Motion Direction Inconsistency‐Based Fight Detection for Multiview Surveillance Videos

Chong, Yung-Wey; Su, Xiaoyan; Wang, Xuehua; Kang, Xiaoning; Zhang, Jun; Ren, Jiankang

doi:10.1155/2021/9965781

Cited by 10 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [5] The paper introduces a multi-view fight detection method for surveillance videos, addressing challenges like varying shooting views and potential misjudgments. Leveraging optical flow analysis and random forest classification, the system computes novel descriptors and achieves improved accuracy, reduced false alarms, and robustness against different viewpoints on the CASIA dataset.…”

Section: Literature Surveymentioning

confidence: 99%

Uncanny Activity Detection Using CCTV Monitoring

Kouser

2024

IJSREM

View full text Add to dashboard Cite

"Uncanny Activity Detection Using CCTV Monitoring" introduces an innovative approach to support public safety through the integration of Machine Learning (ML) in real-time monitoring. In the contemporary world, Closed-Circuit Television (CCTV) surveillance stands as a fundamental and highly effective security measure for various premises, including hospitals, malls, and universities. It serves as a widely recognized tool for preventing and detecting unwanted activities. However, envisioning an public space equipped with several CCTV cameras across multiple buildings presents a logistical challenge. The manual monitoring of events across this expansive network is practically impossible. Furthermore, searching for a specific event in recorded video footage, even after it has occurred, proves to be a time-consuming endeavor. This project addresses the need for an efficient solution to manage and analyze extensive CCTV footage in complex environments, optimizing security practices and response times. Keywords: Anomaly Detection, Deep Learning, Human Behavior Recognition.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Uncanny Activity Detection Using CCTV Monitoring

Kouser

2024

IJSREM

View full text Add to dashboard Cite

show abstract

“…Traditional approaches often rely on handcrafted features, rule-based systems, and predefined thresholds to identify violent actions Bermejo Nievas et al ( 2011), Febin et al (2020), Senst et al (2017), Yao et al (2021), Ye et al (2020), Gao et al (2016). The approach by Febin et al (2020) extracts MoBSIFT features which calculates the SIFT features for motion features.…”

Section: Related Workmentioning

confidence: 99%

Flow accumulation-based violence detection model using transformers

Munusamy,

et al. 2024

Preprint

View full text Add to dashboard Cite

Violence detection in surveillance videos is one of the most challenging tasks in the field of video analysis. This work aims to enhance the accuracy and efficiency of the violence detection model by leveraging optical flow accumulation alongside traditional RGB frames as input to a transformer-based model. A novel frame extraction method is also proposed which accumulates motion information in a video. The flow-accumulated frames and the original frames of the video are combined in the Flow Fusion Attention Block. The proposed approach serves as a solution to increase the classification accuracy of transformer models in violent detection. The model achieves high accuracy by combining the RGB and flow-accumulated frames through the flow fusion attention block. The proposed approach is evaluated using different datasets and the performance is better than the other state-of-the-art approaches for violence detection.

show abstract

“…The accuracy rate of the HF dataset employed in their experiments was 92%. Yao et al [17] used a sparse optical flow algorithm to extract motion magnitude and orientation features around key points of interest. Khalil et al [18] divided the frame into 108 blocks and used a block-matching algorithm to extract one motion vector for each block, representing the displacement of each block of pixels between two consecutive frames.…”

Section: Handcrafted Featuresmentioning

confidence: 99%

Impulsive Aggression Break, Based on Early Recognition Using Spatiotemporal Features

Donia,

El-Behaidy,

Youssif

2023

BDCC

View full text Add to dashboard Cite

The study of human behaviors aims to gain a deeper perception of stimuli that control decision making. To describe, explain, predict, and control behavior, human behavior can be classified as either non-aggressive or anomalous behavior. Anomalous behavior is any unusual activity; impulsive aggressive, or violent behaviors are the most harmful. The detection of such behaviors at the initial spark is critical for guiding public safety decisions and a key to its security. This paper proposes an automatic aggressive-event recognition method based on effective feature representation and analysis. The proposed approach depends on a spatiotemporal discriminative feature that combines histograms of oriented gradients and dense optical flow features. In addition, the principal component analysis (PCA) and linear discriminant analysis (LDA) techniques are used for complexity reduction. The performance of the proposed approach is analyzed on three datasets: Hockey-Fight (HF), Stony Brook University (SBU)-Kinect, and Movie-Fight (MF), with accuracy rates of 96.5%, 97.8%, and 99.6%, respectively. Also, this paper assesses and contrasts the feature engineering and learned features for impulsive aggressive event recognition. Experiments show promising results of the proposed method compared to the state of the art. The implementation of the proposed work is available here.

show abstract

Motion Direction Inconsistency‐Based Fight Detection for Multiview Surveillance Videos

Cited by 10 publications

References 27 publications

Uncanny Activity Detection Using CCTV Monitoring

Uncanny Activity Detection Using CCTV Monitoring

Flow accumulation-based violence detection model using transformers

Impulsive Aggression Break, Based on Early Recognition Using Spatiotemporal Features

Contact Info

Product

Resources

About