ABSTRACT
Change detection is a challenging problem in remote sensing applications. In recent years, many Convolutional Neural Network (CNN)-based change detection methods have been proposed due to the rapid development of deep learning techniques. First, the Neural network receptive field single problem prevails. Besides, most existing methods enhance the network performance by adding an attention mechanism between layers, but this cannot obtain fine-grained features. In addition, the methods with transformer lack a priori information and can waste computational resources. Therefore, to solve these problems, this paper integrates attention with convolution and proposes an Efficient selective receptive field (ESRF) module to adjust the receptive field adaptively. Based on this, we design an efficient change detection network, ESRFnet, to achieve the fusion of multi-scale features. In addition, to focus more on the change region, we also introduce a spatial attention mechanism (SAM) in the network. Finally, we conduct extensive experiments on LEVIR-CD and SYSU datasets, and the results show that the proposed method can handle change regions at different scales well and effectively suppresses the interference of factors such as illumination, as well as has advantages in terms of execution efficiency and accuracy compared with several state-of-the-art methods currently available.
- T. Celik, “Unsupervised change detection in satellite images using principal component analysis and k-means clustering,” IEEE geoscience and remote sensing letters, vol. 6, no. 4, pp. 772–776, 2009. IGoogle Scholar
- O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention. Springer, 2015, pp. 234–241. IGoogle ScholarCross Ref
- R. Caye Daudt, B. Le Saux, and A. Boulch, “Fully convolutional siamese networks for change detection,” in 2018 25th IEEE International Conference on Image Processing (ICIP), 2018, pp. 4063–4067. I, III-D, IGoogle ScholarCross Ref
- S. Fang, K. Li, J. Shao, and Z. Li, “Snunet-cd: A densely connected siamese network for change detection of vhr images,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022. IGoogle Scholar
- M. Liu, Q. Shi, A. Marinoni, D. He, X. Liu, and L. Zhang, “Superresolution-based change detection network with stacked attention module for images with different resolutions,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–18, 2022. IGoogle Scholar
- H. Chen and Z. Shi, “A spatial-temporal attention-based method and a new dataset for remote sensing image change detection,” Remote Sensing, vol. 12, no. 10, p. 1662, 2020. I, III-A1, III-D, I, IIGoogle ScholarCross Ref
- S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “Cbam: Convolutional block attention module,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 3–19. I, II-A, II-CGoogle ScholarDigital Library
- J. Chen, Z. Yuan, J. Peng, L. Chen, H. Huang, J. Zhu, Y. Liu, and H. Li, “Dasnet: Dual attentive fully convolutional siamese networks for change detection in high-resolution satellite images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 1194–1206, 2021. IGoogle ScholarCross Ref
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.Google ScholarDigital Library
- H. Chen, Z. Qi, and Z. Shi, “Remote sensing image change detection with transformers,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–14, 2022. I, III-D, IGoogle Scholar
- W. G. C. Bandara and V. M. Patel, “A transformer-based siamese network for change detection,” arXiv preprint arXiv:2201.01293, 2022. I, III-D, I, IIGoogle ScholarCross Ref
- A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in neural information processing systems, vol. 25, 2012. II-BGoogle ScholarDigital Library
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. II-BGoogle ScholarCross Ref
- X. Ding, X. Zhang, Y. Zhou, J. Han, G. Ding, and J. Sun, “Scaling up your kernels to 31x31: Revisiting large kernel design in cnns,” arXiv preprint arXiv:2203.06717, 2022. I, II-BGoogle Scholar
- X. Li, W. Wang, X. Hu, and J. Yang, “Selective kernel networks,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 510–519. II-BGoogle ScholarCross Ref
- F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” arXiv preprint arXiv:1511.07122, 2015. II-BGoogle Scholar
- J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. II-BGoogle ScholarCross Ref
- Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, “Eca-net: Efficient channel attention for deep convolutional neural networks,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 11 531–11 539. I, II-BGoogle ScholarCross Ref
- Q. Shi, M. Liu, S. Li, X. Liu, F. Wang, and L. Zhang, “A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection,” IEEE Transactions on Geoscience and Remote Sensing, 2021. III-A2Google Scholar
- Y. Liu, C. Pang, Z. Zhan, X. Zhang, and X. Yang, “Building change detection for remote sensing images using a dual-task constrained deep siamese convolutional network model,” IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 5, pp. 811–815, 2020. III-D, I, IGoogle ScholarCross Ref
Index Terms
- An Efficient Convolution Network with Adaptive receptive field feature for High-Resolution Remote Sensing Change Detection
Recommendations
MFGAN: multi feature guided aggregation network for remote sensing image
AbstractRemote sensing image change detection is an important technology in remote sensing data analysis. Existing mainstream solutions are divided into supervised and unsupervised solutions. Among supervised methods, most remote sensing image change ...
SUDANet: A Siamese UNet with Dense Attention Mechanism for Remote Sensing Image Change Detection
Pattern Recognition and Computer VisionAbstractChange detection is one of the main applications of remote sensing images. Pixel-to-pixel change detection using deep learning has been a hot research spot. However, the current approach are not effective enough to fuse deep semantic features and ...
CSA-CDGAN: channel self-attention-based generative adversarial network for change detection of remote sensing images
AbstractRemote sensing images change detection (RSICD) is a task to identify desired significant differences between multi-temporal images acquired at different times. From the existing methods, most of them solved this issue with a Siamese network, ...
Comments