RandCrowns: A Quantitative Metric for Imprecisely Labeled Tree Crown Delineation

TL;DR

This paper introduces RandCrowns, a new evaluation metric for tree crown delineation in remote sensing that accounts for annotation imprecision, providing more robust and consistent assessment compared to traditional methods.

Contribution

The paper develops RandCrowns, an adaptation of the Rand index, specifically designed to evaluate weakly-labeled tree crown delineations considering annotation uncertainty.

Findings

RandCrowns reduces variance caused by annotator differences.

It provides more robust evaluation in the presence of imprecise labels.

Compared to IoU, RandCrowns better handles annotation uncertainty.

Abstract

Supervised methods for object delineation in remote sensing require labeled ground-truth data. Gathering sufficient high quality ground-truth data is difficult, especially when targets are of irregular shape or difficult to distinguish from background or neighboring objects. Tree crown delineation provides key information from remote sensing images for forestry, ecology, and management. However, tree crowns in remote sensing imagery are often difficult to label and annotate due to irregular shape, overlapping canopies, shadowing, and indistinct edges. There are also multiple approaches to annotation in this field (e.g., rectangular boxes vs. convex polygons) that further contribute to annotation imprecision. However, current evaluation methods do not account for this uncertainty in annotations, and quantitative metrics for evaluation can vary across multiple annotators. In this paper, we address these limitations by developing an adaptation of the Rand index for weakly-labeled crown delineation that we call RandCrowns. Our new RandCrowns evaluation metric provides a method to appropriately evaluate delineated tree crowns while taking into account imprecision in the ground-truth delineations. The RandCrowns metric reformulates the Rand index by adjusting the areas over which each term of the index is computed to account for uncertain and imprecise object delineation labels. Quantitative comparisons to the commonly used intersection over union method shows a decrease in the variance generated by differences among multiple annotators. Combined with qualitative examples, our results suggest that the RandCrowns metric is more robust for scoring target delineations in the presence of uncertainty and imprecision in annotations that are inherent to tree crown delineation.