Please use this identifier to cite or link to this item: https://repository.cihe.edu.hk/jspui/handle/cihe/1260
DC FieldValueLanguage
dc.contributor.authorSiu, Wan Chien_US
dc.contributor.otherLi, C.-T.-
dc.contributor.otherLun, D. P. K.-
dc.date.accessioned2021-08-12T06:16:36Z-
dc.date.available2021-08-12T06:16:36Z-
dc.date.issued2018-
dc.identifier.urihttps://repository.cihe.edu.hk/jspui/handle/cihe/1260-
dc.description.abstractThis paper presents a key frame recognition algorithm, using novel offline feature-shifts approach and search window weights. We extract effective feature patches from key frames with an offline feature-shifts approach for real-time key frame recognition. We focus on practical situations in which blurring and shifts in viewpoints occur in our dataset. We compare our method with some conventional keypoint-based matching methods and the newest CNN features for scene recognition. The experimental results illustrate that our method can reasonably preserve the performance in key frame recognition when comparing with methods using online feature-shifts approach. Our proposed method provides larger tolerance of unmatched pairs which is useful for decision making in real-time systems. Moreover, our method is robust to illumination and blurring. We achieve 90% accuracy in a nighttime sequence while CNN approach only attains 60% accuracy. Our method only requires 33.8 ms to match a frame on average using a regular desktop, which is 4 times faster than CNN approach with only CPU mode.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.titleBoosting the performance of scene recognition via offline feature-shifts and search window weightsen_US
dc.typeconference proceedingsen_US
dc.relation.publication2018 IEEE 23rd International Conference on Digital Signal Processing (DSP) Proceedingsen_US
dc.identifier.doi10.1109/ICDSP.2018.8631883-
dc.contributor.affiliationSchool of Computing and Information Sciencesen_US
dc.relation.isbn9781538668115en_US
dc.description.startpage1120-
dc.description.endpage1124-
dc.cihe.affiliatedNo-
item.openairetypeconference proceedings-
item.languageiso639-1en-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_5794-
item.grantfulltextnone-
item.cerifentitytypePublications-
crisitem.author.deptSchool of Computing and Information Sciences-
crisitem.author.orcid0000-0001-8280-0367-
Appears in Collections:CIS Publication
SFX Query Show simple item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.