SmartPhoto

A resource-aware crowdsourcing approach for image sensing with smartphones

Yi Wang, Wenjie Hu, Yibo Wu, Guohong Cao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

30 Citations (Scopus)

Abstract

Photos obtained via crowdsourcing can be used in many critical applications. Due to the limitations of communication bandwidth, storage and processing capability, it is a challenge to transfer the huge amount of crowdsourced photos. To address this problem, we propose a framework, called SmartPhoto, to quantify the quality (utility) of crowd-sourced photos based on the accessible geographical and geo-metrical information (called metadata) including the smart-phone's orientation, position and all related parameters of the built-in camera. From the metadata, we can infer where and how the photo is taken, and then only transmit the most useful photos. Three optimization problems regarding the tradeoffs between photo utility and resource constraints, namely the Max-Utility problem, the online Max-Utility problem and the Min-Selection problem, are studied. Efficient algorithms are proposed and their performance bounds are theoretically proved. We have implemented SmartPhoto in a testbed using Android based smart-phones, and proposed techniques to improve the accuracy of the collected metadata by reducing sensor reading errors and solving object occlusion issues. Results based on real implementations and extensive simulations demonstrate the effectiveness of the proposed algorithms.

Original languageEnglish (US)
Title of host publicationMobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing
PublisherAssociation for Computing Machinery
Pages113-122
Number of pages10
ISBN (Electronic)9781450326209
DOIs
StatePublished - Aug 11 2014
Event15th ACM International Symposium on Mobile Ad Hoc Networking and Computing, MobiHoc 2014 - Philadelphia, United States
Duration: Aug 11 2014Aug 14 2014

Publication series

NameProceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc)
Volume11-14-August-2014

Other

Other15th ACM International Symposium on Mobile Ad Hoc Networking and Computing, MobiHoc 2014
CountryUnited States
CityPhiladelphia
Period8/11/148/14/14

Fingerprint

Smartphones
Metadata
Testbeds
Cameras
Bandwidth
Communication
Sensors
Processing

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Wang, Y., Hu, W., Wu, Y., & Cao, G. (2014). SmartPhoto: A resource-aware crowdsourcing approach for image sensing with smartphones. In MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing (pp. 113-122). (Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc); Vol. 11-14-August-2014). Association for Computing Machinery. https://doi.org/10.1145/2632951.2632979
Wang, Yi ; Hu, Wenjie ; Wu, Yibo ; Cao, Guohong. / SmartPhoto : A resource-aware crowdsourcing approach for image sensing with smartphones. MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing. Association for Computing Machinery, 2014. pp. 113-122 (Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc)).
@inproceedings{9e4cba6f95cd43a6bca67019a183de20,
title = "SmartPhoto: A resource-aware crowdsourcing approach for image sensing with smartphones",
abstract = "Photos obtained via crowdsourcing can be used in many critical applications. Due to the limitations of communication bandwidth, storage and processing capability, it is a challenge to transfer the huge amount of crowdsourced photos. To address this problem, we propose a framework, called SmartPhoto, to quantify the quality (utility) of crowd-sourced photos based on the accessible geographical and geo-metrical information (called metadata) including the smart-phone's orientation, position and all related parameters of the built-in camera. From the metadata, we can infer where and how the photo is taken, and then only transmit the most useful photos. Three optimization problems regarding the tradeoffs between photo utility and resource constraints, namely the Max-Utility problem, the online Max-Utility problem and the Min-Selection problem, are studied. Efficient algorithms are proposed and their performance bounds are theoretically proved. We have implemented SmartPhoto in a testbed using Android based smart-phones, and proposed techniques to improve the accuracy of the collected metadata by reducing sensor reading errors and solving object occlusion issues. Results based on real implementations and extensive simulations demonstrate the effectiveness of the proposed algorithms.",
author = "Yi Wang and Wenjie Hu and Yibo Wu and Guohong Cao",
year = "2014",
month = "8",
day = "11",
doi = "10.1145/2632951.2632979",
language = "English (US)",
series = "Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc)",
publisher = "Association for Computing Machinery",
pages = "113--122",
booktitle = "MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing",

