| 结合边缘检测的语义分割算法 |
| |
| 引用本文： | 王囡,侯志强,赵梦琦,余旺盛,马素刚. 结合边缘检测的语义分割算法[J]. 计算机工程, 2021, 47(7): 257-265. DOI: 10.19678/j.issn.1000-3428.0058167 |
| |
| 作者姓名： | 王囡 侯志强 赵梦琦 余旺盛 马素刚 |
| |
| 作者单位： | 1. 西安邮电大学 计算机学院, 西安 710121;2. 西安邮电大学 陕西省网络数据分析与智能处理重点实验室, 西安 710121;3. 空军工程大学 信息与导航学院, 西安 710077 |
| |
| 基金项目： | 国家自然科学基金（61473309,61703423）。 |
| |
| 摘 要： | 针对语义分割中目标边缘模糊与分割不准确的问题,提出一种结合边缘检测的语义分割网络.整个网络由边缘检测网络和语义分割网络并行组成.利用边缘检测网络与语义分割网络分别提取图像的边缘特征和初步的语义分割特征,通过特征融合模块将边缘特征和语义分割特征进行融合,得到最终的语义分割结果.在CamVid数据集和Cityscapes数...
|
| 关 键 词： | 卷积神经网络 全卷积网络 语义分割 边缘检测 特征融合 |
| 收稿时间： | 2020-04-24 |
| 修稿时间： | 2020-06-03 |
Semantic Segmentation Algorithm Combined with Edge Detection |
| |
| WANG Nan,HOU Zhiqiang,ZHAO Mengqi,YU Wangsheng,MA Sugang. Semantic Segmentation Algorithm Combined with Edge Detection[J]. Computer Engineering, 2021, 47(7): 257-265. DOI: 10.19678/j.issn.1000-3428.0058167 |
| |
| Authors: | WANG Nan HOU Zhiqiang ZHAO Mengqi YU Wangsheng MA Sugang |
| |
| Affiliation: | 1. College of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an 710121, China;2. Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an 710121, China;3. Information and Navigation Institute, Air Force Engineering University, Xi'an 710077, China |
| |
| Abstract: | To address the fuzzy and inaccurate target edges in semantic segmentation,a semantic segmentation network combined with edge detection is proposed.The network consists of an edge detection network and a semantic segmentation network.The edge detection network is used to extract the edge features of the image,while the semantic segmentation network is used to extract the preliminary semantic segmentation features.The edge features and the semantic segmentation features are fused through the feature fusion module to obtain the final semantic segmentation result.The experimental results show that compared with the SegNet algorithm,the proposed algorithm improves the mIoU by 1.5 percentage points on the CamVid dataset and 1.8 percentage points on the Cityscapes dataset.The effectiveness of the proposed algorithm is verified. |
| |
| Keywords: | convolutional neural network Fully Convolutional Network(FCN) semantic segmentation edge detection feature fusion |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
|
