Home of Prime Project

	Personalized Video Reporting System for Intelligent Multiview Environment
1.Introduction
The PRIME project targets at providing a solution for automatic generation of informative and personalized field video reports for future intelligent multiview environments, e.g. surveillance, which is supported by the MEXT Grant-in-Aid for Young Scientists (B) No.23700110 from year 2011 to 2014. In this page, we will record the whole research/ development progress of this project.
Promotion Video for Innovation Japan 2013!

2.Dataset
Here is A Multi-view Video Database we collected using a camera network installed inside JAIST. We will first start our research activities based on this database.		Inquiry on the DB!

Fig.1 Sample image of the JAIST MVS database
3.Tasks, Methods, and Results
3.1 Object Tracking and Event Detection
3.1.1 Multi-view Scene Reconstruction


Oct. 19, 2011: Latest Results of Our Methods for Robust 3D Reconstruction. [APSIPA ASA'11]

3.1.2 Multi-view Multi-object Tracking

Jan. 20, 2012: Methods of Multi-object Tracking from Trajectory Grouping [ICIP 2012]

Nov. 15, 2012: Methods of Multi-object Tracking by Tracking after Detection [RO-MAN 2013]


3.1.3 Hot-spot Event Detection


Apr. 05, 2012: Detection of Group Interactions [ICASSP'13 (Accepted)]

3.2 Automatic Camera Planning
3.2.1 Game Camerawork and Movie Camerawork
3.2.2 Optimal Virtual Camera Position
3.3 Multi-view Video Summarization
3.3.1 Video Summarization via Trajectory Selection
3.3.2 Adaptive Fast-forwarding for Video Summarization


Jul. 11, 2011: Adaptive Fast-forwarding Validated on Sport Videos. [ICME 2011, Spain]
Oct. 25, 2012: Help us finish a subjective evaluation! [Part I]
Nov. 05, 2012: Check the first batch of results for the above subjective evaluation.
Nov. 11, 2012: Surveillance Video Segmentation based on Detected Hot-spots
Jan. 21, 2013: Help us finish a subjective evaluation! [Part II] [English Ver.][日本語版][中文版]
Jan. 25, 2013: Help us finish a subjective evaluation! [Part III] [English Ver.][日本語版][中文版]
Mar. 12, 2013: Resource Allocation Summarization Framework [TMM Supplementals](Accepted)

3.4 Interactive Operational Interface
3.4.1 Interface Design (Envisioned)

3.4.2 Optimal Online Adaptation

Jan. 21, 2013: Automatic Generation of Personalized Field Reports.

4.Related Publications(Full Publication List)
n) F. Chen, "Techniques for Surveillance Video Analysis- from Scene Understanding to Content Presentation", Inspection Engineering, Japan Industrial Publishing, Feb., 2014, (Japanese Version Only)] m) F. Chen, C. De Vleeschouwer, and A.Cavallaro, "Resource Allocation for Personalized Video Summarization," IEEE Transactions on Multimedia, 16(2), pp.455-469, 2014. l) T.T. Tran, F. Chen, K. Kotani and Bac Le Hoai, "Extraction of Discriminative Patterns from Skeleton Sequences for Accurate Action Recognition," Fundamenta Informaticae, (Accepted), 2013. k) T.T. Tran, F. Chen, K. Kotani and Bac Le Hoai, "An Apriori-like Algorithm for Automatic Extraction of the Common Action Characteristics," The IEEE Visual Communications and Image Processing (VCIP) 2013,(Accepted) 2013. j) F. Chen, "Multi-sensored Vision for Autonomous Production of Personalized Video Content," Malaysia-Japan Workshop for Advanced Technology in Information and Knowledge, June. 2013. i) F. Chen, and C. De Vleeschouwer, Personalized Summarization of Broadcasted Soccer Videos with Adaptive Fast-forwarding, 5th International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN) 2013, 2013. h) F. Chen, "Hot-spot Detection by Group Interaction Extraction from Trajectories," The 22nd IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN) 2013, Paper 66. 2013. g) F. Chen and A. Cavallaro, "Detecting Group Interactions by Online Association of Trajectory Data," ICASSP 2013, Paper 2093. 2013.[Sponsored by The Telecommunications Advancement Foundation Grant for Overseas Travel] f) Thang Tran Thanh, F. Chen, K. Kotani and Bac Le Hoai, "Automatic Extraction of Common Action Characteristics," ISSPIT 2012, 2012. e) F. Chen and C. De Vleeschouwer, "Partial Motion Trajectory Grouping Through Rooted Arborescence," ICIP 2012, Paper 2511. 2012. d) T.T. Tran, F. Chen, K. Kotani and Bac Le Hoai, "Extraction of Discriminative Patterns from Skeleton Sequences for Human Action Recognition," RIVF 2012, Paper 41. 2012. c) F. Chen, D. Delannay and C. De Vleeschouwer, "An autonomous framework to produce and distribute personalized team-sport video summaries: a basket-ball case study," IEEE Transcations on Multimedia, 13(6), pp.1381-1394, 2011. b) F. Chen and C. De Vleeschouwer, "Robust Volumetric Reconstruction from Noisy Multi-view Foreground Occupancy Masks," APSIPA ASC 2011, Paper 61. 2011. [PDF] a) F. Chen and C. De Vleeschouwer, "Automatic Summarization of Broadcasted Soccer Videos with Adaptive Fast-forwarding," Int'l Conf. on Multimedia & Expo(ICME) 2011, Paper No.300, 2011.

5. Patents and Exhibitions(Full Publication List)
c) F. Chen, "監視システムにおける監視画像の統合、閲覧及び配信方法," Innovation Japan 2013, Aug.29-30, 2013. b) F. Chen, "映像監視システム、映像処理サーバ及び監視映像の閲覧・配信方法 (A Video Surveillance System and A Method for Browsing and Broadcasting Video Content)," 特願2013-067773, Mar.28, 2013. a) F. Chen, "異種端末向けの個人化ビデオ配信サービス," 北陸技術交流テクノフェア2011, Oct.20-21, 2011.

6.Related Links
Author's Homepage
Results on Action Recognition
Jaist Homepage

Extra Information
Note: All demo videos are encoded in xvid mpeg 4 format. If you could not replay the demo video, please download the latest vlc media player for your os or other proper players.		Get VLC Media Player

Maintained by chen-fan AT jaist.ac.jp. Created on 2011-6-9. Last update 2013-06-02

Personalized Video Reporting System for Intelligent Multiview Environment