浏览全部资源
扫码关注微信
Published： 16 May 2024 ，
移动端阅览
王鑫， 李莹莹， 张香梁. 2024. Ghost引导UNet++的高分遥感影像变化检测. 中国图象图形学报， 29(05):1460-1478
Wang Xin， Li Yingying， Zhang Xiangliang. 2024. Ghost-guided UNet++ for high-resolution remote sensing image change detection. Journal of Image and Graphics， 29(05):1460-1478
目的
2
随着遥感观测技术的飞速发展，遥感影像的分辨率越来越高，如何从高分遥感影像中有效提取具有鉴别性的特征进行地物变化检测成为一个具有挑战性的问题。卷积神经网络广泛应用于计算机视觉领域，但面向遥感影像变化检测时仍存在图像语义或位置信息的丢失及网络参数量过大等缺陷，导致检测性能受限。为此，提出一种新型GUNet++（Ghost-UNet++）网络，用于遥感影像的精准变化检测。
方法
2
首先，为了提取双时相遥感影像更具判别性的深度特征，设计具有多分支架构的高分辨率网络HRNet替换传统UNet++的主干网；其次，采用UNet++解码结构进行差异判别时，引入鬼影（Ghost）模块代替传统卷积模块以降低网络参量，并设计密集跳跃连接进一步加强信息传输，以减少深层位置信息的丢失；最后，设计一个集成注意力模块，将网络的多个语义层次特征进行聚合和细化，抑制语义和位置信息的丢失，进一步增强特征表征能力用于最终的精准变化检测。
结果
2
在LEVIR-CD（LEVIR change detection data set）和Google Data Set两个公开数据集上进行实验，结果表明本文算法变化检测精度高达99.62%和99.16%，且网络参数量仅为1.93 M，与现有主流变化检测方法相比优势明显。
结论
2
提出方法综合考虑了遥感图像中语义和位置信息对变化检测性能的影响，具有良好的特征抽取和表征能力，因此变化检测的精度和效率比现有同类方法更高。
Objective
2
With the rapid development of remote sensing observation technology， the resolutions of remote sensing images （RSIs） are increasing. Thus， how to extract discriminative features effectively from high-resolution RSIs for ground-object change detection has become a challenging problem. The existing RSI change detection methods can be divided into two categories： methods based on conventional image processing approaches and methods based on deep learning （DL） theory. The former extracts low-level or mid-level features from RSIs for change detection， making it easy to implement and have high detection efficiency. However， the increasing resolution of RSIs result in the images having rich ground objects and complex background clutter； thus， the low- or mid-level features can hardly meet the demand of precise change detection. In recent years， DL has been introduced into the field of high-resolution RSI change detection because of its powerful feature extraction capability. Various methods based on convolutional neural networks （CNNs） have been proposed for RSI change detection. Compared with conventional image processing methods， CNNs can extract high-level semantic information for high-resolution RSIs， which is beneficial to precise detection. Although CNNs have greatly raised the accuracy of change detection， they always involve numerous parameters and have high computational complexity. To raise the efficiency of change detection， many scholars have proposed to perform parameter pruning on pretrained models or design simple network structures. However， these strategies lead to the loss of some crucial image information， including semantics and location information， thus reducing the detection accuracy. Therefore， this study proposes a novel Ghost-UNet++ （GUNet++） network for precise RSI change detection to address the problems.
