Quantifying and Detecting Collective Motion in Crowd Scenes
- 9 April 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 5571-5583
Abstract
People in crowd scenes always exhibit consistent behaviors and form collective motions. The analysis of collective motion has motivated a surge of interest in computer vision. Nevertheless, the effort is hampered by the complex nature of collective motions. Considering the fact that collective motions are formed by individuals, this paper proposes a new framework for both quantifying and detecting collective motion by investigating the spatio-temporal behavior of individuals. The main contributions of this work are threefold: 1) an intention-aware model is built to fully capture the intrinsic dynamics of individuals; 2) a structure-based collectiveness measurement is developed to accurately quantify the collective properties of crowds; 3) a multistage clustering strategy is formulated to detect both the local and global behavior consistency in crowd scenes. Experiments on real world data sets show that our method is able to handle crowds with various structures and time-varying dynamics. Especially, the proposed method shows nearly 10% improvement over the competitors in terms of NMI, Purity and RI. Its applicability is illustrated in the context of anomaly detection and semantic scene segmentation.Keywords
Funding Information
- National Natural Science Foundation of China (U1864204, 61773316, U1801262, 61871470, 61761130079)
This publication has 49 references indexed in Scilit:
- Measuring Crowd CollectivenessIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Colour, texture, and motion in level set based segmentation and trackingImage and Vision Computing, 2010
- Collective Information Processing and Pattern Formation in Swarms, Flocks, and CrowdsTopics in Cognitive Science, 2009
- Interaction ruling animal collective behavior depends on topological rather than metric distance: Evidence from a field studyProceedings of the National Academy of Sciences, 2008
- A tutorial on spectral clusteringStatistics and Computing, 2007
- A human-computer interactive method for projected clusteringIEEE Transactions on Knowledge and Data Engineering, 2004
- THE FLOW OF HUMAN CROWDSAnnual Review of Fluid Mechanics, 2003
- Flocks, herds and schools: A distributed behavioral modelACM SIGGRAPH Computer Graphics, 1987
- AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHMJournal of Time Series Analysis, 1982
- Objective Criteria for the Evaluation of Clustering MethodsJournal of the American Statistical Association, 1971