People Detection in Complex Scenes By Using An Improved and Robust HOG Descriptor
The detection of moving people in a complex scene filmed with a single camera is among the most difficult fields of research in vision by computer. In this work, we suggest improving the quality of detection methods based on the histogram of oriented gradients (HOG) descriptor. For that, we purpose to use a combination of type detector/descriptor to minimize the rate of the false detection produced by the descriptor HOG. The implementation of this combination as well as its evaluation on public bases show clearly that the technique which we propose produces many good results at the level of the detection of the people in movement compared with the descriptor HOG
(1) R. Brown, J. Ohmer and F. Maire, Implementation of Kernel Methods on the GPU. Proceedings of the Digital Image Computing on Techniques and Applications, 2005.
(2) N. Dalal and B. Triggs, Histograms of oriented gradients for human detection. In International Conference on Computer Vision & Pattern Recognition, vol. 2, pp. 886–893, 2005.
(3) N. Dalal, B. Triggs and C. Schmid, Human detection using oriented histograms of flow and apparence. In European Conference on Computer Vision, pp. 7-13, 2006.
(4) C. Harris and M. Stephens, A combined corner and edge detector, in Alvey Vision Conference, pp. 147–151, 1988.
(5) B. Hdioud, A. Ezzahout, M. Y. Hadi and R. Oulad Haj Thami, A Real-Time People Tracking System Based on Trajectory Estimation at International Conference on Computer Applications Technology ICCAT'2013, pp. 20-22, Sousse, Tunisia, 2013.
(6) C. Papageorgiou, M. Oren and T. Poggio, A general framework for object detection, in Proc. of the IEEE International Conference on Computer Vision, pp. 555–562, 1999.
(7) P. Viola and M. Jones, Rapid object detection using a boosted cascade of simple feature, in IEEE Proc. of the conference on Computer Vision and Pattern Recognition, pp. 511–518, 2001.
(8) P. Viola, M. J. Jones and D. Snow, Detecting pedestrians using patterns of motion and appearanc, in International Journal of Computer Vision, pp. 153–161, 2005.
(9) L. Zhao, Dressed Human Modeling, Detection, and Parts Localization, PhD thesis, The Robotics Institute, Carnegie Mellon University, Pittsburgh, 2001.
(10) Q. Zhao, J. Kang, H. Tao and W. Hua, Part Based Human Tracking In A Multiple Cues Fusion Framework, in Proc. of the International Conference on Pattern Recognition, pp. 450–455,
(11) D. Gavrila and V. Philomin. Real-time object detection for smart vehicles. International Conference in Computer Vision, 1 :87–93, 1999.
(12) I. Haritaoglu, D. Harwood, and L. S. Davis. W4: Who? when? where? what? A real time system for detecting and tracking people. In Third International Conference on Automatic Face and Gesture Recognition, pages 222–227, 1998.
(13) PETS database; http://www.cvg.reading.ac.uk/PETS2006/data.html
(14) PETS database; http://www.cvg.reading.ac.uk/PETS2007/data.html
Authors wishing to include figures, tables, or text passages that have already been published elsewhere are required to obtain permission from the copyright owner(s) for both the print and online format and to include evidence that such permission has been granted when submitting their papers. Any material received without such evidence will be assumed to originate from the authors.
All authors of manuscripts accepted for publication in the journal Transactions on Networks and Communications are required to license the Scholar Publishing to publish the manuscript. Each author should sign one of the following forms, as appropriate:
License to publish; to be used by most authors. This grants the publisher a license of copyright. Download forms (MS Word formats) - (doc)
Publication agreement — Crown copyright; to be used by authors who are public servants in a Commonwealth country, such as Canada, U.K., Australia. Download forms (Adobe or MS Word formats) - (doc)
License to publish — U.S. official; to be used by authors who are officials of the U.S. government. Download forms (Adobe or MS Word formats) – (doc)
The preferred method to submit a completed, signed copyright form is to upload it within the task assigned to you in the Manuscript submission system, after the submission of your manuscript. Alternatively, you can submit it by email email@example.com