Method
2
First， a high-resolution network called HRNet， which has a multibranch architecture， is designed to replace the traditional UNet++ backbone and thus extract additional discriminative deep features from bitemporal RSIs. In contrast to series structures， HRNet owns a special parallel architecture， which can extract additional discriminative features through multiscale feature fusion. In addition， we choose a lightweight structure （i.e.， HRNet-W16） on the basis of a thorough analysis of various existing HRNet structures to ensure that the whole network possesses low complexity. Second， when applying the UNet++ decoding structure for difference discrimination， the Ghost module is introduced to replace the conventional convolutional module and thus reduce the network parameters； meanwhile， a dense skip connection is designed to enhance the information transmission further and reduce the loss of location information. The core idea of the Ghost module is to adopt simple linear operations instead of the traditional convolutional operations to generate Ghost maps for original features， which may save substantial computational cost. Third， an ensemble attention module is constructed to aggregate and refine the multilevel semantic features of the network， thereby suppressing the loss of semantic and location information and further enhancing the feature representation ability for final accurate change detection. Features generated at various levels usually contain different meanings： shallow ones always contain detailed spatial information， while deep ones reflect rich semantic content. On this basis， we propose an adaptive channel selection mechanism to integrate these different features effectively. Finally， we propose to combine two different loss functions， i.e.， the sigmoid loss function and the dice loss function， for the whole model training to enhance the detection performance further. Compared with the methods that merely use one loss function， this scheme can improve detection performance.
Result
2
A series of experiments is conducted on two publicly available datasets， including LEVIR-CD and Google DataSet， to validate the effectiveness of the proposed method. The experiments consist of ablation analysis and comparison experiments. Specifically， three kinds of ablation analyses are performed. The first one verifies the effects of the modified HRNet-based discriminative feature extraction， the second one mainly evaluates the effectiveness of the ensemble attention modules and the Ghost modules for the whole network， and the third one aims to find the optimal values of a key parameter in the Ghost models. In the comparison experiments， some state-of-the-art algorithms are selected for comparison to verify the superiority of the proposed network. Extensive experimental results demonstrate that for the two famous datasets， the proposed method achieves high change detection accuracy rates of 99.62% and 99.16%. In addition， the parameter of the network is only 1.93 M. Compared with some mainstream change detection approaches， the proposed method is remarkably superior.
Conclusion
2
The proposed method comprehensively considers the effect of semantic and location information in RSIs on the performance of change detection. In addition， the method possesses good feature extraction and representation capabilities. Therefore， the accuracy and efficiency for change detection are higher than those of existing comparable algorithms. In the future， we plan to optimize the proposed architecture by increasing the number and diversity of the training samples to enhance the robustness of models， by using more advanced software and hardware environments for experiments to reduce the training time， and by applying our trained model to other tasks.
