A multi-temporal framework for high-level activity analysis: Violent event detection in visual surveillance

Song, Donghui; Kim, Chansu; Park, Sung-Kee

doi:10.1016/j.ins.2018.02.065

Cited by 20 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On another note, as the latent representation can be viewed as an organized set of elements assessing the presence of specific sub-events, the proposed method works in a hierarchical way. Yet, the temporal relationships between these sub-events are not captured implicitly or explicitly; thus, we believe that the proposed approach could help address the unsolved problem [ 29 ] of high-level action recognition with machine learning based methods as the difficulty that previous algorithms faced with this type of actions lies in the fact that they have important temporal variations between the sub-events composing them. This hierarchical approach also allowed us to infer on times series extended up to various lengths without compromising the accuracy.…”

Section: Discussionmentioning

confidence: 99%

A Hierarchical Learning Approach for Human Action Recognition

Lemieux

Noumeir

2020

Sensors

View full text Add to dashboard Cite

In the domain of human action recognition, existing works mainly focus on using RGB, depth, skeleton and infrared data for analysis. While these methods have the benefit of being non-invasive, they can only be used within limited setups, are prone to issues such as occlusion and often need substantial computational resources. In this work, we address human action recognition through inertial sensor signals, which have a vast quantity of practical applications in fields such as sports analysis and human-machine interfaces. For that purpose, we propose a new learning framework built around a 1D-CNN architecture, which we validated by achieving very competitive results on the publicly available UTD-MHAD dataset. Moreover, the proposed method provides some answers to two of the greatest challenges currently faced by action recognition algorithms, which are (1) the recognition of high-level activities and (2) the reduction of their computational cost in order to make them accessible to embedded devices. Finally, this paper also investigates the tractability of the features throughout the proposed framework, both in time and duration, as we believe it could play an important role in future works in order to make the solution more intelligible, hardware-friendly and accurate.

show abstract

Section: Discussionmentioning

confidence: 99%

A Hierarchical Learning Approach for Human Action Recognition

Lemieux

Noumeir

2020

Sensors

View full text Add to dashboard Cite

show abstract

“… Song, Kim & Park (2018) proposes a new framework for high-level activity analysis based on late fusion and multi-independent temporal perception layers, which is based on late fusion. It is possible to manage the temporal variety of high-level activities using this approach.…”

Section: Classification Of Violence Detection Techniquesmentioning

confidence: 99%

State-of-the-art violence detection techniques in video surveillance security systems: a systematic review

Omarov

Narynov²,

Zhumanov

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

We investigate and analyze methods to violence detection in this study to completely disassemble the present condition and anticipate the emerging trends of violence discovery research. In this systematic review, we provide a comprehensive assessment of the video violence detection problems that have been described in state-of-the-art researches. This work aims to address the problems as state-of-the-art methods in video violence detection, datasets to develop and train real-time video violence detection frameworks, discuss and identify open issues in the given problem. In this study, we analyzed 80 research papers that have been selected from 154 research papers after identification, screening, and eligibility phases. As the research sources, we used five digital libraries and three high ranked computer vision conferences that were published between 2015 and 2021. We begin by briefly introducing core idea and problems of video-based violence detection; after that, we divided current techniques into three categories based on their methodologies: conventional methods, end-to-end deep learning-based methods, and machine learning-based methods. Finally, we present public datasets for testing video based violence detectionmethods’ performance and compare their results. In addition, we summarize the open issues in violence detection in videoand evaluate its future tendencies.

show abstract

“…Fully automated systems can detect human activity through computer vision and machine learning and are more effective and efficient in detecting object movements and recognizing human activity as compared to semiautomated systems [12,13]. Human activity recognition is a difficult task because of many factors such as real-time classification, low video quality of surveillance cameras, and inconsistent light intensity during monitoring [14].…”

Section: Introductionmentioning

confidence: 99%

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

Ahmed¹,

Ramzan²,

Khan³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Violence recognition is crucial because of its applications in activities related to security and law enforcement. Existing semi-automated systems have issues such as tedious manual surveillances, which causes human errors and makes these systems less effective. Several approaches have been proposed using trajectory-based, non-object-centric, and deep-learning-based methods. Previous studies have shown that deep learning techniques attain higher accuracy and lower error rates than those of other methods. However, the their performance must be improved. This study explores the state-of-the-art deep learning architecture of convolutional neural networks (CNNs) and inception V4 to detect and recognize violence using video data. In the proposed framework, the keyframe extraction technique eliminates duplicate consecutive frames. This keyframing phase reduces the training data size and hence decreases the computational cost by avoiding duplicate frames. For feature selection and classification tasks, the applied sequential CNN uses one kernel size, whereas the inception v4 CNN uses multiple kernels for different layers of the architecture. For empirical analysis, four widely used standard datasets are used with diverse activities. The results confirm that the proposed approach attains 98% accuracy, reduces the computational cost, and outperforms the existing techniques of violence detection and recognition.

show abstract

A multi-temporal framework for high-level activity analysis: Violent event detection in visual surveillance

Cited by 20 publications

References 26 publications

A Hierarchical Learning Approach for Human Action Recognition

A Hierarchical Learning Approach for Human Action Recognition

State-of-the-art violence detection techniques in video surveillance security systems: a systematic review

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

Contact Info

Product

Resources

About