Abstract
Efficient phenotyping monitoring of cauliflower is crucial for its breeding and production. However, traditional manual measurement methods are time-consuming and labor-intensive, and existing deep learning (DL) methods mostly focus on the seedling stage, lacking systematic research covering the entire growth period. In this study, RGB images of cauliflower from seedling to harvest were collected. Through systematic screening and evaluation of instance segmentation models, accurate segmentation of plants and curds was achieved, and plant canopy width, leaf area, and curd traits were automatically extracted to track their dynamic changes. Evaluation results showed that YOLO12s-seg was the optimal model. It can achieved a segmentation mask mAP 50 of 99.4% for plants and curds in sparsely planted images and showed an advantage in identifying partially occluded early curds beneath inner leaves. Traits such as plant canopy width and curd diameter automatically extracted from segmentation results were highly consistent with manual measurements (R 2 > 0.90). Furthermore, the Richards model and Sine model were used to accurately fit the growth dynamics of leaf area and curd area, respectively. Based on growth kinetics, curds were classified into three types: mature and compact type, peak-burst type, and steady-increase type. Cluster analysis of 47 germplasms based on high-throughput phenotyping data revealed four groups and their growth characteristics: comprehensively coordinated type, mid-maturity compact type, large high-yield type, and curd-dominant type. Integrating the above functions, a platform for cauliflower growth monitoring and phenotypic analysis was developed. It provided full-process support from automatic image processing to growth dynamic analysis. This work provides an effective automated solution for high-throughput phenotyping analysis and growth dynamic monitoring of cauliflower, and offers a referable analytical framework for crop growth pattern research and intelligent breeding decision-making.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 9
Claim · model-written summary
YOLO12s-seg was the optimal instance segmentation model among those screened for cauliflower plants and curds.
- Taxon
- cauliflower
Brassica oleracea var. botrytist0 - Outcome
- optimal modele0
- Comparator
- instance segmentation modelse1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“Evaluation results showed that YOLO12s-seg was the optimal model”
e1“systematic screening and evaluation of instance segmentation models”
Claim · model-written summary
YOLO12s-seg achieved a segmentation mask mAP 50 of 99.4% for plants and curds in sparsely planted images.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- segmentation mask mAP 50e0
- Value
- 99.4%e0
- Setting
- sparsely planted imagese0
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”
Claim · model-written summary
The model showed an advantage in identifying partially occluded early curds beneath inner leaves.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- identifying partially occluded early curds beneath inner leavese0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“showed an advantage in identifying partially occluded early curds beneath inner leaves”
Claim · model-written summary
Traits such as plant canopy width and curd diameter automatically extracted from segmentation were highly consistent with manual measurements (R2 > 0.90).
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- plant canopy width and curd diametere0
- Value
- R 2 > 0.90e0
- Comparator
- manual measurementse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“Traits such as plant canopy width and curd diameter automatically extracted from segmentation results were highly consistent with manual measurements (R 2 > 0.90)”
Claim · model-written summary
The Richards model accurately fitted the growth dynamics of leaf area.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- growth dynamics of leaf areae0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“the Richards model and Sine model were used to accurately fit the growth dynamics of leaf area and curd area, respectively”
Claim · model-written summary
The Sine model accurately fitted the growth dynamics of curd area.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- growth dynamics of leaf area and curd areae0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“the Richards model and Sine model were used to accurately fit the growth dynamics of leaf area and curd area, respectively”
Claim · model-written summary
Based on growth kinetics, curds were classified into three types: mature and compact, peak-burst, and steady-increase.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- three typese0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“curds were classified into three types: mature and compact type, peak-burst type, and steady-increase type”
Claim · model-written summary
Cluster analysis of 47 germplasms based on high-throughput phenotyping data revealed four groups with distinct growth characteristics.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- four groupse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“Cluster analysis of 47 germplasms based on high-throughput phenotyping data revealed four groups”
Claim · model-written summary
A platform for cauliflower growth monitoring and phenotypic analysis was developed, giving full-process support from automatic image processing to growth dynamic analysis.
- Taxon
- cauliflowerBrassica oleracea var. botrytist0
- Outcome
- platform for cauliflower growth monitoring and phenotypic analysise0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cauliflower”
e0“a platform for cauliflower growth monitoring and phenotypic analysis was developed”