高分辨率遥感影像变化检测深度学习（DL）鬼影模块集成注意力
high-resolution remote sensing imagechange detectiondeep learning（DL）Ghost moduleensemble attention
Chen H， Qi Z P and Shi Z W. 2022a. Remote sensing image change detection with Transformers. IEEE Transactions on Geoscience and Remote Sensing， 60： #5607514 ［DOI： 10.1109/TGRS.2021.3095166http://dx.doi.org/10.1109/TGRS.2021.3095166］
Chen H and Shi Z W. 2020. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing， 12（10）： #1662 ［DOI： 10.3390/rs12101662http://dx.doi.org/10.3390/rs12101662］
Chen T， Lu Z Y， Yang Y， Zhang Y X， Du B and Plaza A. 2022b. A Siamese network based U-Net for change detection in high resolution remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 15： 2357-2369 ［DOI： 10.1109/JSTARS.2022.3157648http://dx.doi.org/10.1109/JSTARS.2022.3157648］
Chollet F. 2017. Xception： deep learning with depthwise separable convolutions//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Honolulu， USA： IEEE： 1800-1807 ［DOI： 10.1109/CVPR.2017.195http://dx.doi.org/10.1109/CVPR.2017.195］
Daudt R C， Le Saux B and Boulch A. 2018. Fully convolutional Siamese networks for change detection//Proceedings of the 25th IEEE International Conference on Image Processing （ICIP）. Athens， Greece： IEEE： 4063-4067 ［DOI： 10.1109/ICIP.2018.8451652http://dx.doi.org/10.1109/ICIP.2018.8451652］
Esser S K， McKinstry J L， Bablani D， Appuswamy R and Modha D S. 2020. Learned step size quantization ［EB/OL］. ［2023-05-09］. https://arxiv.org/pdf/1902.08153.pdfhttps://arxiv.org/pdf/1902.08153.pdf
Fang S， Li K Y， Shao J Y and Li Z. 2022. SNUNet-CD： a densely connected Siamese network for change detection of VHR images. IEEE Geoscience and Remote Sensing Letters， 19： #8007805 ［DOI： 10.1109/LGRS.2021.3056416http://dx.doi.org/10.1109/LGRS.2021.3056416］
Han K， Wang Y H， Tian Q， Guo J Y， Xu C J and Xu C. 2020. GhostNet： more features from cheap operations//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， USA： IEEE： 1577-1586 ［DOI： 10.1109/CVPR42600.2020.00165http://dx.doi.org/10.1109/CVPR42600.2020.00165］
He K M， Zhang X Y， Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 770-778 ［DOI： 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90］
Howard A G， Zhu M L， Chen B， Kalenichenko D， Wang W J， Weyand T， Andreetto M and Adam H. 2017. MobileNets： efficient convolutional neural networks for mobile vision applications ［EB/OL］. ［2023-05-09］. https://arxiv.org/pdf/1704.04861.pdfhttps://arxiv.org/pdf/1704.04861.pdf
Huang C X， Yin J J and Yang J. 2019. Polarimetric SAR change detection with l1-norm principal component analysis. Systems Engineering and Electronics， 41（10）： 2214-2220
黄晨霞， 殷君君， 杨健. 2019. 基于l1范数主成分分析的极化SAR图像变化检测. 系统工程与电子技术， 41（10）： 2214-2220 ［DOI： 10.3969/j.issn.1001-506X.2019.10.09http://dx.doi.org/10.3969/j.issn.1001-506X.2019.10.09］
Hui Z， Wang X M and Gao X B. 2018. Fast and accurate single image super-resolution via information distillation network//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， USA： IEEE： 723-731 ［DOI： 10.1109/CVPR.2018.00082http://dx.doi.org/10.1109/CVPR.2018.00082］
Jin Y W. 2021. Building Recognition and Change Detection from High-Resolution Remotely Sensed Imagery Using Deep Learning. Chengdu： University of Electronic Science and Technology of China （金宇伟. 2021. 基于深度学习的高分辨率遥感影像建筑物识别及变化检测. 成都： 电子科技大学） ［DOI： 10.27005/d.cnki.gdzku.2021.005129］
