Abstract
Weather classification using multiple classes is the most sought technique which has many potential applications. It is extremely difficult to get discriminative features from weather images due to diverse nature of weather conditions. In this paper, we have tried to capture the discriminative features by using feature fusion and feature reduction/selection methods. The proposed method uses combination of Histogram of Gradient (HOG) & deep features, feature selection/reduction and classification. Extensive experiments on the benchmark datasets were carried out using various features extraction and selection/reduction methods in conjunction with various classifiers. The extensive experimental evaluation demonstrates fusion of HOG & DenseNet-161 features with linear SVM classifier achieves the best classification accuracy of 99.65% & 95.2% for MCWRD and MWI dataset respectively. Our method has outperformed the state-of-the-art methods for both datasets. Our method is scalable, as it generates variety of solutions. Based on available compute, user can pick & choose the relevant method.
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
Dalal, N., Triggs, B.: Histogram of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern recognition (CVPR’05) (2005)
Roser, M., Moosmann, F.: Classification of weather situations on single color images. In: Proceedings of IEEE Intelligent Vehicles Symposium, pp. 798–803 (2008)
Yan, X., Luo, Y., Zheng, X.: Weather recognition based on images captured by vision system in vehicle. In: Yu, W., He, H., Zhang, N. (eds.) ISNN 2009. LNCS, vol. 5553, pp. 390–398. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-01513-7_42
Chen, Z., Yang, F., Lindner, A., Barrenetxea, G., Vetterli, M.: How is the weather: automatic inference from images. In: Proceedings of IEEE ICIP (2012)
Zhang, Z., Ma, H.D.: Multi-class weather classification on single images. In: Proceedings of IEEE International Conference on Image Processing (2015)
Zheng, C., Zhang, F., Hou, H., Bi, C., Zhang, M., Zhang, B.: Active discriminative dictionary learning for weather recognition. Math. Probl. Eng. 2016, 8272859, 12 (2016)
Chu, W., Zheng, X., Ding, D.: Camera as weather sensor: estimating weather information from single images. J. Vis. Commun. Image Represent. 46, 233–249 (2017)
Zhu, Z., Li, J., Zhuo, L., Zhang, J.: Extreme weather recognition using a novel fine-tuning strategy and optimized GoogLeNet. In: 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, NSW (2017)
Shi, Y., Li, Y., Liu, J., Liu, X., Murphey, Y.L.: Weather recognition based on edge deterioration and convolutional neural networks. In: 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, pp. 2438–2443 (2018)
Kang, L., Chou, K., Fu, R.: Deep learning-based weather image recognition. In: International Symposium on Computer, Consumer & Control (IS3C), Taichung, Taiwan (2018)
Oluwafemi, A.G., Zenghui, W.: Multi-class weather classification from still image using said ensemble method. In: Southern African Universities Power Engineering Conference, South Africa, pp. 135–140 (2019)
Ibrahim, M.R., Haworth, J., Cheng, T.: WeatherNet: recognizing weather and visual conditions from StreetLevel images using deep residual learning. ISPRS Int. J. Geo-Inf. (2019)
Wang, Y., Li, Y.: Research on multi-class weather classification algorithm based on multi-model fusion. In: IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), China, pp. 2251–2255 (2020)
Xia, J., Xuan, D., Tan, L., Xing, L.: ResNet15: weather recognition on traffic road with deep convolutional neural network. Adv. Meteorol., Hindawi, (2020)
Al-Haija, Q.A., Smadi, M.A., et al.: Multi-class weather classification using resnet-18 CNN for autonomous IoT and CPS applications. In: International Conference on Computational Science and Computational Intelligence (CSCI) (2020)
Zhang, Z., et al.: Scene-free multi-class weather classification on single images. Neurocomputing 207, 365–373 (2016)
Ajayi, G.: Multi-class weather dataset for image classification. Mendeley Data V1, (2018). https://doi.org/10.17632/4drtyfjtfy.1
Chanda, S., Okafor, E., Hamel, S., Stutzmann, D., Schomaker, L.: Deep learning for classification and as tapped-feature generator in medieval word-image. In: 13th IAPR International Workshop on Document Analysis Systems (2018)
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
Deepak, G., Gudla, V.S., AGJ, F. (2023). Multi-class Weather Classification Using Single Image via Feature Fusion and Selection. In: Gupta, D., Bhurchandi, K., Murala, S., Raman, B., Kumar, S. (eds) Computer Vision and Image Processing. CVIP 2022. Communications in Computer and Information Science, vol 1777. Springer, Cham. https://doi.org/10.1007/978-3-031-31417-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-31417-9_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31416-2
Online ISBN: 978-3-031-31417-9
eBook Packages: Computer ScienceComputer Science (R0)