Abstract
Different weather conditions often affect people’s life in all ways. Nowadays, a large part of systems must make decision depending on current weather. Vision-based weather recognition is an important way to know weather conditions. In this paper, we bring in multi-level features: high-level features from Convolutional Neural Network (CNN) and classic low-level features, i.e., Scale-Invariant Feature Transform (SIFT) and Histogram of Gradient (HOG) for the weather recognition task. Furthermore, Support Vector Machine (SVM) is applied in this work. To evaluate the effectiveness of the combination of multi-level features and classifiers in the weather recognition, experimental studies are conducted on the public datasets. Experimental results demonstrate that the reasonable features combination in different conditions of data sizes contribute to efficiency performance.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
