Presentation 2013-12-13
Video Surveillance Technology for the Age of Big Data : An introduction to MoonCafe Project
Shihong LAO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, not only surveillance cameras, but also driver recorders and smart phones have been bringing us more and more video data which are expected to be useful for criminal investigation. In the meantime, it becomes more and more difficult for us to check all the data manually. MoonCafe project is aimed at providing useful video analyzing technology for surveillance. The main research subjects are face or human detection and recognition. Face recognition is expected to play an important role in video surveillance to detect the criminals automatically, but in practice the performance is still not good enough due to the various poses, bad lighting conditions and low resolution. We have improved the robustness of the face recognition and human re-identification by adding pre-processing techniques and training with data of different conditions. By using our high speed human detection technology, we have developed a video browsing tool for indexing and checking the people recorded in the video. This tool can greatly improve the efficiency of the manual work of criminal investigation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) face recognition / human detection / human re-identification
Paper # PRMU2013-84
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/12/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Video Surveillance Technology for the Age of Big Data : An introduction to MoonCafe Project
Sub Title (in English)
Keyword(1) face recognition
Keyword(2) human detection
Keyword(3) human re-identification
1st Author's Name Shihong LAO
1st Author's Affiliation OMRON SOCIAL SOLUTIONS Co., Ltd()
Date 2013-12-13
Paper # PRMU2013-84
Volume (vol) vol.113
Number (no) 346
Page pp.pp.-
#Pages 5
Date of Issue