Please use this identifier to cite or link to this item:
Title: Multi-instance local exemplar comparisons for pedestrian detection
Authors: Sun, C
Zhao, S
Hu, J
Lam, KM 
Keywords: Exemplar
Template matching
Issue Date: 2012
Publisher: IEEE
Source: 2012 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC), 12-15 August 2012, Hong Kong, p. 223-227 How to cite?
Abstract: We propose to use the partial similarity between a sample and a number of exemplars as the image features for visual object detection. Define a part of the object as a sub-window inside the object bounding box, for each part of the object, a codebook of local appearance templates is learned. By using multiple templates for each part, and allowing the template to be compared with a bag of part instances in the neighborhood of the canonical location, the deformable and multi-aspect properties can be captured. A linear classifier is learned with feature selection, selecting a subset of the templates. To improve the efficiency of the detector, a rejection cascade is built by calibrating the linear classifier; the rejection cascade makes decisions using partial scores. Experimental results show that our method substantially improves the performance for human detection.
ISBN: 978-1-4673-2192-1
DOI: 10.1109/ICSPCC.2012.6335624
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Last Week
Last month
Citations as of Aug 14, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.