Earticle

초록

영어

With the aim to solve the problems of large amount of image data transmission and low accuracy of the initial background image extracted in traditional vehicle detecting system, this article proposes a road vehicle detecting algorithm based on compressive sensing. Image signals are sparse in a wavelet basis and the Gaussian random measurement matrix is adopted to compress videos, which reduce the amount of image data transmission. This article uses the proposed improved initial background extracting method and selective background updating method to obtain the initial background image and background updating which improves the accuracy of the initial background image. The vehicle detection and selective reconstruction of foreground image of vehicle are achieved by integrated background subtraction and the orthogonal matching pursuit algorithm. Through many experiments in video monitoring of real scenes, the article proves the correctness and efficiency of the algorithm. It not only improves the accuracy of the initial background image extracted but also reduces the amount of image data transmission and power consumption as well as the price of video transmission.

목차

Abstract
 1. Introduction
 2. The Compressive Sensing Theory
  2.1 Sparse Representation
  2.2 Measurement matrix
  2.3 Reconstruction Algorithm
 3. Road Vehicle Detection Algorithm based on CS
  3.1 Adaptive Background Modeling
  3.2 Background update Policy
 4. Experiment and Analysis
 5. Conclusions
 References

키워드

저자

• Yiqin CAO [ School of Software, East China Jiaotong University, Nanchang 330013, China ]
• Xiaoci ZHOU [ School of Software, East China Jiaotong University, Nanchang 330013, China ]
• Xiaosheng HUANG [ School of Information Engineering, East China Jiaotong University, Nanchang 330013, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605