Individual tree crown segmentation and crown width extraction from a heightmap derived from aerial laser scanning data using a deep learning framework

HIGHLIGHTS

SUMMARY

Although the nursery contained twice as many trees as either the mixed tree plantation or the forest landscape area, the numbers of commission errors and omission errors in the nursery were less than those in the mixed tree plantation and forest landscape area. Individual tree crown in the nursery, forest landscape area, and mixed tree plantation environments were detected using the deep learning method with 86.8, 81.4, and 79.9% overall recall, respectively (the data is the overall recall of three plots from each forest plot type, which is not in Table . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or E-mail:

If you don't have an account, you can create one here.