Forest road extraction from orthophoto images by convolutional neural networks

Continuous monitoring of the forest road infrastructure and keeping track of the changes occurred are important for forestry practices, map updating, forest fire and forest transport decision support systems. In this context, the most of up to date data can be obtained by automatic forest road extraction from satellite images via machine learning (ML). Acquiring sufficient data is one of the most important factors which affect the success of ML and deep learning (DL). DL architectures yield more consistent results for complex data sets compared with ML algorithms. In the present study, three different deep learning (Resnet-18, MobileNet-V2 and Xception) architectures with semantic segmentation architecture were compared for extracting the forest road network from high-resolution orthophoto images and the results were analyzed. The architectures were evaluated through a multiclass statistical analysis based precision, recall, F1 score, intersection over union and overall accuracy (OA). The results present significant values obtained by the Resnet-18 architecture, with 99.72% of OA and 98.87% of precision and by the MobileNet-V2 architecture, with 97.76% of OA and 98.28% of precision. Also the results show that Resnet-18, MobileNet-V2 semantic segmentation architectures can be used efficiently for forest road extraction.