Claim · model-written summary
YOLO12s-seg achieved a segmentation mask mAP 50 of 99.4% for plants and curds in sparsely planted images.
- Taxon
- cauliflower
Brassica oleracea var. botrytist0 - Outcome
- segmentation mask mAP 50e0
- Value
- 99.4%e0
- Setting
- sparsely planted imagese0
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorDirectionQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.

Verbatim
t0“cauliflower”
e0“segmentation mask mAP 50 of 99.4% for plants and curds in sparsely planted images”
Title
Saichuan Cheng; Sidi Wu; Qingqing Shao; et al. Frontiers in Plant Science 2026. doi:10.3389/fpls.2026.1836813
Other claims from this paper (8)
- Method / resource YOLO12s-seg was the optimal instance segmentation model among those screened for cauliflower plants and curds.
- Method / resource The model showed an advantage in identifying partially occluded early curds beneath inner leaves.
- Method / resource Traits such as plant canopy width and curd diameter automatically extracted from segmentation were highly consistent with manual measurements (R2 > 0.90).
- Method / resource The Richards model accurately fitted the growth dynamics of leaf area.
- Method / resource The Sine model accurately fitted the growth dynamics of curd area.
- Observation Based on growth kinetics, curds were classified into three types: mature and compact, peak-burst, and steady-increase.
- Observation Cluster analysis of 47 germplasms based on high-throughput phenotyping data revealed four groups with distinct growth characteristics.
- Method / resource A platform for cauliflower growth monitoring and phenotypic analysis was developed, giving full-process support from automatic image processing to growth dynamic analysis.