Wildfire Segmentation on Satellite Images using Deep Learning

Deep learning and convolutional neural network technologies are increasingly used in the problems of analysis, segmentation and recognition of objects in images. In this article a convolutional neural network for automated wildfire detection on high-resolution aerial photos is presented. Two databases of satellite RGB-images with different spatial resolution containing 1457 and 393 high-resolution images, respectively, were prepared for training and testing the neural network. Various techniques of data augmentation are used to enlarge training and test sets generated by data windowing. U-Net neural network with the ResNet34 as encoder was used in research. Neural network training was learning using the NVIDIA DGX-1 supercomputer. Adaptive moment estimation algorithm was used for optimization of training process. Special metrics, such as Sorensen-Dice coefficient, precision, recall, F1-score and IoU value allows to measure the quality of developed model. The developed algorithm can be successfully applied for early wildland fires detection in practical applications.

[1]  Roman Larionov,et al.  Forest Areas Segmentation on Aerial Images by Deep Learning , 2019, 2019 IEEE East-West Design & Test Symposium (EWDTS).

[2]  Jian Yang,et al.  A multi-band watershed segmentation method for individual tree crown delineation from high resolution multispectral aerial image , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[3]  YangQuan Chen,et al.  Comparing U-Net convolutional network with mask R-CNN in the performances of pomegranate tree canopy segmentation , 2018, Asia-Pacific Remote Sensing.

[4]  Alexey Shvets,et al.  Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[5]  Juazer Rizal Abdul Hamid,et al.  Accuracy assessment of tree crown detection using local maxima and multi-resolution segmentation , 2014 .

[6]  Yang Yu,et al.  Fruit detection for strawberry harvesting robot in non-structural environment based on Mask-RCNN , 2019, Comput. Electron. Agric..

[7]  Vladimir V. Khryashchev,et al.  Comparison of Different Convolutional Neural Network Architectures for Satellite Image Segmentation , 2018, 2018 23rd Conference of Open Innovations Association (FRUCT).

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  M. Bugalho,et al.  Forest Fires and Climate Change , 2009 .

[10]  Sebastian Raschka,et al.  Python Machine Learning , 2015 .

[11]  Caixia Liu,et al.  Integration of multi-resource remotely sensed data and allometric models for forest aboveground biomass estimation in China , 2019, Remote Sensing of Environment.

[12]  Thomas Blaschke,et al.  Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection , 2019, Remote. Sens..

[13]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[14]  Jake Vanderplas,et al.  Python Data Science Handbook: Essential Tools for Working with Data , 2016 .

[15]  David L. Martell,et al.  The impact of fire suppression, vegetation, and weather on the area burned by lightning-caused forest fires in Ontario , 2008 .