We use proprietary and third party's cookies to improve your experience and our services, identifying your Internet Browsing preferences on our website; develop analytic activities and display advertising based on your preferences. If you keep browsing, you accept its use. You can get more information on our Cookie Policy
Cookies Policy
SAFECITY.Story.DATA/CONTEXT MANAGEMENT.Data.MultimediaAnalysis.PatternRecognition - FIWARE Forge Wiki

SAFECITY.Story.DATA/CONTEXT MANAGEMENT.Data.MultimediaAnalysis.PatternRecognition

From FIWARE Forge Wiki

Jump to: navigation, search
Name PatternRecognition
Goal To allow during the training/learning phase the generation of optimal visual data models (face identities, object models, movement pattern models, etc.), that will assist and speed up the detection phase
Description Both classification (SVM, LVQ, etc.) and clustering (density-based, etc.) algorithms will formulate a pattern recognition engine that will be used, having as input visual feature vectors (single or combined), to either produce object, behaviour or primitive event models during the training phase of supervised learning algorithms using training video data from prior threatening events, or generate clusters of such entities using video data from prior threatening events for which respective apriori knowledge does not exist, or detect and identify during the testing phase of both classification or clustering algorithms the situation hint (object, primitive event or behaviour) during the overall process of situation insights generation. The modeling phase generates behavioural models and detected patterns in visual data from previous similar public safety threat events in archived video feeds, while the detection phase is assisted by them to identify the exact detected object or primitive event/behaviour in the currently monitored video feed.
Version 1.0 Source Athens Information Technology - AIT, Sofia Tsekeridou
Scope Platform Epic {{{Epic}}} Theme
Status Pending MoSCoW priority MST Relative priority
Chapter Data/Context Management, Enabler Multimedia Analysis
Stakeholder Owner Athens Information Technology - AIT, Sofia Tsekeridou
Complexity Rationale

Personal tools
Create a book