Weather Recognition of Street Scene Based on Sparse Deep Neural Networks
Wei Liu, Yue Yang, and Longsheng Wei
School of Automation, China University of Geosciences
Wuhan, Hubei 430074, China
Recognizing different weather conditions is a core component of many different applications of outdoor video analysis and computer vision. Street analysis performance, including detecting street objects, detecting road lines, recognizing street sign and etc., varies greatly with weather, so modeling based on weather recognition is the key resolution in this field. Features derived from intrinsic properties of different weather conditions contribute to successful classification. We first propose using deep learning features from convolutional neural networks (CNN) for fine recognition. In order to reduce the parameter redundancy in CNN, we used sparse decomposition to dramatically cut down the computation. Recognition results for databases show superior performance and indicate the effectiveness of extracted features.
-  K. Garg and A. K. Nayar, “Detection and Removal of Rain from Videos,” Proc. of the 2004 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 528-535, 2004.
-  H. Kurihata, T. Takahashi, I. Ide, Y. Mekada, H. Murase, Y. Tamatsu, and T. Miyahara, “Rainy Weather Recognition from In-Vehicle Camera Images for Driver Assistance,” 2005 IEEE Intelligent Vehicles Symp., pp. 205-210, 2005.
-  H. Kurihata, T. Takahashi, Y. Mekada, I. Ichiro, H. Murase, Y. Tamatsu, and T. Miyahara, “Raindrop Detection from In-Vehicle Video Camera Images for Rainfall Judgment,” The 1st Int. Conf. on Innovative Computing, Information and Control, pp. 544-547, 2006.
-  X. Yan, Y. Luo, and X. Zheng, “Weather recognition based on Images Captured by Vision System in Vehicle,” 6th Int. Symp. on Neural Networks, 2009.
-  H. Song, Y. Chen, and Y. Gao, “Weather Condition Recognition Based on Feature Extraction and K-NN,” Foundations and Practical Applications of Cognitive Systems and Information Processing, Advances in Intelligent Systems and Computing, Vol.215, pp. 199-210, 2013.
-  A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in neural information processing systems, pp. 1097-1105, 2012.
-  V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” Proc. of 27th Int. Conf. on Machine Learning, 2010.
-  Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, “Caffe: Convolutional architecture for fast feature embedding,” arXiv preprint, arXiv:1408.5093, 2014.
-  L. van der Maaten and G. Hinton, “Visualizing data useing t-SNE,” JMLR, Vol.9, pp. 2579-2605, 2008.
-  B. Liu, M. Wang, H. Foroosh, M. Tappen, and M. Penksy, “Sparse Convolutional Neural Networks,” CVPR, pp. 806-814, 2015.
-  S. G. Narasimhan, C. Wang, and S. K. Nayar, “All the Images of an Outdoor Scene,” European Conf. on Computer Vision (ECCV), LNCS 2352, pp. 148-162, 2002.