摘要
建筑物的变化检测在遥感图像处理和模式识别领域中具有重要意义,但在深度学习算法的应用中,数据标注一直是一个显著的挑战,特别是在变化检测的场景下。因此,针对基于深度学习的变化检测算法中数据标注的难题,本文提出了一种半监督学习方法。该方法采用了融合双时相特征的孪生网络来进行特征提取,并构建了一个教师-学生网络框架以实施模型的半监督训练。为了进一步提升半监督变化检测的准确度,本文在深度特征上引入了随机扰动,以此来实现一致性正则化。此外,在图像深度特征的层面上,本文还提出通过捕获双时相图像特征的差异来形成决策边界以区分双时相图变化的方法。该方法在Levir-CD和WHU_Building两个公开数据集上分别实现了83.04%和85.57%的交并比(Intersection over Union,IoU)。实验结果表明,本文提出的方法在使用少量标注数据的前提下,能够达到与全监督训练相近的性能。
Change detection in buildings holds significant importance in the fields of remote sensing image processing and pattern recognition.However,data annotation has always been a prominent challenge in the application of deep learning algorithms,especially in change detection scenarios.To address the data annotation challenges in deep learning-based change detection algorithms,this paper proposes an innovative semi-supervised learning method.This method employs a Siamese network that fuses bi-temporal features for feature extraction and constructs a teacher-student network framework for semi-supervised model training.To further enhance the accuracy of semi-supervised change detection,this paper introduces random perturbations in deep features to achieve consistency regularization.Additionally,on the level of image deep features,the paper proposes a method for forming decision boundaries by capturing differences in bi-temporal image features to distinguish changes in bitemporal images.This method achieved Intersection over Union(IoU)scores of 83.04%and 85.57%on the Levir-CD and WHU Building datasets,respectively.Experimental results show that the proposed method can achieve performance levels close to fully supervised training with a limited amount of labeled data.
作者
柴文光
罗崇熙
Chai Wenguang;Luo Chongxi(School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China)
出处
《广东工业大学学报》
2025年第3期36-43,共8页
Journal of Guangdong University of Technology
基金
国家自然科学基金资助项目(61772143)
广东省重点领域研发计划项目(2021B0101220006)。
关键词
遥感图像
变化检测
一致性正则化
半监督学习
remote sensing images
change detection
consistency regularization
semi-supervised learning
