Dynamic scene classification using spatial and temporal cues

Show simple item record

dc.contributor.author Vasudevan, Arun Balajee
dc.contributor.author Muralidharan, Srikanth
dc.contributor.author Chintapalli, Shiva Pratheek
dc.contributor.author Raman, Shanmuganathan
dc.contributor.other 5th International Workshop on Video Event Categorization, Tagging and Retrieval (VECTaR2013), In conjunction with IEEE International Conference on Computer Vision (ICCV)
dc.coverage.spatial Sydney, AU
dc.date.accessioned 2014-04-25T10:57:04Z
dc.date.available 2014-04-25T10:57:04Z
dc.date.issued 2013-12-08
dc.identifier.citation Vasudevan, A. B,; Muralidharan, S.; Chintapalli, S. P. and Raman, Shanmuganathan, "Dynamic scene classification using spatial and temporal cues", in 5th International Workshop on Video Event Categorization, Tagging and Retrieval (VECTaR2013), In conjunction with IEEE International Conference on Computer Vision (ICCV), Sydney, AU, URL: http://www.iccv2013.org, Dec. 8, 2013. en_US
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/1218
dc.identifier.uri http://dx.doi.org/10.1109/ICCVW.2013.110
dc.description.abstract A real world scene may contain several objects with different spatial and temporal characteristics. This paper proposes a novel method for the classification of natural scenes by processing both spatial and temporal information from the video. For extracting the spatial characteristics, we build spatial pyramids using the spatial pyramid matching (SPM) algorithm on SIFT descriptors while for the motion characteristics, we introduce a five dimensional feature vector extracted from the optical flow field. We employ SPM on combined SIFT and motion feature descriptors to perform classification. We demonstrate that the proposed approach shows significant improvement in scene classification as compared to the SPM algorithm on SIFT spatial feature descriptors alone. en_US
dc.description.statementofresponsibility by A. B. Vasudevan, S. Muralidharan, S. P. Chintapalli and Shanmuganathan Raman
dc.language.iso en en_US
dc.subject Classification en_US
dc.subject Dynamic en_US
dc.subject Human visual system (HVS). en_US
dc.subject SIFT en_US
dc.subject Spatial pyramid matching en_US
dc.subject Temporal Cues en_US
dc.title Dynamic scene classification using spatial and temporal cues en_US
dc.type Article en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account