RESUMO
The number of wheat spikes has an important influence on wheat yield, and the rapid and accurate detection of wheat spike numbers is of great significance for wheat yield estimation and food security. Computer vision and machine learning have been widely studied as potential alternatives to human detection. However, models with high accuracy are computationally intensive and time consuming, and lightweight models tend to have lower precision. To address these concerns, YOLO-FastestV2 was selected as the base model for the comprehensive study and analysis of wheat sheaf detection. In this study, we constructed a wheat target detection dataset comprising 11,451 images and 496,974 bounding boxes. The dataset for this study was constructed based on the Global Wheat Detection Dataset and the Wheat Sheaf Detection Dataset, which was published by PP Flying Paddle. We selected three attention mechanisms, Large Separable Kernel Attention (LSKA), Efficient Channel Attention (ECA), and Efficient Multi-Scale Attention (EMA), to enhance the feature extraction capability of the backbone network and improve the accuracy of the underlying model. First, the attention mechanism was added after the base and output phases of the backbone network. Second, the attention mechanism that further improved the model accuracy after the base and output phases was selected to construct the model with a two-phase added attention mechanism. On the other hand, we constructed SimLightFPN to improve the model accuracy by introducing SimConv to improve the LightFPN module. The results of the study showed that the YOLO-FastestV2-SimLightFPN-ECA-EMA hybrid model, which incorporates the ECA attention mechanism in the base stage and introduces the EMA attention mechanism and the combination of SimLightFPN modules in the output stage, has the best overall performance. The accuracy of the model was P=83.91%, R=78.35%, AP= 81.52%, and F1 = 81.03%, and it ranked first in the GPI (0.84) in the overall evaluation. The research examines the deployment of wheat ear detection and counting models on devices with constrained resources, delivering novel solutions for the evolution of agricultural automation and precision agriculture.
RESUMO
Crop evapotranspiration is a key parameter influencing water-saving irrigation and water resources management of agriculture. However, current models for estimating maize evapotranspiration primarily rely on meteorological data and empirical coefficients, and the estimated evapotranspiration contains uncertainties. In this study, the evapotranspiration data of summer maize were collected from typical stations in Northern China (Yucheng Station), and a back-propagation neural network (BP) model for predicting maize evapotranspiration was constructed based on meteorological data, soil data, and crop data. To further improve its accuracy, the maize evapotranspiration model was optimized using three bionic optimization algorithms, namely the sand cat swarm optimization (SCSO) algorithms, hunter-prey optimizer (HPO) algorithm, and golden jackal optimization (GJO) algorithm. The results showed that the fusion of meteorological, soil moisture, and crop data can effectively improve the accuracy of the maize evapotranspiration model. The model showed higher accuracy with the hybrid optimization model SCSO-BP compared to the stand-alone BP neural network model, with improvements of 2.7-4.8%, 17.2-25.5%, 13.9-26.8%, and 3.3-5.6% in terms of R2, RMSE, MAE, and NSE, respectively. Comprehensively compared with existing maize evapotranspiration models, the SCSO-BP model presented the highest accuracy, with R2 = 0.842, RMSE = 0.433 mm/day, MAE = 0.316 mm/day, NSE = 0.840, and overall global evaluation index (GPI) ranking the first. The results have reference value for the calculation of daily evapotranspiration of maize in similar areas of northern China.
