@article{ART003287738},
author={Ahn, Hyang Sig and YoungKyu Shin and Tae-Bong Choi},
title={Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training},
journal={Journal of Environmental Impact Assessment},
issn={1225-7184},
year={2025},
volume={34},
number={6},
pages={624-641}
TY - JOUR
AU - Ahn, Hyang Sig
AU - YoungKyu Shin
AU - Tae-Bong Choi
TI - Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training
JO - Journal of Environmental Impact Assessment
PY - 2025
VL - 34
IS - 6
PB - Korean Society Of Environmental Impact Assessment
SP - 624
EP - 641
SN - 1225-7184
AB - Binary segmentation faces persistent challenges from false negatives (FNs), particularly inapplications where missing small target regions can undermine reliability. FNs are critical in sparseland-cover mapping tasks because they represent true targets that models fail to detect. Here, wepropose a two-stage U-Net training strategy that automatically accumulates FP and FN regions fromStage 1 predictions and reuses them as auxiliary supervisory signals through a second output headduring Stage 2 learning. This enhances the model’s ability to revisit uncertain or ambiguous areas without any architectural modification. The method was applied to mapping sparsely distributedginseng fields from high-resolution aerial imagery from South Korea. The approach substantiallyreduced FNs, tolerated a modest increase in FPs, and improved Intersection over Union (IoU) byapproximately 0.10 across various training conditions. Because the strategy only modifies the trainingscheme and not the model architecture, it is compatible with U-Net variants and generalizable to otherdomains where FN suppression and stability are essential. The findings demonstrate that learningfrom accumulated error regions offers an efficient and practical pathway toward more reliablesegmentation in complex real world environments.
KW - aerial imagery;two-stage training;false negatives;ginseng field mapping;agricultural land cover segmentation
DO -
UR -
ER -
Ahn, Hyang Sig, YoungKyu Shin and Tae-Bong Choi. (2025). Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training. Journal of Environmental Impact Assessment, 34(6), 624-641.
Ahn, Hyang Sig, YoungKyu Shin and Tae-Bong Choi. 2025, "Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training", Journal of Environmental Impact Assessment, vol.34, no.6 pp.624-641.
Ahn, Hyang Sig, YoungKyu Shin, Tae-Bong Choi "Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training" Journal of Environmental Impact Assessment 34.6 pp.624-641 (2025) : 624.
Ahn, Hyang Sig, YoungKyu Shin, Tae-Bong Choi. Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training. 2025; 34(6), 624-641.
Ahn, Hyang Sig, YoungKyu Shin and Tae-Bong Choi. "Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training" Journal of Environmental Impact Assessment 34, no.6 (2025) : 624-641.
Ahn, Hyang Sig; YoungKyu Shin; Tae-Bong Choi. Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training. Journal of Environmental Impact Assessment, 34(6), 624-641.
Ahn, Hyang Sig; YoungKyu Shin; Tae-Bong Choi. Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training. Journal of Environmental Impact Assessment. 2025; 34(6) 624-641.
Ahn, Hyang Sig, YoungKyu Shin, Tae-Bong Choi. Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training. 2025; 34(6), 624-641.
Ahn, Hyang Sig, YoungKyu Shin and Tae-Bong Choi. "Improving Binary Segmentation Accuracy for Agricultural Land Monitoring through Two-Stage U-Net Training" Journal of Environmental Impact Assessment 34, no.6 (2025) : 624-641.
