Multimodal Technologies for Perception of Humans: First International Evaluation Workshop on Classification of Events, Activities and Relationships, CLEAR 2006, Southampton, UK, April 6-7, 2006, Revised Selected Papers

Rainer Stiefelhagen, Keni Bernardin, Rachel Bowers, John Garofolo, Djamel Mostefa (auth.), Rainer Stiefelhagen, John Garofolo (eds.)3540695672, 9783540695677

This book constitutes the thoroughly refereed post-proceedings of the First International CLEAR 2006 Evaluation Campaign and Workshop on Classification of Events, Activities and Relationships for evaluation of multimodal technologies for the perception of humans, their activities and interactions. The workshop was held in Southampton, UK, in April 2006.

The 29 revised full system description papers and one institutional paper presented together with two invited papers were carefully reviewed and selected for inclusion in the book.

CLEAR is an international effort to evaluate systems that are designed to analyze people’s identities, activities, interactions and relationships in human-human interaction scenarios, as well as related scenarios. The papers are organized in topical sections on 3D person tracking, 2D face detection and tracking, person tracking on surveillance data, vehicle tracking, person identification, head pose estimation, acoustic scene analysis, and other evaluations.

---

Table of contents :
Front Matter….Pages –
The CLEAR 2006 Evaluation….Pages 1-44
3D Audiovisual Person Tracking Using Kalman Filtering and Information Theory….Pages 45-54
A Generative Approach to Audio-Visual Person Tracking….Pages 55-68
An Audio-Visual Particle Filter for Speaker Tracking on the CLEAR’06 Evaluation Dataset….Pages 69-80
Multi-and Single View Multiperson Tracking for Smart Room Environments….Pages 81-92
UPC Audio, Video and Multimodal Person Tracking Systems in the Clear Evaluation Campaign….Pages 93-104
A Joint System for Single-Person 2D-Face and 3D-Head Tracking in CHIL Seminars….Pages 105-118
Speaker Tracking in Seminars by Human Body Detection….Pages 119-126
TUT Acoustic Source Tracking System 2006….Pages 127-136
Tracking Multiple Speakers with Probabilistic Data Association Filters….Pages 137-150
2D Person Tracking Using Kalman Filtering and Adaptive Background Learning in a Feedback Loop….Pages 151-160
PittPatt Face Detection and Tracking for the CLEAR 2006 Evaluation….Pages 161-170
The AIT Outdoors Tracking System for Pedestrians and Vehicles….Pages 171-182
Evaluation of USC Human Tracking System for Surveillance Videos….Pages 183-189
Multi-feature Graph-Based Object Tracking….Pages 190-199
Multiple Vehicle Tracking in Surveillance Videos….Pages 200-208
Robust Appearance Modeling for Pedestrian and Vehicle Tracking….Pages 209-215
Robust Vehicle Blob Tracking with Split/Merge Handling….Pages 216-222
A Decision Fusion System Across Time and Classifiers for Audio-Visual Person Identification….Pages 223-232
The CLEAR’06 LIMSI Acoustic Speaker Identification System for CHIL Seminars….Pages 233-240
Person Identification Based on Multichannel and Multimodality Fusion….Pages 241-248
ISL Person Identification Systems in the CLEAR Evaluations….Pages 249-257
Audio, Video and Multimodal Person Identification in a Smart Room….Pages 258-269
Head Pose Estimation on Low Resolution Images….Pages 270-280
Evaluation of Head Pose Estimation for Studio Data….Pages 281-290
Neural Network-Based Head Pose Estimation and Multi-view Fusion….Pages 291-298
Head Pose Estimation in Seminar Room Using Multi View Face Detectors….Pages 299-304
Head Pose Detection Based on Fusion of Multiple Viewpoint Information….Pages 305-310
CLEAR Evaluation of Acoustic Event Detection and Classification Systems….Pages 311-322
The CLEAR 2006 CMU Acoustic Environment Classification System….Pages 323-330
2D Multi-person Tracking: A Comparative Study in AMI Meetings….Pages 331-344
Head Pose Tracking and Focus of Attention Recognition Algorithms in Meeting Rooms….Pages 345-357
Back Matter….Pages –