Phenotypic Traits Estimation and Preliminary Yield Assessment in Different Phenophases of Wheat Breeding Experiment Based on UAV Multispectral Images

Improved YOLO-FastestV2 wheat spike detection model based on a multi-stage attention mechanism with a LightFPN detection head

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.

A lightweight network for improving wheat ears detection and counting based on YOLOv5s

Introduction

Recognizing wheat ears plays a crucial role in predicting wheat yield. Employing deep learning methods for wheat ears identification is the mainstream method in current research and applications. However, such methods still face challenges, such as high computational parameter volume, large model weights, and slow processing speeds, making it difficult to apply them for real-time identification tasks on limited hardware resources in the wheat field. Therefore, exploring lightweight wheat ears detection methods for real-time recognition holds significant importance.

Methods

This study proposes a lightweight method for detecting and counting wheat ears based on YOLOv5s. It utilizes the ShuffleNetV2 lightweight convolutional neural network to optimize the YOLOv5s model by reducing the number of parameters and simplifying the complexity of the calculation processes. In addition, a lightweight upsampling operator content-aware reassembly of features is introduced in the feature pyramid structure to eliminate the impact of the lightweight process on the model detection performance. This approach aims to improve the spatial resolution of the feature images, enhance the effectiveness of the perceptual field, and reduce information loss. Finally, by introducing the dynamic target detection head, the shape of the detection head and the feature extraction strategy can be dynamically adjusted, and the detection accuracy can be improved when encountering wheat ears with large-scale changes, diverse shapes, or significant orientation variations.

Results and discussion

This study uses the global wheat head detection dataset and incorporates the local experimental dataset to improve the robustness and generalization of the proposed model. The weight, FLOPs and mAP of this model are 2.9 MB, 2.5 * 109 and 94.8%, respectively. The linear fitting determination coefficients R2 for the model test result and actual value of global wheat head detection dataset and local experimental Site are 0.94 and 0.97, respectively. The improved lightweight model can better meet the requirements of precision wheat ears counting and play an important role in embedded systems, mobile devices, or other hardware systems with limited computing resources.

Remotely Sensed Phenotypic Traits for Heritability Estimates and Grain Yield Prediction of Barley Using Multispectral Imaging from UAVs

This study tested the potential of parametric and nonparametric regression modeling utilizing multispectral data from two different unoccupied aerial vehicles (UAVs) as a tool for the prediction of and indirect selection of grain yield (GY) in barley breeding experiments. The coefficient of determination (R²) of the nonparametric models for GY prediction ranged between 0.33 and 0.61 depending on the UAV and flight date, where the highest value was achieved with the DJI Phantom 4 Multispectral (P4M) image from 26 May (milk ripening). The parametric models performed worse than the nonparametric ones for GY prediction. Independent of the retrieval method and UAV, GY retrieval was more accurate in milk ripening than dough ripening. The leaf area index (LAI), fraction of absorbed photosynthetically active radiation (fAPAR), fraction vegetation cover (fCover), and leaf chlorophyll content (LCC) were modeled at milk ripening using nonparametric models with the P4M images. A significant effect of the genotype was found for the estimated biophysical variables, which was referred to as remotely sensed phenotypic traits (RSPTs). Measured GY heritability was lower, with a few exceptions, compared to the RSPTs, indicating that GY was more environmentally influenced than the RSPTs. The moderate to strong genetic correlation of the RSPTs to GY in the present study indicated their potential utility as an indirect selection approach to identify high-yield genotypes of winter barley.

