Object recognition in videos by sequential frame extraction using convolutional neural networks and fully connected neural networks

机译：通过使用卷积神经网络和全连接神经网络的顺序帧提取，对视频中的对象进行识别

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper, a method to develop an interactive application in order to detect objects from videos is proposed. The application is able to classify the video according to a particular genre. Also, upon user input, it is also able to detect the particular object being shown at that instant on the screen. A sequential frame extraction method of videos and also deep learning approach of Convolutional Neural Networks along with Fully Connected Neural Networks is used for this task. The method gives good accuracy of average 77 percent.

机译：本文提出了一种开发交互式应用程序以从视频中检测对象的方法。该应用程序能够根据特定类型对视频进行分类。同样，在用户输入时，它也能够检测到当时在屏幕上显示的特定对象。视频的顺序帧提取方法以及卷积神经网络和全连接神经网络的深度学习方法均用于此任务。该方法的平均准确度高达77％。

著录项

来源
《International Conference on Energy, Communication, Data Analytics and Soft Computing》|2017年|1485-1488|共4页
会议地点 Chennai(IN)
作者
Meghajit Mazumdar; V Sarasvathi; Akshay Kumar;
展开▼
作者单位

Department of Computer Science and Engineering PESIT Bangalore South Campus Bangalore Karnataka India;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Videos; Training; Object recognition; Convolutional neural networks; Biological neural networks; Task analysis; Neurons;

机译：影片；训练;对象识别；卷积神经网络生物神经网络；任务分析；神经元;

相似文献

外文文献
中文文献
专利

1. KeyFrame extraction based on face quality measurement and convolutional neural network for efficient face recognition in videos [J] . Abed Rahma, Bahroun Sahbi, Zagrouba Ezzeddine Multimedia Tools and Applications . 2021,第15期

机译：基于面部质量测量和卷积神经网络的关键帧提取，以便视频高效脸部识别
2. Convolutional neural networks for relevance feedback in content based image retrieval A Content based image retrieval system that exploits convolutional neural networks both for feature extraction and for relevance feedback [J] . Lorenzo Putzu, Luca Piras, Giorgio Giacinto Multimedia Tools and Applications . 2020,第37a38期

机译：基于内容的图像检索的相关反馈的卷积神经网络基于内容的图像检索系统，用于利用特征提取和相关性反馈的卷积神经网络
3. The Recognition Of Partially Occluded Objects with Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks [J] . Joseph Lin Chu, Adam Krzy?ak Journal of Artificial Intelligence and Soft Computing Research . 2014,第1期

机译：支持向量机，卷积神经网络和深信度网络对部分遮挡物体的识别
4. Object Recognition in Videos by Sequential Frame Extraction using Convolutional Neural Networks and Fully Connected Neural Networks [C] . Meghajit Mazumdar, Sarasvathi V., Akshay Kumar International Conference on Energy, Communication, Data Analytics and Soft Computing . 2017

机译：使用卷积神经网络和完全连接的神经网络顺序帧提取通过顺序帧提取对象识别
5. Object Recognition in Videos Utilizing Hierarchical and Temporal Objectness with Deep Neural Networks. [D] . Peng, Liang. 2017

机译：利用具有深度神经网络的分层和时间对象性的视频中的对象识别。
6. Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction [O] . Dat Tien Nguyen, Ki Wan Kim, Hyung Gil Hong, 2017

机译：基于卷积神经网络的可见光和热成像摄像机视频对人体图像的性别识别
7. Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction [O] . Dat Tien Nguyen, Ki Wan Kim, Hyung Gil Hong, 2017

机译：基于卷积神经网络的可见光和热像仪视频对人体图像的性别识别
8. Multi-Frame Convolutional Neural Networks for Object Detection in Temporal Data. [R] . Downs, J. 2017

机译：用于时态数据目标检测的多帧卷积神经网络。

Object recognition in videos by sequential frame extraction using convolutional neural networks and fully connected neural networks

摘要

著录项

相似文献

相关主题

期刊订阅