| 基于多层信息融合的实时语义分割 及其在电力场景中的应用 |
| |
| 引用本文： | 周晨轶,王文,卢杉,徐亦白. 基于多层信息融合的实时语义分割 及其在电力场景中的应用[J]. 计算机与现代化, 2019, 0(8): 17. DOI: 10.3969/j.issn.1006-2475.2019.08.004 |
| |
| 作者姓名： | 周晨轶 王文 卢杉 徐亦白 |
| |
| 作者单位： | 国网浙江省电力有限公司信息通信分公司,浙江 杭州,310007;国网浙江省电力有限公司信息通信分公司,浙江 杭州,310007;国网浙江省电力有限公司信息通信分公司,浙江 杭州,310007;国网浙江省电力有限公司信息通信分公司,浙江 杭州,310007 |
| |
| 基金项目： | 国网浙江省电力有限公司科技项目（5211XT17000C） |
| |
| 摘 要： | 语义分割是计算机视觉的一项基础工作。本文提出一种新型的结合点卷积与空洞卷积的上采样结构,并基于该结构设计一个能融合多层信息的实时语义分割模型。该模型在Cityscapes数据集上的mIoU能达到72.1%,对于640×360的输入图像,运行速度能达到125 fps,同时该模型在电力场景数据集下也有很好的效果。此外,本文还将该模型移植到移动端,实现一款基于语义分割的电力场景增强现实应用。
|
| 关 键 词： | 深度学习 语义分割 卷积神经网络 电力场景 |
| 收稿时间： | 2019-08-16 |
Real-time Semantic Segmentation Based on Multi-scale Fusion #br# and Its Application in Electric Power Scene |
| |
| ZHOU Chen-yi,WANG Wen,LU Shan,XU Yi-bai. Real-time Semantic Segmentation Based on Multi-scale Fusion #br# and Its Application in Electric Power Scene[J]. Computer and Modernization, 2019, 0(8): 17. DOI: 10.3969/j.issn.1006-2475.2019.08.004 |
| |
| Authors: | ZHOU Chen-yi WANG Wen LU Shan XU Yi-bai |
| |
| Abstract: | Semantic segmentation is a basic work in computer vision. In this paper, a new upsampling structure combined point-wise convolution with dilation convolution is proposed and a real-time semantic segmentation model is designed based on this structure. The model can reach 72.1% mIoU and 125 fps running speed with the input of 640×360 on Cityscapes data set and has also good performance on a electric power scene data set. In addition, the paper transplants the model to the mobile terminal and implements an augmented reality application of electric power scene based on semantic segmentation. |
| |
| Keywords: | deep learning semantic segmentation convolutional neural networks electric power scene |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机与现代化》浏览原始摘要信息 |
|
点击此处可从《计算机与现代化》下载全文 |
|
