Abstract
Building detection in remote sensing image plays an important role in urban planning and construction, management and military fields. Most of the building detection methods utilized deep neural networks to achieve better detection results. However, these methods either train their models on panchromatic images or on the fused images of panchromatic and multispectral images, which do not take into full consideration the advantages of high resolution and multispectral of earth observation images. In this paper, a large-scale building dataset is presented, more than 10 million single buildings were annotated both on panchromatic images and the corresponding multispectral images. Moreover, a building detection method is proposed based on complementary convolutional feature via fusion on panchromatic and multispectral images. Experimental results on the proposed dataset and ResNet-101 demonstrate that, complementary convolutional feature based building detection methods outperform the methods that only use panchromatic convolution feature and multispectral convolution feature.
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
Liu, W., Ma, L., Chen, H., Han, Z., Soomro, N.Q.: Sea–land segmentation for panchromatic remote sensing imagery via integrating improved MNcut and Chan–Vese model. IEEE Geosci. Remote Sens. Lett. 14(12), 2443–2447 (2017)
Zhu, D., Wang, B., Zhang, L.: Airport target detection in remote sensing images: a new method based on two-way saliency. IEEE Geosci. Remote Sens. Lett. 12(5), 1096–1100 (2015)
Tan, Y., Xiong, S., Li, Y.: Automatic extraction of built-up areas from panchromatic and multispectral remote sensing images using double-stream deep convolutional neural networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11(11), 3988–4004 (2018)
Liu, X., Liu, Q., Wang, Y.: Remote sensing image fusion based on two-stream fusion network. Inf. Fusion 55, 1–15 (2020)
Lu, Z., Liu, K., Liu, Z., Wang, C., Shen, M., Xu, T.: An efficient annotation method for big data sets of high-resolution earth observation images. In: Proceedings of the 2nd International Conference on Big Data Technologies, pp. 240–243 (2019)
Ševo, I., Avramović, A.: Convolutional neural network based automatic object detection on aerial images. IEEE Geosci. Remote Sens. Lett. 13(5), 740–744 (2016)
Zhang, Q., Wang, Y., Liu, Q., Liu, X., Wang, W.: CNN based suburban building detection using monocular high resolution google earth images. In: 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 661–664. IEEE (2016)
Ma, C., Mu, X., Sha, D.: Multi-layers feature fusion of convolutional neural network for scene classification of remote sensing. IEEE Access 7, 121685–121694 (2019)
Deng, L.J., Feng, M., Tai, X.C.: The fusion of panchromatic and multispectral remote sensing images via tensor-based sparse modeling and hyper-laplacian prior. Inf. Fusion 52, 76–89 (2019)
Ye, F., Li, X., Zhang, X.: FusionCNN: a remote sensing image fusion algorithm based on deep convolutional neural networks. Multimed. Tools Appl. 78(11), 14683–14703 (2018). https://doi.org/10.1007/s11042-018-6850-3
Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105(10), 1865–1883 (2017)
Zhu, Q., Zhong, Y., Zhao, B., Xia, G.S., Zhang, L.: Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery. IEEE Geosci. Remote Sens. Lett. 13(6), 747–751 (2016)
Luus, F.P., Salmon, B.P., Van den Bergh, F., Maharaj, B.T.J.: Multiview deep learning for land-use classification. IEEE Geosci. Remote Sens. Lett. 12(12), 2448–2452 (2015)
Zou, Q., Ni, L., Zhang, T., Wang, Q.: Deep learning based feature selection for remote sensing scene classification. IEEE Geosci. Remote Sens. Lett. 12(11), 2321–2325 (2015)
Acknowledgment
This work is supported by Major Special Provincial Industrialization Application Project of High-Resolution Earth Observation System (No. 79-Y40G03-9001-18/20), the Key Research and Development Program of Shandong Province (No. 2018JMRH0102), Science and Technology Development Program of Jinan, Doctoral Foundation of University of Jinan (No. XBS1653) and Natural Science Foundation of University of Jinan (Nos. XKY1803, XKY1804, XKY1928).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, Z. et al. (2020). Building Detection via Complementary Convolutional Features of Remote Sensing Images. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12305. Springer, Cham. https://doi.org/10.1007/978-3-030-60633-6_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-60633-6_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60632-9
Online ISBN: 978-3-030-60633-6
eBook Packages: Computer ScienceComputer Science (R0)