe[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Washington D C:IEEE Computer Society Press,2012:32-37.
[12] KIM J,RAMIREZ RIVERA A,RYU B,et al.SimultaneousForeground Detection and Classification With Hybrid Features[C]∥Proceedings of the IEEE International Conference on Computer Vision.2015:3307-3315.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!