Multi-instance local exemplar comparisons for pedestrian detection

Chensheng Sun, Sanyuan Zhao, Jiwei Hu, Kin Man Lam

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

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.
Original languageEnglish
Title of host publication2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012
Pages223-227
Number of pages5
DOIs
Publication statusPublished - 26 Nov 2012
Event2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012 - Hong Kong, Hong Kong
Duration: 12 Aug 201215 Aug 2012

Conference

Conference2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012
Country/TerritoryHong Kong
CityHong Kong
Period12/08/1215/08/12

Keywords

  • cascade
  • Exemplar
  • multi-instance
  • similarity
  • template matching

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this