Human Activity Recognition Based on Loss-Net Fusion Domain Convolutional Neural Networks

机译：基于损失网融合域卷积神经网络的人类活动识别

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Human activity recognition is now a hot issue in artificial intelligence research. The purpose of activity recognition is to analyze behaviors in an unknown video or image sequence by computer. Unlike previous static recognition, the challenge of behavior recognition is how to capture motions between still frames. For reports of Convolutional Neural Network(CNN) architecture in the past, we used a method of implicitly capturing motion information between adjacent frames to improve the CNN architecture, taking the original video frames as input and predicting the action class without explicit optical action class calculation directly. Our architecture was trained and tested using videos from the UCF-101 human behavior database and achieved very ideal results.

机译：人类活动识别现在是人工智能研究中的一个热门问题。活动识别的目的是通过计算机分析未知视频或图像序列中的行为。与以前的静态识别不同，行为识别的挑战在于如何捕获静止帧之间的运动。对于过去的卷积神经网络（CNN）架构的报告，我们使用一种隐式捕获相邻帧之间的运动信息的方法来改进CNN架构，以原始视频帧作为输入并预测动作类别，而无需进行显式的光学动作类别计算直。我们的体系结构使用UCF-101人类行为数据库中的视频进行了培训和测试，并取得了非常理想的结果。

著录项

来源
《IEEE International Conference on Computation, Communication and Engineering》|2019年|146-149|共4页
会议地点 Fujian(CN)
作者
Zhang Ning; Lee Suk-Hwan; Lee Eung-Joo;
展开▼
作者单位

Tongmyong Unvierstiy Dept. of Information and Communication Engineering;

Tongmyong University 428 Sinseon-ro Nam-gu Dept. of Information Protection Engineering Busan Republic of Korea;

Tongmyong Unvierstiy Dept. of Information and Communication Engineeri;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Optical flow; Convolutional neural networks; Streaming media; Feature extraction; Computer vision; Activity recognition; Image recognition;

机译：光流卷积神经网络流媒体；特征提取;计算机视觉;活动识别；影像识别;

相似文献

外文文献
中文文献
专利

1. Data-level information enhancement: Motion-patch-based Siamese Convolutional Neural Networks for human activity recognition in videos [J] . Zhang Yujia, Po Lai Man, Liu Mengyang, Expert systems with applications . 2020,第Juna期

机译：数据级信息增强：视频中的运动补丁暹罗卷积神经网络，用于视频中的人类活动识别
2. Human Activity Recognition Based on Single Sensor Square HV Acceleration Images and Convolutional Neural Networks [J] . Mario Munoz-Organero IEEE sensors journal . 2019,第4期

机译：基于单传感器方形高压加速度图像和卷积神经网络的人体活动识别
3. Convolutional Neural Networks and Long Short-Term Memory for skeleton-based human activity and hand gesture recognition [J] . Nunez Juan C., Cabido Raul, Pantrigo Juan J., Pattern Recognition: The Journal of the Pattern Recognition Society . 2018,第期

机译：基于骨架的人类活动和手势识别的卷积神经网络和长短短期记忆
4. Human Activity Recognition Based on Loss-Net Fusion Domain Convolutional Neural Networks [C] . Zhang Ning, Lee Suk-Hwan, Lee Eung-Joo IEEE International Conference on Computation, Communication and Engineering . 2019

机译：基于损耗净融合域卷积神经网络的人类活动识别
5. A Human Visual System Inspired Feature Recognition Method Using Convolutional Neural Networks [D] . Koester, Evan. 2018

机译：基于卷积神经网络的人类视觉系统启发特征识别方法
6. Electroencephalography Based Fusion Two-Dimensional (2D)-Convolution Neural Networks (CNN) Model for Emotion Recognition System [O] . Yea-Hoon Kwon, Sae-Byuk Shin, Shin-Dug Kim 2018

机译：基于脑电图的融合二维（2D）-卷积神经网络（CNN）模型用于情绪识别系统
7. Human activity recognition and classification using of convolutional neural networks and recurrent neural networks [O] . Mohammed ALBABA, Alhakam QASSAB, Arif YILMAZ 2020

机译：人类活动认可与卷积神经网络和经常性神经网络的分类

Human Activity Recognition Based on Loss-Net Fusion Domain Convolutional Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