As one of the main disasters that limit the formation of wheat yield and affect the quality of wheat, lodging poses a great threat to safety production. Therefore, an improved PSPNet (Pyramid Scene Parsing Network) integrating the Normalization-based Attention Module (NAM) (NAM-PSPNet) was applied to the high-definition UAV RGB images of wheat lodging areas at the grain-filling stage and maturity stage with the height of 20 m and 40 m. First, based on the PSPNet network, the lightweight neural network MobileNetV2 was used to replace ResNet as the feature extraction backbone network. The deep separable convolution was used to replace the standard convolution to reduce the amount of model parameters and calculations and then improve the extraction speed. Secondly, the pyramid pool structure of multi-dimensional feature fusion was constructed to obtain more detailed features of UAV images and improve accuracy. Then, the extracted feature map was processed by the NAM to identify the less significant features and compress the model to reduce the calculation. The U-Net, SegNet and DeepLabv3+ were selected as the comparison models. The results show that the extraction effect at the height of 20 m and the maturity stage is the best. For the NAM-PSPNet, the MPA (Mean Pixel Accuracy), MIoU (Mean Intersection over Union), Precision, Accuracy and Recall is, respectively, 89.32%, 89.32%, 94.95%, 94.30% and 95.43% which are significantly better than the comparison models. It is concluded that NAM-PSPNet has better extraction performance for wheat lodging areas which can provide the decisionmaking basis for severity estimation, yield loss assessment, agricultural operation, etc.

Winter wheat is one of the most important food crops in China, and it is of great significance to ensure national food security. The accurate extraction of wheat-growing areas is a prerequisite for growth assessments, stress monitoring, and yield assessments. In this study, GF-6 (8 m resolution) and Sentinel-2 (10 m resolution) remote sensing images were used to create datasets for the accurate extraction of winter-wheat growing areas by improving the U-Net model. First, U-Net was used as the base network to extract features, and then the convolutional block attention module (CBAM) was embedded in the basic convolutional units in the coding and decoding layers of the network to enhance or suppress the features to improve the feature-expression capability of the model, and to finally complete the end-to-end winter-wheat planting-area extraction. SegNet, DeepLabV3+, and U-Net-CBAM were selected as the comparison models, and they were tested using the test set in the Sentinel-2 dataset. The precision of the U-Net-CBAM model trained on the GF-6 dataset was 84.92%, the MIoU was 77.1%, the recall was 88.28%, the overall precision (OA) was 91.64%, and the F₁ was 86.45%. For training on Sentinel-2 dataset, those values were: 90.06% for precision, 83.18% for MIoU, 90.78% for recall, 93.93% for OA, and 90.52% for F₁, which showed significantly better results than those of the comparison models, indicating that U-Net-CBAM improved the accuracy of winter-wheat area extraction. It also showed that the segmentation performance of the training and test sets from different datasets was much lower than the segmentation performance from the same dataset.

Aboveground biomass (AGB) is an important indicator used to predict crop yield. Traditional spectral features or image textures have been proposed to estimate the AGB of crops, but they perform poorly at high biomass levels. This study thus evaluated the ability of spectral features, image textures, and their combinations to estimate winter wheat AGB. Spectral features were obtained from the wheat canopy reflectance spectra at 400–1000 nm, including original wavelengths and seven vegetation indices. Effective wavelengths (EWs) were screened through use of the successive projection algorithm, and the optimal vegetation index was selected by correlation analysis. Image texture features, including texture features and the normalized difference texture index, were extracted using gray level co-occurrence matrices. Effective variables, including the optimal texture subset (OTEXS) and optimal normalized difference texture index subset (ONDTIS), were selected by the ranking of feature importance using the random forest (RF) algorithm. Linear regression (LR), partial least squares regression (PLS), and RF were established to evaluate the relationship between each calculated feature and AGB. Results demonstrate that the ONDTIS with PLS based on the validation datasets exhibited better performance in estimating AGB for the post-seedling stage (R² = 0.75, RMSE = 0.04). Moreover, the combinations of the OTEXS and EWs exhibited the highest prediction accuracy for the seeding stage when based on the PLS model (R² = 0.94, RMSE = 0.01), the post-seedling stage when based on the LR model (R² = 0.78, RMSE = 0.05), and for all stages when based on the RF model (R² = 0.87, RMSE = 0.05). Hence, the combined use of spectral and image textures can effectively improve the accuracy of AGB estimation, especially at the post-seedling stage.