The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 717–723, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-717-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 717–723, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-717-2020

  12 Aug 2020

12 Aug 2020

SEGMENTATION OF SINGLE STANDING DEAD TREES IN HIGH-RESOLUTION AERIAL IMAGERY WITH GENERATIVE ADVERSARIAL NETWORK-BASED SHAPE PRIORS

P. Polewski1, J. Shelton1, W. Yao1, and M. Heurich2 P. Polewski et al.
  • 1Dept. of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, China
  • 2Dept. for Conservation and Research, Bavarian Forest National Park, Grafenau, Germany

Keywords: GAN, CNN, active contour, color infrared, forest health monitoring

Abstract. The use of multispectral imagery for monitoring biodiversity in ecosystems is becoming widespread. A key parameter of forest ecosystems is the distribution of dead wood. This work addresses the segmentation of individual dead tree crowns in nadir-view aerial infrared imagery. While dead vegetation produces a distinct spectral response in the near infrared band, separating adjacent trees within large swaths of dead stands remains a challenge. We tackle this problem by casting the segmentation task within the active contour framework, a mathematical formulation combining learned models of the object’s shape and appearance as prior information. We explore the use of a deep convolutional generative adversarial network (DCGAN) in the role of the shape model, replacing the original linear mixture-of-eigenshapes formulation. Also, we rely on probabilities obtained from a deep fully convolutional network (FCN) as the appearance prior. Experiments conducted on manually labeled reference polygons show that the DCGAN is able to learn a low-dimensional manifold of tree crown shapes, outperforming the eigenshape model with respect to the similarity of the reproduced and referenced shapes on about 45 % of the test samples. The DCGAN is successful mostly for less convex shapes, whereas the baseline remains superior for more regular tree crown polygons.