Hybrid Spatial Pyramid Pooling Network to Change Detection for High Resolution Remote Sensing Images

SHAO Pan; GAO Ziang

doi:10.11834/jrs.20233229

Views : 0 下载量: 98 CSCD: 0 更多指标

R-PDF
PDF
Export
Share
Collection
Album

Hybrid Spatial Pyramid Pooling Network to Change Detection for High Resolution Remote Sensing Images
Pages: 1-11(2023)
Published Online： 02 November 2023 ，
DOI： 10.11834/jrs.20233229

扫描看全文

邵攀，高梓昂.XXXX.面向高分辨率遥感影像变化检测的混合空间金字塔池化网络.遥感学报，XX（XX）： 1-11

SHAO Pan，GAO Ziang. XXXX. Hybrid Spatial Pyramid Pooling Network to Change Detection for High Resolution Remote Sensing Images. National Remote Sensing Bulletin， XX（XX）：1-11
邵攀，高梓昂.XXXX.面向高分辨率遥感影像变化检测的混合空间金字塔池化网络.遥感学报，XX（XX）： 1-11 DOI： 10.11834/jrs.20233229.

SHAO Pan，GAO Ziang. XXXX. Hybrid Spatial Pyramid Pooling Network to Change Detection for High Resolution Remote Sensing Images. National Remote Sensing Bulletin， XX（XX）：1-11 DOI： 10.11834/jrs.20233229.

摘要

以残差网络为基础，结合高分辨率遥感影像的特点，提出一种全新的端到端变化检测网络--混合空间金字塔池化网络（Hybrid spatial pyramid pooling network，HSPPNet）。HSPPNet首先将空洞卷积和注意力机制引导卷积并行集成，构建一种混合空间金字塔池化模块，以便有效提取高分辨率遥感影像中不同形状尺度的变化对象。然后，通过定义一种截断-补偿加权交叉熵函数和一种类别级IoU函数并将二者集成，得到一种全新的自适应平衡损失函数，来降低变化类与未变化类严重不均衡问题对变化检测的影响。最后设计一种简单有效的输入模块，通过综合考虑两期遥感影像及其差异图来增强变化信息。通过以上三点，HSPPNet增强了深度学习变化检测的性能。两组常用公开变化检测数据集上的实验结果表明HSPPNet可行、有效。

Abstract

Objective Change detection (CD) is the process to identify the land cover changes of interest

by analyzing bi-temporal remote sensing images acquired in the same geographical area at different times. As a hot research topic in remote sensing

CD plays an important role in many practical applications

such as urban research

environmental monitoring

and disaster assessment. With the rapid development of deep learning

its applications have expanded to the remote sensing CD task

leading to the development of numerous deep learning-based CD methods. Although the existing deep learning-based CD methods have their own advantages and can implement the CD task effectively

their applicability and robustness need to be further analyzed. How to design an appropriate network model to obtain more reliable and accurate CD results is still an open problem. Currently

there are still two main challenges for CD: 1) The changed objects existing in remote sensing images have various scales and shapes

and 2) the proportions of the changed and unchanged classes are often significantly unbalanced

i.e.

the number of the changed pixels are usually much less than that of the unchanged pixels.Method To deal with these two challenges

this paper proposes a novel end-to-end CD network for high resolution remote sensing images based on the residual network

i.e.

hybrid spatial pyramid pooling network (HSPPNet). First

a hybrid spatial pyramid pooling (HSPP) module is built by integrating atrous convolutions and attention-mechanism-guided convolutions in parallel

in order to effectively extract the changed objects with different shapes and scales from high-resolution remote sensing images. Then

an adaptive balancing loss function is presented to alleviate the impacts of the serious imbalance between changed and unchanged classes on CD. The loss function is constructed by defining a truncation-compensation weighting cross entropy function and a class-level IoU function and integrating them. Finally

a simple but effective input module that considers both the bi-temporal remote sensing images and their difference image is designed to enhance the change information. Owing to the above three points

the proposed HSPPNet method enhances the performance of deep learning CD.Result Experiments were carried out with two public CD datasets

namely the CDD and Google datasets

in order to evaluate the performance of the proposed HSPPNet method. Six state-of-the-art deep learning methods were used as the comparative methods. Quantitative analysis of CD results was done on four evaluation metrics

namely precision

recall

overall accuracy

and F1-score. For the CDD and Google datasets

the overall accuracy/F1-score values of the proposed HSPPNet method are 0.9943/0.9758 and 0.9399/0.9076

respectively

which are superior to the six comparative methods.Conclusion The experimental results on two public CD datasets demonstrate that the proposed HSPPNet is effective and feasible. In addition

the results of ablation experiments show that all of the HSPP module

the adaptive balancing loss function

and the input module proposed in this work can enhance the CD performance effectively.

