Detecting Abnormal Behavioral Patterns in Crowd Scenarios

Mousavi, Hossein; Galoogahi, Hamed Kiani; Perina, Alessandro; Murino, Vittorio

doi:10.1007/978-3-319-31053-4_11

Cited by 15 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…of IMF is designated k 2 , and it was expressed earlier in (14). Different interaction behaviors of people in the group results in varying values of k 2 .…”

Section: Parameter K 2 For Imf the Internal Parametermentioning

confidence: 99%

Group activity recognition with an interaction force based on low‐level features

Wateosot

Suvonvorn

2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Group activity recognition of humans is an important task for video surveillance systems. In complex situations, however, ambiguities usually arise as a result of chaotic movements in the scene, especially when it is solved based upon motion trajectory analysis involving object segmentation and tracking. In this work, we present an interaction force model (IFM) to recognize group activity using low‐level feature based on dense optical flow. The IFM used to define interaction among people consists of three principal forces: group motion force (GMF), interaction motion force (IMF), and reciprocal motion force (RMF), to model the behaviors of the activity. Our algorithm is evaluated using the well‐known NUS‐HGA and BEHAVE datasets. Results of our approach reveal good efficiency with high accuracy, regardless of the surrounding conditions, and is competitive with other state‐of‐the‐art methods. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

“…of IMF is designated k 2 , and it was expressed earlier in (14). Different interaction behaviors of people in the group results in varying values of k 2 .…”

Section: Parameter K 2 For Imf the Internal Parametermentioning

confidence: 99%

Group activity recognition with an interaction force based on low‐level features

Wateosot

Suvonvorn

2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…high-density crowds, occlusion and shadowing, and low resolutions). Recently, Mousavi et al proposed the HOT (Histogram of Oriented Tracklets) descriptor that merges orientation and magnitude into 2D histograms [8], and it is mainly used to recognize abnormal behaviors (e.g. panic and violence).…”

Section: Manuscriptmentioning

confidence: 99%

“…The difficulty in obtaining complete trajectories can be alleviated by putting together a set of fragments of motion features (named tracklets) tracked within a short period of time continuously to form a longer trajectory. In order to balance the tracking time and the computational performance of traditional KLT operations, tracklets are usually extracted from dense feature points (corner points) using specific mechanisms to enforce the spatio-temporal coherence between tracklets [16].…”

Section: Trajectory Trackingmentioning

confidence: 99%

Dual-channel CNN for efficient abnormal behavior identification through crowd feature engineering

Lü

et al. 2018

Machine Vision and Applications

View full text Add to dashboard Cite

His current research interests include distributed control algorithms, distributed information fusion, cooperative control, model predictive control, and machine learning. He has published more than 180 papers in international conferences and journals. His research has been supported by Royal Society, EPSRC, EU FP7, British Council, and industries. He is a board member of International Journal of Model, Identification, and Control, Cognitive Computations, Intelligent Industrial Systems, and Frontiers Robotics and AI. He served as a member of organizing committee and programme committee for many international conferences. Prof. Gu is a senior member of IEEE.

show abstract

“…It is based on the assumption that individual objects in a crowded scene are often too small to be identified or of any major values for crowd monitoring purpose. For example, Mousavi proposed the HOT (Histogram of Oriented Tracklets) descriptor that merges orientation and magnitude of mid-level features [4]. These mid-level features are acquired by Kanade-Lucas-Tomasi Tracking (KLT) algorithm that can re-initialize the detection of salient points for augmenting the target features of crowd behaviors.…”

Section: Introductionmentioning

confidence: 99%

Towards Intelligent Crowd Behavior Understanding Through the STFD Descriptor Exploration

Lü

et al. 2018

Sens Imaging

View full text Add to dashboard Cite

Realizing the automated and online detection of crowd anomalies from surveillance CCTVs is a research-intensive and application-demanding task. This research proposes a novel technique for detecting crowd abnormalities through analyzing the spatial and temporal features of input video signals. This integrated solution defines an image descriptor (named spatio-temporal feature descriptor-STFD) that reflects the global motion information of crowds over time. A CNN has then been adopted to classify dominant or large-scale crowd abnormal behaviors. The work reported has focused on: 1) detecting moving objects in online (or near real-time) manner through spatio-temporal segmentations of crowds that is defined by the similarity of group trajectory structures in temporal space and the foreground blocks based on Gaussian Mixture Model (GMM) in spatial space; 2) dividing multiple clustered groups based on the spectral clustering method by considering image pixels from spatio-temporal segmentation regions as dynamic particles; 3) generating the STFD descriptor instances by calculating the attributes (i.e., collectiveness, stability, conflict and crowd density) of particles in the corresponding groups; 4) inputting generated STFD descriptor instances into the devised convolutional neural network (CNN) to detect suspicious crowd behaviors. The test and evaluation of the devised models and techniques have selected the PETS database as the primary experimental data sets. Results against benchmarking models and systems have shown promising advancements of this novel approach in terms of accuracy and efficiency for detecting crowd anomalies.

show abstract

Detecting Abnormal Behavioral Patterns in Crowd Scenarios

Cited by 15 publications

References 41 publications

Group activity recognition with an interaction force based on low‐level features

Group activity recognition with an interaction force based on low‐level features

Dual-channel CNN for efficient abnormal behavior identification through crowd feature engineering

Towards Intelligent Crowd Behavior Understanding Through the STFD Descriptor Exploration

Contact Info

Product

Resources

About