Learning context for collective activity recognition
Authors:
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3273-3280
Abstract
In this paper we present a framework for the recognition of collective human activities. A collective activity is defined or reinforced by the existence of coherent behavior of individuals in time and space. We call such coherent behavior `Crowd Context'. Examples of collective activities are “queuing in a line” or “talking”. Following, we propose to recognize collective activities using the crowd context and introduce a new scheme for learning it automatically. Our scheme is constructed upon a Random Forest structure which randomly samples variable volume spatio-temporal regions to pick the most discriminating attributes for classification. Unlike previous approaches, our algorithm automatically finds the optimal configuration of spatio-temporal bins, over which to sample the evidence, by randomization. This enables a methodology for modeling crowd context. We employ a 3D Markov Random Field to regularize the classification and localize collective activities in the scene. We demonstrate the flexibility and scalability of the proposed framework in a number of experiments and show that our method outperforms state-of-the art action classification techniques.Keywords
This publication has 25 references indexed in Scilit:
- A discriminatively trained, multiscale, deformable part model2008
- Progressive search space reduction for human pose estimation2008
- A mobile vision system for robust multi-person tracking2008
- Scene Segmentation for Behaviour Correlation2008
- Tensor Canonical Correlation Analysis for Action Classification2007
- Learning, detection and representation of multi-agent events in videosArtificial Intelligence, 2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Hybrid Models for Human Motion Recognition2005
- The pyramid match kernel: discriminative classification with sets of image features2005
- Markov random field models in computer vision1994