RIMOC, a feature to discriminate unstructured motions: Application to violence detection for video-surveillance

Ribeiro, Pedro; Audigier, Romaric; Pham, Quoc Cuong

doi:10.1016/j.cviu.2015.11.001

Cited by 47 publications

(30 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, the systems work as a witness to violent events. Included in this approach are violence detection using surveillance video signals [16][17][18] and physiological signals measured from the subjects who were watching the violent scenes, e.g. EDA [19], EEG [20].…”

Section: Research In Violence Detectionmentioning

confidence: 99%

See 1 more Smart Citation

VITEC: A Violence Detection Framework

Ferdinando

Huuki

Liang

et al. 2019

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Hundreds of millions of youths suffer from various violence everyyear all over the globe. Negative impacts due to violence motivate much research and numerous studies on violence, ranging from the social sciences, such as psychology and education, to engineering. However, those attempts go their own way, making the achieved results, especially the ones from engineering, not so useful. Also, they gain attention only from their own communities. Based on the Sensor and Social Web (SEWEB) concept, Violence Detection (VITEC) was proposed as a possible framework to facilitate multi-disciplinary researchers in their fight against violence. At its core, it consists of a primary agent, which is violence detection using physiological signals and activity recognition measured from the young persons, and a secondary agent, which is violence detection using surveillance video. The second layer of the proposed framework contains a cloud computing service with a Personal Safety Network database. The cloud computing service manages all data, notifications, and some more thorough processing. The upper layer is for both observed young persons and members of the Personal Safety Network. The proposed framework also offers business opportunities. The existing school violence/bullying intervention programs can take advantage of VITEC by providing almost instant notifications of violent events, enabling the victims to get immediate help and intensifying coordination among different sectors to fight against violence. In the long run, VITEC may provide an answer related to the vision of having a world free from violence in 2030, as addressed by the UN Special Representative of Secretary-General on violence against children.

show abstract

Section: Research In Violence Detectionmentioning

confidence: 99%

“…Surveillance videos were from various data sets: BEHAVE, the CAVIAR, and Crowded Violence Ribeiro et al 2016 [17] Accuracies were around 90% using various databases. The system can be used in various contexts.…”

Section: Authorsmentioning

confidence: 99%

VITEC: A Violence Detection Framework

Ferdinando

Huuki

Liang

et al. 2019

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

show abstract

“…It was shown that ViF offers greater classification ability on crowded data when compared to OViF, but when combined they achieve greater accuracy. Riberio et al [30] introduce the Rotation Invariant Motion Coherence RIMOC feature that is based on the eigen-values of second order statistics extracted from a Histogram of Oriented Flows. A multi-scale structure is used to model spatio-temporal configurations of features.…”

Section: Related Workmentioning

confidence: 99%

Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures

Lloyd

Rosin

Marshall

et al. 2017

Machine Vision and Applications

View full text Add to dashboard Cite

The severity of sustained injury resulting from assault-related violence can be minimised by reducing detection time. However, it has been shown that human operators perform poorly at detecting events found in video footage when presented with simultaneous feeds. We utilise computer vision techniques to develop an automated method of abnormal crowd detection that can aid a human operator in the detection of violent behaviour. We observed that behaviour in city centre environments often occurs in crowded areas, resulting in individual actions being occluded by other crowd members. We propose a real-time descriptor that models crowd dynamics by encoding changes in crowd texture using temporal summaries of grey level cooccurrence matrix features. We introduce a measure of inter-frame uniformity and demonstrate that the appearance of violent behaviour changes in a less uniform manner when compared to other types of crowd behaviour. Our proposed method is computationally cheap and offers real-time description. Evaluating our method using a privately held CCTV dataset and the publicly available Violent Flows, UCF Web Abnormality and UMN Abnormal Crowd datasets, we

show abstract

“…In [22,23], spatio-temporal oriented energy (SOE) was exploited, in which a set of energy filters was used to capture a wide range of image dynamics and filter the irrelevant variation. Ribeiro et al [24] proposed a Rotation-Invariant feature modeling MOtion Coherence (RIMOC) descriptor for violence detection in unstructured scenes, which was able to capture the structure and discriminate motion in a spatio-temporal volume. However, pixel-wise descriptors are unable to capture the contextual information in scenes, which is necessary for AED in some cases, e.g., irregular co-occurrence events.…”

Section: ) Pixel-wise Descriptormentioning

confidence: 99%

Abnormal event detection in crowded scenes using histogram of oriented contextual gradient descriptor

Duan

et al. 2018

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Detecting abnormal events in crowded scenes is an important but challenging task in computer vision. Contextual information is useful for discovering salient events in scenes; however, it cannot be characterized well by commonly used pixel-based descriptors, such as the HOG descriptor. In this paper, we propose contextual gradients between two local regions and then construct a histogram of oriented contextual gradient (HOCG) descriptor for abnormal event detection based on the contextual gradients. The HOCG descriptor is a distribution of contextual gradients of sub-regions in different directions, which can effectively characterize the compositional context of events. We conduct extensive experiments on several public datasets and compare the experimental results using state-of-the-art approaches. Qualitative and quantitative analysis of experimental results demonstrate the effectiveness of the proposed HOCG descriptor.

show abstract

RIMOC, a feature to discriminate unstructured motions: Application to violence detection for video-surveillance

Cited by 47 publications

References 22 publications

VITEC: A Violence Detection Framework

VITEC: A Violence Detection Framework

Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures

Abnormal event detection in crowded scenes using histogram of oriented contextual gradient descriptor

Contact Info

Product

Resources

About