Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/198368
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKuan-Wen Chenen_US
dc.contributor.authorChun-Hsin Wangen_US
dc.contributor.authorXiao Weien_US
dc.contributor.authorQiao Liangen_US
dc.contributor.authorChu-Song Chenen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.contributor.authorYi-Ping Hungen_US
dc.date.accessioned2013en_US
dc.date.accessioned2020-04-06T07:46:04Z-
dc.date.available2020-04-06T07:46:04Z-
dc.date.issued2017en_US
dc.identifier.other10.1109/TITS.2016.2570811en_US
dc.identifier.urihttp://localhost/handle/Hannan/198368-
dc.description.abstractThis paper presents an algorithm for ego-positioning by using a low-cost monocular camera for systems based on the Internet-of-Vehicles. To reduce the computational and memory requirements, as well as the communication load, we tackle the model compression task as a weighted k-cover problem for better preserving the critical structures. For real-world vision-based positioning applications, we consider the issue of large scene changes and introduce a model update algorithm to address this problem. A large positioning data set containing data collected for more than a month, 106 sessions, and 14275 images is constructed. Extensive experimental results show that submeter accuracy can be achieved by the proposed ego-positioning algorithm, which outperforms existing vision-based approaches.en_US
dc.format.extent364,en_US
dc.format.extent376en_US
dc.publisherIEEEen_US
dc.relation.haspart7506097.pdfen_US
dc.titleVision-Based Positioning for Internet-of-Vehiclesen_US
dc.typeArticleen_US
dc.journal.volume18en_US
dc.journal.issue2en_US
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7506097.pdf3.4 MBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKuan-Wen Chenen_US
dc.contributor.authorChun-Hsin Wangen_US
dc.contributor.authorXiao Weien_US
dc.contributor.authorQiao Liangen_US
dc.contributor.authorChu-Song Chenen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.contributor.authorYi-Ping Hungen_US
dc.date.accessioned2013en_US
dc.date.accessioned2020-04-06T07:46:04Z-
dc.date.available2020-04-06T07:46:04Z-
dc.date.issued2017en_US
dc.identifier.other10.1109/TITS.2016.2570811en_US
dc.identifier.urihttp://localhost/handle/Hannan/198368-
dc.description.abstractThis paper presents an algorithm for ego-positioning by using a low-cost monocular camera for systems based on the Internet-of-Vehicles. To reduce the computational and memory requirements, as well as the communication load, we tackle the model compression task as a weighted k-cover problem for better preserving the critical structures. For real-world vision-based positioning applications, we consider the issue of large scene changes and introduce a model update algorithm to address this problem. A large positioning data set containing data collected for more than a month, 106 sessions, and 14275 images is constructed. Extensive experimental results show that submeter accuracy can be achieved by the proposed ego-positioning algorithm, which outperforms existing vision-based approaches.en_US
dc.format.extent364,en_US
dc.format.extent376en_US
dc.publisherIEEEen_US
dc.relation.haspart7506097.pdfen_US
dc.titleVision-Based Positioning for Internet-of-Vehiclesen_US
dc.typeArticleen_US
dc.journal.volume18en_US
dc.journal.issue2en_US
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7506097.pdf3.4 MBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKuan-Wen Chenen_US
dc.contributor.authorChun-Hsin Wangen_US
dc.contributor.authorXiao Weien_US
dc.contributor.authorQiao Liangen_US
dc.contributor.authorChu-Song Chenen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.contributor.authorYi-Ping Hungen_US
dc.date.accessioned2013en_US
dc.date.accessioned2020-04-06T07:46:04Z-
dc.date.available2020-04-06T07:46:04Z-
dc.date.issued2017en_US
dc.identifier.other10.1109/TITS.2016.2570811en_US
dc.identifier.urihttp://localhost/handle/Hannan/198368-
dc.description.abstractThis paper presents an algorithm for ego-positioning by using a low-cost monocular camera for systems based on the Internet-of-Vehicles. To reduce the computational and memory requirements, as well as the communication load, we tackle the model compression task as a weighted k-cover problem for better preserving the critical structures. For real-world vision-based positioning applications, we consider the issue of large scene changes and introduce a model update algorithm to address this problem. A large positioning data set containing data collected for more than a month, 106 sessions, and 14275 images is constructed. Extensive experimental results show that submeter accuracy can be achieved by the proposed ego-positioning algorithm, which outperforms existing vision-based approaches.en_US
dc.format.extent364,en_US
dc.format.extent376en_US
dc.publisherIEEEen_US
dc.relation.haspart7506097.pdfen_US
dc.titleVision-Based Positioning for Internet-of-Vehiclesen_US
dc.typeArticleen_US
dc.journal.volume18en_US
dc.journal.issue2en_US
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7506097.pdf3.4 MBAdobe PDF