Unsupervised Domain Adaptation for Forest Fire Recognition Using Transferable Knowledge from Public Datasets

• Published in: Forests 2023-01, Vol.14 (1), p.52
• Main Authors: Yan, Zhengjun, Wang, Liming, Qin, Kui, Zhou, Feng, Ouyang, Jineng, Wang, Teng, Hou, Xinguo, Bu, Leping
• Format: Article
• Language: English
• Subjects: Accuracy; Adaptation; Artificial neural networks; Benchmarks; Datasets; Deep learning; deep neural network; Domains; Forest & brush fires; Forest fire detection; forest fire recognition; Forest fires; Forests; Industrial applications; Knowledge management; Localization; Machine learning; Methods; Neural networks; Property damage; Recognition; Sensors; Transfer learning; unsupervised domain adaptation
• ISSN: 1999-4907; 1999-4907
• DOI: 10.3390/f14010052

Deep neural networks (DNNs) have driven the recent advances in fire detection. However, existing methods require large-scale labeled samples to train data-hungry networks, which are difficult to collect and even more laborious to label. This paper applies unsupervised domain adaptation (UDA) to transfer knowledge from a labeled public fire dataset to another unlabeled one in practical application scenarios for the first time. Then, a transfer learning benchmark dataset called Fire-DA is built from public datasets for fire recognition. Next, the Deep Subdomain Adaptation Network (DSAN) and the Dynamic Adversarial Adaptation Network (DAAN) are experimented on Fire-DA to provide a benchmark result for future transfer learning research in fire recognition. Finally, two transfer tasks are built from Fire-DA to two public forest fire datasets, the aerial forest fire dataset FLAME and the large-scale fire dataset FD-dataset containing forest fire scenarios. Compared with traditional handcrafted feature-based methods and supervised CNNs, DSAN reaches 82.5% performance of the optimal supervised CNN on the testing set of FLAME. In addition, DSAN achieves 95.8% and 83.5% recognition accuracy on the testing set and challenging testing set of FD-dataset, which outperform the optimal supervised CNN by 0.5% and 2.6%, respectively. The experimental results demonstrate that DSAN achieves an impressive performance on FLAME and a new state of the art on FD-dataset without accessing their labels during training, a fundamental step toward unsupervised forest fire recognition for industrial applications.