evaluate_field_crowns: Compute evaluation metrics for the field-collected crowns

In weecology/NeonTreeEvaluation_package: Evaluate Individual Tree Segmentation Algorithms against Benchmark Data

Compute evaluation metrics for the field-collected crowns

Description

evaluate_field_crowns implements the matching and scoring algorithm on crowns that were drawn on a tablet while physically standing in the field.

Usage

evaluate_field_crowns(
  predictions,
  summarize = TRUE,
  show = TRUE,
  project = FALSE
)

Arguments

predictions	a submission document
summarize	Compute summary statistics for crown recall
show	Logical. Plot the overlayed annotations for each plot?
project	Whether to project the supplied bounding box coordinates from image coordinates into geographic coordinates (utm QGS84). This is needed for computing recall scores.

Details

For details on the protocol for field-based crown delineation see Graves et al. (2018). see field_crowns Not all evaluation data are available for all plots. This function will look for matching plot name and ignore other plots.

Value

If summarize is True, a set of summary measures from summary_statistics for the overall score, the entire site score, and the per-plot score. If False, a dataframe with the intersection-over-union scores for each prediction.

References

Graves S, Gearhart J, Caughlin TT, Bohlman S. 2018. A digital mapping method for linking high-resolution remote sensing images to individual tree crowns. PeerJ Preprints 6:e27182v1 https://doi.org/10.7287/peerj.preprints.27182v1

Examples

data("submission")
df <- submission %>% dplyr::filter(plot_name=="OSBS_95_competition")
results <- evaluate_field_crowns(df,project = FALSE, summarize = TRUE)

weecology/NeonTreeEvaluation_package documentation built on Aug. 27, 2024, 10:53 a.m.