Identification of nutritious rice varieties through non-destructive detection technology is important for high-quality seed production. With the development of technology, rapid and non-destructive identification methods based on unmanned aerial vehicle (UAV) remote sensing technology are increasingly gaining attention in the scientific community. This study utilized hyperspectral imaging technology to acquire spectral reflectance data from the rice canopy during the grain filling stage. Different models (stepwise multiple linear regression (SMLR) and the Back Propagation Neural Network (BPNN)) for estimating rice protein content based on canopy spectral information were constructed using both multiple stepwise regression and BP neural networks. The results showed that the model based on BPNN estimation performed best for predicting grain protein content, with an R² = 0.9516 and RMSE = 0.3492, indicating high accuracy and stability in the model. Overall, hyperspectral imaging technology combined with various models could significantly help to identify rice varieties. Further, the current findings provide a technical reference for the selection of high-quality rice varieties in a non-destructive manner.

Identification of nutritious rice variety through non-destructive detection technology is necessary for high quality seed production. With the development in technology, rapid and non-destructive identification methods based on unmanned aerial vehicle (UAV) remote sensing technology are increasingly gaining scientific community attention. This study utilized hyperspectral imaging technology to acquire spectral reflectance data from the rice canopy during the grain-filling stage. Different models (Stepwise Multiple Linear Regression, SMLR and the Back Propagation Neural Network, BPNN) for estimating rice nutritional quality indicators based on canopy spectral information were constructed using both multiple stepwise regression and BP neural networks. The results showed that the model based on BPNN estimation performed best for predicting grain protein content, with an R2 =0.9516 and RMSE=0.3492, indicating high accuracy and stability of the model. Overall, hyperspectral imaging technology combined with various model could significantly help to identify rice varieties. Further, the current findings provide a technical reference for the selection of high-quality rice varieties in a non-destructive manner.

The number of grains per spike is a critical determinant of wheat yield and plays an important role in phenotyping, breeding evaluation, and yield-related trait analysis. However, conventional grain counting methods rely on manual operation, which is time-consuming, labor-intensive, and prone to subjective bias, making them unsuitable for high-throughput applications. To address these limitations, this study proposes an improved wheat grain detection and counting method based on YOLOv8 integrated with a P2 detection layer and an Efficient Multi-Scale Attention (EMA) mechanism. The P2 detection layer enhances the resolution of shallow feature maps, improving the model’s ability to detect small and densely distributed grains. Meanwhile, the EMA module strengthens multi-scale feature representation and improves training stability and generalization performance, particularly in complex canopy and overlapping grain scenarios. Experimental results demonstrate that the proposed YOLOv8-EMA-P2 model achieves a precision of 96.10%, recall of 95.60%, mAP@0.5 of 96.80%, and mAP@0.5:0.95 of 68.40% on the test set, indicating strong detection performance. For counting performance, the model achieves a coefficient of determination (R²) of 0.8384, with a root mean square error (RMSE) of 1.8517, mean absolute error (MAE) of 1.2628, and mean relative error (MRE) of 5.33%. In addition, the average inference time per image is 6.5 ms, demonstrating its potential for real-time applications. Overall, the proposed method improves the accuracy, robustness, and efficiency of wheat grain detection and counting, providing an effective solution for automated wheat phenotyping and yield estimation.