This study suggests a novel extraction pipeline based on terrestrial laser scanning across multiple growth stages to address the current deficiency of three-dimensional (3D) phenotypic traits for wheat populations derived from 3D point clouds. This study presents 3D Wheat Point-seg Net (3D WP-seg Net), a novel 3D point cloud segmentation network that incorporates an SA-CrossAttention module to address the difficulties presented by complex structures, background noise, non-uniform point distributions, and scale variations in plot-level wheat point cloud data. Plot height, canopy area, and volume are examples of common phenotypic parameters that are successfully extracted using this technique. Additionally, two new phenotypic parameters: plot extension distance and lodging angle are suggested by fusing the centroid and slice-skeletonization algorithms. A software platform called 3D Trait Analysis was created to facilitate multi-sensor 3D data processing and trait extraction. A genome-wide association study (GWAS) was then conducted using the extracted population-level traits to find potential genes linked to these new phenotypes. While the segmentation accuracies of 3D WP-seg Net achieved 93.1%, 88.3%, and 92.5% under various sensor systems, the results showed a strong correlation between the predicted and measured plot heights (R² = 0.954). Furthermore, four candidate genes linked to extension distance were found on chromosomes 1A, 2A, and 4A, and five putative genes controlling plot lodging angle were found on chromosomes 2D, 3A, and 7A. The multi-stage 3D phenotyping and analysis framework for wheat populations established by this study improves the accuracy of point cloud segmentation and trait quantification while offering a new and efficient method for the genetic analysis of important population-level traits.

In response to the current focus on two-dimensional phenotypic analysis of sliced bread evaluation parameters, this study developed an innovative technology using an inexpensive 3D laser scanner to accurately capture and analyze the three-dimensional structure of both the entire bread slice and the pore surface of the slice. A 3D line-scan laser profiling sensor integrated with a three-axis motion platform was used to efficiently acquire 3D point cloud data of bread surfaces. For the pre-processed point cloud data, a segmentation model called 3D-PoreSegNet was proposed to separate the bread surface and pore regions within the point cloud. By using 2D projection, contour extraction and inverse transformation techniques, accurate 3D structural information of the pore edges was obtained. Based on the pore edges and the entire point cloud data, we successfully reconstructed the 3D pore structures and extracted detailed phenotypic parameters for both the bread and its pores. Furthermore, two novel phenotypic parameters, pore distribution and pore layer distribution, were proposed to provide more scientific support for comprehensive quality assessment of bread. To facilitate rapid phenotypic analysis, we developed the Bread3D-Measure software. Experimental results showed high accuracy in extracting 13 phenotypic parameters, including seven total traits - height (97.3 %), length (95.2 %), width (95.6 %), surface area (86.6 %), volume (82.8 %), symmetry index (91.5 %) and uniformity index (93.4 %) and six pore-related parameters - maximum pore diameter (84.7 %), maximum pore area (82.6 %), pore count (87.1 %), maximum pore depth (90.3 %), maximum pore volume (83.7 %) and pore elongation (78.5 %). These results confirm the effectiveness of the proposed method in meeting the requirements of various phenotypic applications.

Stomata on the leaves of wheat serve as important gateways for gas exchange with the external environment. Their morphological characteristics, such as size and density, are closely related to physiological processes like photosynthesis and transpiration. However, due to the limitations of existing analysis methods, the efficiency of analyzing and mining stomatal phenotypes and their associated genes still requires improvement. To enhance the accuracy and efficiency of stomatal phenotype traits analysis and to uncover the related key genes, this study selected 210 wheat varieties. A novel semantic segmentation model based on transformer for wheat stomata, called Wheat Stoma Former (WSF), was proposed. This model enables fully automated and highly efficient stomatal mask extraction and accurately analyzes phenotypic traits such as the length, width, area, and number of stomata on both the adaxial (Ad) and abaxial (Ab) surfaces of wheat leaves based on the mask images. The model evaluation results indicate that coefficients of determination (R²) between the predicted values and the actual measurements for stomatal length, width, area, and number were 0.88, 0.86, 0.81, and 0.93, respectively, demonstrating the model’s high precision and effectiveness in stomatal phenotypic trait analysis. The phenotypic data were combined with sequencing data from the wheat 660 K SNP chip and subjected to a genome-wide association study (GWAS) to analyze the genetic basis of stomatal traits, including length, width, and number, on both adaxial and abaxial surfaces. A total of 36 SNP peak loci significantly associated with stomatal traits were identified. Through candidate gene identification and functional analysis, two genes—TraesCS2B02G178000 (on chromosome 2B, related to stomatal number on the abaxial surface) and TraesCS6A02G290600 (on chromosome 6A, related to stomatal length on the adaxial surface)—were found to be associated with stomatal traits involved in regulating stomatal movement and closure, respectively. In conclusion, our WSF model demonstrates valuable advances in accurate and efficient stomatal phenotyping for locating genes related to stomatal traits in wheat and provides breeders with accurate phenotypic data for the selection and breeding of water-efficient wheat varieties.

