Context pruned histogram of oriented gradients for pedestrian detection

Author

Vimal, S.P. ; Ajay, B. ; Thiruvikiraman, P.K.

Author_Institution

Dept. of CS&IS, Birla Inst. of Technol. & Sci., Pilani, India

fYear

2013

fDate

22-23 March 2013

Firstpage

718

Lastpage

722

Abstract

The contextual information has been found to assist the object detection in many ways. The contextual information in the detection tasks can serve to disambiguate the recognition process when the object to be detected is cluttered in the environment. Also, it can help speeding up the detection process itself. In this paper, we have shown that the use of spatial contextual information makes the process of detecting of pedestrian in still images efficient. We have tested our approach in the INRIA dataset consisting of 999 images and the results are found to be encouraging.

Keywords

computer vision; object detection; pedestrians; INRIA dataset; computer vision; context pruned histogram of oriented gradient; detection task; object detection; pedestrian detection; recognition process disambiguation; spatial contextual information; still image; Computer vision; Conferences; Context; Detectors; Feature extraction; Histograms; Object detection; Histogram of Oriented Gradients (HOG); Pedestrian Detection; Spatial Context;

fLanguage

English

Publisher

ieee

Conference_Titel

Automation, Computing, Communication, Control and Compressed Sensing (iMac4s), 2013 International Multi-Conference on

Conference_Location

Kottayam

Print_ISBN

978-1-4673-5089-1

Type

conf

DOI

10.1109/iMac4s.2013.6526501

Filename

6526501