TY - GEN
T1 - Demo abstract - MediaScope
T2 - 12th International Conference on Information Processing in Sensor Networks, IPSN 2013 - Part of CPSWeek 2013
AU - Xu, Xing
AU - Jiang, Yurong
AU - Terlecky, Peter
AU - Abdelzaher, Tarek
AU - Bar-Noy, Amotz
AU - Govindan, Ramesh
PY - 2013
Y1 - 2013
N2 - Motivated by an availability gap for visual media, where images and videos are uploaded from mobile devices well after they are generated, we explore the selective, timely retrieval of media content from a collection of mobile devices. We envision this capability being driven by similarity-based queries posed to a cloud search front-end, which in turn dynamically retrieves media objects from mobile devices that best match the respective queries within a given time limit. Building upon a crowd-sensing framework, we have designed and implemented a system called MediaScope that provides this capability. MediaScope is an extensible framework that supports nearest-neighbor and other geometric queries on the feature space (e.g., clusters, spanners), and contains novel retrieval algorithms that attempt to maximize the retrieval of relevant information. From experiments on a prototype, MediaScope is shown to achieve near-optimal query completeness and low to moderate overhead on mobile devices.
AB - Motivated by an availability gap for visual media, where images and videos are uploaded from mobile devices well after they are generated, we explore the selective, timely retrieval of media content from a collection of mobile devices. We envision this capability being driven by similarity-based queries posed to a cloud search front-end, which in turn dynamically retrieves media objects from mobile devices that best match the respective queries within a given time limit. Building upon a crowd-sensing framework, we have designed and implemented a system called MediaScope that provides this capability. MediaScope is an extensible framework that supports nearest-neighbor and other geometric queries on the feature space (e.g., clusters, spanners), and contains novel retrieval algorithms that attempt to maximize the retrieval of relevant information. From experiments on a prototype, MediaScope is shown to achieve near-optimal query completeness and low to moderate overhead on mobile devices.
KW - Crowd-sensing
KW - Feature-extraction
KW - Image-retrieval
KW - Mobile-device
UR - http://www.scopus.com/inward/record.url?scp=84876746382&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84876746382&partnerID=8YFLogxK
U2 - 10.1145/2461381.2461424
DO - 10.1145/2461381.2461424
M3 - Conference contribution
AN - SCOPUS:84876746382
SN - 9781450319591
T3 - IPSN 2013 - Proceedings of the 12th International Conference on Information Processing in Sensor Networks, Part of CPSWeek 2013
SP - 313
EP - 314
BT - IPSN 2013 - Proceedings of the 12th International Conference on Information Processing in Sensor Networks, Part of CPSWeek 2013
Y2 - 8 April 2013 through 11 April 2013
ER -