A cooperative scheme for late leaf spot estimation in peanut using UAV multispectral images

In Australia, peanuts are mainly grown in Queensland with tropical and subtropical climates. The most common foliar disease that poses a severe threat to quality peanut production is late leaf spot (LLS). Unmanned aerial vehicles (UAVs) have been widely investigated for various plant trait estimations. The existing works on UAV-based remote sensing have achieved promising results for crop disease estimation using a mean or a threshold value to represent the plot-level image data, but these methods might be insufficient to capture the distribution of pixels within a plot. This study proposes two new methods, namely measurement index (MI) and coefficient of variation (CV), for LLS disease estimation on peanuts. We first investigated the relationship between the UAV-based multispectral vegetation indices (VIs) and the LLS disease scores at the late growth stages of peanuts. We then compared the performances of the proposed MI and CV-based methods with the threshold and mean-based methods for LLS disease estimation. The results showed that the MI-based method achieved the highest coefficient of determination and the lowest error for five of the six chosen VIs whereas the CV-based method performed the best for simple ratio (SR) index among the four methods. By considering the strengths and weaknesses of each method, we finally proposed a cooperative scheme based on the MI, the CV and the mean-based methods for automatic disease estimation, demonstrated by applying this scheme to the LLS estimation in peanuts.

Rapid prediction of winter wheat yield and nitrogen use efficiency using consumer-grade unmanned aerial vehicles multispectral imagery

Rapid and accurate assessment of yield and nitrogen use efficiency (NUE) is essential for growth monitoring, efficient utilization of fertilizer and precision management. This study explored the potential of a consumer-grade DJI Phantom 4 Multispectral (P4M) camera for yield or NUE assessment in winter wheat by using the universal vegetation indices independent of growth period. Three vegetation indices having a strong correlation with yield or NUE during the entire growth season were determined through Pearson's correlational analysis, while multiple linear regression (MLR), stepwise MLR (SMLR), and partial least-squares regression (PLSR) methods based on the aforementioned vegetation indices were adopted during different growth periods. The cumulative results showed that the reciprocal ratio vegetation index (repRVI) had a high potential for yield assessment throughout the growing season, and the late grain-filling stage was deemed as the optimal single stage with R², root mean square error (RMSE), and mean absolute error (MAE) of 0.85, 793.96 kg/ha, and 656.31 kg/ha, respectively. MERIS terrestrial chlorophyll index (MTCI) performed better in the vegetative period and provided the best prediction results for the N partial factor productivity (NPFP) at the jointing stage, with R², RMSE, and MAE of 0.65, 10.53 kg yield/kg N, and 8.90 kg yield/kg N, respectively. At the same time, the modified normalized difference blue index (mNDblue) was more accurate during the reproductive period, providing the best accuracy for agronomical NUE (aNUE) assessment at the late grain-filling stage, with R², RMSE, and MAE of 0.61, 7.48 kg yield/kg N, and 6.05 kg yield/kg N, respectively. Furthermore, the findings indicated that model accuracy cannot be improved by increasing the number of input features. Overall, these results indicate that the consumer-grade P4M camera is suitable for early and efficient monitoring of important crop traits, providing a cost-effective choice for the development of the precision agricultural system.

Detection method of wheat spike improved YOLOv5s based on the attention mechanism

In wheat breeding, spike number is a key indicator for evaluating wheat yield, and the timely and accurate acquisition of wheat spike number is of great practical significance for yield prediction. In actual production; the method of using an artificial field survey to count wheat spikes is time-consuming and labor-intensive. Therefore, this paper proposes a method based on YOLOv5s with an improved attention mechanism, which can accurately detect the number of small-scale wheat spikes and better solve the problems of occlusion and cross-overlapping of the wheat spikes. This method introduces an efficient channel attention module (ECA) in the C3 module of the backbone structure of the YOLOv5s network model; at the same time, the global attention mechanism module (GAM) is inserted between the neck structure and the head structure; the attention mechanism can be more Effectively extract feature information and suppress useless information. The result shows that the accuracy of the improved YOLOv5s model reached 71.61% in the task of wheat spike number, which was 4.95% higher than that of the standard YOLOv5s model and had higher counting accuracy. The improved YOLOv5s and YOLOv5m have similar parameters, while RMSE and MEA are reduced by 7.62 and 6.47, respectively, and the performance is better than YOLOv5l. Therefore, the improved YOLOv5s method improves its applicability in complex field environments and provides a technical reference for the automatic identification of wheat spike numbers and yield estimation. Labeled images, source code, and trained models are available at: https://github.com/228384274/improved-yolov5.