代云锋;刘丽娜;

• 1:宁波冶金勘察设计研究股份有限公司
• 2:宁波市鄞州区测绘院

摘要(Abstract)：

针对基于深度学习的变化检测模型搭建中提高变化检测精度这一难点，在综合考虑面向像元和面向对象变化检测算法的基础上，设计了一种基于改进混合卷积特征提取模块的变化检测模型。该模型结合多切片思想和并行神经网络结构，融合不同尺寸的卷积核获取丰富的多尺度特征。首先，利用超像素分割算法将测试影像分割成无重叠的同质性区域；然后，选取一定数量的样本对模型进行训练，得到测试影像的像素级变化检测结果；最后，利用投票法，将网络得到的像素级结果与分割对象相结合，得到最终的变化检测结果。实验结果表明，基于该方法的网络模型性能较好，该模型可以有效学习多时相影像中的空间信息及差异特征，同时结合分割算法能够降低虚检率和漏检率，有效提高了变化检测精度。

关键词(KeyWords)： 改进混合卷积;多特征提取;多切片;深度特征融合;变化检测

Abstract:

Keywords:

基金项目(Foundation):

作者(Authors): 代云锋;刘丽娜;

参考文献(References)：

• [1] SINGH A.Digital change detection techniques using remotely sensed data[J].International journal of remote sensing,1988,10(6):989-1003.
• [2] 万安国，王建强，武可强.新余市生态环境遥感动态监测与分析[J].测绘与空间地理信息，2020,43(6):75-80.
• [3] 刘俊，孟雪，温小荣，等.基于不同立地质量的森林蓄积量遥感估测[J].西北林学院学报，2016,31(1):186-191.
• [4] 张良培，武辰.多时相遥感影像变化检测的现状与展望[J].测绘学报，2017,46(10):249-261.
• [5] BENEDEK C,TAM′AS S.A mixed markov model for change detection in aerial photos with large time differences [C]//Proceedings of 2008 19th International Conference on Pattern Recognition.Tampa,FL,USA:IEEE,2008:1-4.
• [6] 赵生银，安如，朱美如.联合像元-深度-对象特征的遥感图像城市变化检测[J].测绘学报，2019,48(11):1452-1463.
• [7] LI L,LI X,ZHANG Y,et al.Change detection for high-resolution remote sensing imagery using object-oriented change vector analysis method[C]//Proceedings of the IEEE International Geoscience and Remote Sensing Symposium.Beijing,China:IEEE,2016:2873-2876.
• [8] 宋业冲，李英成，耿中元，等.深度学习方法在光伏用地遥感检测中的应用[J].测绘科学，2020,45(11):84-92.
• [9] CHEN J,YUAN Z,PENG J,et al.DASNet:dual attentive fully convolutional Siamese networks for change detection in high-resolution satellite images[J].IEEE journal of selected topics in applied earth observations and remote sensing,2020,14:1194-1206.
• [10] SUN W,WANG R.Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM [J].IEEE geoscience and remote sensing letters,2018:1-5.
• [11] PANDA M K,SHARMA A,BAJPAI V,et al.Encoder and decoder network with ResNet-50 and global average feature pooling for local change detection[J].Computer vision and image understanding,2022,222:103501.
• [12] 张翠军，安冉，马丽.改进U-Net的遥感图像中建筑物变化检测[J].计算机工程与应用，2021,57(3):239-246.
• [13] 樊玮，周末，黄睿.多尺度深度特征融合的变化检测[J].中国图象图形学报，2020,25(4):669-678.
• [14] GOODFELLOW I,BENGIO Y,COURVILLE A.Deep learning[M].Cambridge:MIT Press,2016:326-366.
• [15] CHOLLET F.Xception:deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on computer Vision and Pattern Recognition.Honolulu,HI,USA:IEEE,2017:1251-1258.
• [16] LIU C,YE Q,HUANG X,et al.SuperConv:strengthening the convolution kernel via weight sharing[C]//Proceedings of International Conference on Neural Information Processing.Switzerland:Springer,2020:676-687.
• [17] SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA:IEEE,2016:2818-2826.
• [18] 周飞燕，金林鹏，董军.卷积神经网络研究综述[J].计算机学报，2017,40(6):1229-1251.
• [19] 赵景晨.基于超像素和孪生卷积神经网络的无监督高分辨率多光谱遥感影像变化检测技术[D].杭州：浙江大学，2018.
• [20] OTSU N.A threshold selection method from gray-level histograms [J].IEEE transactions on systems man and cybernetics,2007,9(1):62-66.
• [21] BENEDEK C,SZIRáNYI T.Change detection in optical aerial images by a multilayer conditional mixed Markov model [J].IEEE transactions on geoscience and remote sensing,2009,47(10):3416-3430.