本文已被：浏览 814次 下载 1679次
Received:September 21, 2020 Revised:October 13, 2020
Received:September 21, 2020 Revised:October 13, 2020
中文摘要: 随着科技的不断发展, 越来越多的人工智能技术应用于社会生活. 依据这一现实, 本文运用当前较为热门的图像处理技术进行能识别视频中异常行为并给出预测值的系统开发. 首先, 我们利用双流膨胀3D卷积网络(Two-Stream-I3D)特征提取技术对视频进行特征提取. 其次, 运用Python对特征进行处理, 转化为深度学习网络所能识别的特征, 最后进行GRNN广义回归网络训练, 最终达到能对特征值进行良好的异常概率回归的效果. 实验表明, 运用本系统针对测试集近50例的视频的检测下, 系统的平均准确率达74%, 具有良好的性能.
中文关键词: 异常行为识别 双流膨胀3D卷积神经网络 概率回归
Abstract:Amid the continuous progress in technology, artificial intelligence technologies have been widely applied to the social life. This study develops a system that can identify abnormal behaviors in videos with predictive values. Firstly, we employ a Two-Stream Inflated3D (Two-Stream-I3D) convolutional neural network to extract features from the video. Secondly, we rely on Python to transform the features into those that can be recognized by a deep learning network. Finally, we perform GRNN training for abnormal probability regression. Experimental results show that the system can achieve the average accuracy of nearly 74% for abnormal behavior recognition during the detection of nearly 50 cases.
文章编号： 中图分类号： 文献标志码：
基金项目:广东省自然科学基金面上项目(2019A1515011375); 广州市科技计划重点领域研发计划(202007030005); 国家自然科学基金面上项目(61876067)
引用文本：
刘良鑫,林勉芬,钟良泉,彭雯雯,曲超,潘家辉.基于3D双流卷积神经网络的异常行为检测.计算机系统应用,2021,30(5):120-127
LIU Liang-Xin,LIN Mian-Fen,ZHONG Liang-Quan,PENG Wen-Wen,QU Chao,PAN Jia-Hui.Two-Stream Inflated 3D CNN for Abnormal Behavior Detection.COMPUTER SYSTEMS APPLICATIONS,2021,30(5):120-127
刘良鑫,林勉芬,钟良泉,彭雯雯,曲超,潘家辉.基于3D双流卷积神经网络的异常行为检测.计算机系统应用,2021,30(5):120-127
LIU Liang-Xin,LIN Mian-Fen,ZHONG Liang-Quan,PENG Wen-Wen,QU Chao,PAN Jia-Hui.Two-Stream Inflated 3D CNN for Abnormal Behavior Detection.COMPUTER SYSTEMS APPLICATIONS,2021,30(5):120-127