Ke L， Lin Y K， Zeng Z， Zhang L F and Meng L K. 2018. Adaptive change detection with significance test. IEEE Access， 6： 27442-27450 ［DOI： 10.1109/ACCESS.2018.2807380http://dx.doi.org/10.1109/ACCESS.2018.2807380］
Li H， Kadav A， Durdanovic I， Samet H and Graf H P. 2017. Pruning filters for efficient ConvNets//Proceedings of the 5th International Conference on Learning Representations （ICLR）. Toulon， France： OpenReview.net： 1-13
Long J， Shelhamer E and Darrell T. 2015. Fully convolutional networks for semantic segmentation//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Boston， USA： IEEE： 3431-3440 ［DOI： 10.1109/CVPR.2015.7298965http://dx.doi.org/10.1109/CVPR.2015.7298965］
Peng D F， Bruzzone L， Zhang Y J， Guan H Y， Ding H Y and Huang X. 2021. SemiCDNet： a semisupervised convolutional neural network for change detection in high resolution remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing， 59（7）： 5891-5906 ［DOI： 10.1109/TGRS.2020.3011913http://dx.doi.org/10.1109/TGRS.2020.3011913］
Peng D F， Zhang Y J and Guan H Y. 2019. End-to-end change detection for high resolution satellite images using improved UNet++. Remote Sensing， 11（11）： #1382 ［DOI： 10.3390/rs11111382http://dx.doi.org/10.3390/rs11111382］
Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition ［EB/OL］. ［2023-05-24］. http://www.arxiv.org/pdf/1409.1556.pdfhttp://www.arxiv.org/pdf/1409.1556.pdf
Solano-Correa Y T， Bovolo F and Bruzzone L. 2018. An approach for unsupervised change detection in multitemporal VHR images acquired by different multispectral sensors. Remote Sensing， 10（4）： #533 ［DOI： 10.3390/rs10040533http://dx.doi.org/10.3390/rs10040533］
Sun K， Xiao B， Liu D and Wang J D. 2019. Deep high-resolution representation learning for human pose estimation//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Los Angeles， USA： IEEE： 5686-5696 ［DOI： 10.1109/CVPR.2019.00584http://dx.doi.org/10.1109/CVPR.2019.00584］
Tian S Q， Zhong Y F， Zheng Z， Ma A L， Tan X C and Zhang L P. 2022. Large-scale deep learning based binary and semantic change detection in ultra high resolution remote sensing imagery： from benchmark datasets to urban application. ISPRS Journal of Photogrammetry and Remote Sensing， 193： 164-186 ［DOI： 10.1016/j.isprsjprs.2022.08.012http://dx.doi.org/10.1016/j.isprsjprs.2022.08.012］
Wang X， Huang J， Chu Y L， Shi A Y and Xu L Z. 2018. Change detection in bitemporal remote sensing images by using feature fusion and fuzzy C-means. KSII Transactions on Internet and Information Systems， 12（4）： 1714-1729 ［DOI： 10.3837/tiis.2018.04.017http://dx.doi.org/10.3837/tiis.2018.04.017］
Wang X， Wang S Y， Ning C and Zhou H Y. 2021. Enhanced feature pyramid network with deep semantic embedding for remote sensing scene classification. IEEE Transactions on Geoscience and Remote Sensing， 59（9）： 7918-7932 ［DOI： 10.1109/TGRS.2020.3044655http://dx.doi.org/10.1109/TGRS.2020.3044655］
Wang Y H， Gao L R， Chen Z C and Zhang B. 2020. Deep learning and superpixel-based method for high-resolution remote sensing image change detection. Journal of Image and Graphics， 25（6）： 1271-1282
王艳恒， 高连如， 陈正超， 张兵. 2020. 结合深度学习和超像元的高分遥感影像变化检测. 中国图象图形学报， 25（6）： 1271-1282 ［DOI： 10.11834/jig.190319http://dx.doi.org/10.11834/jig.190319］
Wang Z P， Shen Y， Wang L， Zhang Q L and You S C. 2020. High-resolution remote sensing image building change detection based on one-class classifier framework. Geomatics and Information Science of Wuhan University， 45（10）： 1610-1618
