A Multi-Temporal Instance Segmentation Framework and Exhaustively Annotated Tree Crown Dataset for a Subtropical Urban Forest Case
Remote Sensing · 03.04.2026 · 18 (7) · 1082
DOI: 10.3390/rs18071082 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.04.2026. Verfasst von Weihong Lin und 4 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangzhou Science and Technology Plan Project, GDAS’s Project of Science and Technology Development, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate individual tree crown identification is essential for urban forestry, yet existing datasets often lack exhaustive annotations and multi-temporal diversity. To address this limitation, an exhaustively annotated dataset was curated for crown instance segmentation, comprising 47,754 labeled individual crowns from approximately 110 species across three temporal phases. Anchored in a “crown geometry” labeling criterion focusing on upper-canopy individuals visible in the imagery, and the high-resolution imagery captured seasonal variations in shape, color, and texture, providing an empirical basis for within-site robustness. Utilizing this dataset, this study (1) compared five instance segmentation models; (2) evaluated their generalization capabilities across different temporal phases; and (3) tested a multi-temporal joint training strategy and a non-maximum suppression (NMS)-based fusion. The experiments revealed significant overfitting in single-temporal models. While ConvNeXt-V2 achieved a high segmentation mean Average Precision (Segm_mAP) of 0.852 within the same temporal phase, its performance dropped sharply to 0.361 across phases. Bi-temporal joint training significantly mitigated this issue, improving cross-temporal performance to 0.665 and further increasing within-phase accuracy to 0.874. In contrast, tri-temporal training reduced accuracy (0.748), demonstrating that effective generalizability depends on the strategic selection of complementary temporal phases rather than the mere accumulation of data. The multi-temporal training framework provided in this study could serve as a practical reference and a foundational benchmark for further urban forest structural monitoring research.
Förderung
- Guangzhou Science and Technology Plan Project
- GDAS’s Project of Science and Technology Development
- National Natural Science Foundation of China
Zitieren
APA
Lin, W., Jiang, H., Ku, M., Zhang, J., & Wang, B. (2026). A Multi-Temporal Instance Segmentation Framework and Exhaustively Annotated Tree Crown Dataset for a Subtropical Urban Forest Case. Remote Sensing, 18(7), 1082. https://doi.org/10.3390/rs18071082
Vancouver
Lin W, Jiang H, Ku M, Zhang J, Wang B. A Multi-Temporal Instance Segmentation Framework and Exhaustively Annotated Tree Crown Dataset for a Subtropical Urban Forest Case. Remote Sensing. 2026;18(7):1082. doi:10.3390/rs18071082
BibTeX
@article{Lin2026,
author = {Lin, Weihong and Jiang, Hao and Ku, Mengjun and Zhang, Jing and Wang, Baomin},
title = {A Multi-Temporal Instance Segmentation Framework and Exhaustively Annotated Tree Crown Dataset for a Subtropical Urban Forest Case},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {7},
pages = {1082},
doi = {10.3390/rs18071082}
}
EUVIMED