A probabilistic framework for representing and visually recognizing complex multi-agent action is presented. Motivated by work in model-based object recognition and designed for the recognition of action from visual evidence, the representation has three components: (1) temporal structure descriptions representing the logical and temporal relationships between agent goals, (2) belief networks for probabilistically representing and recognizing individual agent goals from visual evidence, and (3) belief networks automatically generated from the temporal structure descriptions that support the recognition of the complex action. We describe our current work on recognizing American football plays from noisy trajectory data. 1
|
4387
|
Probabilistic Reasoning in Intelligent Systems
– Pearl
- 1988
|
|
1875
|
Artificial Intelligence: A Modern Approach
– Russell, Norvig
- 1995
|
|
1705
|
Maintaining Knowledge about Temporal Intervals
– Allen
- 1983
|
|
582
|
An Introduction to Bayesian Networks
– Jensen
- 1996
|
|
326
|
Collaborative plans for complex group action
– Grosz, Kraus
- 1996
|
|
297
|
Object Recognition by Computer: The Role of Geometric Constraints
– Grimson
- 1990
|
|
235
|
A Bayesian model of plan recognition
– Charniak, Goldman
- 1993
|
|
156
|
Generalized plan recognition
– Kautz, Allen
- 1986
|
|
131
|
Localizing overlapping parts by searching the interpretation tree
– Grimson, Lozano-Pérez
- 1987
|
|
84
|
Agent architectures for flexible, practical teamwork
– Tambe
- 1997
|
|
74
|
The BATmobile: Towards a Bayesian automated taxi
– Forbes, Huang, et al.
- 1995
|
|
63
|
Tracking dynamic team activity
– Tambe
- 1996
|
|
62
|
The automated mapping of plans for plan recognition
– Huber, Durfee, et al.
- 1994
|
|
57
|
Accounting for context in plan recognition, with application to traffic monitoring
– Pynadath, Wellman
- 1995
|
|
56
|
From image sequences towards conceptual descriptions
– Nagel
- 1988
|
|
48
|
Automatic symbolic traffic scene analysis using belief networks
– Huang, Koller, et al.
- 1994
|
|
39
|
action: The role of knowledge in the perception of motion
– Movement
- 1997
|
|
39
|
Advanced Visual Surveillance using Bayesian Networks
– Buxton, Gong
- 1995
|
|
28
|
Model-Based influence diagrams for machine vision
– Levitt, Agosta, et al.
- 1990
|
|
26
|
The Computational Perception of Scene Dynamics
– Mann, Jepson, et al.
- 1996
|
|
26
|
Where to look next using a Bayes net: Incorporating geometric relations
– Rimey, Brown
- 1992
|
|
20
|
Closed-world tracking
– Intille, Bobick
- 1995
|
|
16
|
Probabilistic Temporal Reasoning with Endogenous Change
– Hanks, Madigan, et al.
- 1995
|
|
15
|
Agent orientated annotation in model based visual surveillance
– Remagnino, Tan, et al.
- 1998
|
|
11
|
Multi-agent mental-state recognition and its application to air-combat modelling
– Rao, Murray
- 1994
|
|
11
|
A REPLAI of SOCCER: Recognizing Intentions in the Domain of Soccer Games
– Retz-Schmidt
- 1988
|
|
11
|
The structure of bayes networks for visual recognition
– Agosta
- 1990
|
|
8
|
Template-based multi-agent plan recognition for tactical situation assessment
– Azarewicz, Fala, et al.
- 1989
|
|
6
|
Plan-Based Plan Recognition Models for the Effective Coordination of Agents Through Observation
– Huber
- 1996
|
|
6
|
Association of situation graphs with temporal variations in image sequences
– Nagel, Kollnig, et al.
- 1995
|
|
1
|
Association of motion verbs with vehcile movements extracted from dense optical flow fields
– Kollnig, Nagel, et al.
- 1994
|
|
