Online Identification of Primary Social Groups

@inproceedings{Matsiki2014OnlineIO,
  title={Online Identification of Primary Social Groups},
  author={Dimitra Matsiki and Anastasios Dimou and Petros Daras},
  booktitle={MMM},
  year={2014}
}
Online group identification is a challenging task, due to the inherent dynamic nature of groups. In this paper, a novel framework is proposed that combines the individual trajectories produced by a tracker along with a prediction of their evolution, in order to identify existing groups. In addition to the widely known criteria used in the literature for group identification, we present a novel one, which exploits the motion pattern of the trajectories. The proposed framework utilizes the past… 

References

SHOWING 1-10 OF 16 REFERENCES

Probabilistic group-level motion analysis and scenario recognition

TLDR
This work builds on a mature multi-camera multi-target person tracking system that operates in real-time and derives probabilistic models to analyze individual track motion as well as group interactions to recognize group interactions without making hard decisions about the underlying group structure.

Vision-Based Analysis of Small Groups in Pedestrian Crowds

TLDR
This work automatically detects small groups of individuals who are traveling together by bottom-up hierarchical clustering using a generalized, symmetric Hausdorff distance defined with respect to pairwise proximity and velocity.

Using Film to Analyze Pedestrian Behavior

TLDR
An alternative theoretical framework and methodological procedure for the imposition of cartesian coordinates on a film record, corrected for “foreshortened perspective,” permits the accurate location, and systematic measurement of distances between, directions, and velocities of individual pedestrian movement.

Non-parametric motion-priors for flow understanding

TLDR
A novel method for extracting the dominant dynamic properties of crowded scenes from a single, static, uncalibrated camera using a codebook of tracklets and modifying a state-of-the-art multiple object tracking algorithm leading to significant improvement is presented.

Mining Paths of Complex Crowd Scenes

TLDR
This paper describes a relatively inexpensive technique that does not require the use of conventional trackers to identify the main paths of highly cluttered scenes, approximating them with spline curves.

Tracking Groups of People for Video Surveillance

TLDR
A method for tracking groups of people in a metro scene to recognise abnormal behaviours such as violence or van-dalism is proposed and results illustrating the algorithm are presented.

Who are you with and where are you going?

TLDR
This model views pedestrians as decision-making agents who consider a plethora of personal, social, and environmental factors to decide where to go next and forms prediction of pedestrian behavior as an energy minimization on this model.

Tracking in unstructured crowded scenes

TLDR
This work proposes to model various crowd behavior (or motion) modalities at different locations of the scene by employing Correlated Topic Model (CTM) of [16], and enables a diverse set of unstructured crowd domains which range from cluttered time-lapse microscopy videos of cell populations in vitro, to footage of crowded sporting events.

Crowd detection in video sequences

TLDR
A scheme that looks at the motion patterns of crowd in the spatio-temporal domain and gives an efficient implementation that can detect crowd in real-time that detects moving crowd in a video sequence.

ClassCut for Unsupervised Class Segmentation

We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object instances and learning a class model. The method is based on a segmentation