Multi-Class Weather Classification from Still Image Using Said Ensemble Method

Abstract

In the field of computer vision, multi-class outdoor weather classification is a difficult task to perform due to diversity and lack of distinct weather characteristic or features. This research proposed a novel framework for identifying different weather scenes from still images using heterogeneous ensemble methods. Our approach is based on a method called Selection Based on Accuracy Intuition and diversity (SAID) of stacked ensemble algorithms. This involves the extraction of histogram of features from different weather scenes. The blending and boosting of different weather features using stacked ensemble algorithms increases recognition rate of different weather conditions compared to other classification and ensemble methods. The paper presents academic and practitioners a new insight into diversity of heterogeneous ensemble methods for solving the challenges of weather recognition from still images.