}

Wang, Y, Hu, W, Wu, Y & Cao, G 2014, SmartPhoto: A resource-aware crowdsourcing approach for image sensing with smartphones. in MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing. Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc), vol. 11-14-August-2014, Association for Computing Machinery, pp. 113-122, 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing, MobiHoc 2014, Philadelphia, United States, 8/11/14. https://doi.org/10.1145/2632951.2632979

SmartPhoto : A resource-aware crowdsourcing approach for image sensing with smartphones. / Wang, Yi; Hu, Wenjie; Wu, Yibo; Cao, Guohong.

MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing. Association for Computing Machinery, 2014. p. 113-122 (Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc); Vol. 11-14-August-2014).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - SmartPhoto

T2 - A resource-aware crowdsourcing approach for image sensing with smartphones

AU - Wang, Yi

AU - Hu, Wenjie

AU - Wu, Yibo

AU - Cao, Guohong

PY - 2014/8/11

Y1 - 2014/8/11

N2 - Photos obtained via crowdsourcing can be used in many critical applications. Due to the limitations of communication bandwidth, storage and processing capability, it is a challenge to transfer the huge amount of crowdsourced photos. To address this problem, we propose a framework, called SmartPhoto, to quantify the quality (utility) of crowd-sourced photos based on the accessible geographical and geo-metrical information (called metadata) including the smart-phone's orientation, position and all related parameters of the built-in camera. From the metadata, we can infer where and how the photo is taken, and then only transmit the most useful photos. Three optimization problems regarding the tradeoffs between photo utility and resource constraints, namely the Max-Utility problem, the online Max-Utility problem and the Min-Selection problem, are studied. Efficient algorithms are proposed and their performance bounds are theoretically proved. We have implemented SmartPhoto in a testbed using Android based smart-phones, and proposed techniques to improve the accuracy of the collected metadata by reducing sensor reading errors and solving object occlusion issues. Results based on real implementations and extensive simulations demonstrate the effectiveness of the proposed algorithms.

AB - Photos obtained via crowdsourcing can be used in many critical applications. Due to the limitations of communication bandwidth, storage and processing capability, it is a challenge to transfer the huge amount of crowdsourced photos. To address this problem, we propose a framework, called SmartPhoto, to quantify the quality (utility) of crowd-sourced photos based on the accessible geographical and geo-metrical information (called metadata) including the smart-phone's orientation, position and all related parameters of the built-in camera. From the metadata, we can infer where and how the photo is taken, and then only transmit the most useful photos. Three optimization problems regarding the tradeoffs between photo utility and resource constraints, namely the Max-Utility problem, the online Max-Utility problem and the Min-Selection problem, are studied. Efficient algorithms are proposed and their performance bounds are theoretically proved. We have implemented SmartPhoto in a testbed using Android based smart-phones, and proposed techniques to improve the accuracy of the collected metadata by reducing sensor reading errors and solving object occlusion issues. Results based on real implementations and extensive simulations demonstrate the effectiveness of the proposed algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84939807945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939807945&partnerID=8YFLogxK

U2 - 10.1145/2632951.2632979

DO - 10.1145/2632951.2632979

M3 - Conference contribution

T3 - Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc)

SP - 113

EP - 122

BT - MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing

PB - Association for Computing Machinery

ER -

Wang Y, Hu W, Wu Y, Cao G. SmartPhoto: A resource-aware crowdsourcing approach for image sensing with smartphones. In MobiHoc 2014 - Proceedings of the 15th ACM International Symposium on Mobile Ad Hoc Networking and Computing. Association for Computing Machinery. 2014. p. 113-122. (Proceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc)). https://doi.org/10.1145/2632951.2632979