Violence Recognition from Videos using Deep Learning Techniques

Soliman, Mosaad; Kamal, Mohamed Hussein; Nashed, Mina; Mostafa, Youssef Mohamed; Chawky, Bassel S.; Khattab, Dina

doi:10.1109/icicis46948.2019.9014714

Cited by 107 publications

(67 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One of them is hockey fights dataset [18]. The other is the Real-Life Violence Situations dataset [1].…”

Section: Resultsmentioning

confidence: 99%

“…In Table 1, the proposed model accuracies are compared with three previous related work. Soliman et al [1], Gao et al [11], and Bilinski et al [15]. Although many related research faced a problem with hockey fights dataset where the standard background of all the videos is white ice.…”

Section: Resultsmentioning

confidence: 99%

“…Hockey fight dataset RLVS dataset Soliman et al [1] 95.1% 94.9% Gao et al [11] 92.81% --Bilinski et al [15] 93.7% --Proposed model 94.5% 92% The model was evaluated on one of the widely used hockey fights datasets, and a recently introduced RLVS dataset. The model showed competitive performance in comparison with related work.…”

Section: Methodsmentioning

confidence: 99%

“…RLVS is the main benchmark dataset. Soliman et al [1] introduce it. The dataset consisted of 2000 trimmed videos of full length of 3 hours.…”

Section: A Datasets I) Real-life Violence Situations Datasetmentioning

confidence: 99%

“…Anomaly is that some instance deviates from the standard format of the majority of the other instances. In the field of pattern, recognition the term "anomaly detection" was introduced to detect an anomaly using the study of the characteristics of the instances and classify what is normalmajor-characteristic from what is not [1].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Violence Detection In Surveillance Videos Using Deep Learning

Moaaz

Mohamed

2020

النشرة المعلوماتیة فی الحاسبات والمعلومات

View full text Add to dashboard Cite

Nowadays computer technologies are flowering especially the artificial intelligence field. It lives its prosperous years. Recently it closes the gap between humans and machines with the facilitation of supporting decisions. One of these gaps is the surveillance cameras labors' attentiveness and the lack of instantaneous detection of violence actions on the scenes of such cameras. In this paper we present an end to end deep neural network to detect the violence scenes in the surveillance cameras, the proposed system composed of set of phases. It extracts a set of selectively distributed frames of the video clip, performs spatio-temporal features, and passes them to a fully connected neural to classify the video to violence or non-violence action. The model is evaluated on different datasets; like Real Life Violence Situations aka RLVS and Hockey Fight Detection datasets. The accuracy was 92% and 94.5% respectively, which outperformed the previous related works.

show abstract

“…One of them is hockey fights dataset [18]. The other is the Real-Life Violence Situations dataset [1].…”

Section: Resultsmentioning

confidence: 99%