ePrints

Combining human perception and geometric restrictions for automatic pedestrian detection

Lookup NU author(s): Dr Quoc Vuong

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

Automatic detection systems do not perform as well as human observers, even on simple detection tasks. A potential solution to this problem is training vision systems on appropriate regions of interests (ROIs), in contrast to training on predefined and arbitrarily selected regions. Here we focus on detecting pedestrians in static scenes. Our aim is to answer the following question: Can automatic vision systems for pedestrian detection be improved by training them on perceptually-defined ROIs?

Publication metadata

Author(s): Castrillón-Santana M, Vuong QC

Editor(s): Marín, R; Onaindía, E; Bugarín, A; Santos, J

Publication type: Book Chapter

Publication status: Published

Book Title: Current Topics in Artificial Intelligence

Year: 2006

Volume: 4177

Pages: 163-170

Print publication date: 16/11/2005

Series Title: Lecture Notes in Artificial Intelligence

Publisher: Springer Verlag

Place Published: Santiago de Compostela, Spain

URL: http://dx.doi.org/10.1007/11881216_18

DOI: 10.1007/11881216_18

Notes: Revised selected papers from the 11th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2005, Santiago de Compostela, Spain, November 16-18, 2005.

Library holdings: Search Newcastle University Library for this item

ISBN: 9783540459149

Share