• Journal of Information Technology Services
• /
• v.23 no.4
• /
• pp.45-53
• /
• 2024

Recently, as social anxiety regarding violent crimes accompanied by frequent occurrences of violence has increased, the need for intelligent video analysis in CCTV systems for crime prevention and rapid response to incidents has grown. One of the methods used for detecting violent behavior through video analysis is action-based detection using pose estimation. However, relying solely on joint angles and changes obtained from pose estimation to detect violent acts can lead to issues. False positives occur when non-violent actions such as petting a head or hugging are mistakenly classified as violent behavior. This study aims to reduce the frequency of false positives in action-based violence detection methods that utilize only pose estimation. We propose a new violence detection method that combines the results of facial emotion recognition (anger, disgust, fear, sadness, surprise, happiness, and neutrality) of the expected victim with the existing pose estimation-based violence detection method. By combining pose estimation with facial emotion recognition results on a video dataset consisting of YouTube videos and self-made videos, we were able to achieve a higher accuracy rate of 92.5% compared to the traditional method which solely relies on pose estimation. Future research will focus on studying violence detection in actual CCTV scenarios to improve the reliability of the result data.

• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.234-239
• /
• 2017

A real-time violence detection algorithm based on a new descriptor using the magnitude and direction changes of movement in images is proposed. The descriptor was developed from the observation that the changes of violent actions are much larger than those of normal movements. Descriptor feature vectors consisting of descriptor values during several frames are obtained and these are inputs to SVM(Support Vector Machine) classifier for discriminating violence actions from and non-violence actions. Comparison experiments between the ViF(Violent Flow) and the proposed algorithm were conducted with three different types of datasets. The experimental results show that the proposed algorithm outperforms the ViF in every case.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.95-100
• /
• 2012

In this paper, we see the means for the assault, the type of unlawful exercise of power. Also, we see the violence, the physical exercise accompanying with assault. Now, it has caused numerous crimes in elevators. This paper is to present a way to extract the violence and assault that occurred in elevators. Key frame was extract by color histogram method, one of the ways to scene change detection techniques. Extracted key frames are key frames of a scene containing a forensic crime scene video. Also, the key frames of the scene should be submitted to the forensic evidence.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.671-682
• /
• 2024

Violence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short-term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1-score. The use of ResNet50V2 for feature extraction can improve model performance.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.98-106
• /
• 2020

Currently, as Internet users increase, the use of swearword is indiscriminately increasing. As a result, cyber violence among teenagers is increasing very seriously, and among them, cyber-language violence is the most serious. In order to eradicate cyber-language violence, research on detection of swearword has been conducted, but the method of detecting swearword by looking at the meaning of words and the flow of context is insufficient. Therefore,in this paper,we propose a method of detecting swearword using FastText model and LSTM model so that deliberately modified swearword and standard language can be accurately detected by looking at the flow of context.

• Journal of Korean Academy of Nursing
• /
• v.31 no.6
• /
• pp.1067-1076
• /
• 2001

This study was to developed to create a CD-ROM and an educational program for the prevention of sexual harassment and violence and to contribute to the perception and add to the coping of the victims of sexual harassment and violence as well as the child, parents, and teachers. Method: The study's methods were literature reviews, surveys, and assessments of the negotiation process for educational needs of sexual harassed and abused children. Result: The sexual harassment and violence prevention program will contain four subjects : 1) sexual development of a preschool child, 2) characteristics of sexual harassment and violence of a preschool child, 3) safe sex, early detection of sexual violence syndrome, and coping strategies. The CD-RON was composed from three sites. The first was a child site, the second was a parent/teacher site, and the third was a game site for evaluations. The child site consisted of 10 possible scenarios of sexual harassment and violence that a child could experience. The parent/teacher site consisted of knowledge and information for prevention and coping strategies for sexual harassment and violence. At the end of each situation question and answer sections that were used for formative evaluation. Also, the game site could be a summative evaluation. Conclusion: The effects of this program and the CD-ROM were based of the promotion of reverence for humanity and gender equality for preschool childen. Eventually, children, parents, and teachers will have prevention and coping ability that will reduce the occurrence of sexual harassment and violence in Korea

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.430-439
• /
• 2015

The demand of violence detection techniques using a video analysis to help prevent crimes is increasing recently. Many researchers have studied vision based behavior recognition but, violent behavior analysis techniques usually focus on violent scenes in television and movie content. Many methods previously published usually used both a color(e.g., skin and blood) and motion information for detecting violent scenes because violences usually involve blood scenes in movies. However, color information (e.g., blood scenes) may not be useful cues for violence detection in surveillance videos, because they are rarely taken in real world situations. In this paper, we propose a method of violent behavior detection in surveillance videos using motion vectors such as flow vector magnitudes and changes in direction except the color information. In order to evaluate the proposed algorithm, we test both USI dataset and various real world surveillance videos from YouTube.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.11
• /
• pp.2191-2203
• /
• 2011

In this paper, we propose a fast and robust algorithm for fighting behavior detection based on Motion Vectors (MV), in order to solve the problem of low speed and weak robustness in traditional fighting behavior detection. Firstly, we analyze the characteristics of fighting scenes and activities, and then use motion estimation algorithm based on block-matching to calculate MV of motion regions. Secondly, we extract features from magnitudes and directions of MV, and normalize these features by using Joint Gaussian Membership Function, and then fuse these features by using weighted arithmetic average method. Finally, we present the conception of Average Maximum Violence Index (AMVI) to judge the fighting behavior in surveillance scenes. Experiments show that the new algorithm achieves high speed and strong robustness for fighting behavior detection in surveillance scenes.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.53-59
• /
• 2018

Due to the recent developments in computer vision technology, complex actions can be recognized with reasonable accuracy in smart cities. In contrast, violence recognition such as events related to fight and knife, has gained less attention. The capability of visual surveillance can be used for detecting fight in streets or in prison centers. In this paper, we proposed a deep learning-based violence recognition method for surveillance cameras. A convolutional neural network (CNN) model is trained and fine-tuned on available benchmark datasets of fights and knives for violence recognition. When an abnormal event is detected, an alarm can be sent to the nearest police station to take immediate action. Moreover, when the probabilities of fight and knife classes are predicted very low, this situation is considered as normal situation. The experimental results of the proposed method outperformed other state-of-the-art CNN models with high margin by achieving maximum 99.21% accuracy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.109-111
• /
• 2013

The attack refers to the act deliberately to stimulate an abomination to the people. Of violence, such as physical aggression, direct physical forcing. Assault said to contact the opponent's body with the power to superior opponent. In other words, it is the act of hitting an opponent with the fist. In this paper, the violence and assaults that occur in elevators extracted using a color histogram of scene change detection technique.