关键词

遥感变化检测深度学习混合空间金字塔池化注意力机制损失函数截断-补偿加权交叉熵类别级IoU

Keywords

remote sensingchange detectiondeep learninghybrid spatial pyramid poolingattention mechanismloss functiontruncation-compensation weighting cross entropyclass-level IoU

references

Chen H, Qi Z and Shi, Z W. 2022. Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing, 60, Art no. 5607514. [DOI: 10.1109/ TGRS.2021.3095166http://dx.doi.org/10.1109/TGRS.2021.3095166]

Chen H and Shi Z. 2020. A spatial-temporal attention-based method and a new dataset for remote sensing Image change detection. Remote Sensing, 12(10), noArt. 1662. [DOI: 10.3390/rs 12101662http://dx.doi.org/10.3390/rs12101662]

Chen J, Lu M, Chen X H, Chen J and Chen L J. 2013. A spectral gradient difference based approach for land cover change detection. ISPRS Journal of Photogrammetry and Remote Sensing, 85: 1-12. [DOI: 10.1016/j.isprsjprs.2013.07.009http://dx.doi.org/10.1016/j.isprsjprs.2013.07.009]

Chen J, Yuan Z Y, Peng J, Chen L, Huang H Z, Zhu J W, Liu Y and Li H F. 2021. DASNet: dual attentive fully convolutional Siamese networks for change detection of high resolution satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14:1194-1206. [DOI: 10. 3390/rs12101662http://dx.doi.org/10.3390/rs12101662]

Chen L C, Papandreou G, Kokkinos I, Murphy K and Yuille A L. 2018a. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 834-848. [DOI:10.1109/TPAMI.2017. 2699184http://dx.doi.org/10.1109/TPAMI.2017.2699184]

Chen L C, Zhu Y, Papandreou G, Schroff F and Adam H. 2018b. Encoder-decoder with atrous separable convolution for semantic image segmentation. European Conference on Computer Vision. [DOI: 10.1007/978-3-030-01234-249http://dx.doi.org/10.1007/978-3-030-01234-249]

Daudt R C, Saux B L and Boulch A. 2018. Fully convolutional Siamese networks for change detection. Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP). [DOI: 10.1109/ICIP.2018.8451652http://dx.doi.org/10.1109/ICIP.2018.8451652]

Dian Y Y, Fang S H and Yao C H. 2016. Change detection for high-resolution images using multilevel segment method. Journal of Remote Sensing, 20(1) : 129-137.

佃袁勇, 方圣辉, 姚崇怀. 2016 .多尺度分割的高分辨率遥感影像变化检测. 遥感学报, 20(1): 129-137 [DOI: 10.11834/jrs. 20165074http://dx.doi.org/10.11834/jrs.20165074]

Fu J, Liu J, Tian H J, Li Y, Bao Y J, Fang Z W and Lu H Q. 2020. Dual attention network for scene segmentation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [DOI: 10.1109/CVPR. 2019.003 26http://dx.doi.org/10.1109/CVPR.2019.00326]

Gu L, Xu S Q and Zhu L Q. 2020. Detection of building changes in remote sensing images via FlowS-Unet. Acta Automatica Sinica, 46(6): 1291-1300

顾炼, 许诗起, 竺乐庆. 2020.基于FlowS-Unet的遥感图像建筑物变化检测. 自动化学报, 46(06): 1291-1300. [DOI: 10.16383/j.aas.c180122http://dx.doi.org/10.16383/j.aas.c180122]

Cheng H Q, Wu H Y, Zheng J, Qi K L and Liu W X. 2021. A hierarchical self-attention augmented Laplacian pyramid expanding network for change detection in high-resolution remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 182: 52-66. [DOI: 10.1016/j.isprsjprs.2021. 10.001http://dx.doi.org/10.1016/j.isprsjprs.2021.10.001]

He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770-778. [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]

Hussain M, Chen D M, Cheng A, Wei H and Stanley D. 2013. Change detection from remotely sensed images: From pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, 80: 91-106. [DOI: 10.1016/j.isprsjprs. 2013.03.006http://dx.doi.org/10.1016/j.isprsjprs.2013.03.006]

Lebedev M A, Vizilter Y V, Vygolov O, Knyaz V A and Rubis A Y. 2018. Change detection in remote sensing images using conditional adversarial networks. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. [DOI: 10.5194/isprs-archives-XLII-2- 565-2018http://dx.doi.org/10.5194/isprs-archives-XLII-2-565-2018]

Liang Z H, Li X,,Deng P, Sheng S and Jiang F Q. 2022. Remote sensing image change detection fusion method integrating multi-scale feature attention. Acta Geodaetica et Cartographica Sinica, 51(5): 668-676.

