Geo-Crowdsourcing Media Content
Currently,core features are being served in MediaQ V.1.1. MediaQ server can be accessed
. More advanced features will be added in the next version by the end of 2013.
MediaQ is a novel online media management framework to collect, organize, share, search, and trade user-generated mobile images and videos by the public. It provides a synergistic hybrid of
storage (e.g., YouTube), trading (e.g., Ebay), social sharing (e.g., Facebook) for videos and pictures which is effectively tied by IMSC’s proprietary technologies.
MediaQ consists of MediaQ server and mobile app for smartphone using iPhone or Android OS. It allows video uploads from user’s smartphone to be automatically geo-tagged on a map, while also
adding metadata such as its recorded real time and indicating the specific direction a camera was pointed, per frame. Media content can be exactly pinned on the map with directional accuracy.
Signed participants can post specific content requests that will automatically ping other participants near a designated content assignment location enticing them to get out their phones and
Integrated Media Systems Center at USC has developed new patented technologies to support the MediaQ framework:
Unique techniques to represent video contents have been developed by using metadata. Individual frames of video (or any meaningful video segment) will be automatically annotated by objective
metadata which capture 4 dimensions in real world: capture time (When), camera location and viewing direction (Where), keyword (What) and people (Who), termed W4-Metadata, utilizing
sophisticated geospatial and computer vision techniques.
New way of collecting videos and pictures from the public has been implemented by using geo-crowdsourcing, which makes user-generated media contents to be collected in a coordinated manner
for a specific purpose. Our geo-crowdsourcing can orchestrate the collaboration of requesters and workers in an optimal way based on temporal and spatial information.
Current MediaQ screenshots
MediaQ Demo (2013):
PBS Newshour Inauguration Coverage using our system (2013):
NATO Summit Coverage (2012):
THE QUEST FOR INFORMATION: Read more
For MediaQ Server Tutorial, click
For MediaQ Android App Tutorial, click
For MediaQ Server Video, click
For MediaQ Android App Video, click
Journal and Magazine Papers
- [J2] "Relevance Ranking in Georeferenced Video Search", Sakire Arslan Ay, Roger Zimmermann, Seon Ho Kim Multimedia Systems Journal (MMSJ '10), Springer-Verlag, Volume 16, Pages: 105-125, 2010.
- [J1] "A Design and Implementation of Geo-Tagged Video Search Framework", Seon Ho Kim, Sakire Arslan Ay, Roger Zimmermann Journal of Visual Communication and Image Representation, Elsevier (JVCI '10), Academic Press, Inc., Volume 21, Pages: 773-786, Orlando, FL, USA, 2010.
Conference and Workshop Papers
- [C10] "Large-scale Geo-tagged Video Indexing and Queries", Ma He, Seon Ho Kim, Sakire Arslan Ay, Roger Zimmermann "Accepted to appear in Geoinformatica, 2014" 2014.
- [C9] "An Efficient Index Structure for Large-scale Geo-tagged Video Databases", Ying Lu, Cyrus Shahabi and Seon Ho Kim "Accepted to appear in the ACM GIS, Nov. 2014" 2014.
- [C8] "A Benchmark to Evaluate Mobile Video Upload to Cloud Infrastructures", Afsin Akdogan, Hien To, Seon Ho Kim, Cyrus Shahabi "Fifth workshop on Big Data Benchmarks, Performance Optimization, and Emerging Hardware (BPOE-5), Sep. 2014" 2014.
- [C7] "Active Key Frame Selection for 3D Model Reconstruction from Crowdsourced Geo-tagged Videos", Guanfeng Wang, Ying Lu, Luming Zhang, Abdullah Alfarrarjeh, Roger Zimmermann, Seon Ho Kim and Cyrus Shahabi "IEEE International Conference on Multimedia and Expo (ICME), July 2014" 2014.
- [C6] "Frame Selection Algorithms for Automatic Generation of Panoramic Images from Crowdsourced Geo-tagged Videos", Seon Ho Kim, Ying Lu, Junyuan Shi, Abdullah Alfarrarjeh, Cyrus Shahabi, Guanfeng Wang, Roger Zimmermann "Accepted to appear in Web and Wireless Geographical Information Systems (W2GIS)" (W2GIS '14), Seoul, South Korea 2014.
- [C5] "MediaQ: Mobile Multimedia Management System", Seon Ho Kim, Ying Lu, Giorgos Constantinou, Cyrus Shahabi, Guanfeng Wang, Roger Zimmermann "ACM Multimedia Systems" (ACM MMSys '14), Singapore 2014.
- [C4] "Automatic Geotagging and Querying of Indoor Videos", Kim, Joon-Seok and Kim, Seon Ho and Li, Ki-Joune "Proceedings of the Fifth ACM SIGSPATIAL International Workshop on Indoor Spatial Awareness" (ISA '13), Orlando, florida ACM, Pages: 50--53, New York, NY, USA, ISBN: 978-1-4503-2526-4, 2013.
- [C3] "GeoCrowd: Enabling Query Answering with Spatial Crowdsourcing", Leyla Kazemi and Cyrus Shahabi "Proceedings of the 20th International Conference on Advances in Geographic Information Systems" (ACM SIGSPATIAL '12), Redondo Beach, CA, USA 2012.
- [C2] "Automatic Tag Generation and Ranking for Sensor-Rich Outdoor Videos", Zhijie Shen, Sakire Arslan Ay, Seon Ho Kim, Roger Zimmermann "Proceedings of the 19th ACM international conference on Multimedia" (ACM MM '11), New York, NY, USA 2011.
- [C1] "Viewable Scene Modeling for Geospatial Video Search", Sakire Arslan Ay, Roger Zimmermann, Seon Ho Kim "Proceedings of the 16th ACM international conference on Multimedia" (ACM MM '08), Vancouver, Canada ACM New York, Pages: 309-318, NY, USA, ISBN: 978-1-60558-303-7, 2008.