Abstract
Super‐resolution methods take several images from the same location and fuse them into one, called a super‐resolution image. If the fusion is carried out correctly, it is possible to recognize details from the super‐resolution image which are not visible in the original images. In this study, a super‐resolution technique is applied to sequences of National Oceanic and Atmospheric Administration, Advanced Very High Resolution Radiometer (NOAA/AVHRR) scenes using a varying number of images and acquisition times, in order to determine whether it is possible to recognize forested and non‐forested areas from NOAA/AVHRR images more accurately using a super‐resolution method than with the original images. The overall proportion of forest and the proportion of forest with a growing stock volume of over 50 m3/ha were calculated for each pixel, and the results evaluated using landscape indices, r.m.s. error (RMSE) and a parameter showing how large a proportion of the estimates are closer to the ground truth in the original image sequence than in the corresponding super‐resolution image. The results showed the super‐resolution estimates to be better in all cases than those based on the original image material, but the improvement was marginal. Neither the number of images nor the image acquisition time had any obvious effect on the results.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
