Unified smoke and fire detection in an evolutionary framework with self-supervised progressive data augment
This work addresses a domain-specific problem in fire safety by enhancing detection models for uncertain fluid patterns like smoke and flame, though it appears incremental in its approach.
The paper tackled the problem of simultaneous smoke and fire detection in images by collecting and re-labeling a large dataset as a multi-label classification task, and proposed an evolutionary framework with self-supervised progressive data augmentation, which improved generalization performance as shown in experiments.
Few researches have studied simultaneous detection of smoke and flame accompanying fires due to their different physical natures that lead to uncertain fluid patterns. In this study, we collect a large image data set to re-label them as a multi-label image classification problem so as to identify smoke and flame simultaneously. In order to solve the generalization ability of the detection model on account of the movable fluid objects with uncertain shapes like fire and smoke, and their not compactible natures as well as the complex backgrounds with high variations, we propose a data augment method by random image stitch to deploy resizing, deforming, position variation, and background altering so as to enlarge the view of the learner. Moreover, we propose a self-learning data augment method by using the class activation map to extract the highly trustable region as new data source of positive examples to further enhance the data augment. By the mutual reinforcement between the data augment and the detection model that are performed iteratively, both modules make progress in an evolutionary manner. Experiments show that the proposed method can effectively improve the generalization performance of the model for concurrent smoke and fire detection.