An overview of violence detection techniques: current challenges and future directions

Mumtaz, Nadia; Ejaz, Naveed; Habib, Sami J.; Mohsin, Syed Muhammad; Tiwari, Prayag; Band, Shahab S.; Kumar, Neeraj

doi:10.1007/s10462-022-10285-3

Cited by 27 publications

(8 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to a recent study by Mumtaz et al [ 46 ], the main studies for recognizing violent human actions contain little information about efficiency results, i.e., information about the complexity and number of parameters, confirming that their objective was to find good results in terms of accuracy while increasing the complexity of the model. It was shown that proposals based on optical flow, 3D CNN, LSTM, two-stream networks, and 3D skeletons have high computational costs and cannot be used in real-time scenarios.…”

Section: Related Workmentioning

confidence: 99%

Efficient Human Violence Recognition for Surveillance in Real Time

Huillcen Baca,

Palomino Valdivia,

Gutierrez Caceres

2024

Sensors

View full text Add to dashboard Cite

Human violence recognition is an area of great interest in the scientific community due to its broad spectrum of applications, especially in video surveillance systems, because detecting violence in real time can prevent criminal acts and save lives. The majority of existing proposals and studies focus on result precision, neglecting efficiency and practical implementations. Thus, in this work, we propose a model that is effective and efficient in recognizing human violence in real time. The proposed model consists of three modules: the Spatial Motion Extractor (SME) module, which extracts regions of interest from a frame; the Short Temporal Extractor (STE) module, which extracts temporal characteristics of rapid movements; and the Global Temporal Extractor (GTE) module, which is responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated for its efficiency, effectiveness, and ability to operate in real time. The results obtained on the Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to various alternatives. In addition, the VioPeru dataset was created, which contains violent and non-violent videos captured by real video surveillance cameras in Peru, to validate the real-time applicability of the model. When tested on this dataset, the effectiveness of our model was superior to the best existing models.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Human Violence Recognition for Surveillance in Real Time

Huillcen Baca,

Palomino Valdivia,

Gutierrez Caceres

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…CNN and Sequence Models [39] They can have good classification accuracy and can be computationally light depending on the number of layers used. They also can adapt to new data.…”

Section: Reference(s) Strengths Weaknessesmentioning

confidence: 99%

MultiWave-Net: An Optimized Spatiotemporal Network for Abnormal Action Recognition Using Wavelet-Based Channel Augmentation

Elmasry,

Abd El Ghany,

Salem

et al. 2024

View full text Add to dashboard Cite

Human behavior is regarded as one of the most complex notions present nowadays, due to the large magnitude of possibilities. These behaviors and actions can be distinguished as normal and abnormal. However, abnormal behavior is a vast spectrum, so in this work, abnormal behavior is regarded as human aggression or in another context when car accidents occur on the road. As this behavior can negatively affect the surrounding traffic participants, such as vehicles and other pedestrians, it is crucial to monitor such behavior. Given the current prevalent spread of cameras everywhere with different types, they can be used to classify and monitor such behavior. Accordingly, this work proposes a new optimized model based on a novel integrated wavelet-based channel augmentation unit for classifying human behavior in various scenes, having a total number of trainable parameters of 5.3 m with an average inference time of 0.09 s. The model has been trained and evaluated on four public datasets: Real Live Violence Situations (RLVS), Highway Incident Detection (HWID), Movie Fights, and Hockey Fights. The proposed technique achieved accuracies in the range of 92% to 99.5% across the used benchmark datasets. Comprehensive analysis and comparisons between different versions of the model and the state-of-the-art have been performed to confirm the model’s performance in terms of accuracy and efficiency. The proposed model has higher accuracy with an average of 4.97%, and higher efficiency by reducing the number of parameters by around 139.1 m compared to other models trained and tested on the same benchmark datasets.

show abstract

“…Automatic Violence Detection and Classification (AVDC) of video content has recently emerged as a critical problem [1,2], leading to an increased focus on using Deep Learning (DL), computer vision, and image processing methods for flagging unsuitable content and detecting violent behaviour [3]. Automatic and real-time video analysis is imperative to identifying violent offenders and maintaining the safety of cities [4,5].…”

Section: Introductionmentioning

confidence: 99%

BrutNet: A novel approach for violence detection and classification using DCNN with GRU

Haque,

Nyeem,

Afsha

2024

The Journal of Engineering

View full text Add to dashboard Cite

Automatic Violence Detection and Classification (AVDC) with deep learning has garnered significant attention in computer vision research. This paper presents a novel approach for combining a custom Deep Convolutional Neural Network (DCNN) with a Gated Recurrent Unit (GRU) in developing a new AVDC model called BrutNet. Specifically, a time‐distributed DCNN (TD‐DCNN) is developed to generate a compact 2D representation with 512 spatial features per frame from a set of equally‐spaced frames of dimension 16090 in short video segments. Further to leverage the temporal information, a GRU layer is utilised, generating a condensed 1D vector that enables binary classification of violent or non‐violent content through multiple dense layers. Overfitting is addressed by incorporating dropout layers with a rate of 0.5, while the hidden and output layers employ rectified linear unit (ReLU) and sigmoid activations, respectively. The model is trained on the NVIDIA Tesla K80 GPU through Google Colab, demonstrating superior performance compared to existing models across various video datasets, including hockey fights, movie fights, AVD, and RWF‐2000. Notably, the model stands out by requiring only 3.416 million parameters and achieving impressive test accuracies of 97.62%, 100%, 97.22%, and 86.43% on the respective datasets. Thus, BrutNet exhibits the potential to emerge as a highly efficient and robust AVDC model in support of greater public safety, content moderation and censorship, computer‐aided investigations, and law enforcement.

show abstract

An overview of violence detection techniques: current challenges and future directions

Cited by 27 publications

References 88 publications

Efficient Human Violence Recognition for Surveillance in Real Time

Efficient Human Violence Recognition for Surveillance in Real Time

MultiWave-Net: An Optimized Spatiotemporal Network for Abnormal Action Recognition Using Wavelet-Based Channel Augmentation

BrutNet: A novel approach for violence detection and classification using DCNN with GRU

Contact Info

Product

Resources

About