Deep Learning-Guided High-Completeness Building Segmentation Sample Selection via Otsu Thresholding

Liangcun Jiang

doi:10.1109/LGRS.2025.3612492

Deep Learning-Guided High-Completeness Building Segmentation Sample Selection via Otsu Thresholding

2025-01-01

0

PRE

AI

DOI：10.1109/LGRS.2025.3612492

Original

Original request for help

Save

Abstract

En 中文

Deep learning (DL) has significantly accelerated remote sensing (RS) imagery interpretation. However, annotation errors, such as omission, misalignment, and geometric deformation, can severely degrade model performance. Among these, omissions—where objects in the imagery are partially or entirely missing from their corresponding labels—are particularly detrimental. To address this issue, this letter proposes a method for selecting high-completeness training samples using a model trained on a building segmentation dataset with omission errors. Utilizing Otsu’s thresholding characteristic for foreground–background discrimination, the method estimates the reference completeness of each sample and identifies those with high completeness based on a given threshold. Extensive experiments are conducted on both a simulated dataset with omission errors and an OpenStreetMap (OSM)-derived building segmentation dataset. The results demonstrate that the proposed method effectively identifies high-completeness samples. Furthermore, models trained on these selected samples exhibit significantly improved performance compared with those trained on the original, unfiltered datasets.

Keywords:

Deep learning (DL)

omission error

remote sensing (RS) image segmentation

sample selection

training data quality

Deep Learning-Guided High-Completeness Building Segmentation Sample Selection via Otsu Thresholding

Abstract

Journal

Organization

Cited Papers