field_crowns: Compute evaluation statistics for one plot of field-annotated...

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

Compute evaluation statistics for one plot of field-annotated crowns

Description

Compute evaluation statistics for one plot of field-annotated crowns

Usage

field_crowns(x, show = TRUE, project_boxes = TRUE)

Arguments

x	submission csv table or polygon shp file
show	Logical. Plot the overlayed annotations for each plot?
project_boxes	Logical. Should the boxes be projected into utm coordinates? This is needed if the box coordinates are given from the image origin (top left is 0,0)
compute_PR	Logical. Should the average precision and recall be computed?

Details

The format of the submission is either a csv with 5 columns: plot_name, xmin, ymin, xmax, ymax with #' Each row contains information for one predicted bounding box or a shp file of unprojected polygons. The plot column should be named the same as the files in the dataset (e.g. SJER_021), not the path to the file (e.g. /path/to/SJER_021.tif).

Value

If compute_PR=T, the recall and precision scores for the plot, if False, the intersection-over-union scores for each prediction.

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