[1]杨大为,刘志权.基于改进 VGG16 的自编码器视频异常检测算法[J].计算机技术与发展,2024,34(04):95-100.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 015]
 YANG Da-wei,LIU Zhi-quan.Auto-encoder Video Anomaly Detection Algorithm Based on Improved VGG16[J].,2024,34(04):95-100.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 015]
点击复制

基于改进 VGG16 的自编码器视频异常检测算法()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年04期
页码:
95-100
栏目:
媒体计算
出版日期:
2024-04-10

文章信息/Info

Title:
Auto-encoder Video Anomaly Detection Algorithm Based on Improved VGG16
文章编号:
1673-629X(2024)04-0095-06
作者:
杨大为刘志权
沈阳理工大学 信息科学与工程学院,辽宁 沈阳 110159
Author(s):
YANG Da-weiLIU Zhi-quan
School of Information Science and Engineering,Shenyang Ligong University,Shenyang 110159,China
关键词:
自编码器U-Net特征提取VGG16残差连接结构相似性
Keywords:
auto-encoderU-Netfeature extractionVGG16residual connectionstructure similarity
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 04. 015
摘要:
在使用自编码器结构的神经网络处理视频异常检测任务时,U-Net 风格的自编码器由于编码器层数深度过浅,导致在面对复杂的数据集时,不能充分抽取更多有用的特征信息。 同时,在训练模型时使用 MSE( 均方误差) ,仅考虑了预测帧与真实帧之间的像素级相似性,对于复杂场景,像素级相似性可能无法准确判断预测帧与真实帧之间的相似性。 针对以上问题,对基于 U-Net 风格的自编码器进行改进,提出了一种使用改进的 VGG16 作为编码器的视频异常检测算法,同时在均方误差的基础上添加结构相似性( SSIM)损失函数。 改进的 VGG16 去掉了全连接层,并加入了残差连接防止特征退化,添加 SSIM 在计算像素级相似性的同时计算图像的亮度、对比度和结构等方面的相似性来优化网络。 实验结果表明,改进后的算法,在 Ped2 数据集上检测效果达到 95. 91% ,在 Avenue 数据集上检测效果达到 84. 89% ,与改进前的方法相比分别提高了 0. 80% 和 0. 19% ,验证了所提方法的有效性。
Abstract:
When using the auto-encoder structure neural network to process video anomaly detection tasks,the U-Net style auto-encodercannot fully extract more useful feature?
information when facing complex data sets due to the shallow depth of the encoder layer. At thesame time,when training the model,MSE is used,only considering the?
pixel level similarity between the predicted frame and the realframe. For complex scenes,pixel level similarity may not accurately determine the similarity between the?
predicted frame and the realframe. To solve the above problems, the U - Net style auto - encoder is improved,and a video anomaly detection algorithm using theimproved?
VGG16 as the encoder is proposed. At the same time,the structure similarity ( SSIM) loss function is added on the basis of MSE. The improved VGG16 removes the fully connected layer and adds residual connections to prevent feature degradation. SSIM isadded to optimize the network by calculating pixel level similarity while also calculating image brightness, contrast, and structuralsimilarity. The experimental results show that the improved algorithm achieves a detection performance of 95. 91% on the Ped2 dataset and 84. 89% on the Avenue dataset,which is 0. 80% and 0. 19% higher than that of the previous method,respectively,verifying the effectiveness of the proposed method.

相似文献/References:

[1]刘 鑫,赵慧杰,武苏雯.基于U-Net的岩层图像裂缝检测算法应用[J].计算机技术与发展,2021,31(05):73.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 013]
 ,,et al.ApplicationofU-NetBasedRockFormationImageCrackDetectionAlgorithm[J].,2021,31(04):73.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 013]
[2]李博文,唐贵进,崔子冠.基于Retinex模型的弱光照图像增强算法[J].计算机技术与发展,2021,31(05):79.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 014]
 ,AWeaklyIlluminatedImageEnhancementAlgorithm BasedonRetinexModel[J].,2021,31(04):79.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 014]
[3]史健婷,崔闫靖,常 亮.基于优化 U-Net 网络的乳腺肿瘤区域分割方法[J].计算机技术与发展,2021,31(08):156.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 027]
 SHI Jian-ting,CUI Yan-jing,CHANG Liang.A Segmentation Method of Breast Tumor Region Based onOptimized U-Net[J].,2021,31(04):156.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 027]
[4]龚 安,赵 莉,姚鑫杰.基于改进的 U-Net 网络模型的气胸分割算法[J].计算机技术与发展,2021,31(10):173.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 029]
 GONG An,ZHAO Li,YAO Xin-jie.Pneumothorax Segmentation Algorithm Based on Improved U-Net Network Model[J].,2021,31(04):173.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 029]
[5]张洪波,隋文涛,袁摇 林,等.基于深度自编码器网络的压盖缺陷检测[J].计算机技术与发展,2022,32(02):143.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 023]
 ZHANG Hong-bo,SUI Wen-tao,YUAN Lin,et al.Capping Defect Detection Based on Deep Autoencoder Network[J].,2022,32(04):143.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 023]
[6]杨元英,王安志*,何淋艳,等.基于生成式对抗网络的图像修复研究进展[J].计算机技术与发展,2022,32(02):75.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 012]
 YANG Yuan-ying,WANG An-zhi*,HE Lin-yan,et al.Advances in Image Inpainting Based on Generative Adversarial Networks[J].,2022,32(04):75.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 012]
[7]喻鲁立,陈 黎.基于 U-Net 的多尺度视网膜血管分割方法[J].计算机技术与发展,2022,32(04):140.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 024]
 YU Lu-li,CHEN Li.Multi-scale Segmentation of Retinal Vessels Based on U-Net[J].,2022,32(04):140.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 024]
[8]黄 莉,何美玲*.基于 U-Net 改进模型的多模态脑肿瘤分割方法[J].计算机技术与发展,2022,32(11):58.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 009]
 HUANG Li,HE Mei-ling*.Multi-model Brain Tumor Segmentation Method Based on Improved U-Net Model[J].,2022,32(04):58.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 009]
[9]邓 祥,俞 璐,谢 钧,等.基于重构误差的深度聚类方法[J].计算机技术与发展,2022,32(11):30.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 005]
 DENG Xiang,YU Lu,XIE Jun,et al.Deep Clustering Method Based on Reconstruction Error[J].,2022,32(04):30.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 005]
[10]季倓正,邵允学,吕摇 刚.基于深度学习的钢坯入炉前定位技术[J].计算机技术与发展,2022,32(S2):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 006]
 JI Tan-zheng,SHAO Yun-xue,LYU Gang.Positioning Technology of Billet before Furnace Based on Deep Learning[J].,2022,32(04):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 006]

更新日期/Last Update: 2024-04-10