Violent/Non-Violent Video Classification based on Deep Neural Network

机译：基于深度神经网络的暴力/非暴力视频分类

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In the context of video surveillance, detecting violence is an important task. This work presents a deep neural network based novel video classification to label violenceon-violence classes. First of all, frame-level descriptors are constructed based on optical flow and variants of Weber Local Descriptor. A novel scheme is presented to summarize the frame-level descriptors in to the video-level descriptor. An architecture for deep neural network with four hidden layers is proposed to classify a video as violent or non-violent. Proposed method is tested on two benchmark datasets. Comparison of performance with state-of-the-art systems establishes the superiority of the proposed method.

机译：在视频监视的背景下，检测暴力是一项重要任务。这项工作提出了一种基于深度神经网络的新颖视频分类，以标记暴力/非暴力类别。首先，基于光流和Weber Local Descriptor的变体构造帧级描述符。提出了一种新颖的方案来将帧级描述符概括为视频级描述符。提出了具有四个隐藏层的深度神经网络架构，以将视频分类为暴力或非暴力。建议的方法在两个基准数据集上进行了测试。将性能与最先进的系统进行比较，证明了所提出方法的优越性。

著录项

来源
《International Conference on Advances in Pattern Recognition》|2017年|1-6|共6页
会议地点 Bangalore(IN)
作者
Sounak Mondal; Soumyajit Pal; Sanjoy Kumar Saha; Bhabatosh Chanda;
展开▼
作者单位

Department of Computer Science and Engineering Jadavpur University Kolkata India;

Ele;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Neural networks; Histograms; Feature extraction; Training; Prototypes; Computer architecture; Benchmark testing;

机译：神经网络;直方图；特征提取;训练;原型；计算机架构;基准测试;

相似文献

外文文献
中文文献
专利

1. SIFT and Tensor Based Object Detection and Classification in Videos Using Deep Neural Networks [J] . N. Najva, K. Edet Bijoy Procedia Computer Science . 2016,第1期

机译：使用深度神经网络的视频中基于SIFT和Tensor的视频对象检测和分类
2. Movie trailer classification using deer hunting optimization based deep convolutional neural network in video sequences [J] . Prashant Giridhar Shambharkar, M. N. Doja Multimedia Tools and Applications . 2020,第29a30期

机译：电影拖车分类使用基于鹿狩猎优化的视频序列中的深卷积神经网络
3. Classification Program and Story Boundaries Segmentation in TV News Broadcast Videos via Deep Convolutional Neural Network [J] . Mounira Hmayda, Ridha Ejbali, Mourad Zaied Journal of computer sciences . 2020,第5期

机译：通过深度卷积神经网络，电视新闻广播视频中的分类计划和故事边界分割
4. Violent/Non-Violent Video Classification based on Deep Neural Network [C] . Sounak Mondal, Soumyajit Pal, Sanjoy Kumar Saha, International Conference on Advances in Pattern Recognition . 2017

机译：基于深神经网络的暴力/非暴力视频分类
5. Deep Neural Networks with Applications in Image and Video Classification and Recovery [D] . Kappeler, Armin. 2016

机译：深度神经网络及其在图像和视频分类与恢复中的应用
6. Can pre-trained convolutional neural networks be directly used as a feature extractor for video-based neonatal sleep and wake classification? [O] . Muhammad Awais, Xi Long, Bin Yin, 2020

机译：可以预先训练的卷积神经网络直接用作基于视频的新生儿睡眠和唤醒分类的特征提取器吗？
7. SIFT and Tensor Based Object Detection and Classification in Videos Using Deep Neural Networks [O] . Najva N., Bijoy K. Edet 2016

机译：使用深度神经网络的视频中基于SIFT和Tensor的视频对象检测和分类

Violent/Non-Violent Video Classification based on Deep Neural Network

摘要

著录项

相似文献

相关主题

期刊订阅