250 likes | 385 Views
Digital Video Library. Experience in Large Scale Content Management VIEW Technologies Symposium – CUHK – August 2002 Howard Wactlar Carnegie Mellon University, USA. Acquisition. Distribution. Analysis and Organization. ………………………. Digital Compression. ………………………. Broadcast TV. Radio.
E N D
Digital Video Library Experience in Large Scale Content Management VIEW Technologies Symposium – CUHK – August 2002 Howard Wactlar Carnegie Mellon University, USA
Acquisition Distribution Analysis and Organization ………………………. Digital Compression ………………………. Broadcast TV Radio Surveillance PDA Cell Phone Speech Recognition Image Analysis Natural Language Interpretation 0 1 1 1 0 1 0 1 0 0 0 1 1 0 …… …… …… …… …… …… …… …… Segmentation Cable Database Satellite Internet Training Film Video Life Cycle
Informedia Overview Establishment of large video libraries as a network searchable information resource Mission: Enable Search and Discovery in the Video Medium REQUIREMENTS: • Automated process for information extraction from video • Full-content search and retrieval from all spoken language and visual documents • APPROACH: • Integration of machine speech, image and natural language understanding for library creation and exploration
Sample Corpora CNN News Broadcasts 1997-2002 (2050 hours) • 68,000 segments/stories • 1.7 Million “shots” • China Historical and Cultural Documentaries (100 hours) • English language • Western perspective
Recognizing Scene Text and Faces Scene Text Detection
Understanding Speech in Natural Settings Style Variations careful, clear, articulated, formal, casual spontaneous, normal, read, dictated, intimate Voice Quality breathy, creaky, whispery, tense, lax, modal Speaking Rate normal, slow, fast, very fast Context sport, professional, interview, free conversation, man-machine dialogue Stress in noise, with increased vocal effort (Lombard reflex), emotional factors (e.g. angry), under cognitive load
Gathering Information with Faulty Technology • Retrieval performance in the presence of inaccuracy and ambiguity in the underlying cognitive processing • Approximate match in meaning and visualization • Presentation and reuse of library content • New data type with space and time dimensions • Restricted use intellectual property • Interoperability in the absence of standards
Annual Video and Audio Production Commercial • 4500 motion pictures -> 9,000 hours/year (4.5 TB) • 33,000 TV stations x 4 hrs/day -> 48,000,000 hrs/yr (24,000 TB) • 44,000 radio stations x 4 hrs/day -> 65,500,000 hrs/yr (3,275 TB) Personal • Photographs: 80 billion images -> 410,000 TB/yr • Home videos: 1.4 billion tapes -> 300,000 TB/yr • X-rays: 2 billion -> 17,000 TB/yr Surveillance • Airports: 14,000 terminals x 140 cameras x 24 hrs/day -> 48 M hrs/day
Annual Print Production Commercial • 22,600 newspapers x 30 pgs/day -> 124 TB/year • 80,000 periodicals x 5,000 pgs/yr -> 52 TB/yr • 40,000 scholarly journals x 1,700 pgs/yr -> 9 TB/yr
Video Visualization ____ Summarizing and Visualizing the Result Set
Summarizing Thousands of VideosExample: Map Collage Drought Drought North Pacific Ocean South Pacific Ocean Fire Floods Map collage summarizing “El Niño effects” showing distribution by nation with overlaid thumbnails
The Need for Visualization Strategies • As digital video assets grow, so do possible result sets • We transmit with limited bandwidths to limited screen “real estate” • As automated processing improves, more metadata enables more dimensions and interfaces into the video content • Users want to apply multiple perspectives interchangeably • Direct manipulation interfaces are required to place the user in control
Video Digests Overview first, zoom and filter, then details-on-demand • Concatenate scene elements into a single panoramic view • Visualize word-based relationships • Establish timelines showing trends against time • Present maps (or diagrams) showing geographic (or spatial) correlations • Combine digests into a single view or animated into a temporal presentation (the auto-documentary)
Metadata Extractor Summarizer Content-based Metadata Extraction Enables Video Visualization and Summarization People Event Affiliation Location Topics Time Personalized Presentation User Perspective Templates
Information Goals • Generate information perspectives on-demand: • e.g., by time, location, personalities, events • Eliminate redundancy • Link all the way back to source content to interactively and dynamically provide any level of detail and summarization • Communicate results
Knowledge Goals • Detect trends • Reveal relationships • Infer causality • Discover anomalies • ….
Acquisition Distribution Analysis and Organization ………………………. Digital Compression ………………………. Broadcast TV Radio Surveillance PDA Cell Phone Speech Recognition Image Analysis Natural Language Interpretation 0 1 1 1 0 1 0 1 0 0 0 1 1 0 …… …… …… …… …… …… …… …… Segmentation Cable Database Satellite Internet Training Film Video Life Cycle $$ $$
Application Space Consumer and Business • Evolving and archived news and information • Education and training • Sports and entertainment • Interactive television • Personal memory aids Professional and Enterprise • Conventions and tradeshows • Meetings/corporate memory
Digital Video Library Thank you