English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The FOR-instance dataset (available athttps://doi.org/10.5281/zenodo.8287792) addresses the challenge of accurateindividual tree segmentation from laser scanning data, crucial forunderstanding forest ecosystems and sustainable management. Despite the growingneed for detailed tree data, automating segmentation and tracking scientificprogress remains difficult. Existing methodologies often overfit small datasetsand lack comparability, limiting their applicability. Amid the progresstriggered by the emergence of deep learning methodologies, standardizedbenchmarking assumes paramount importance in these research domains. This datapaper introduces a benchmarking dataset for dense airborne laser scanning data,aimed at advancing instance and semantic segmentation techniques and promotingprogress in 3D forest scene segmentation. The FOR-instance dataset comprisesfive curated and ML-ready UAV-based laser scanning data collections fromdiverse global locations, representing various forest types. The laser scanningdata were manually annotated into individual trees (instances) and differentsemantic classes (e.g. stem, woody branches, live branches, terrain, lowvegetation). The dataset is divided into development and test subsets, enablingmethod advancement and evaluation, with specific guidelines for utilization. Itsupports instance and semantic segmentation, offering adaptability to deeplearning frameworks and diverse segmentation strategies, while the inclusion ofdiameter at breast height data expands its utility to the measurement of aclassic tree variable. In conclusion, the FOR-instance dataset contributes tofilling a gap in the 3D forest research, enhancing the development andbenchmarking of segmentation algorithms for dense airborne laser scanning data.

FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees