Abstract
In this paper, in order to improve the accuracy and robustness of the fog figure visibility estimation, we propose an image visibility estimation method based on the improved Residual convolutional neural networks (i.e., ResNets). The Convolutional Block Attention Module (CBAM) is embedded in the structure of ResNet34, effectively improving the performance of the network. We use this method to conduct experiments based on airport surveillance video, comparing our method with other methods tested on the same data set. In the experiments of this paper, we use data augmentation (DA) to expand the number of the image samples, and use stochastic gradient descent (SGD) to minimize the loss. The experimental results show that the visibility estimation method proposed in this paper outperforms in terms of prediction accuracy and training speed under the same conditions.
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
Hautiere, N., Tarel, J.P., et al.: Automatic fog detection and estimation of visibility distance through use of an onboard camera. Mach. Vis. Appl. 17(1), 8–20 (2006)
Hu, J., Shen, L., et al.: Squeeze-and-excitation networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 7132–7141 (2017)
Ioffe, S, Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift, pp. 448–456 (2015)
Krizhevsky, A., et al.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2017)
Woo, S., Park, J., Lee, J. Y., Kweon, I. S.: CBAM: convolutional block attention module. In: European Conference on Computer Vision, pp. 3–19 (2018)
Li, X., Wang, W., et al.: Selective kernel networks, pp. 16–20 (2019)
Miao, K., Wang, C., et al.: Road visibility estimation method based on AlexNet algorithm. Comput. Modern. (6), 87 (2019)
Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. advances in neural information processing systems. In: Advances in Neural Information Processing Systems, pp. 2204–2212 (2014)
Nayar, S.K., Narasimhan, S.G.: Vision in bad weather. In: IEEE Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece (1999.09.20–1999.09.27), vol. 2, pp. 820–827 (1999)
Outay, F., Taha, B., Chaabani, H., Kamoun, F., Werghi, N., Yasar, A.-U.-H.: Estimating ambient visibility in the presence of fog: a deep convolutional neural network approach. Pers. Ubiquit. Comput. 25(1), 51–62 (2019). https://doi.org/10.1007/s00779-019-01334-w
Sakaridis, C., Dai, D., et al.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vis. 126(9), 973–992 (2017)
Tang, S., Qian, L., et al.: A visibility detection method based on transfer learning. Comput. Eng. 45(9), 242–247 (2019)
Song, H., Hao, Y., et al.: Traffic visibility estimation based on dynamic camera calibration. Chin. J. Comput. 038(006), 1172–1187 (2015)
Steffens, C.: Measurement of visibility by photographic photometry. Ind. Eng. Chem. 41(11), 2396–2399 (1949)
Steffens, C.: Visibility monitoring using conventional roadside cameras. Transp. Res. Emerg. Technol. 22, 17–28 (2012)
Sun, K.H.Z.R.: Deep residual learning for image recognition. In: 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2016), Anchorage, Alaska, June 2008, pp. 770–778 (2016)
Tan, R.T.: Visibility in bad weather from a single image. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), Anchorage, Alaska, USA, 24–26 June 2008 (2008)
Wang, F., Jiang, M., et al.: Residual attention network for image classification, pp. 6450–6458 (2017)
Wang, X., Girshick, R., et al.: Non-local neural networks, pp. 7794–7803 (2017)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yan, J., Wu, S., Chen, L., Huang, Y., Li, H. (2021). Residual Neural Network Based on Attention Mechanism for Visibility Estimation of Fog Figure. In: Xu, J., García Márquez, F.P., Ali Hassan, M.H., Duca, G., Hajiyev, A., Altiparmak, F. (eds) Proceedings of the Fifteenth International Conference on Management Science and Engineering Management. ICMSEM 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 78. Springer, Cham. https://doi.org/10.1007/978-3-030-79203-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-79203-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79202-2
Online ISBN: 978-3-030-79203-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)