Extended Data Fig. 2: Examples from the postprocessing algorithm separating clumped trees.

a, Example of predicted tree crowns in the rainforest, with many trees being predicted as clumped objects. b, Results after the postprocessing algorithm separated the clumped crowns. The algorithm first finds the object centres, and then relabels the image based on weighted distances to the identified centres. Thus, blobs containing multiple centres are divided into various instances accordingly. The algorithm adds a large penalty for not-in-sight centres, and additionally performs a majority filtering to remove the lone-pixels.