Dark-Channel Mixed Attention Based Neural Networks for Smoke Detection in Fog Environment

Abstract

Although deep learning has been widely applied to smoke detection tasks, most of these methods only consider the problem in normal weather, which leads to a drastic performance decreasing when detecting smoke in fog. Existing methods propose to add the synthetic fog to the images collected in normal environments, and to train the models on the augmented datasets. However, these methods only alleviate the problem. Due to that the generalization ability of a machine learning method can only be guaranteed if training and test datasets are with the same data distribution, the distribution gap between synthetic and real-world images limits the upper bound of the detection performance. In this paper, we develop a general smoke detection dataset with diverse real-world collected samples. Furthermore, we develop a novel smoke detection method based on dark-channel assisted mixed attention. Experiments show the importance of the built dataset and the effectiveness of our detection method.

Defogging Learning Based on an Improved DeepLabV3+ Model for Accurate Foggy Forest Fire Segmentation

“…However, this approach requires additional computational cost, which may result in higher execution time, especially when processing a large number of images. On the other hand, the smoke detection model that utilizes dark channel-aided mixed attention does not require additional computational cost, but the performance of the model is much inferior to ours due to the prior-based approach [21].…”

“…More and more deep learning techniques are being used to solve the issue of forest fires in hazy photos. For example, Yang et al [21] designed a smoke detection model that leverages dark channel-assisted hybrid attention, while Merve Balki Tas et al [22] created a smoke detection idea specifically for foggy wildfires. Huang et al [23] also designed a GXTD detection model with a defogging function.…”