Abstract
Computer vision research usually needs sufficient high-quality images. However, the contrast of images captured at night is always low, which makes many classification tasks difficult. For example, it is hard for an unmanned surface vessel to sense the environment at night. In this paper, we attempt to solve the low-light image classification problem via using deep learning methods. Inspired by the multi-scale Retinex algorithm, we design a novel convolutional structure named dedark block to enhance the low-light image and add it to the CNN architecture for object recognition. By creating different models, we gradually improve our models to close to the result of CNN baseline based high-quality images, and every model is good motivated. Besides the strong learning ability of CNN, the dedark block which is regarded as pre-training also plays an important role in our final model. At last, the result of every model is evaluated on two classical datasets, and all of them achieve great performance.
L. Shen contributed equally.
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
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lin, M., Chen, Q., Yan, S.: Network in network. Computer Science (2013)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. arXiv preprint arXiv:1608.06993 (2016)
Jobson, D.J., Rahman, Z.-U., Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (1997)
Petro, A.B., Sbert, C., Morel, J.M.: Multiscale retinex. Image Process. Line 4, 71–88 (2014)
Provenzi, E., De Carli, L., Rizzi, A., Marini, D.: Mathematical definition and analysis of the retinex algorithm. J. Opt. Soc. Am. A Optics Image Sci. Vis. 22(12), 2613–2621 (2005)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Pizer, S.M., et al.: Adaptive histogram equalization and its variations. Comput. Vis. Graphics Image Process. 39(3), 355–368 (1987)
Celik, T., Tjahjadi, T.: Contextual and variational contrast enhancement. IEEE Trans. Image Process. 20(12), 3431–3441 (2011)
Land, E.H.: The retinex theory of color vision. Sci. Am. 237(6), 108–129 (1977)
Jobson, D.J., Rahman, Z.-U., Woodell, G.A.: Properties and performance of a center/surround retinex. IEEE Trans. Image Process. 6(3), 451–462 (1997)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3119–3127 (2015)
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)
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)
Fu, X., Huang, J., Zeng, D., Huang, Y., Ding, X., Paisley, J.: Removing rain from single images via a deep detail network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1715–1723 (2017)
Cai, B., Xiangmin, X., Jia, K., Qing, C., Tao, D.: DehazeNet: an end-to-end system for single image haze removal. IEEE Trans. Image Process. 25(11), 5187–5198 (2016)
Chevalier, M., Thome, N., Cord, M., Fournier, J., Henaff, G., Dusch, E.: LR-CNN for fine-grained classification with varying resolution. In: 2015 IEEE International Conference on Image Processing (ICIP), pp. 3101–3105. IEEE (2015)
Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: AOD-Net: all-in-one dehazing network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4770–4778 (2017)
Liu, D., Wen, B., Liu, X., Huang, T.S.: When image denoising meets high-level vision tasks: A deep learning approach. arXiv preprint arXiv:1706.04284 (2017)
Vasiljevic, I., Chakrabarti, A., Shakhnarovich, G.: Examining the impact of blur on recognition by convolutional networks. arXiv preprint arXiv:1611.05760 (2016)
Diamond, S., Sitzmann, V., Boyd, S., Wetzstein, G., Heide, F.: Dirty pixels: optimizing image classification architectures for raw sensor data. arXiv preprint arXiv:1701.06487 (2017)
Nilsback, M.-E., Zisserman, A.: Automated flower classification over a large number of classes. In: Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing, December 2008
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. Computer Science (2014)
Acknowledgments
This work was supported by the Guangdong Innovative and Entrepreneurial Research Team Program under Grant 2014ZT05G304.
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
Yue, Z. et al. (2018). Sea Surface Object Recognition Under the Low-Light Environment. In: Chen, Z., Mendes, A., Yan, Y., Chen, S. (eds) Intelligent Robotics and Applications. ICIRA 2018. Lecture Notes in Computer Science(), vol 10985. Springer, Cham. https://doi.org/10.1007/978-3-319-97589-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-97589-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97588-7
Online ISBN: 978-3-319-97589-4
eBook Packages: Computer ScienceComputer Science (R0)