Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/151340
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMa, Junjieen_US
dc.contributor.authorDai, Yapingen_US
dc.contributor.authorTan, Yap Pengen_US
dc.date.accessioned2021-07-09T01:29:27Z-
dc.date.available2021-07-09T01:29:27Z-
dc.date.issued2019-
dc.identifier.citationMa, J., Dai, Y. & Tan, Y. P. (2019). Atrous convolutions spatial pyramid network for crowd counting and density estimation. Neurocomputing, 350, 91-101. https://dx.doi.org/10.1016/j.neucom.2019.03.065en_US
dc.identifier.issn0925-2312en_US
dc.identifier.other0000-0002-8593-3074-
dc.identifier.urihttps://hdl.handle.net/10356/151340-
dc.description.abstractScale variation because of perspective distortion is still a challenge for crowd analysis. To address this problem, an atrous convolutions spatial pyramid network (ACSPNet) is proposed to perform crowd counts and density maps for both sparse and congested scenarios. Atrous Convolutions sequenced with increasing atrous rates are utilized to exaggerate the receptive field and maintain the resolution of extracted features. Different rates of atrous convolution blocks in the pyramid are skip-connected to integrate multi-scale information and extent scale perception ability. Atrous Spatial Pyramid Pooling (ASPP) is employed to resample information at different scales and contain global context. We evaluate our ACSPNet on five challenging benchmark crowd counting datasets and our method achieves state-of-the-art mean absolute error (MAE) and mean squared error (MSE) performances.en_US
dc.description.sponsorshipInfo-communications Media Development Authority (IMDA)en_US
dc.description.sponsorshipNanyang Technological Universityen_US
dc.language.isoenen_US
dc.relation.ispartofNeurocomputingen_US
dc.rights© 2019 Elsevier B.V. All rights reserved.en_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleAtrous convolutions spatial pyramid network for crowd counting and density estimationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.identifier.doi10.1016/j.neucom.2019.03.065-
dc.identifier.scopus2-s2.0-85064698107-
dc.identifier.volume350en_US
dc.identifier.spage91en_US
dc.identifier.epage101en_US
dc.subject.keywordsCrowd Countingen_US
dc.subject.keywordsCrowd Density Estimationen_US
dc.description.acknowledgementThis research was carried out at the Rapid-Rich Object Search (ROSE) Lab at Nanyang Technological University, Singapore. The ROSE Lab is supported by the Infocomm Media Development Authority, Singapore.en_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:EEE Journal Articles

Page view(s)

52
Updated on Nov 25, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.