Volume 6, Issue 3
A Novel Human Detection Algorithm Based on Foreground Segmentation

Chunguang Liu, Zhiheng Gong, Huijie Zhu, Yanan Liu, Yue Zhou & Zhonghua Han

Journal of Fiber Bioengineering & Informatics, 6 (2013), pp. 285-292.

Published online: 2013-06

Preview Purchase PDF 0 2015
Export citation
  • Abstract

In computer vision applications, human detection occupies an important position. HOG (Histograms of Oriented Gradient) is a classical algorithm which was used in the area of object detection. But the complex background would greatly affect the test accuracy when taking HOG as a human characteristic for human detection. In order to improve the accuracy of human detection, this paper applied a new algorithm which was based on foreground segmentation. We could get each closed region by Oriented Watershed Transform and Ultrametric Contour Map, then the foreground and the background could be distinguished. Finally we removed the background and calculated the foreground characteristic. The experimental results show that this approach was effective in improving detection accuracy.

  • Keywords

Human Detection HOG Foreground Segmentation Closed Region

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-6-285, author = {}, title = {A Novel Human Detection Algorithm Based on Foreground Segmentation}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2013}, volume = {6}, number = {3}, pages = {285--292}, abstract = {In computer vision applications, human detection occupies an important position. HOG (Histograms of Oriented Gradient) is a classical algorithm which was used in the area of object detection. But the complex background would greatly affect the test accuracy when taking HOG as a human characteristic for human detection. In order to improve the accuracy of human detection, this paper applied a new algorithm which was based on foreground segmentation. We could get each closed region by Oriented Watershed Transform and Ultrametric Contour Map, then the foreground and the background could be distinguished. Finally we removed the background and calculated the foreground characteristic. The experimental results show that this approach was effective in improving detection accuracy.}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbi09201306}, url = {http://global-sci.org/intro/article_detail/jfbi/4842.html} }
TY - JOUR T1 - A Novel Human Detection Algorithm Based on Foreground Segmentation JO - Journal of Fiber Bioengineering and Informatics VL - 3 SP - 285 EP - 292 PY - 2013 DA - 2013/06 SN - 6 DO - http://doi.org/10.3993/jfbi09201306 UR - https://global-sci.org/intro/article_detail/jfbi/4842.html KW - Human Detection KW - HOG KW - Foreground Segmentation KW - Closed Region AB - In computer vision applications, human detection occupies an important position. HOG (Histograms of Oriented Gradient) is a classical algorithm which was used in the area of object detection. But the complex background would greatly affect the test accuracy when taking HOG as a human characteristic for human detection. In order to improve the accuracy of human detection, this paper applied a new algorithm which was based on foreground segmentation. We could get each closed region by Oriented Watershed Transform and Ultrametric Contour Map, then the foreground and the background could be distinguished. Finally we removed the background and calculated the foreground characteristic. The experimental results show that this approach was effective in improving detection accuracy.
Chunguang Liu, Zhiheng Gong, Huijie Zhu, Yanan Liu, Yue Zhou & Zhonghua Han . (2019). A Novel Human Detection Algorithm Based on Foreground Segmentation. Journal of Fiber Bioengineering and Informatics. 6 (3). 285-292. doi:10.3993/jfbi09201306
Copy to clipboard
The citation has been copied to your clipboard