|
|
Weather Classification of Sunny or Cloudy Day Based on an Outdoor Color Image |
ZHANG Shi-hui1,2,DU Xue-zhe1,HE Qi1,DONG Li-jian1 |
1. School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
2. The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, Qinhuangdao, Hebei 066004, China |
|
|
Abstract A novel approach to classify whether an outdoor color image is sunny or cloudy is proposed by using random forest. Firstly, two new weather features named sky frequency histogram and shadow energy are defined respectively, and their calculation methods are presented. Meanwhile, the transmission feature is introduced in weather classification for the first time. These three features are combined with the existing features to form the candidate weather feature set. Secondly, a new feature importance calculation method named Fisher-Random Forest is proposed to select weather features. Finally, the selected weather features are input into the random forest classifier in the form of vector to classify whether the outdoor color image is sunny or cloudy. The experimental results demonstrate that, compared with other methods, the proposed approach has higher accuracy and better generality.
|
Received: 18 July 2017
Published: 10 October 2019
|
|
Corresponding Authors:
Shi-hui ZHANG
E-mail: sshhzz@ysu.edu.cn
|
|
|
|
[1]Narasimham S G, Nayar S K. Vision and the atmosphere[J]. International Journal of Computer Vision, 2002, 48(3): 233-254.
[2]Kurihata H, Takahashi T, Ide I, et al. Rainy weather recognition from in-vehicle camera images for driver assistance[C]// Intelligent Vehicles Symposium. IEEE, Las Vegas, USA, 2005: 205-210.
[3]Kurihata H, Takahashi T, Mekada Y, et al. Raindrop detection from in-vehicle video camera images for rainfall judgment[C]// International Conference on Innovative Computing, Information and Control. IEEE, Beijing, China, 2006: 544-547.
[4]程淑红, 高许, 周斌. 基于多特征提取和SVM参数优化的车型识别[J]. 计量学报, 2018,39(3): 348-352.
Cheng S H, Gao X, Zhou B. Vehicle recognition based on multi-feature extraction and SVM parameter optimization [J]. Acta Metrologica Sinica, 2018, 39(3): 348-352.
[5]Jonsson P. Classification of road conditions: from camera images and weather data[C]// International Conference on Computational Intelligence for Measurement Systems and Applications. IEEE, Ottawa, Canada, 2011:1-6.
[6]Olaiya F, Adeyemo A B. Application of data mining techniques in weather prediction and climate change studies[J]. International Journal of Information Engineering & Electronic Business, 2012, 4(1): 51-59.
[7]Garg K, Nayar S K. Detection and removal of rain from videos[C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, Washington DC, USA, 2004: 1528-1535.
[8]Roser M, Moosmann F. Classification of weather situations on single color images[C]// Intelligent Vehicles Symposium. IEEE, Eindhoven, Netherlands, 2008: 798-803.
[9]Yan X, Luo Y, Zheng X. Weather recognition based on images captured by vision system in vehicle[C]// International Symposium on Neural Networks: Advances in Neural Networks. Springer, Wuhan, China, 2009: 390-398.
[10]Lu C, Lin D, Jia J, et al. Two-Class Weather Classification[C]// IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Columbus, USA, 2014: 3718-3725.
[11]Zhang Z, Ma H. Multi-class weather classification on single images[C]// International Conference on Image Processing. IEEE, Quebec City, Canada, 2015: 4396-4400.
[12]Hulst H C. Light Scattering by Small Particles[M]. New York:Dover Publications Inc, 1981.
[13]Tao L, Yuan L, Sun J. SkyFinder: attribute-based sky image search[J]. ACM Transactions on Graphics, 2009, 28(3): 68.1-68.5.
[14]Lalonde J F, Efros A A, Narasimhan S G. Detecting ground shadows in outdoor consumer photographs[C]// European Conference on Computer Vision. Springer, Heraklion, Greece, 2010: 322-335.
[15]He K, Sun J, Tang X. Single image haze removal using dark channel prior[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2009, 33(12): 2341-2353.
[16]Kopf J, Neubert B, Chen B, et al. Deep photo: model-based photograph enhancement and viewing[J]. ACM Transactions on Graphics, 2008, 27(5): 116.1-116.10.
[17]Breiman L. Random Forests [J]. Machine Learning, 2001, 45(1):5-32. |
|
|
|