Abstract
This paper focuses on solving the problem of information loss during the generation of remote sensing image captions. In the field of artificial intelligence, the automatic description of remote sensing images is an important but rarely studied task. In the traditional framework, due to the higher pixels of the remote sensing image and the smaller target, when the image is processed and classified, the information is largely lost. In this case, we propose a new remote sensing image captioning framework using deep learning technology and attention mechanism. The experimental results show that the model can generate a full sentence description for remote sensing images.
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
References
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: 28th Annual Conference on Neural Information Processing Systems, pp. 2017–2015. MIT Press, Montreal (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: 28th Annual Conference on Neural Information Processing Systems, pp. 91–99. MIT Press, Montreal (2015)
Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Explain images with multimodal recurrent neural networks. arXiv preprint arXiv:1410.1090 (2014)
Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: 25th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128–3137. IEEE, Boston (2015)
Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 25th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156–3164. IEEE, Boston (2015)
Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: 25th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625–2634. IEEE, Boston (2015)
Chen, X., Zitnick, C.L.: Mind’s eye: a recurrent visual representation for image caption generation. In: 25th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2422–2431. IEEE, Boston (2015)
Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)
Mikolov, T., Karafiát, M., Burget, L., Cernocký, J., Khudanpur, S.: Recurrent neural network based language model. In: 11th Annual Conference of the International Speech Communication Association. ISCA, Makuhari (2010)
Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: 28th International Conference on Machine Learning, pp. 1017–1024. ACM, Bellevue (2011)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Shi, Z., Zou, Z.: Can a machine generate humanlike language descriptions for a remote sensing image? IEEE Trans. Geosci. Remote Sens. 55(6), 3623–3634 (2017)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (61472161), Science & Technology Development Project of Jilin Province (20180101334JC).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, S., Chen, J., Wang, G. (2018). Intensive Positioning Network for Remote Sensing Image Captioning. In: Peng, Y., Yu, K., Lu, J., Jiang, X. (eds) Intelligence Science and Big Data Engineering. IScIDE 2018. Lecture Notes in Computer Science(), vol 11266. Springer, Cham. https://doi.org/10.1007/978-3-030-02698-1_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-02698-1_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02697-4
Online ISBN: 978-3-030-02698-1
eBook Packages: Computer ScienceComputer Science (R0)