Next Article in Journal
Evaluation of Vegetation Indexes and Green-Up Date Extraction Methods on the Tibetan Plateau
Previous Article in Journal
A Compensation Method of Saturated Waveform for Space-Borne Laser Altimeter
Previous Article in Special Issue
Correction: Marchese et al. Mt. Etna Paroxysms of February–April 2021 Monitored and Quantified through a Multi-Platform Satellite Observing System. Remote Sens. 2021, 13, 3074
 
 
Article

Forest Fire Segmentation from Aerial Imagery Data Using an Improved Instance Segmentation Model

College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, China
*
Author to whom correspondence should be addressed.
Academic Editors: Klemen Zakšek, Francesco Marchese, Nicola Genzano and Carolina Filizzola
Remote Sens. 2022, 14(13), 3159; https://doi.org/10.3390/rs14133159
Received: 26 May 2022 / Revised: 28 June 2022 / Accepted: 29 June 2022 / Published: 1 July 2022
In recent years, forest-fire monitoring methods represented by deep learning have been developed rapidly. The use of drone technology and optimization of existing models to improve forest-fire recognition accuracy and segmentation quality are of great significance for understanding the spatial distribution of forest fires and protecting forest resources. Due to the spreading and irregular nature of fire, it is extremely tough to detect fire accurately in a complex environment. Based on the aerial imagery dataset FLAME, this paper focuses on the analysis of methods to two deep-learning problems: (1) the video frames are classified as two classes (fire, no-fire) according to the presence or absence of fire. A novel image classification method based on channel domain attention mechanism was developed, which achieved a classification accuracy of 93.65%. (2) We propose a novel instance segmentation method (MaskSU R-CNN) for incipient forest-fire detection and segmentation based on MS R-CNN model. For the optimized model, the MaskIoU branch is reconstructed by a U-shaped network in order to reduce the segmentation error. Experimental results show that the precision of our MaskSU R-CNN reached 91.85%, recall 88.81%, F1-score 90.30%, and mean intersection over union (mIoU) 82.31%. Compared with many state-of-the-art segmentation models, our method achieves satisfactory results on forest-fire dataset. View Full-Text
Keywords: fire recognition; instance segmentation; computer vision; deep learning; aerial imagery fire recognition; instance segmentation; computer vision; deep learning; aerial imagery
Show Figures

Graphical abstract

MDPI and ACS Style

Guan, Z.; Miao, X.; Mu, Y.; Sun, Q.; Ye, Q.; Gao, D. Forest Fire Segmentation from Aerial Imagery Data Using an Improved Instance Segmentation Model. Remote Sens. 2022, 14, 3159. https://doi.org/10.3390/rs14133159

AMA Style

Guan Z, Miao X, Mu Y, Sun Q, Ye Q, Gao D. Forest Fire Segmentation from Aerial Imagery Data Using an Improved Instance Segmentation Model. Remote Sensing. 2022; 14(13):3159. https://doi.org/10.3390/rs14133159

Chicago/Turabian Style

Guan, Zhihao, Xinyu Miao, Yunjie Mu, Quan Sun, Qiaolin Ye, and Demin Gao. 2022. "Forest Fire Segmentation from Aerial Imagery Data Using an Improved Instance Segmentation Model" Remote Sensing 14, no. 13: 3159. https://doi.org/10.3390/rs14133159

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop