WVD: A New Synthetic Dataset for Video-Based Violence Detection

Nadeem, Muhammad Shahroz; Franqueira, Virginia N. L.; Kurugöllü, Fatih; Zhai, Xiaojun

doi:10.1007/978-3-030-34885-4_13

Cited by 9 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 provides a summary of the comparison of the proposed Smart-City CCTV Violence Detection (SCVD) dataset with other datasets used to train deep neural networks (DNNs) for detecting violence and weapons in videos. The datasets considered in this comparison include those used for violence detection, such as Nanyang Technological University (NTU) CCTV-Fights [23], Hockey Fight [24], Real-Life Violent Situations (RLVS) [19], and RWF-2000 [25], as well as those for weapons detection, including Sohas [26] and Weapon Violence dataset (WVD) [27].…”

Section: Proposed Smart-city Cctv Violence Detection (Scvd) Datasetmentioning

confidence: 99%

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

Aremu

Alameeri

et al. 2023

Preprint

View full text Add to dashboard Cite

Detection of violence and weaponized violence in closed-circuit television (CCTV) footage requires a comprehensive approach. In this work, we introduce the Smart-City CCTV Violence Detection (SCVD) dataset, specifically designed to facilitate the learning of weapon distribution in surveillance videos. To tackle the complexities of analyzing 3D surveillance video for violence recognition tasks, we propose a novel technique called, SSIVD-Net (Salient-Super-Image for Violence Detection). Our method reduces 3D video data complexity, dimensionality, and information loss while improving inference, performance, and explainability through the use of Salient-Super-Image representations. Considering the scalability and sustainability requirements of futuristic smart cities, the authors introduce the Salient-Classifier, a novel architecture combining a kernelized approach with a residual learning strategy. We evaluate variations of SSIVD-Net and Salient Classifier on our SCVD dataset and benchmark against state-of-the-art (SOTA) models commonly employed in violence detection. Our approach exhibits significant improvements in detecting both weaponized and non-weaponized violence instances. By advancing the SOTA in violence detection, our work offers a practical and scalable solution suitable for real-world applications. The proposed methodology not only addresses the challenges of violence detection in CCTV footage but also contributes to the understanding of weapon distribution in smart surveillance. Ultimately, our research findings should enable smarter and more secure cities, as well as enhance public safety measures.

show abstract

Section: Proposed Smart-city Cctv Violence Detection (Scvd) Datasetmentioning

confidence: 99%

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

Aremu

Alameeri

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To detect weapons in videos, Sohas [26] and Weapon Violence Dataset (WVD) [27] were created. Sohas contains images with bounding box annotations, while WVD contains synthetic videos of length 10 to 72 seconds generated from the GTA-V computer game and annotated at the video level.…”

Section: Super-imagementioning

confidence: 99%

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

Aremu

2023

Preprint

View full text Add to dashboard Cite

<p> Detection of violence and weaponized violence in closed-circuit television (CCTV) footage requires a comprehensive approach. In this work, we introduce the \emph{Smart-City CCTV Violence Detection (SCVD)} dataset, specifically designed to facilitate the learning of weapon distribution in surveillance videos. To tackle the complexities of analyzing 3D surveillance video for violence recognition tasks, we propose a novel technique called, \emph{SSIVD-Net} (\textbf{S}alient-\textbf{S}uper-\textbf{I}mage for \textbf{V}iolence \textbf{D}etection). Our method reduces 3D video data complexity, dimensionality, and information loss while improving inference, performance, and explainability through the use of Salient-Super-Image representations. Considering the scalability and sustainability requirements of futuristic smart cities, the authors introduce the \emph{Salient-Classifier}, a novel architecture combining a kernelized approach with a residual learning strategy. We evaluate variations of SSIVD-Net and Salient Classifier on our SCVD dataset and benchmark against state-of-the-art (SOTA) models commonly employed in violence detection. Our approach exhibits significant improvements in detecting both weaponized and non-weaponized violence instances. By advancing the SOTA in violence detection, our work offers a practical and scalable solution suitable for real-world applications. The proposed methodology not only addresses the challenges of violence detection in CCTV footage but also contributes to the understanding of weapon distribution in smart surveillance. Ultimately, our research findings should enable smarter and more secure cities, as well as enhance public safety measures.</p>

show abstract

“…Further, labelling violence related data through open source labelling service is also difficult. Due to these factors, WVD dataset [9] was selected for training, validation and testing in stage 1. To test the generalisation of our method on a real world dataset, the final testing was performed on the USI dataset in stage 2.…”

Section: Datasetsmentioning

confidence: 99%

“…2) Stage 2: Using the weak labels generated through stage 1, state-of-the-art object detection methods are retrained to produce strong labels. the strong labels are evaluated against WVD [9] and USI human labelled test sets. Figure 2 shows the two-stage process by which labels are generated.…”

Section: Proposed Approachmentioning

confidence: 99%

See 1 more Smart Citation

Deep Labeller: Automatic Bounding Box Generation for Synthetic Violence Detection Datasets

Nadeem¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

WVD: A New Synthetic Dataset for Video-Based Violence Detection

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 9 publications

References 6 publications

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

Deep Labeller: Automatic Bounding Box Generation for Synthetic Violence Detection Datasets

Contact Info

Product

Resources

About

WVD: A New Synthetic Dataset for Video-Based Violence Detection

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 9 publications

References 6 publications

SSIVD-Net: A Novel Salient Super Image Classification &amp; Detection Technique for Weaponized Violence

SSIVD-Net: A Novel Salient Super Image Classification &amp; Detection Technique for Weaponized Violence

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

Deep Labeller: Automatic Bounding Box Generation for Synthetic Violence Detection Datasets

Contact Info

Product

Resources

About

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence

SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence