Proceedings Article10.1109/ICCV.2001.937608
Multi-agent event recognition
Somboon Hongeng,Ramakant Nevatia +1 more
- 07 Jul 2001
- Vol. 2, pp 84-91
207
TL;DR: This paper presents a new approach to recognizing multiagent events observed by a static camera by propagating the constraints and likelihoods of event threads in a temporal logic network.
read more
Abstract: This paper presents a new approach to recognizing multiagent events observed by a static camera. To track objects robustly, knowledge about the ground plane and the events is used. An event is considered as composed of action threads, each thread being executed by a single actor. A single thread of action is recognized from the characteristics of the trajectory and moving blob of the actor using Bayesian methods. A multi-agent event is represented by a number of action threads related by temporal constraints. Multi-agent events are recognized by propagating the constraints and likelihoods of event threads in a temporal logic network.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Dissertation
Segmentation, recognition, and alignment of collaborative group motion
Ruonan Li
- 01 Jan 2011
TL;DR: This dissertation aims to investigate the role of recognition, recognition, and alignment in the development of collaborative group mode in the context of a game-theoretic framework.
1
•Proceedings Article
Fusion framework for video event recognition
Qiao Ma,Baptiste Fosty,Carlos Crispim-Junior,Inria Sophia Antipolis,Sophia Antipolis +4 more
- 12 Feb 2013
TL;DR: In this article, a multisensor fusion framework for video activities recognition based on statistical reasoning and D-S evidence theory is presented, which consists in the combination of the events' uncertainty computation with the trained database and the fusion method based on the conflict management of evidences.
1
Review for Team's Behavior Recognition
Fu Yu,Wang Zhiwen +1 more
TL;DR: This paper in detail analyze and summarize the existing research achievements in the area of the team's behavior recognition from four aspects of target tracking and detection, representation of behavior, construction of classification and behavior recognition.
1
•Dissertation
Representing and recognizing temporal sequences
Aaron F. Bobick,Yifan Shi +1 more
- 01 Jan 2006
TL;DR: Comparisons with standard SCFG and HMM prove a P-Net based system is easier to construct and has a superior ability to classify complex human activity and detect anomaly.
Classifier Boosting for Human Activity Recognition
Raffay Hamid
- 01 Jan 2012
TL;DR: The ability to visually infer human activities happening in an environment is becoming increasingly important due to the tremendous practical applications it offers and systems that can automatically recognize human activities can potentially help in monitoring people's health as they age, and to fight crime through improved surveillance.
1
References
Detecting and tracking moving objects for video surveillance
Isaac Cohen,Gerard Medioni +1 more
- 23 Jun 1999
TL;DR: The proposed tracker allows to deal with partial occlusions, stop and go motion in very challenging situations and demonstrates results on a number of different real sequences.
266
Action recognition using probabilistic parsing
Aaron F. Bobick,Yuri A. Ivanov +1 more
- 23 Jun 1998
TL;DR: A new approach to the recognition of temporal behaviours and activities is presented that provides techniques for generating a discrete symbol stream from continuous low level detectors and for enforcing temporal exclusion constraints during parsing.
Representation and optimal recognition of human activities
Somboon Hongeng,Francois Bremond,Ramakant Nevatia +2 more
- 13 Jun 2000
TL;DR: Towards the goal of realizing a generic automatic human activity recognition system, a new formalism is proposed using a chained hierarchical representation using three type of entities: image features, mobile object properties and scenarios.
105
Video sequence interpretation for visual surveillance
N. Rota,M. Thonnat +1 more
TL;DR: A framework based on two kinds of a priori knowledge: predefined scenarios and contextual information is proposed that has been applied on video sequences of the AVS-PV visual surveillance European project.
Visual recognition of multi-agent action using binary temporal relations
Stephen S. Intille,Aaron F. Bobick +1 more
- 23 Jun 1999
TL;DR: The current work on recognizing American football plays from noisy trajectory data is described, and a probabilistic framework for representing and visually recognizing complex multi-agent action is presented.
25