Enhancing pedestrian detection using context information

Página do item simplificado
dc.contributor.authorCandido J.
dc.contributor.authorMarengoni M.
dc.date.accessioned2024-03-12T23:59:12Z
dc.date.available2024-03-12T23:59:12Z
dc.date.issued2018
dc.description.abstract© 2018 Jorge Candido and Mauricio Marengoni.Detecting pedestrians among other objects in a digital image is a relevant task in the field of computer vision. This paper presents a method to improve the performance of a pedestrian detection algorithm using context information. A neural network is used to classify the region below pedestrian candidates as being floor or non-floor. We assume that a pedestrian must be standing on a floor area. This scene context information is used to eliminate some of the false-positive pedestrian candidates, therefore improving detector precision. The neural network uses 10 feature channels extracted from the original image to perform the region classification. This method may be used along with a large family of pedestrian-detecting algorithms. We used the ACF-LDCF algorithm to perform the tests in this research. The result shows that this method is very effective. We achieve a gain of 7% in ACF-LDCF algorithm performance on the Caltech pedestrian benchmark.
dc.description.firstpage1074
dc.description.issuenumber7
dc.description.lastpage1078
dc.description.volume14
dc.identifier.doi10.3844/jcssp.2018.1074.1080
dc.identifier.issn1549-3636
dc.identifier.urihttps://dspace.mackenzie.br/handle/10899/35606
dc.relation.ispartofJournal of Computer Science
dc.rightsAcesso Aberto
dc.subject.otherlanguageFeature extraction
dc.subject.otherlanguageNeural network
dc.subject.otherlanguagePedestrian detection
dc.titleEnhancing pedestrian detection using context information
dc.typeArtigo
local.scopus.citations0
local.scopus.eid2-s2.0-85052852388
local.scopus.updated2024-05-01
local.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85052852388&origin=inward
Arquivos
Coleções
Artigos de periódico