A Utility Model for Photo Selection in Mobile Crowdsensing

Existing mobile photo crowdsensing approaches focus on the participant-to-server photo pre-selection, i.e., reducing the photo redundancy from participants to a server. The server may still receive plenty of photos for a target area. Yet, another important problem is to select a proper photo subset of an area from the server to a requester. This is a challenging problem because the selected subset with a small size should attain both coverage on the PoIs - Points of Interest (i.e., photo coverage of the area) and quality on the views (i.e., view quality). In this paper, we propose a novel and generic server-to-requester photo selection approach even when there are neither photo shooting direction information nor reference photos. A utility model is designed to measure photo merits of coverage and quality by exploiting photos’ spatial distribution and visual representativeness. We present two photo selection schemes, basic and PoI number-aware, to maximize the photo selection utility with multiple levels of granularity. Experimental results on real-world datasets show that our basic scheme outperforms the baselines by an average of <inline-formula><tex-math notation="LaTeX">$33\%$</tex-math><alternatives><mml:math><mml:mrow><mml:mn>33</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="zhou-ieq1-2941927.gif"/></alternatives></inline-formula> and <inline-formula><tex-math notation="LaTeX">$18.7\%$</tex-math><alternatives><mml:math><mml:mrow><mml:mn>18</mml:mn><mml:mo>.</mml:mo><mml:mn>7</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="zhou-ieq2-2941927.gif"/></alternatives></inline-formula> on photo coverage and view quality, respectively. Our PoI number-aware scheme can yield an additionally 44.8 percent improvement on the photo coverage performance.

[1]  Deborah Estrin,et al.  Examining micro-payments for participatory sensing data collections , 2010, UbiComp.

[2]  Ramesh Govindan,et al.  MediaScope: Selective on-demand media retrieval from mobile devices , 2013, 2013 ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[3]  Fan Ye,et al.  Mobile crowdsensing: current state and future challenges , 2011, IEEE Communications Magazine.

[4]  Charu C. Aggarwal,et al.  Recursive Ground Truth Estimator for Social Data Streams , 2016, 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[5]  Xiaomei Zhang,et al.  Resource-Aware Photo Crowdsourcing Through Disruption Tolerant Networks , 2016, 2016 IEEE 36th International Conference on Distributed Computing Systems (ICDCS).

[6]  Licia Capra,et al.  Urban Computing: Concepts, Methodologies, and Applications , 2014, TIST.

[7]  Jon M. Kleinberg,et al.  Mapping the world's photos , 2009, WWW '09.

[8]  Steven M. Seitz,et al.  Scene Summarization for Online Image Collections , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[9]  Maxim Sviridenko,et al.  Approximation Algorithms for Maximum Coverage and Max Cut with Given Sizes of Parts , 1999, IPCO.

[10]  Andreas Krause,et al.  Submodular Function Maximization , 2014, Tractability.

[11]  Jiangtao Wang,et al.  PSAllocator: Multi-Task Allocation for Participatory Sensing with Sensing Capability Constraints , 2017, CSCW.

[12]  Mor Naaman,et al.  How flickr helps us make sense of the world: context and content in community-contributed media collections , 2007, ACM Multimedia.

[13]  Xue Liu,et al.  SmartEye: Real-time and efficient cloud image sharing for disaster environments , 2015, 2015 IEEE Conference on Computer Communications (INFOCOM).

[14]  Vikas Kumar,et al.  CrowdSearch: exploiting crowds for accurate real-time image search on mobile phones , 2010, MobiSys '10.

[15]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[16]  Qi Han,et al.  Toward real-time and cooperative mobile visual sensing and sharing , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[17]  Zoran Popovic,et al.  PhotoCity: training experts at large-scale image acquisition through a competitive game , 2011, CHI.

[18]  Liming Chen,et al.  A Generic Framework for Constraint-Driven Data Selection in Mobile Crowd Photographing , 2017, IEEE Internet of Things Journal.

[19]  Konstantinos N. Plataniotis,et al.  Toward a No-Reference Image Quality Assessment Using Statistics of Perceptual Color Descriptors , 2016, IEEE Transactions on Image Processing.

[20]  Daqing Zhang,et al.  Sparse mobile crowdsensing: challenges and opportunities , 2016, IEEE Communications Magazine.

[21]  S. Govindarajulu,et al.  A Comparison of SIFT, PCA-SIFT and SURF , 2012 .

[22]  Slava Kisilevich,et al.  Towards Acquisition of Semantics of Places and Events by Multi-perspective Analysis of Geotagged Photo Collections , 2013 .

[23]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[24]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[25]  Zhu Wang,et al.  Mobile Crowd Sensing and Computing , 2015, ACM Comput. Surv..

[26]  Xing Xie,et al.  FlierMeet: A Mobile Crowdsensing System for Cross-Space Public Information Reposting, Tagging, and Sharing , 2015, IEEE Transactions on Mobile Computing.

[27]  Md. Yusuf Sarwar Uddin,et al.  PhotoNet: A Similarity-Aware Picture Delivery Service for Situation Awareness , 2011, 2011 IEEE 32nd Real-Time Systems Symposium.

[28]  Srinivasan Seshan,et al.  CARE: content aware redundancy elimination for challenged networks , 2012, HotNets-XI.

[29]  Henriette Cramer,et al.  Aesthetic capital: what makes london look beautiful, quiet, and happy? , 2014, CSCW.

[30]  Ramesh Govindan,et al.  PhotoNet+: outlier-resilient coverage maximization in visual sensing applications , 2012, IPSN.

[31]  Xinbing Wang,et al.  A Picture is Worth a Thousand Words: Share Your Real-Time View on the Road , 2017, IEEE Transactions on Vehicular Technology.

[32]  Yi Wang,et al.  Photo crowdsourcing for area coverage in resource constrained environments , 2017, IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.

[33]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[34]  Yi Wang,et al.  SmartPhoto: A Resource-Aware Crowdsourcing Approach for Image Sensing with Smartphones , 2014, IEEE Transactions on Mobile Computing.

[35]  Luo Juan,et al.  A comparison of SIFT, PCA-SIFT and SURF , 2009 .

[36]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..

[37]  Ming Xu,et al.  FIDC: A framework for improving data credibility in mobile crowdsensing , 2017, Comput. Networks.

[38]  Jing Gao,et al.  Truth Discovery on Crowd Sensing of Correlated Entities , 2015, SenSys.

[39]  Ming Xu,et al.  From Uncertain Photos to Certain Coverage: a Novel Photo Selection Approach to Mobile Crowdsensing , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.