A Comparative Analysis of Different Violence Detection Algorithms from Videos

Vashistha, Piyush; Singh, Juginder Pal; Khan, Mohd. Aamir

doi:10.1007/978-981-15-0694-9_54

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[4][5][6]7] Some studies look into videos to detect physical violence by using classification techniques such as traditional violence detection using machine learning, support vector machine (SVM) and deep Learning. Feature extraction and object detection techniques, k-nearest neighbors (k-nn), random forest classifier [8][9][10][11][12][13][14]. Another significant artificial intelligence method in violence detection is using machine learning algorithms in identifying stress, panic, and fear in speech through physiological sensory data, speech, and audio analysis [16].…”

Section: Introductionmentioning

confidence: 99%

Violence Detection with Machine Learning: A Sociodemographic Approach

Ensari

ENSARİ

Dağtekin

2023

EJOSAT

View full text Add to dashboard Cite

This study suggests that by implementing machine learning methods on a sociodemographic data set can be helpful in preventing domestic violence. This approach is important in predicting high-risk factors that an offender may cause and it offers treatment, and financial or mental health aids in order to prevent domestic violence. In this sense, this proposal is critical at a personal and social level in creating a secure and healthy environment as well as empowering an equal society. In our study, we use k-nearest neighbor (k-nn), support vector machine (SVM), decision tree (DT), and Gaussian Naive Bayes (GNB) machine learning algorithms for the prediction analysis. We provide the comparison of the classifiers with precision, recall, F1 score, and accuracy performance measures. According to our analysis, the decision tree (DT) performs the best performance in terms of accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Violence Detection with Machine Learning: A Sociodemographic Approach

Ensari

ENSARİ

Dağtekin

2023

EJOSAT

View full text Add to dashboard Cite

show abstract

“…The fusion features descriptor extracted prominent features and fed to support vector machine (SVM) classifier to detect crowded and uncrowded violent event scenes in the video. Recently, some of the surveys [11][12][13] have published different feature extraction techniques used to detect violent events in videos. The most existing methods based on the spatio-temporal interest points [8], features fusion [9,10], optical flow [14], textures [15,16], trajectories [17], descriptors and deep learning techniques [18].…”

Section: Introductionmentioning

confidence: 99%

Violent Video Event Detection Based on Integrated LBP and GLCM Texture Features

Lohithashva¹,

Aradhya²,

Guru³

2020

RIA

View full text Add to dashboard Cite

Violent event detection is an interesting research problem and it is a branch of action recognition and computer vision. The detection of violent events is significant for both the public and private sectors. The automatic surveillance system is more attractive and interesting because of its wide range of applications in abnormal event detection. Since many years researchers were worked on violent activity detection and they have proposed different feature descriptors on both vision and acoustic technology. Challenges still exist due to illumination, complex background, scale changes, sudden variation, and slowmotion in videos. Consequently, violent event detection is based on the texture features of the frames in both crowded and uncrowned scenarios. Our proposed method used Local Binary Pattern (LBP) and GLCM (Gray Level Co-occurrence Matrix) as feature descriptors for the detection of a violent event. Finally, prominent features are used with five different supervised classifiers. The proposed feature extraction technique used Hockey Fight (HF) and Violent Flows (VF) two standard benchmark datasets for the experimentation.

show abstract