| 领域知识优化深度置信网络的遥感变化检测 |
| |
| 引用本文： | 张海明,王明常,陈学业,王凤艳,杨国东,高苏.领域知识优化深度置信网络的遥感变化检测[J].武汉大学学报(信息科学版),2022,47(5):762-768. |
| |
| 作者姓名： | 张海明 王明常 陈学业 王凤艳 杨国东 高苏 |
| |
| 作者单位： | 1.吉林大学地球探测科学与技术学院，吉林 长春，130026 |
| |
| 基金项目： | 国家自然科学基金41472243自然资源部城市国土资源监测与仿真重点实验室开放基金KF-2018-03-020自然资源部城市国土资源监测与仿真重点实验室开放基金KF-2019-04-080自然资源部地面沉降监测与防治重点实验室开放基金KLLSMP201901吉林省教育厅“十三五”科学研究规划项目JJKH20200999KJ |
| |
| 摘 要： | 为提高高分辨率遥感影像变化检测精度，提出一种以领域知识为优化策略的深度学习变化检测方法。利用改进的变化矢量分析和灰度共生矩阵算法获取影像的光谱和纹理变化，设定合理阈值获得变化区域待选样本；引入领域知识中图斑形状特征指数与光谱知识，筛选得到高质量的训练样本；构建并训练了深度置信网络模型，使用优化策略对深度学习变化检测结果进行优化，以减少“椒盐”噪声和伪变化区对检测精度的影响。通过高分二号与IKONOS影像的变化检测实验表明，该方法较优化前准确率与召回率最大增幅分别为7.58%和14.69%（高分二号）、17.08%和23.87%（IKONOS），虚警率和漏检率最大降幅为30.22%和23.30%（高分二号）、17.08%和23.87%（IKONOS），能够有效提高变化检测精度。
|
| 关 键 词： | 遥感 变化检测 深度置信网络 领域知识 高分二号 |
| 收稿时间： | 2019-12-25 |
Remote Sensing Change Detection Based on Deep Belief Networks Optimized by Domain Knowledge |
| |
| Institution: | 1.College of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, China2.Key Laboratory of Urban Land Resources Monitoring and Simulation, MNR, Shenzhen 518000, China3.Yunnan Provincial Mapping Institute, Kunming 650034, China |
| |
| Abstract: | Objectives A method of deep learning change detection with domain knowledge as an optimization strategy was proposed to improve the change detection precision of high-resolution remote sensing im?ages. Methods The improved change vector analysis algorithm and grey-level co-occurrence matrix algorithm were used to obtain the spectral and texture changes of images, and reasonable thresholds were set to divide the changed samples from the unchanged samples based on the spectral and texture change intensity maps. The pattern shape index and spectral knowledge in domain knowledge were introduced as an optimization strategy to filter the changed samples for obtaining high-quality training samples. The deep belief network model was constructed and trained, and the results of deep learning change detection were optimized by the optimization strategy to reduce the influence of "salt and pepper noise" and false change zones on the detection accuracy. Results The Results of change detection experiments show that the accuracies of Gaofen-2 and IKONOS imageswere increased by 7.58% and 14.69% and the recall by 17.08% and 23.87%, respectively, while the false alarms and were decreased by 30.22% and 23.30% and the missing alarms by 17.08% and 23.87%, respectively. Conclusions Compared with the method before the optimization strategy was adopted, the proposed method in this paper can effectively improve the precision of change detection, and it provides a new way of using remote sensing images to improve the precision of deep learning change detection. |
| |
| Keywords: | |
|
| 点击此处可从《武汉大学学报(信息科学版)》浏览原始摘要信息 |
| 点击此处可从《武汉大学学报(信息科学版)》下载免费的PDF全文 |
|