王志盼， 沈彦， 王亮， 张清凌， 尤淑撑. 2020. 单类分类框架下的高分辨率遥感影像建筑物变化检测算法. 武汉大学学报（信息科学版）， 45（10）： 1610-1618 ［DOI： 10.13203/j.whugis20180485http://dx.doi.org/10.13203/j.whugis20180485］
Woo S， Park J， Lee J Y and Kweon I S. 2018. CBAM： convolutional block attention module//Proceedings of the 15th European Conference on Computer Vision （ECCV）. Munich， Germany： Springer： 3-19 ［DOI： 10.1007/978-3-030-01234-2_1http://dx.doi.org/10.1007/978-3-030-01234-2_1］
Xu C A， Lyu Y F， Zhang X H， Liu Y， Cui C H and Gu X Q. 2021. A discriminative feature representation method based on dual attention mechanism for remote sensing image scene classification. Journal of Electronics and Information Technology， 43（3）： 683-691
徐从安， 吕亚飞， 张筱晗， 刘瑜， 崔晨浩， 顾祥岐. 2021. 基于双重注意力机制的遥感图像场景分类特征表示方法. 电子与信息学报， 43（3）： 683-691 ［DOI： 10.11999/JEIT200568http://dx.doi.org/10.11999/JEIT200568］
Yan L， Xia W， Zhao Z and Wang Y R. 2018. A novel approach to unsupervised change detection based on hybrid spectral difference. Remote Sensing， 10（6）： #841 ［DOI： 10.3390/rs10060841http://dx.doi.org/10.3390/rs10060841］
Yang K P， Xia G S， Liu Z C， Du B， Yang W， Pelillo M and Zhang L P. 2022. Asymmetric Siamese networks for semantic change detection in aerial images. IEEE Transactions on Geoscience and Remote Sensing， 60： #5609818 ［DOI： 10.1109/TGRS.2021.3113912http://dx.doi.org/10.1109/TGRS.2021.3113912］
Yu C Q， Xiao B， Gao C X， Yuan L， Zhang L， Sang N and Wang J D. 2021. Lite-HRNet： a lightweight high-resolution network//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， USA： IEEE： 10435-10445 ［DOI 10.1109/CVPR46437.2021.01030http://dx.doi.org/10.1109/CVPR46437.2021.01030］
Zhang B， Zhang Y J and Wang S G. 2019. A lightweight and discriminative model for remote sensing scene classification with multidilation pooling module. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 12（8）： 2636-2653 ［DOI： 10.1109/JSTARS.2019.2919317http://dx.doi.org/10.1109/JSTARS.2019.2919317］
Zhang X Y， Zhou X Y， Lin M X and Sun J. 2018. ShuffleNet： an extremely efficient convolutional neural network for mobile devices//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， USA： IEEE： 6848-6856 ［DOI： 10.1109/CVPR.2018.00716http://dx.doi.org/10.1109/CVPR.2018.00716］
Zhao X， Wang T， Zhang Y， Zheng Y H， Zhang K and Wang L H. 2022. Remote sensing image change detection based on improved DeepLabv3 + Siamese network. Journal of Geo-Information Science， 24（8）： 1604-1616
赵祥， 王涛， 张艳， 郑迎辉， 张昆， 王龙辉. 2022 基于改进DeepLabv3+孪生网络的遥感影像变化检测方法. 地球信息科学学报， 24（8）： 1604-1616 ［DOI： 10.12082/dqxxkx.2022.220029http://dx.doi.org/10.12082/dqxxkx.2022.220029］
Zheng Z， Zhong Y F， Tian S Q， Ma A L and Zhang L P. 2022. ChangeMask： deep multi-task encoder-Transformer-decoder architecture for semantic change detection. ISPRS Journal of Photogrammetry and Remote Sensing， 183： 228-239 ［DOI： 10.1016/j.isprsjprs.2021.10.015http://dx.doi.org/10.1016/j.isprsjprs.2021.10.015］
Zhou Y， Chen S L， Zhao J Q， Zhang D and Wang H Z. 2021. Weakly semantic based attention network for interpretable object detection in remote sensing imagery. Acta Electronica Sinica， 49（4）： 679-689
周勇， 陈思霖， 赵佳琦， 张迪， 王瀚正. 2021. 基于弱语义注意力的遥感图像可解释目标检测.电子学报， 49（4）： 679-689 ［DOI： 10.12263/DZXB.20200554http://dx.doi.org/10.12263/DZXB.20200554］
Zhou Z W， Rahman Siddiquee M M， Tajbakhsh N and Liang J M. 2018. UNet++： a nested U-Net architecture for medical image segmentation//Proceedings of the 4th International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Granada， Spain： Springer： 3-11 ［DOI： 10.1007/978-3-030-00889-5_1http://dx.doi.org/10.1007/978-3-030-00889-5_1］
相关文章
相关作者
相关机构
京公网安备11010802024621