Visibility Level Estimation in Winter CCTV Images Based on Decision Level Fusion Using Logistic Regression
Shotaro KAWATA, Sho Takahashi, Toru Hagiwara · 2020
This paper proposes a method for estimating the degree of visibility (visibility level) in winter closed-circuit television (CCTV) images by decision level fusion based on logistic regression (LR). The proposed method classifies on the basis of two support vector machines (SVMs) classifiers and fuses the classification results by utilizing LRbased late fusion. In the proposed method, the SVMs which tentatively estimate visibility are constructed based on each CCTV image feature that represents the contrast of images and neuron values of the neural network. Also, the proposed method evaluates the visibility based on LR model trained by using SVM outputs. The effectiveness of our method is verified from experiments by utilizing actual CCTV images.