High-Precision Automated Soybean Phenotypic Feature Extraction Based on Deep Learning and Computer Vision
Open Access
Abstract
The automated collection of plant phenotypic information has become a trend in breeding and smart agriculture. Four YOLOv8-based models were used to segment mature soybean plants placed in a simple background in a laboratory environment, identify pods, distinguish the number of soybeans in each pod, and obtain soybean phenotypes. The YOLOv8-Repvit model yielded the most optimal recognition results, with an coefficient value of 0.96 for both pods and beans, and the RMSE values were 2.89 and 6.90, respectively. Moreover, a novel algorithm was devised to efficiently differentiate between the main stem and branches of soybean plants, called the midpoint coordinate algorithm (MCA). This was accomplished by linking the white pixels representing the stems in each column of the binary image to draw curves that represent the plant structure. The proposed method reduces computational time and spatial complexity in comparison to the A* algorithm, thereby providing an efficient and accurate approach for measuring the phenotypic characteristics of soybean plants. This research lays a technical foundation for obtaining the phenotypic data of densely overlapped and partitioned mature soybean plants under field conditions at harvest.
Keywords
Funding Information
- National Key Research and Development Program of China (2022YFE0130200, U22A20467, 32101610, 32371991, tscx202211143, PCCE-KF-2023-09)
- National Natural Science Foundation of China (2022YFE0130200, U22A20467, 32101610, 32371991, tscx202211143, PCCE-KF-2023-09)
- TaiShan Industrial Experts Program (2022YFE0130200, U22A20467, 32101610, 32371991, tscx202211143, PCCE-KF-2023-09)
- State Key Laboratory of Plant Cell and Chromosome Engineering (2022YFE0130200, U22A20467, 32101610, 32371991, tscx202211143, PCCE-KF-2023-09)
This publication has 52 references indexed in Scilit:
- Maize tassel number and tasseling stage monitoring based on near-ground and UAV RGB images by improved YoloV8Precision Agriculture, 2024
- SPP-extractor: Automatic phenotype extraction for densely grown soybean plantsThe Crop Journal, 2023
- Improvement of Soybean; A Way Forward Transition from Genetic Engineering to New Plant Breeding TechnologiesMolecular Biotechnology, 2022
- High‐throughput NGS‐based genotyping and phenotyping: Role in genomics‐assisted breeding for soybean improvementLegume Science, 2021
- Computer vision approach to characterize size and shape phenotypes of horticultural crops using high-throughput imageryComputers and Electronics in Agriculture, 2021
- From species to cultivar: Soybean cultivar recognition using joint leaf image patterns by multiscale sliding chord matchingBiosystems Engineering, 2020
- 3D model processing for high throughput phenotype extraction – the case of cornComputers and Electronics in Agriculture, 2020
- History, current status, and prospects of soybean production and research in sub-Saharan AfricaThe Crop Journal, 2018
- Machine vision based soybean quality evaluationComputers and Electronics in Agriculture, 2017
- Current Knowledge in Soybean CompositionJournal of the American Oil Chemists' Society, 2014