Abstract
Spatiotemporal fusion is an effective way to provide remote sensing images with both high temporal resolution and high spatial resolution for earth observation. Most of the existing methods require at least three images as input, which may increase the difficulty in practical applications. Towards this end, a cross-paired wavelet based spatiotemporal fusion network (CPW-STFN) for remote sensing images is proposed. The wavelet transform decomposes the low and high frequency components of the image into four channels, so that it enables the model to train features of different level separately. The proposed CPW-STFN can extract the detail textures as well as the global information better and easier. In other words, we achieved a spatiotemporal fusion method with only two cross-paired images as inputs which are the fine resolution image at reference date and the coarse resolution image at prediction date. In addition, a compound loss function containing a wavelet loss to promote the spatial detail preservation is proposed. In this paper, the fusion ability of the proposed CPW-STFN was tested by the commonly used datasets CIA and LGC, and compared with other methods including state-of-the-art models STARFM, FSDAF, EDCSTFN, MLFF-GAN and GAN-STFM. CPW-STFN performs better than GAN-STFM which also requires only two input images, and not inferior to the other methods which require at least three inputs, proving its advantage and potential.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, J., Li, Y., He, L., Chen, J., Plaza, A.: Spatio-temporal fusion for remote sensing data: an overview and new benchmark. Sci. China Inf. Sci. 63(4), 7–23 (2020)
Tan, Z., Di, L., Zhang, M., Guo, L., Gao, M.: An enhanced deep convolutional model for spatiotemporal image fusion. Remote Sensing 11(24), 2898 (2019)
Chen, B., Huang, B., Xu, B.: Comparison of spatiotemporal fusion models: a review. Remote Sensing 7(2), 1798–1835 (2015)
Gao, F., Masek, J., Schwaller, M., Hall, F.: On the blending of the landsat and MODIS surface reflectance: predicting daily Landsat surface reflectance. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 44(8), 2207–2218 (2006)
Zhu, X., Chen, J., Gao, F., Chen, X., Masek, J.G.: An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions. Remote Sens. Environ. 114(11), 2610–2623 (2010)
Hilker, T., Wulder, M.A., Coops, N.C., et al.: A new data fusion model for high spatial- and temporal-resolution mapping of forest disturbance based on Landsat and MODIS. Remote Sens. Environ. 113(8), 1613–1627 (2009)
Zhukov, B., Oertel, D., Lanzl, F., Reinhackel, G.: Unmixing-based multisensor multiresolution image fusion. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 37(3), 1212–1226 (1999)
Wu, M., Niu, Z., Wang, C., Wu, C., Wang, L.: Use of MODIS and Landsat time series data to generate high-resolution temporal synthetic Landsat data using a spatial and temporal reflectance fusion model. J. Appl. Remote. Sens. 6(1), 063507 (2012)
Xue, J., Leung, Y., Fung, T.: A bayesian data fusion approach to spatio-temporal fusion of remotely sensed images. Remote Sensing 9(12), 1310 (2017)
Shen, H., Meng, X., Zhang, L.: An integrated framework for the spatio-temporal-spectral fusion of remote sensing images. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 54(12), 7135–7148 (2016)
Huang, B., Song, H.: Spatiotemporal reflectance fusion via sparse representation. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 50(10), 3707–3716 (2012)
Song, H., Liu, Q., Wang, G., Hang, R., Huang, B.: Spatiotemporal satellite image fusion using deep convolutional neural networks. IEEE J. Selected Topics Appli Earth Observat. Remote Sensing 11(3), 821–829 (2018)
Li, Y., Li, J., He, L., Chen, J., Plaza, A.: A new sensor bias-driven spatio-temporal fusion model based on convolutional neural networks. Sci. China Inf. Sci. 63(4), 140302 (2020)
Liu, X., Deng, C., Chanussot, J., Hong, D., Zhao, B.: StfNet: a two-stream convolutional neural network for spatiotemporal image fusion. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 57(9), 6552–6564 (2019)
Tan, Z., Gao, M., Li, X., Jiang, L.: A flexible reference-insensitive spatiotemporal fusion model for remote sensing images using conditional generative adversarial network. IEEE Trans. Geosci. Remote Sens. 60, 1–13 (2021)
Chen, J., Wang, L., Feng, R., Liu, P., Han, W., Chen, X.: CycleGAN-STF: spatiotemporal fusion via CycleGAN-based image generation. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 59(7), 5851–5865 (2020)
Song, B., Liu, P., Li, J., Wang, L., Zhang, L., He, G., et al.: MLFF-GAN: a multilevel feature fusion with GAN for spatiotemporal remote sensing images. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 60, 1–16 (2022)
Zhu, X., Helmer, E.H., Gao, F., Liu, D., Chen, J., Lefsky, M.A.: A flexible spatiotemporal method for fusing satellite images with different resolutions. Remote Sens. Environ. 172, 165–177 (2016)
Xue, S., Qiu, W., Liu, F., Jin, X.: Wavelet-based residual attention network for image super-resolution. Neurocomputing 382, 116–126 (2020)
Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-srnet: a wavelet-based cnn for multi-scale face super resolution. In: IEEE International Conference on Computer Vision, pp. 1689–1697. IEEE, Venice, Italy (2017)
Hsu, W.Y., Jian, P.W.: Detail-enhanced wavelet residual network for single image super-resolution. IEEE Trans. Instrum. Meas.Instrum. Meas. 71, 1–13 (2022)
Zhang, H., Jin, Z., Tan, X., Li, X.: Towards lighter and faster learning wavelets progressively for image super-resolution. In: 28th ACM International Conference on Multimedia, pp. 2113–2121. ACM, Seattle, USA (2020)
Emelyanova, I.V., McVicar, T.R., Van Niel, T.G., Li, L.T., Van Dijk, A.I.: Assessing the accuracy of blending Landsat–MODIS surface reflectances in two landscapes with contrasting spatial and temporal dynamics: A framework for algorithm selection. Remote Sens. Environ. 133, 193–209 (2013)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Yuhas, R.H., Goetz, A.F., Boardman, J.W.: Descrimination among semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm. In: The Third Annual JPL Airborne Geoscience Workshop, pp. 147–149. AVIRIS Workshop. California, USA (1992)
Acknowledgement
This work was supported by the National Natural Science Foundation of China (NSFC) under Grant no. 42171302 and the Key R&D Program of Hubei Province, China (2021BAA185).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, X., Yu, S., Li, X., Li, S., Tan, Z. (2023). A Cross-Paired Wavelet Based Spatiotemporal Fusion Network for Remote Sensing Images. In: Lu, H., et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14359. Springer, Cham. https://doi.org/10.1007/978-3-031-46317-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-46317-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46316-7
Online ISBN: 978-3-031-46317-4
eBook Packages: Computer ScienceComputer Science (R0)