Abstract
The traditional methods of field-based phenotypic data collection for crop germplasm resources are often inefficient and highly subjective. As the foundation for breeding innovation, these resources require precise identification of phenotypic traits for effective evaluation and utilization. Therefore, efficient and standardized management of germplasm data is critical during the breeding process. To address this, we have developed an intelligent recognition and management system focused on the crop’s organ characteristics. The system consists of a web client for overall project management and data download, and a WeChat Mini Program for data collection and uploading. Both components are integrated with image analysis models. Using a soybean variety screening experiment as a case study, we have constructed multiple high-definition datasets for soybean phenotypic traits, and employed YOLOv11 series models for object detection, image classification, instance segmentation, and pose estimation to build analytical models for each of these traits. All models achieved a mean average precision (mAP@0.5) exceeding 94%, along with a top1_accuracy of 0.999. In practical evaluations, all models took between 0.71 and 3.03 s to make predictions for 100 images, achieving an accuracy rate of over 98%. This system delivers a comprehensive solution for field phenotypic identification of crop germplasm resources, substantially enhancing the efficiency and objectivity of data collection and analysis. It serves as a valuable decision-support tool for precision breeding and digital agriculture.
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 5
Claim · model-written summary
The soybean organ-trait models achieved a mean average precision (mAP@0.5) exceeding 94%.
- Taxon
- soybean
Glycine maxe4 - Outcome
- mean average precision (mAP@0.5)e1
- Value
- exceeding 94%e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“All models achieved a mean average precision (mAP@0.5) exceeding 94%”
e4“we have constructed multiple high-definition datasets for soybean phenotypic traits”
Claim · model-written summary
The soybean organ-trait models achieved a top1_accuracy of 0.999.
- Taxon
- soybeanGlycine maxe4
- Outcome
- top1_accuracye2
- Value
- 0.999e2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e2“along with a top1_accuracy of 0.999”
e4“we have constructed multiple high-definition datasets for soybean phenotypic traits”
Claim · model-written summary
The models took between 0.71 and 3.03 s to make predictions for 100 images.
- Taxon
- soybeanGlycine maxe4
- Outcome
- to make predictions for 100 imagese3
- Value
- 0.71 and 3.03 se3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e3“all models took between 0.71 and 3.03 s to make predictions for 100 images”
e4“we have constructed multiple high-definition datasets for soybean phenotypic traits”
Claim · model-written summary
In practical evaluations the models achieved an accuracy rate of over 98%.
- Taxon
- soybeanGlycine maxe4
- Outcome
- accuracy ratee5
- Value
- over 98%e5
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e5“achieving an accuracy rate of over 98%”
e4“we have constructed multiple high-definition datasets for soybean phenotypic traits”
Claim · model-written summary
The system substantially enhances the efficiency and objectivity of soybean germplasm data collection and analysis compared with traditional methods.
- Taxon
- soybeanGlycine maxe4
- Outcome
- efficiency and objectivity of data collection and analysise7
- Comparator
- traditional methods of field-based phenotypic data collectione6
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e6“The traditional methods of field-based phenotypic data collection for crop germplasm resources are often inefficient and highly subjective”
e7“substantially enhancing the efficiency and objectivity of data collection and analysis”
e4“we have constructed multiple high-definition datasets for soybean phenotypic traits”