基于负样本多通道优化SSD网络的钢铁厂提取 |
| |
作者姓名: | 卢凯旋 李国清 陈正超 昝露洋 李柏鹏 高建威 |
| |
作者单位: | 1. 中国科学院遥感与数字地球研究所, 北京 100094;
2. 中国科学院大学资源与环境学院, 北京 100094;
3. 河南省遥感测绘院, 郑州 450003 |
| |
基金项目: | 中国科学院A类战略性先导科技专项(XDA19080302)资助 |
| |
摘 要: | 准确提取钢铁厂对去产能监测和环境保护具有重要意义。传统的人工目视解译方法效率低、成本高,无法满足开展大区域钢铁厂监测的需求。以深度学习目标检测网络SSD为基础,构建面向遥感影像钢铁厂提取的深度学习目标检测网络,提出maxout模块,将负样本通路优化为多分支结构,突出难分负样本特征并提升网络对无用特征的抵制效果。利用国产GF-1数据对京津冀地区的钢铁厂进行快速自动提取实验。与人工解译的钢铁厂点位数据的对比表明,该目标检测方法的提取精度达到80%以上。
|
关 键 词: | 深度学习 GF-1遥感影像 钢铁厂提取 京津冀地区 maxout模块 目标检测 |
收稿时间: | 2019-01-23 |
修稿时间: | 2019-03-20 |
Extraction of steel plants based on optimized SSD network incorporating negative sample's multi channels |
| |
Authors: | LU Kaixuan LI Guoqing CHEN Zhengchao ZAN Luyang LI Baipeng GAO Jianwei |
| |
Institution: | 1. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China;
2. College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China;
3. Institute of Remote Sensing and Surveying and Mapping Henan, Zhengzhou 450003, China |
| |
Abstract: | It is important to accurately detect steel plants for capacity reduction monitoring and environmental protection. The traditional method is time-consuming and laborious, and can not be used to monitor the steel plants in large areas. We propose a stable and accurate method by adding a maxout module to SSD, namely, transforming the negative sample path into a multi-branch structure. The neural network learns abundant features of hard negative samples, and thereby increases resistance to the useless features. Meanwhile, we used the well-trained model to detect steel plants in the Jing-Jin-Ji area based on GF-1 data. The results were compared with the data of the steel plants obtained from visual interpretation. Our method detects steel plants in the Jing-Jin-Ji area with an accuracy of more than 80%. |
| |
Keywords: | deep learning GF-1 data steel plant detection Jing-Jin-Ji area maxout module object detection |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |