Welcome to the InfoSci Platform
Reference Hub1
Moving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene

Moving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene

Yan Wang, Yang Yu, Gang Yan, Yingchun Guo
Copyright: © 2014 |Volume: 6 |Issue: 1 |Pages: 16
ISSN: 1937-965X|EISSN: 1937-9668|EISBN13: 9781466652712|DOI: 10.4018/ijapuc.2014010104
Cite Article Cite Article

MLA

Wang, Yan, et al. "Moving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene." IJAPUC vol.6, no.1 2014: pp.44-59. http://doi.org/10.4018/ijapuc.2014010104

APA

Wang, Y., Yu, Y., Yan, G., & Guo, Y. (2014). Moving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene. International Journal of Advanced Pervasive and Ubiquitous Computing (IJAPUC), 6(1), 44-59. http://doi.org/10.4018/ijapuc.2014010104

Chicago

Wang, Yan, et al. "Moving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene," International Journal of Advanced Pervasive and Ubiquitous Computing (IJAPUC) 6, no.1: 44-59. http://doi.org/10.4018/ijapuc.2014010104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In order to detect the moving object under dynamic scenes accurately, this paper proposes a moving object detection method which is based on the precise background compensation. First, the SURF (Speeded-Up Robust Features) algorithm is used to extract feature points, and the BBF(Best-Bin-First) search algorithm is adopted to match feature points, in addition the reverse constraint strategy is employed to remove the mismatching points. To enhance the accuracy of the background compensation, a dynamic threshold is set to remove the target feature points influence for the global motion parameters. At last, a combination of interval three-frame- -differencing and morphological method is used to detect the moving objects. Experimental results show that this method has good performance on multiple moving targets detection.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.