Event Detection Based on a Pedestrian Interaction Graph Using Hidden Markov Models

@inproceedings{Burkert2011EventDB,
  title={Event Detection Based on a Pedestrian Interaction Graph Using Hidden Markov Models},
  author={Florian Burkert and Matthias Butenuth},
  booktitle={PIA},
  year={2011}
}
In this paper, we present a new approach for event detection of pedestrian interaction in crowded and cluttered scenes. Existing work is focused on the detection of an abnormal event in general or on the detection of specific simple events incorporating only up to two trajectories. In our approach, event detection in large groups of pedestrians is performed by exploiting motion interaction between pairs of pedestrians in a graph-based framework. Event detection is done by analyzing the temporal… 
COMPLEX EVENT DETECTION IN PEDESTRIAN GROUPS FROM UAVS
TLDR
A new hierarchical event detection approach for highly complex scenarios in pedestrian groups on the basis of airborne image sequences from UAVs is presented by using a dynamic pedestrian graph of a scene which contains basic pairwise pedestrian motion interaction labels in the first layer.
Integrating pedestrian simulation, tracking and event detection for crowd analysis
TLDR
Experimental results show the benefit of the integrated framework using simulation and real-world data for crowd analysis.
Estimation of crowd density from UAVs images based on corner detection procedures and clustering analysis
TLDR
A new testing procedure based on feature from accelerated segment test (FAST) algorithms is introduced to detect the crowd features from UAV images taken from different camera orientations and positions and the results show that the proposed algorithms are able to extract crowd Features from different UAV pictures.
Visualizing Crowd Movement Patterns Using a Directed Kernel Density Estimation
TLDR
This paper investigates how to display dynamic densities (and the density changes) to identify movement patterns and investigates the application of directed kernel density estimation (DKDE).
Towards multi-layer pedestrian behaviour maps for simulation, tracking, interpretation and indoor navigation
This paper describes the concept of multi-layer pedestrian behaviour maps, their creation through the application of different computational technologies, as well as their usage for different

References

SHOWING 1-10 OF 14 REFERENCES
Trajectory Classification Using Switched Dynamical Hidden Markov Models
TLDR
The ability of the approach to properly describe trajectories with sudden changes is shown, with real data from two different scenarios: a shopping center and a university campus, as well as a set of human activities in both scenarios is successfully recognized.
Event Detection by Eigenvector Decomposition Using Object and Frame Features
  • F. Porikli, T. Haga
  • Computer Science
    2004 Conference on Computer Vision and Pattern Recognition Workshop
  • 2004
TLDR
An event detection framework that has two significant advantages over past work: an extended set of time-wise and object-wise statistical features including not only the trajectory coordinates but also the histograms and HMM based representations of object's speed, orientation, location, size, and aspect ratio and a spectral clustering algorithm that can automatically estimate the optimal number of clusters.
Hidden Markov Models for Optical Flow Analysis in Crowds
TLDR
The results with simulated crowds show the effectiveness of the proposed approach on detecting abnormalities in dense crowds, and in order to increase the detection sensitivity a local modelling approach is used.
Abnormal crowd behavior detection using social force model
TLDR
A novel method to detect and localize abnormal behaviors in crowd videos using Social Force model and it is shown that the social force approach outperforms similar approaches based on pure optical flow.
Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors
TLDR
A novel algorithm for detection of certain types of unusual events based on multiple local monitors which collect low-level statistics that is robust and works well in crowded scenes where tracking-based algorithms are likely to fail.
Learning object motion patterns for anomaly detection and improved object detection
TLDR
The proposed method provides a new higher-level layer to the traditional surveillance pipeline for anomalous event detection and scene model feedback and successfully used the proposed scene model to detect local as well as global anomalies in object tracks.
A system for learning statistical motion patterns
TLDR
Experimental results show the robustness of the tracking algorithm, the efficiency of the algorithm for learning motion patterns, and the encouraging performance of algorithms for anomaly detection and behavior prediction.
Social force model for pedestrian dynamics.
  • Helbing, Molnár
  • Physics
    Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics
  • 1995
TLDR
Computer simulations of crowds of interacting pedestrians show that the social force model is capable of describing the self-organization of several observed collective effects of pedestrian behavior very realistically.
People trajectory mining with statistical pattern recognition
  • S. Calderara, R. Cucchiara
  • Computer Science
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
  • 2010
TLDR
A statistical framework for trajectories mining that analyzes, in an integrated solution, several aspects of the trajectories such as location, shape and speed properties and demonstrates the efficacy of the framework in clustering people trajectories with the purpose of analyze frequent behaviors in complex environments.
...
1
2
...