English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Combining Human Perception and Geometric Restrictions for Automatic Pedestrian Detection

Castrillón-Santana, M., & Vuong, Q. (2006). Combining Human Perception and Geometric Restrictions for Automatic Pedestrian Detection. Current Topics in Artificial Intelligence: 11th Conference of the Spanish Association for Artificial Intelligence (CAEPIA 2005), 163-170.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Castrillón-Santana, M1, Author           
Vuong, QC1, Author           
Marin, R., Editor
Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              

Content

show
hide
Free keywords: -
 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?

Details

show
hide
Language(s):
 Dates: 2006-10
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: URI: http://www-gsi.dec.usc.es/caepia05/en/index_en.html
DOI: 10.1007/11881216_18
BibTex Citekey: 4227
 Degree: -

Event

show
hide
Title: 11th Conference of the Spanish Association for Artificial Intelligence (CAEPIA 2005)
Place of Event: Santiago de Compostela, Spain
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Current Topics in Artificial Intelligence: 11th Conference of the Spanish Association for Artificial Intelligence (CAEPIA 2005)
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Heidelberg, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 163 - 170 Identifier: -