Abstract
Infrastructure surveillance, topographic map-making, urban dynamics, and town planning applications all use high resolution satellite (HRS) imagery to detect changes. Change detection (CD) in these images is critical due to the large amount of information and challenging data. However, the high computing complexity of the network, related to dense convolution layers and an abundance of data to discourage the researcher from designing an efficient and precise CD architecture. The algorithm used to design this architecture must not only be correct, but also efficient in terms of speed and accuracy. Hence, we focus on developing computationally efficient self attention-mechanism-based Attention Augmented Convolution with the backbone of UNet (AAUNet) architecture for CD tasks. Two image pairs, each with a channel-C, can be layered together to create a channel-2C image as an input to train this architecture. The novelty of this method is the standard convolution of original UNet is replaced by a self-attention mechanism based attention augmented (AA) convolution layer in the proposed network. This attention augmented convolutional operation is used to capture long-range global information, however, the standard convolution layer has a significant weakness in that it only works on local information. Therefore, we use attention augmented convolutional layer as an alternative to standard convolution layers. It is allowing us to design network with fewer parameters, speedup training, less computation complexity, and enhance segmentation performance of the model. Test results on LEVIR-CD, SZATKI AirChange (AC), and Onera Satellite Change Detection (OSCD), benchmark datasets demonstrated that the proposed approach beats its predominance as far as Intersection over Union (IoU), number of parameters, and deduction of inference time over the current techniques.
Supported by organization SGGSIET, Nanded.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chughtai, A.H., Abbasi, H., Ismail, R.K.: A review on change detection method and accuracy assessment for land use land cover. Remote Sensing Applications: Society and Environment, p. 100482 (2021)
Patil, P.W., Dudhane, A., Kulkarni, A., Murala, S., Gonde, A.B., Gupta, S.: An unified recurrent video object segmentation framework for various surveillance environments. IEEE Trans. Image Process. 30, 7889–7902 (2021)
Bruzzone, L., Prieto, D.: Automatic analysis of the difference image for unsupervised change detection. IEEE Trans. Geosci. Remote Sens. 38(3), 1171–1182 (2000)
Patil, P.W., Dudhane, A., Chaudhary, S., Murala, S.: Multi-frame based adversarial learning approach for video surveillance. Pattern Recogn. 122, 108350 (2022)
Banerjee, T., Gurram, P., Whipps, G.T.: A bayesian theory of change detection in statistically periodic random processes. IEEE Trans. Inf. Theory 67(4), 2562–2580 (2021)
Lucas, B., Pelletier, C., Schmidt, D., Webb, G.I., Petitjean, F.: A bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping. Machine Learning, pp. 1–33 (2021)
Zhang, Y., Peng, D., Huang, X.: Object-based change detection for VHR images based on multiscale uncertainty analysis. IEEE Geosci. Remote Sens. Lett. 15(1), 13–17 (2018)
Sun, Y., Lei, L., Li, X., Sun, H., Kuang, G.: Nonlocal patch similarity based heterogeneous remote sensing change detection. Pattern Recogn. 109, 107598 (2021)
Liu, J., Gong, M., Qin, K., Zhang, P.: A deep convolutional coupling network for change detection based on heterogeneous optical and radar images. IEEE Trans. Neural Networks Learning Syst. 29(3), 545–559 (2016)
Chaudhary, S., Murala, S.: Tsnet: deep network for human action recognition in hazy videos. In: 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 3981–3986 (2018)
Liu, R., Jiang, D., Zhang, L., Zhang, Z.: Deep depthwise separable convolutional network for change detection in optical aerial images. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sensing 13, 1109–1118 (2020)
Zhan, Y., Fu, K., Yan, M., Sun, X., Wang, H., Qiu, X.: Change detection based on deep siamese convolutional network for optical aerial images. IEEE Geosci. Remote Sens. Lett. 14(10), 1845–1849 (2017)
Daudt, R.C., Le Saux, B., Boulch, A.: Fully convolutional siamese networks for change detection. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 4063–4067. IEEE (2018)
Heidary, F., Yazdi, M., Dehghani, M., Setoodeh, P.: Urban change detection by fully convolutional siamese concatenate network with attention. arXiv preprint arXiv:2102.00501 (2021)
Patil, P.S., Holambe, R.S., Waghmare, L.M.: Effcdnet: transfer learning with deep attention network for change detection in high spatial resolution satellite images. Digital Signal Process. 118, 103250 (2021)
Vaswani, A., et al.: Attention is all you need, arXiv preprint arXiv:1706.03762 (2017)
Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations, arXiv preprint arXiv:1803.02155 (2018)
Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3286–3295 (2019)
Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models, arXiv preprint arXiv:1906.05909 (2019)
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
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, 2020
Singh, A., Singh, K.K.: Unsupervised change detection in remote sensing images using fusion of spectral and statistical indices. The Egyptian Journal of Remote Sensing and Space Science 21(3), 345–351 (2018)
R. C. Daudt, B. Le Saux, A. Boulch, and Y. Gousseau, "Urban change detection for multispectral earth observation using convolutional neural networks," in IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2018, pp. 2115–2118
Phutke, S.S., Murala, S.: Diverse receptive field based adversarial concurrent encoder network for image inpainting. IEEE Signal Process. Lett. 28, 1873–1877 (2021)
Zhang, Z., Liu, Q., Wang, Y.: Road extraction by deep residual u-net. IEEE Geosci. Remote Sens. Lett. 15(5), 749–753 (2018)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97–136 (1980)
Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural combinatorial optimization with reinforcement learning, arXiv preprint arXiv:1611.09940, 2016
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate, arXiv preprint arXiv:1409.0473 (2014)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Park, J., Woo, S., Lee, J.-Y., Kweon, I.S.: Bam: bottleneck attention module. arXiv preprint arXiv:1807.06514 (2018)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International conference on machine learning. PMLR, pp. 7354–7363 (2019)
Noori, M., Bahri, A., Mohammadi, K.: Attention-guided version of 2d unet for automatic brain tumor segmentation. In: 2019 9th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 269–275. IEEE (2019)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167 (2015)
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network, arXiv preprint arXiv:1505.00853 (2015)
Chen, H., Shi, Z.: A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing 12(10), 1662 (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization, arXiv preprint arXiv:1412.6980 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Patil, P.S., Holambe, R.S., Waghmare, L.M. (2022). AAUNet: An Attention Augmented Convolution Based UNet for Change Detection in High Resolution Satellite Images. In: Raman, B., Murala, S., Chowdhury, A., Dhall, A., Goyal, P. (eds) Computer Vision and Image Processing. CVIP 2021. Communications in Computer and Information Science, vol 1567. Springer, Cham. https://doi.org/10.1007/978-3-031-11346-8_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-11346-8_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11345-1
Online ISBN: 978-3-031-11346-8
eBook Packages: Computer ScienceComputer Science (R0)