evaluate_field_stems: Compute evaluation scores for the field collected stem data

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

Compute evaluation scores for the field collected stem data

Description

evaluate_field_stems implements the matching and scoring algorithm on field stems that were collected by the NEON Woody Vegetation structure data.

Usage

evaluate_field_stems(predictions, project = TRUE, show = T, summarize = T)

Arguments

predictions	The format of the submission is a csv with 5 columns: plot_name, xmin, ymin, xmax, ymax follows Each row contains information for one predicted bounding box. The plot column should be named the same as the files in the dataset (e.g. SJER_021), not the path to the file. Not all evaluation data are available for all plots. This function will look for matching plot name and ignore other plots.
project	Whether to project the supplied bounding box coordinates from image coordinates into geographic coordinates (utm QGS84). This is needed for computing recall scores.
show	Whether to show figures during evaluation.
summarize	logical If True, report the root mean squared error (RMSE) between the number of field crowns and predicted crowns. If false, return the list of crowns per plot.

Details

The following filters were applied to the raw NEON field data (ID) after download. An overstory reference tree must have: * Valid spatial coordinates * A unique height measurement per sampling period. Species double recorded but with different heights were discarded * Sampled in more than one year to verify height measurement * Changes in between year field heights of less than 6m * A minimum height of 3m to match the threshold in the remote sensing workflow. * Be at least within 5m of the canopy as measured by the LiDAR height model extracted at the stem location. The was used to prevent matching with understory trees in the event that overstory trees were eliminated due to failing in one of the above conditions, or not sampled by NEON.

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.

Examples

df<-submission %>% dplyr::filter(plot_name %in% c("SJER_052"))
results<-evaluate_field_stems(predictions=df,project = FALSE, show=TRUE, summarize = TRUE)

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