An approach to detect crowd panic behavior using flow-based feature

Hao, Yu; Xu, Zhijie; Wang, Jing; Liu, Ying; Fan, Jiulun

doi:10.1109/iconac.2016.7604963

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baker et al [20,21] used STV for 3D scene segmentation. Ngo et al [22] used STT techniques for the detection of camera cuts, wipes and dissolves in a video sequence. In this approach, a STT was analyzed by first convolving with the first derivative Gaussian, and then processed using Gabor decomposition, in which the real components of multiple spatial-frequency channel envelopes were retrieved to form the texture feature vector.…”

Section: Stv-based Motion Encapsulation and Stt Feature Representationmentioning

confidence: 99%

Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis

Hao

Liu

et al. 2018

Int. J. Autom. Comput.

Self Cite

View full text Add to dashboard Cite

Abnormal crowd behaviors in high density situations can pose great danger to public safety. Despite the extensive installation of closed-circuit television (CCTV) cameras, it is still difficult to achieve real-time alerts and automated responses from current systems. Two major breakthroughs have been reported in this research. Firstly, a spatial-temporal texture extraction algorithm is developed. This algorithm is able to effectively extract video textures with abundant crowd motion details. It is through adopting Gaborfiltered textures with the highest information entropy values. Secondly, a novel scheme for defining crowd motion patterns (signatures) is devised to identify abnormal behaviors in the crowd by employing an enhanced gray level co-occurrence matrix model. In the experiments, various classic classifiers are utilized to benchmark the performance of the proposed method. The results obtained exhibit detection and accuracy rates which are, overall, superior to other techniques.

show abstract

Section: Stv-based Motion Encapsulation and Stt Feature Representationmentioning

confidence: 99%

Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis

Hao

Liu

et al. 2018

Int. J. Autom. Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Succession of panic attacks may result in a change or imbalance of neurotransmitters in the brain of patients. In addition, if panic attacks relapse often with the continuous fear, it will cause crucial impact in the patient's daily life [8].…”

Section: Introductionmentioning

confidence: 99%

Brainwave Detection Model for Panic Attacks Based on Event-related Potential

Sirikongtham¹,

Paireekreng²,

Chit³

2019

JUBPAS

View full text Add to dashboard Cite

Panic attacks could adversely affect a patient’s daily life and can pose risks to others. The symptoms of panic attacks can be timely observed by detecting the brainwave. This research presents a model that can evaluate the level of panic attack symptoms using the brainwaves detection during (or before) the symptom occurs. It helps monitor the patient’s brainwave based on Event-related potential (ERP). The model is derived from the simulation with horror pictures and frightening sound on the experimental group of 30 people. The survey related to symptoms has been used regarding to the criteria of the Beck Anxiety Inventory (BAI). The results showed that there is a consistent change of Electroencephalography (EEG) in each change of brainwaves where its quantitative analysis found that the changes of Beta, Gamma, and Alpha directly affect the model of Brainwaves Panic Attacks Measurement (BPAM) which is associated with panic attacks. 1 out of 30 cases scored higher than the average of the BPAM at 220 The Model BPAM can detect the risk to be Panic Attack compared to the use of tests Beck Anxiety Inventory (BAI) were found to be consistent. The test value BAI Score 19-63 was BPAM Score 401-1000. In addition, the results found that at P300 the brainwave pattern of EEG in meditation had decreased significantly whereas the brainwave related to attention had increased considerably for which human brain can potentially respond to stimulated external events.

show abstract

“…When the ribbon-shaped motion texture becomes denser and more irregular, the corresponding magnitude in the statistical histogram will increase more rapidly. Based on the preliminary study [1], the algorithm used for crowd behavior analysis can be simplified as follows: at the training (current-state template building) stage, the average value of the first group of frames is calculated, and this value is then used to define the Initial state. Once an empirical threshold value is defined (subjecting to application scenarios such as indoor/outdoor, crowd density, and dynamic state), if the difference between a consecutive pair of STT slices exceeds the threshold then it can be presumed a crowd behavioral pattern change has occurred.…”

Section: Optimization Through Gabor Filteringmentioning

confidence: 99%

“…A typical pipeline of the crowd abnormality detecting system contains three processing phases [1]. In the first video data acquisition phase, the raw video signals are collected and stored in suitable digital formats; and then static or dynamic features contained within the information packets will be extracted; and at last, predefined feature patterns describing signal-, statistical-, and/or even semantic-level explanations of the "video events" will be used to evaluate the similarity and differences of the features extracted from the live feeds [2,3 and 4].…”

Section: Introductionmentioning

confidence: 99%

An effective video processing pipeline for crowd pattern analysis

Hao

Wang

et al. 2017

2017 23rd International Conference on Automation and Computing (ICAC)

Self Cite

View full text Add to dashboard Cite

Abstract-With the purpose of automatic detection of crowd patterns including abrupt and abnormal changes, a novel approach for extracting motion "textures" from dynamic SpatioTemporal Volume (STV) blocks formulated by live video streams has been proposed. This paper starts from introducing the common approach for STV construction and corresponding Spatio-Temporal Texture (STT) extraction techniques. Next the crowd motion information contained within the random STT slices are evaluated based on the information entropy theory to cull the static background and noises occupying most of the STV spaces. A preprocessing step using Gabor filtering for improving the STT sampling efficiency and motion fidelity has been devised and tested. The technique has been applied on benchmarking video databases for proof-of-concept and performance evaluation. Preliminary results have shown encouraging outcomes and promising potentials for its real-world crowd monitoring and control applications.

show abstract

An approach to detect crowd panic behavior using flow-based feature

Cited by 9 publications

References 12 publications

Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis

Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis

Brainwave Detection Model for Panic Attacks Based on Event-related Potential

An effective video processing pipeline for crowd pattern analysis

Contact Info

Product

Resources

About