| 一种基于2D时空信息提取的行为识别算法 |
| |
| 引用本文： | 刘董经典,孟雪纯,张紫欣,杨旭,牛强.一种基于2D时空信息提取的行为识别算法[J].智能系统学报,2020,15(5):900-909. |
| |
| 作者姓名： | 刘董经典 孟雪纯 张紫欣 杨旭 牛强 |
| |
| 作者单位： | 中国矿业大学 计算机科学与技术学院，江苏 徐州 221008 |
| |
| 摘 要： | 基于计算机视觉的人体行为识别技术是当前的研究热点，其在行为检测、视频监控等领域都有着广泛的应用价值。传统的行为识别方法，计算比较繁琐，时效性不高。深度学习的发展极大提高了行为识别算法准确性，但是此类方法和图像处理领域相比，效果上存在一定的差距。设计了一种基于DenseNet的新颖的行为识别算法，该算法以DenseNet做为网络的架构，通过2D卷积操作进行时空信息的学习，在视频中选取用于表征行为的帧，并将这些帧按时空次序组织到RGB空间上，传入网络中进行训练。在UCF101数据集上进行了大量实验，实验准确率可以达到94.46%。
|
| 关 键 词： | 行为识别 视频分析 神经网络 深度学习 卷积神经网络 分类 时空特征提取 密集连接卷积网络 |
A behavioral recognition algorithm based on 2D spatiotemporal information extraction |
| |
| LIU Dongjingdian,MENG Xuechun,ZHANG Zixin,YANG Xu,NIU Qiang.A behavioral recognition algorithm based on 2D spatiotemporal information extraction[J].CAAL Transactions on Intelligent Systems,2020,15(5):900-909. |
| |
| Authors: | LIU Dongjingdian MENG Xuechun ZHANG Zixin YANG Xu NIU Qiang |
| |
| Affiliation: | College of Computer Science & Technology, China University of Mining and Technology , Xuzhou 221008, China |
| |
| Abstract: | Human behavior recognition technology based on computer vision is a research hotspot currently. It is widely applied in various fields of social life, such as behavioral detection, video surveillance, etc. Traditional behavior recognition methods are computationally cumbersome and time-sensitive. Therefore, the development of deep learning has greatly improved the accuracy of behavior recognition algorithms. However, compared with the field of image processing, there is a certain gap in the effect of such methods. We introduce a novel behavior recognition algorithm based on DenseNet, which uses DenseNet as the network architecture, learns spatio-temporal information through 2D convolution, selects frames for characterizing behavior in video, organizes these frames into RGB space in time-space order and inputs them into our network to train the network. We have carried out a large number experiments on the UCF101 dataset, and our method can reach an accuracy rate of 94.46%. |
| |
| Keywords: | behavior recognition video analysis neural networks deep learning convolutional neural networks classification spatiotemporal feature densenet |
|
| 点击此处可从《智能系统学报》浏览原始摘要信息 |
|
点击此处可从《智能系统学报》下载全文 |
|
