Foreground Detection via Background Subtraction and Improved Three-Frame Differencing

被引：2
作者：
Sandeep Singh Sengar
Susanta Mukhopadhyay
机构：
[1] Indian Institute of Technology (Indian School of Mines),Department of Computer Science and Engineering
来源：
Arabian Journal for Science and Engineering | 2017年 / 42卷
关键词：
Moving object detection; Background subtraction; Frame differencing; Threshold; Morphology;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Moving object detection is a widely used and important research topic in computer vision and video processing. Foreground aperture, ghosting and sudden illumination changes are the main problems in moving object detection. To consider the above problems, this work proposes two approaches: (i) improved three-frame difference method and (ii) combining background subtraction and improved three-frame difference method for the detection of multiple moving objects from indoor and outdoor real video dataset. This work accurately detects the moving objects with varying object size and number in different complex environments. We compute the detection error and processing time of two proposed as well as previously existing approaches. Experimental results and error rate analysis show that our methods detect the moving targets efficiently and effectively as compared to the traditional approaches.
引用
收藏
页码：3621 / 3633
页数：12
相关论文
共 31 条
  • [1] Aslandogan YA(1999)Techniques and systems for image and video retrieval IEEE Trans. Knowl. Data Eng. 11 56-63
  • [2] Yu CT(2016)Moving object area detection using normalized self adaptive optical flow Optik-Int. J. Light Electron Optics 127 6258-6267
  • [3] Sengar SS(2014)A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos Comput. Vis. Image Underst. 122 4-21
  • [4] Mukhopadhyay S(2015)Visual tracking based on improved foreground detection and perceptual hashing Neurocomputing 152 413-428
  • [5] Sobral A(2010)Background subtraction for automated multisensor surveillance: a comprehensive review EURASIP J. Adv. Signal Process. 2010 1-24
  • [6] Vacavant A(2008)Foreground segmentation based on selective foreground model Electron. Lett. IEEE 44 851-852
  • [7] Fei M(2011)Vibe: a universal background subtraction algorithm for video sequences IEEE Trans. Image Process. 20 1709-1724
  • [8] Li J(2004)Statistical modeling of complex background for foreground object detection IEEE Trans. Image Process. 13 1459-1472
  • [9] Liu H(2011)Object detection using background subtraction and foreground motion estimation IPSJ Trans. Comput. Vision Appl. 3 9-20
  • [10] Cristani M(2006)Moving vehicles segmentation based on bayesian framework for gaussian motion model Pattern Recognit Lett. 27 956-967
1234