The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-3/W12-2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-355-2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-355-2020
06 Nov 2020
 | 06 Nov 2020

SEMANTIC SEGMENTATION OF ENDANGERED TREE SPECIES IN BRAZILIAN SAVANNA USING DEEPLABV3+ VARIANTS

D. L. Torres, R. Q. Feitosa, L. E. C. La Rosa, P. N. Happ, J. Marcato Junior, W. N. Gonçalves, J. Martins, and V. Liesenberg

Keywords: Fully Convolution Neural Networks, Unmanned Aerial Vehicles (UAVs), Deep Learning, Semantic Segmentation

Abstract. Knowing the spatial distribution of endangered tree species in a forest ecosystem or forest remnants is a valuable information to support environmental conservation practices. The use of Unmanned Aerial Vehicles (UAVs) offers a suitable alternative for this task, providing very high-resolution images at low costs. In parallel, recent advances in the computer vision field have led to the development of effective deep learning techniques for end-to-end semantic image segmentation. In this scenario, the DeepLabv3+ is well established as the state-of-the-art deep learning method for semantic segmentation tasks. The present paper proposes and assesses the use of DeepLabv3+ for mapping the threatened Dipteryx alata Vogel tree, popularly also known as cumbaru. We also compare two backbone networks for feature extraction in the DeepLabv3+ architecture: the Xception and MobileNetv2. Experiments carried out on a dataset consisting of 225 UAV/RGB images of an urban area in Midwest Brazil demonstrated that DeepLabv3+ was able to achieve in mean overall accuracy and F1-score above 90%, and IoU above 80%. The experimental analysis also pointed out that the MobileNetv2 backbone overcame its counterpart by a wide margin due to its comparatively simpler architecture in view of the available training data.