The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIV-M-2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-M-2-2020, 99–104, 2020
https://doi.org/10.5194/isprs-archives-XLIV-M-2-2020-99-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-M-2-2020, 99–104, 2020
https://doi.org/10.5194/isprs-archives-XLIV-M-2-2020-99-2020

  17 Nov 2020

17 Nov 2020

IDENTIFYING EPIPHYTES IN DRONES PHOTOS WITH A CONDITIONAL GENERATIVE ADVERSARIAL NETWORK (C-GAN)

A. Shashank1, V. V. Sajithvariyar1, V. Sowmya1, K. P. Soman1, R. Sivanpillai2, and G. K. Brown3 A. Shashank et al.
  • 1Center for Computational Engineering and Networking, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, TN 641 112, India
  • 2Wyoming GIS Center, University of Wyoming, Laramie, WY 82072, USA
  • 3Department of Botany, University of Wyoming, Laramie, WY 82072, USA

Keywords: UAV, CNN, PIX2PIX, UNET, Segmentation, Image translation

Abstract. Unmanned Aerial Vehicle (UAV) missions often collect large volumes of imagery data. However, not all images will have useful information, or be of sufficient quality. Manually sorting these images and selecting useful data are both time consuming and prone to interpreter bias. Deep neural network algorithms are capable of processing large image datasets and can be trained to identify specific targets. Generative Adversarial Networks (GANs) consist of two competing networks, Generator and Discriminator that can analyze, capture, and copy the variations within a given dataset. In this study, we selected a variant of GAN called Conditional-GAN that incorporates an additional label parameter, for identifying epiphytes in photos acquired by a UAV in forests within Costa Rica. We trained the network with 70%, 80%, and 90% of 119 photos containing the target epiphyte, Werauhia kupperiana (Bromeliaceae) and validated the algorithm’s performance using a validation data that were not used for training. The accuracy of the output was measured using structural similarity index measure (SSIM) index and histogram correlation (HC) coefficient. Results obtained in this study indicated that the output images generated by C-GAN were similar (average SSIM = 0.89–0.91 and average HC 0.97–0.99) to the analyst annotated images. However, C-GAN had difficulty to identify when the target plant was away from the camera, was not well lit, or covered by other plants. Results obtained in this study demonstrate the potential of C-GAN to reduce the time spent by botanists to identity epiphytes in images acquired by UAVs.