Modelling Crowd Scenes for Event Detection

By Ernesto L. Andrade, Scott Blunsden, Robert B. Fisher. International Conference on Pattern Recognition, 2006

308 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/54cf4e85cea0f6f1ec8b3fa318cb2c488a5a7f79

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yang Cong
2. Junsong Yuan
3. Ji Liu
4. Mubarak Shah
5. Shandong Wu
6. Brian E. Moore
7. Cláudio Rosito Jung
8. Julio C. S. Jacques Junior

In Computer Vision and Pattern Recognition

1. Junsong Yuan
2. Yang Cong
3. Mubarak Shah
4. Ji Liu
5. Luc Van Gool
6. Jiaya Jia
7. Xiaogang Wang
8. Nicu Sebe

In Signal Processing

1. Shandong Wu
2. Brian E. Moore
3. Julio C. S. Jacques Junior
4. Soraia Raupp Musse
5. Alexis Oyama
6. Cláudio Rosito Jung
7. Ramin Mehran
8. Antonio Fernández-Caballero

Citations in the corpus

• Crowd Analysis Using Computer Vision Techniques (2010, methodology): “In fact, computer graphics have been used to train or validate computer vision algorithms [9], [10], and in particular, crowd synthesis approaches have been explored to validate crowd analysis algorithms [11], [41], [2].”
• Abnormal event detection in crowded scenes using sparse representation (2013, methodology): “[10] use unsupervised feature extraction to encode normal crowd behaviour.”
• Crowd analysis: a survey (2008, background): “[6–8] characterize crowd behaviour by observing the crowd optical flow associated with the crowd and use unsupervised feature extraction to encode normal crowdbehaviour.”
• Abnormal crowd behavior detection using social force model (2009, methodology): “[15] proposed a method for event detection in the crowd scene using HMM.”
• Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models (2009, methodology): “Flow-based approaches have modeled motion deviations in the form of HMMs [3] or Baye’s classifiers [4] to represent sparse human motion.”
• Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes (2010, methodology): “Limiting our review of the literature to work directly related to analysis of crowded scenes, common features used for modeling crowded motions include optical flow [9, 10, 11, 12], gradient [13], spatiotemporal volume [14], etc.”
• A survey of video datasets for human action and activity recognition (2013, methodology): “The BEHAVE project has published several works using this dataset with a focus on crowd analysis, such as event detection [16,17,20], simulation and modelling of crowd problems [15,20], optical flow anomalies [18,19] and multiagent activities recognition [27].”