Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes

By Shandong Wu, Brian E. Moore, Mubarak Shah. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

569 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c84462f6cea04ee6301e306e2a2b2a70aeaa7dd3

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

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

A Cause and Effect Analysis of Motion Trajectories for Modeling Actions (2014, methodology): “Using the “particle” concept [29, 28], a pixel in a video frame corresponds to a particle and the motions in the scene are represented quantitatively by the motions of the particles using dense optical flow.”
Generalized Out-of-Distribution Detection: A Survey (2021, unknown): “To alleviate the problem, shallow methods implement feature engineering to reduce the dimensionality [326], [327].”
Fuzzy human motion analysis: A review (2014, background): “In our daily life, anomaly detection is important to infer the abnormal behavior of a person, such as an action or an activity that is not following the routine or deviated from the normal behavior [7,167,168].”
Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes (2016, unknown): “Object trajectory estimation is often of interest in cases of anomaly detection; see [18, 22, 23, 24, 25, 26, 27, 28, 29].”
Video-Based Abnormal Human Behavior Recognition—A Review (2012, unknown): “The authors of [136] used Lagrangian par-”
Crowded Scene Analysis: A Survey (2015, methodology): “For that reason, several optical-ﬂow alike features have been presented in recent years [11]–[13], [22], [53]–[55], these methods avoid tracking from the macroscopic level and have achieved some success in addressing complex crowd ﬂows in the scenes.”
Real-World Anomaly Detection in Surveillance Videos (2018, background): “Beyond violent and non-violent patterns discrimination, authors in [39, 7] proposed to use tracking to model the normal motion of people and detect deviation from that normal motion as an anomaly.”
Future Frame Prediction for Anomaly Detection - A New Baseline (2017, background): “For feature extraction module, early work usually utilizes low-level trajectory features, a sequence of image coordinates, to represent the regular patterns [32][35].”
Sparse reconstruction cost for abnormal event detection (2011, background): “In [26], they define a chaotic invariant to describe the event.”
Abnormal Event Detection at 150 FPS in MATLAB (2013, methodology): “Specifically, in [8, 20], extracted trajectories were utilized by tracking object-of-interest to represent normal patterns.”
Anomaly Detection and Localization in Crowded Scenes (2014, methodology): “These include the modeling of motion patterns with histograms of pixel change [5], histograms of optical flow [19], [8], [20], or optical flow measures [3], [4], [17], [1].”
Video anomaly detection based on local statistical aggregates (2012, methodology): “Quantitative comparison of our algorithm with [8], [16] and [22].”
Abnormal event detection in crowded scenes using sparse representation (2013, methodology): “There are several statistics models, such as Gaussian model, Gaussian Mixture Model (GMM) or Mixture Principle Component Analysis (MPPCA) [16], Hidden Markov Model (HMM) [17], Markov Random Field (MRF) [3] or spatio-temporal MRF [16], Latent Dirichlet Allocation (LDA) [34].”