Physical Violence Detection in Video Streaming Using Partitioned Skeleton Analysis

Narynov, Sergazy; Zhumanov, Zhandos; Gumar, Aidana; Khassanova, Mariyam; Omarov, Batyrkhan

doi:10.23919/iccas52745.2021.9649827

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to surveillance film, the scenes are also clearly focused primarily on the acts of interest occurring and high-quality sound effects are audible. In the case of streaming services [9][10][11][12], it is required to identify violence to ensure that videos follow the rules and regulations like the removal of violent videos in case of rule break or age restriction access for children. Furthermore, it is important to classify violence into multiple categories which can be used for recommendation purposes.…”

Section: Introductionmentioning

confidence: 99%

Computational Comparison of CNN Based Methods for Violence Detection

Singh

Tyagi

2023

Preprint

View full text Add to dashboard Cite

In this paper, we approach with four different CNN-based models i.e., VGG-19, VGG-16, InceptionV3 and MobileNetV3 with an improved version of the previous models for violence detection and recognition from videos. The proposed models use the pre-trained models as the base model for feature extraction and for classification after freezing the rest of the layer, the head model is prepared with averagepooling2D of (5, 5), and after flattening only one dense layer having 512 nodes with ‘ReLU’ activation function, dropout layer of 0.5 and last output layer with only 2 classes and ‘softmax’ activation function. This head model of fully connected layers was used in the proposed models. These models are trained and evaluated on the Hockey fight dataset and Real life violence situations detection datasets. The experimental results are far better in terms of accuracy and other performance metrics and the models have reduced parameters and less computational time than previous models.

show abstract

Section: Introductionmentioning

confidence: 99%