Forest roads extraction through a convolution neural network aided method

Forest roads are important features of the environment that have significant impacts on wildlife habitats. The U-net and U-shaped Fully Convoluted Network (FCN) deep-learning methods have demonstrated great potential in successfully extracting paved roads in urban environments; however, they require a large amount of pixel-based training samples, which is resource-consuming. During this study, a convolutional neural network (CNN) aided method for forest road identification and extraction was developed. The algorithm utilized the multivariate Gaussian and Laplacian of Gaussian (LoG) filters and VGG 16 on high spatial resolution multispectral imagery to extract both primary road and secondary roads in forested areas. It was tested on imagery over two areas in the Hearst forest located in central Ontario, Canada. Based on validation against manually digitized roads, over 74% of the roads from both test areas were successfully extracted.

Automated summary

This study developed a method based on convolutional neural networks for forest road identification and extraction, successfully extracting roads in forested areas from high spatial resolution multispectral imagery.