智能机房监控系统中损失函数与图像合成的优化

朱曦阳; 张春; 张德兵

Chinese

您当前的位置：

首页 >

文章列表页 >

智能机房监控系统中损失函数与图像合成的优化

更新时间：2026-09-04

- 智能机房监控系统中损失函数与图像合成的优化
- Optimization of Loss Function and Image Synthesis in Smart Server Monitoring System
- 微电子学与计算机 2019年36卷第1期页码：37-40
- 作者机构：
  
  清华大学微电子学研究所,北京,100084
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目 61327809
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
朱曦阳, 张春, 张德兵. 智能机房监控系统中损失函数与图像合成的优化[J]. 微电子学与计算机, 2019, 36(1): 37-40, 45.

ZHU Xi-yang, ZHANG Chun, ZHANG De-bing. Optimization of Loss Function and Image Synthesis in Smart Server Monitoring System[J]. 2019, 36(1): 37-40.
朱曦阳, 张春, 张德兵. 智能机房监控系统中损失函数与图像合成的优化[J]. 微电子学与计算机, 2019, 36(1): 37-40, 45. DOI：

ZHU Xi-yang, ZHANG Chun, ZHANG De-bing. Optimization of Loss Function and Image Synthesis in Smart Server Monitoring System[J]. 2019, 36(1): 37-40. DOI：

摘要

为了实时监控机房服务器的工作状态

提出了一种智能机房监控方案

其通过基于卷积网络的图像识别完成服务器以及指示灯状态的识别与监控.针对目标识别中样本类别失衡会导致训练模型不收敛的问题

设计了一种自动调控样本类别失衡的损失函数及参数更新算法

用于平衡难易样本的训练

在VOC2007数据集上的测试精度为78.3%

好于YOLOv2等先进算法.为了减少训练数据采集所需要的成本

提出了一种基于多尺度化随机边缘信息融合算法的图像合成方法

使合成图片更加注重边缘信息

在Cityscapes数据集测试的像素精度为71%

较大程度超过pix2pix等方法

证明其可以大大降低图像采集成本.

Abstract

A smart server monitoring system is proposed to detect the working status of the server in real time

which finishes the recognition of the status of the server and indicator light through image recognition based on convolutional neural network. In order to solve the problem of class imbalance in target recognition

a novel loss function is designed to adjust class imbalances automatically. Its test accuracy of VOC2007 is 78.3%

which is better than the advanced methods such as YOLOv2. In addition

an image synthesis method based on multi-scale edge information fusion algorithm is proposed to reduce the cost of data collection. Its pixel precision of Cityscapes is 71%

which is much better than pix2pix.

关键词

Keywords

references

Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu, Hawaii, USA: IEEE, 2017: 5967-5976.

Joseph Redmon, Ali Farhadi. YOLO9000: Better, faster, stronger[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu, Hawaii, USA: IEEE, 2017: 6517-6525.

Joseph Redmon, Santosh Divvala, Ross Girshick, et al. You only look once: unified, real-time object detection[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas, Nevada, USA: IEEE, 2016: 779-788.

Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector[C]//European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, Cham, 2016: 21-37.

Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2017, 39(6): 1137-1149. DOI: 1137

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种高效检测道路物体的强拓展性特征提取网络

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

超低功耗实时时钟电路的设计

低功耗设计的双链电源关断策略的实现与验证

基于监控指标关联性的微服务异常检测