梁哲恒, 黎宵, 邓鹏, 盛森, 姜福泉. 2022. 融合多尺度特征注意力的遥感影像变化检测方法. 测绘学报, 51(5): 668-676 [DOI: 10.11947/j.AGCS.2022. 20200540http://dx.doi.org/10.11947/j.AGCS.2022.20200540]

Liu J F, Chen K M, Xu G L, Sun X, Yan M L, Diao W H and Han H Z. 2020. Convolutional neural network-based transfer learning for optical aerial images change detection. IEEE Geoscience and Remote Sensing Letters, 17(1): 127-131. [DOI: 10.1109/ LGRS. 2019.2916601http://dx.doi.org/10.1109/LGRS.2019.2916601]

Liu M X, Chai Z Q, Deng H J and Liu R.2022. A CNN-Transformer network with multiscale context aggregation for fine-grained cropland change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15:4297-4306. [DOI: 10.1109/JSTARS.2022.3177235http://dx.doi.org/10.1109/JSTARS.2022.3177235]

Peng D F, Bruzzone L, Zhang Y J, Guan H Y, Ding H Y and Huang X. 2020. 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/TGR S. 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, Art no. 1382. [DOI: 10.3390/rs 121016 62http://dx.doi.org/10.3390/rs12101662]

Qi J W, Wang W F, Zhang L and Wang G Y. 2023. Building change detection of remote sensing image based on improved DeepLabV3+. Bulletin of Surveying and Mapping, 4:145-149

齐建伟, 王伟峰, 张乐, 王光彦. 2023. 基于改进DeepLabV3+算法的遥感影像建筑物变化检测. 测绘通报, 4:145-149[DOI:10.13474/j.cnki.11-2246.2023.0119http://dx.doi.org/10.13474/j.cnki.11-2246.2023.0119]

Shi W Z, Zhang M, Zhang R, Chen S X and Zhan Z. 2020. Change detection based on artificial intelligence: state-of-the-art and challenges. Remote Sensing, 12(10), noArt.1688. [DOI: 10.3390/rs 12101688http://dx.doi.org/10.3390/rs12101688]

Tian Z, He T, Shen C H and Yan Y L. 2020. Decoders matter for semantic segmentation: data-dependent decoding enables flexible feature aggregation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [DOI: 10.1109/CVPR.2019.00324http://dx.doi.org/10.1109/CVPR.2019.00324]

Wang C, Wang S, Chen X, Li J Y and Xie T. 2023. Object-level change detection of multi-sensor optical remote sensing images combined with UNet++ and multi-level difference module. Acta Geodaetica et Cartographica Sinica, 52(2): 283-296

王超, 王帅, 陈晓, 李俊勇, 谢涛. 2033. 联合UNet++和多级差分模块的多源光学遥感影像对象级变化检测. 测绘学报, 52(2):283-296. [DOI:10.11947/j.AGCS.2023. 20220202http://dx.doi.org/10.11947/j.AGCS.2023.20220202]

Zhang C X, Yue P, Tapete D, Jiang L C, Boyi S G, Huang L and Liu G C. 2020. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 166: 183-200. [DOI: 10.1016/j.isprsjprs.2020.06.003http://dx.doi.org/10.1016/j.isprsjprs.2020.06.003]

Zhang M and Shi W Z. 2020. A feature difference convolutional neural network-based change detection method. IEEE Transactions on Geoscience and Remote Sensing, 58(10): 7232-7246. [DOI: 10.1109/TGRS.2020.2981051http://dx.doi.org/10.1109/TGRS.2020.2981051]

Zhang X W, Yue Y Z, Gao W X, Yun S, Su Q, Yin H L and Zhang Y N. 2021. DifUNet++: a satellite images change detection network based on UNet++ and differential pyramid. IEEE Geoscience and Remote Sensing Letters, 19, Art no. 8006605 [DOI: 10.1109/ LGRS.2021. 3049370http://dx.doi.org/10.1109/LGRS.2021.3049370]

Zhou Z W, Siddiquee M M R, Tajbakhsh N and Liang J M. 2020. UNet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging. 39(6):1856-1867. [DOI:10.1109/TMI.2019.2959609http://dx.doi.org/10.1109/TMI.2019.2959609]

Alert me when the article has been cited

提交

Optical-signal token guided change detection network for heterogeneous remote sensing image

Review of remote sensing change detection in deep learning： Bibliometric and analysis

Remote sensing change detection technology in the Era of artificial intelligence： Inheritance， development and challenges

PolSAR image deep learning super-resolution model based on multi-scale attention mechanism