| 基于改进Faster-RCNN的IT设备图像定位与识别 |
| |
| 引用本文： | 张晓,丁云峰. 基于改进Faster-RCNN的IT设备图像定位与识别[J]. 计算机系统应用, 2021, 30(9): 288-294. DOI: 10.15888/j.cnki.csa.008077 |
| |
| 作者姓名： | 张晓 丁云峰 |
| |
| 作者单位： | 中国科学院大学, 北京 100049;中国科学院 沈阳计算技术研究所 系统与软件事业部, 沈阳 110168 |
| |
| 摘 要： | 本文根据国家电网IT设备识别的具体应用场景的特点,通过改进Faster-RCNN实现设备的精确识别定位,进而提高了电网数据中心管理的效率.文章主要在注意力机制、初始锚框调整以及锚框融合等方面进行改进.通过与常见图像算法的横向比较发现改进后的模型在收敛速度上提高了30％,精度上提高了1％.
|
| 关 键 词： | 图像识别 注意力机制 卷积网络 图像定位 |
| 收稿时间： | 2020-12-08 |
| 修稿时间： | 2021-01-08 |
Identification and Location of IT Equipment Based on Improved Faster-RCNN |
| |
| ZHANG Xiao,DING Yun-Feng. Identification and Location of IT Equipment Based on Improved Faster-RCNN[J]. Computer Systems& Applications, 2021, 30(9): 288-294. DOI: 10.15888/j.cnki.csa.008077 |
| |
| Authors: | ZHANG Xiao DING Yun-Feng |
| |
| Affiliation: | University of Chinese Academy of Sciences, Beijing 100049, China; System and Software Division, Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shengyang 110168, China |
| |
| Abstract: | In this study, according to the characteristics of specific application scenarios for the IT equipment identification of State Grid, accurate identification and positioning of the equipment is realized with improved Faster-RCNN, thereby improving the management efficiency of the grid data center. The algorithm is improved mainly in terms of the attention mechanism, the initial anchor box adjustment and the anchor box fusion. The comparison with common image algorithms shows that the improved model has the convergence speed and the accuracy increased by 30% and 1%, respectively. |
| |
| Keywords: | image identification attention mechanism convolutional network image positioning |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
