Cauliflower Plant and Curd Growth Traits from High-Throughput Phenotyping

99.4% mask mAP50 was achieved by the YOLO12s-seg model for segmenting cauliflower plants and curds in sparsely planted images. This dataset contains phenotypic traits automatically extracted from RGB images covering the entire growth period from seedling to harvest. It was created by Saichuan Cheng and published on figshare under a CC-BY-4.0 license.

Use Cases

• Modeling plant growth dynamics based on automatically extracted leaf area and canopy width data.
• Classifying curd growth patterns based on traits like curd diameter and area fitted with growth models.
• Clustering cauliflower germplasms based on high-throughput phenotyping data to identify growth characteristic groups.
• Training instance segmentation models for agricultural applications based on the described image dataset.

Strengths

• Model evaluation shows high accuracy with a segmentation mask mAP50 of 99.4% for plants and curds.
• Automatically extracted traits like plant canopy width and curd diameter showed high consistency with manual measurements (R² > 0.90).
• Data covers the entire growth period from seedling to harvest, which the description notes is often lacking in other studies.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 18.6 KB, suggesting limited scope.

Provenance

Source

Saichuan Cheng via figshare.

Collection Method

Traits automatically extracted from RGB images using instance segmentation models.

Freshness

Last updated 2026-05-13 05:56:30; freshness should be verified.