2D Bidirectional Gated Recurrent Unit Convolutional Neural Networks for End-to-End Violence Detection in Videos

Traore, Abdarahmane; Akhloufi, Moulay A.

doi:10.1007/978-3-030-50347-5_14

Cited by 13 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN + Long Short-Term Memory (LSTM) and 3D-CNNbased models [60]- [64]. Sudhakaran and Lanz used frame differences instead of RGB frames as an input of the 2D CNN + LSTM to generate a better representation of changes between adjacent frames [65].…”

Section: There Have Been Various Violence Detection Methods With 2dmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Spatio-Temporal Modeling Methods for Real-Time Violence Recognition

Kang

Park

2021

IEEE Access

View full text Add to dashboard Cite

Violence recognition is challenging since recognition must be performed on videos acquired by a lot of surveillance cameras at any time or place. It should make reliable detections in real time and inform surveillance personnel promptly when violent crimes take place. Therefore, we focus on efficient violence recognition for real-time and on-device operation, for easy expansion into a surveillance system with numerous cameras. In this paper, we propose a novel violence detection pipeline that can be combined with the conventional 2-dimensional Convolutional Neural Networks (2D CNNs). In particular, framegrouping is proposed to give the 2D CNNs the ability to learn spatio-temporal representations in videos. It is a simple processing method to average the channels of input frames and group three consecutive channelaveraged frames as an input of the 2D CNNs. Furthermore, we present spatial and temporal attention modules that are lightweight but consistently improve the performance of violence recognition. The spatial attention module named Motion Saliency Map (MSM) can capture salient regions of feature maps derived from the motion boundaries using the difference between consecutive frames. The temporal attention module called Temporal Squeeze-and-Excitation (T-SE) block can inherently highlight the time periods that are correlated with a target event. Our proposed pipeline brings significant performance improvements compared to the 2D CNNs followed by the Long Short-Term Memory (LSTM) and much less computational complexity than existing 3D-CNN-based methods. In particular, MobileNetV3 and EfficientNet-B0 with our proposed modules achieved state-of-the-art performance on six different violence datasets. Our codes are available at https://github.com/ahstarwab/Violence_Detection. INDEX TERMS Real-time violence detection, efficient spatio-temporal attention, efficient convolution method for spatio-temporal modeling

show abstract

Section: There Have Been Various Violence Detection Methods With 2dmentioning

confidence: 99%

“…SPIL [12] computed the interaction weights to model feature and position relations between extracted human skeleton points for violence recognition. Lastly, VGG-16 + Bi-GRU [64] used a pretrained VGG-16 followed by a bidirectional Gated Recurrent Units (GRU).…”

Section: Comparison With Other Methods On Violence Datasetsmentioning

confidence: 99%

Efficient Spatio-Temporal Modeling Methods for Real-Time Violence Recognition

Kang

Park

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Traoré and Akhloufi [ 51 ] used a pre-trained VGG-16 with INRA person dataset to extract spatial features, which then feeds a type of RNN called BiGRU (bidirectional gated recurrent unit). Finally, as a classifier the authors used three fully connected layers, the last one with softmax activation.…”

Section: Selected Article Descriptionmentioning

confidence: 99%

Literature Review of Deep-Learning-Based Detection of Violence in Video

Negre,

Alonso,

González-Briones

et al. 2024

Sensors

View full text Add to dashboard Cite

Physical aggression is a serious and widespread problem in society, affecting people worldwide. It impacts nearly every aspect of life. While some studies explore the root causes of violent behavior, others focus on urban planning in high-crime areas. Real-time violence detection, powered by artificial intelligence, offers a direct and efficient solution, reducing the need for extensive human supervision and saving lives. This paper is a continuation of a systematic mapping study and its objective is to provide a comprehensive and up-to-date review of AI-based video violence detection, specifically in physical assaults. Regarding violence detection, the following have been grouped and categorized from the review of the selected papers: 21 challenges that remain to be solved, 28 datasets that have been created in recent years, 21 keyframe extraction methods, 16 types of algorithm inputs, as well as a wide variety of algorithm combinations and their corresponding accuracy results. Given the lack of recent reviews dealing with the detection of violence in video, this study is considered necessary and relevant.

show abstract

“…However, the keyframe selection approaches may require careful parameter tuning and may encounter challenges in handling extremely dynamic scenes. [58] 3D-RESNET NA 76% 2D-RNN [59] GATED-CNN NA 98% FTCF [60] FTCFNET-CNN NA 98.5% CNN-SLSTM [61] RESNET-28 NA 99.20% THE PROPOSED MODEL KFCRNET+DEEPKEYFRM 0.039 99.62…”

Section: E Quantitative Analysismentioning

confidence: 99%

Augmenting the Robustness and Efficiency of Violence Detection Systems for Surveillance and Non-Surveillance Scenarios

Shoaib,

Ullah,

Abbasi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Violence detection holds immense significance in ensuring public safety, security, and law enforcement in various domains. With the increasing availability of video data from surveillance cameras and social media platforms, the need for accurate and efficient violence detection algorithms has become paramount. Automated violence detection systems can aid law enforcement agencies in identifying and responding to violent incidents promptly, thereby preventing potential threats and ensuring public protection. This research focuses on violence detection in large video databases, proposing two keyframebased models named DeepkeyFrm and AreaDiffKey. The keyframes selection process is critical in violence detection systems, as it reduces computational complexity and enhances accuracy. EvoKeyNet and KFCRNet are the proposed classification models that leverage feature extraction from optimal keyframes. EvoKeyNet utilizes an evolutionary algorithm to select optimal feature attributes, while KFCRNet employs an ensemble of LSTM, Bi-LSTM, and GRU models with a voting scheme. Our key contributions include the development of efficient keyframes selection methods and classification models, addressing the challenge of violence detection in dynamic surveillance scenarios. The proposed models outperform existing methods in terms of accuracy and computational efficiency, with accuracy results as follows: 98.98% (Hockey Fight), 99.29% (Violent Flow), 99% (RLVS), 91% (UCF-Crime), and 91% (ShanghaiTech). The ANOVA and Tukey tests were performed to validate the statistical significance of the differences among all models. The proposed approaches, supported by the statistical tests, pave the way for more effective violence detection systems, holding immense promise for a safer and secure future. As violence detection technology continues to evolve, our research stands as a crucial stepping stone towards achieving improved public safety and security in the face of dynamic challenges

show abstract

2D Bidirectional Gated Recurrent Unit Convolutional Neural Networks for End-to-End Violence Detection in Videos

Cited by 13 publications

References 18 publications

Efficient Spatio-Temporal Modeling Methods for Real-Time Violence Recognition

Efficient Spatio-Temporal Modeling Methods for Real-Time Violence Recognition

Literature Review of Deep-Learning-Based Detection of Violence in Video

Augmenting the Robustness and Efficiency of Violence Detection Systems for Surveillance and Non-Surveillance Scenarios

Contact Info

Product

Resources

About