Stomata serve as critical gateways for gas exchange between plants and the external environment. Elucidating stomatal morphology and its dynamic variations is essential for decoding plant growth, development, and environmental response mechanisms. Traditional stomata phenotyping methods rely on destructive sampling and manual measurements. These approaches are constrained by low throughput, a lack of generalizability, and limited metrics, which severely hinder large-scale analytical research. To address these challenges, this study proposes a universal deep learning framework (EasyStoma) for multi-crops in-situ stomatal image analysis. By innovatively incorporating the Efficient Multi-Scale Attention module and the Deformable Convolution, the proposed EasyStomaFormer network effectively mitigates complex background interference and edge blurring in multi-species imagery. Experimental results demonstrate that EasyStomaFormer achieves mIoU of 92.31% for stomata and 87.18% for pores, representing improvements of 3.94% and 3.93% over the baseline model. Compared to other networks, EasyStomaFormer exhibits a performance lead ranging from 2%/4% to 7%/17% (for stomata and pore) and demonstrates superior robustness in multi-species generalization tests. Utilizing the high-precision stomatal and pore masks extracted by EasyStomaFormer, we established a comprehensive system comprising 59 phenotypic metrics. This introduces six novel indicators, including the Row Alignment Score and Voronoi Diagram-based parameters. Based on these metrics, we discovered that monocots exhibit significantly higher spatial distribution indices compared to dicots. Fuerthermore, we developed the companion software to enable the rapid and automated batch acquisition of universal stomatal phenotypic data. This work represents a significant methodological breakthrough for understanding stomatal development regulation, breeding for environmental adaptability, and researching plant-environment interactions.

High-throughput phenotypic characterization of wheat throughout the growing season is a key requirement for modern crop breeding and precision agriculture. Despite recent advances in unmanned aerial vehicle (UAV)–based remote sensing, challenges remain in the effective fusion of multi-source data and modeling the temporal dynamics of phenotypic traits. In this study, an automated framework was proposed for full-season wheat phenotyping using UAV-acquired multi-source remote sensing data. The Wheat Multi-source Data Segmentation Architecture (WMSA) was first constructed, within which a three-dimensional (3D) point cloud segmentation network, referred to as 3D Wheat Point-Transformer (3D Wheat PT), was developed by integrating Feature Complementary Mapping (FCM) and the Cross-Spatial Joint Enhancement (CSJE) module. This network enabled accurate separation of wheat plot point clouds from background elements under different planting conditions. Additionally, a plot-level co-registration between two-dimensional (2D) imagery and point clouds was achieved using a fusion-based projection strategy combined with feature matching, ensuring spatial consistency across data modalities. Based on the proposed framework, phenotypic analysis system WheatMorph was implemented to support visualization, automated segmentation, and quantitative trait extraction from 2D images and point clouds, forming an integrated workflow from data acquisition to result output. The phenotypic traits collected at 15 temporal sampling stages were used to construct dynamic time-series curves, which were applied for growth stage identification and cultivar classification. Machine learning models were established using dynamic phenotypic features for trait prediction. The experimental results demonstrated strong agreement between the predicted and measured canopy height (R² = 0.943). The proposed 3D Wheat PT achieved point cloud segmentation accuracies of 94.4, 91.8, and 92.5% across three experimental sites and cultivation patterns. When canopy height growth rate dynamics were used as input features, a Long Short-Term Memory-based model achieved the highest prediction accuracy of 76.7% at the jointing stage (127 days after sowing). The proposed approach provides a robust and scalable solution for multi-source phenotypic data extraction and temporal analysis throughout the wheat growing season, demonstrating its potential for large-scale crop phenotyping and UAV-based agricultural remote sensing applications.

Wheat spikes are key organs for yield formation, and their number, morphology, and spatial distribution strongly influence grain-bearing capacity and yield potential. However, under field conditions, spike phenotyping is constrained by severe occlusion and overlap among spikes, leaves, stems, and neighbouring plants, making conventional two-dimensional (2D) imaging and manual measurements insufficient for accurately characterizing three-dimensional (3D) spike structure. Here, we developed an integrated framework for automatic segmentation, trait extraction, and phenotypic analysis of wheat spike point clouds acquired by a gantry-based field 3D laser scanning platform. We proposed 3D Spike Former, a point-cloud segmentation network built on Point Transformer V3, incorporating a Cross Slice Attention Module and a Feature Complementary Mapping module to enhance recognition of fine spike structures, boundary regions, and complex field backgrounds. Based on segmented spike point clouds, multi-scale 3D traits were automatically extracted, including spike number in internal and external rows, global and local uniformity, spike length, width, inclination angle, surface area, and volume. A software package, 3D Spike Trait Analysis, was further developed to support streamlined and visualized spike phenotyping. The framework effectively captured growth-stage-dependent spike distribution, within-plot spatial heterogeneity, and genotypic variation in spike architecture. Extracted traits enabled dynamic variety ranking and phenotypic clustering using principal component analysis, random forest modelling, and hierarchical clustering. Spike length estimates agreed well with manual measurements (R² = 0.912), and 3D Spike Former achieved 91.4% precision. This study provides an efficient field-based approach for 3D wheat spike phenotyping, population structure evaluation, and genetic analysis of complex spike traits.