The number of maize seedlings is a key determinant of maize yield. Thus, timely, accurate estimation of seedlings helps optimize and adjust field management measures. Differentiating “multiple seedlings in a single hole” of maize accurately using deep learning and object detection methods presents challenges that hinder effectiveness. Multivariate regression techniques prove more suitable in such cases, yet the presence of weeds considerably affects regression estimation accuracy. Therefore, this paper proposes a maize and weed identification method that combines shape features with threshold skeleton clustering to mitigate the impact of weeds on maize counting. The threshold skeleton method (TS) ensured that the accuracy and precision values of eliminating weeds exceeded 97% and that the missed inspection rate and misunderstanding rate did not exceed 6%, which is a significant improvement compared with traditional methods. Multi-image characteristics of the maize coverage, maize seedling edge pixel percentage, maize skeleton characteristic pixel percentage, and connecting domain features gradually returned to maize seedlings. After applying the TS method to remove weeds, the estimated R² is 0.83, RMSE is 1.43, MAE is 1.05, and the overall counting accuracy is 99.2%. The weed segmentation method proposed in this paper can adapt to various seedling conditions. Under different emergence conditions, the estimated R² of seedling count reaches a maximum of 0.88, with an RMSE below 1.29. The proposed approach in this study shows improved weed recognition accuracy on drone images compared to conventional image processing methods. It exhibits strong adaptability and stability, enhancing maize counting accuracy even in the presence of weeds.

The Normalized Difference Vegetation Index (NDVI) is an important remote sensing index that is widely used to assess vegetation coverage, monitor crop growth, and predict yields. Traditional NDVI calculation methods often rely on multispectral or hyperspectral imagery, which are costly and complex to operate, thus limiting their applicability in small-scale farms and developing countries. To address these limitations, this study proposes an NDVI estimation method based on low-cost RGB (red, green, and blue) UAV (unmanned aerial vehicle) imagery combined with deep learning techniques. This study utilizes field data from five major crops (cotton, rice, maize, rape, and wheat) throughout their whole growth periods. RGB images were used to extract conventional features, including color indices (CIs), texture features (TFs), and vegetation coverage, while convolutional features (CFs) were extracted using the deep learning network ResNet50 to optimize the model. The results indicate that the model, optimized with CFs, significantly enhanced NDVI estimation accuracy. Specifically, the R² values for maize, rape, and wheat during their whole growth periods reached 0.99, while those for rice and cotton were 0.96 and 0.93, respectively. Notably, the accuracy improvement in later growth periods was most pronounced for cotton and maize, with average R² increases of 0.15 and 0.14, respectively, whereas wheat exhibited a more modest improvement of only 0.04. This method leverages deep learning to capture structural changes in crop populations, optimizing conventional image features and improving NDVI estimation accuracy. This study presents an NDVI estimation approach applicable to the whole growth period of common crops, particularly those with significant population variations, and provides a valuable reference for estimating other vegetation indices using low-cost UAV-acquired RGB images.

Soil moisture content is a crucial indicator for understanding the water requirements of crops. The effective monitoring of soil moisture content can provide support for irrigation decision-making and agricultural water management. Traditional ground-based measurement methods are time-consuming and labor-intensive, and point-scale monitoring cannot effectively represent the heterogeneity of soil moisture in the field. Unmanned aerial vehicle (UAV) remote sensing technology offers an efficient and convenient way to monitor soil moisture content in large fields, but airborne multispectral data are prone to spectral saturation effects, which can further affect the accuracy of monitoring soil moisture content. Therefore, we aim to construct effective drought indices for the accurate characterization of soil moisture content in winter wheat fields by utilizing unmanned aerial vehicles (UAVs) equipped with LiDAR, thermal infrared, and multispectral sensors. Initially, we estimated wheat plant height using airborne LiDAR sensors and improved traditional spectral indices in a structured manner based on crop height. Subsequently, we constructed the normalized land surface temperature–structured normalized difference vegetation index (NLST-SNDVI) space by combining the SNDVI with land surface temperature and calculated the improved Temperature–Vegetation Drought Index (iTVDI). The results are summarized as follows: (1) the structured spectral indices exhibit better resistance to spectral saturation, making the NLST-SNDVI space closer to expectations than the NLST-NDVI space, with higher fitting accuracy for wet and dry edges; (2) the iTVDI calculated based on the NLST-SNDVI space can effectively characterize soil moisture content, showing a significant correlation with measured surface soil moisture content; (3) the global Moran’s I calculated based on iTVDI deviations ranges between 0.18 and 0.30, all reaching significant levels, indicating that iTVDI has good spatial applicability. In conclusion, this study proved the effectiveness of the drought index based on a structured vegetation index, and the results can provide support for crop moisture monitoring and irrigation decision-making in the field.

The study of estimating rapeseed above-ground biomass (AGB) is of significant importance, as it can reflect the growth status of crops, enhance the commercial value of crops, promote the development of modern agriculture, and predict yield. Previous studies have mostly estimated crop AGB by extracting spectral indices from spectral images. This study aims to construct a model for estimating rapeseed AGB by combining spectral and LiDAR data. This study incorporates LiDAR data into the spectral data to construct a regression model. Models are separately constructed for the overall rapeseed varieties, nitrogen application, and planting density to find the optimal method for estimating rapeseed AGB. The results show that the R² for all samples in the study reached above 0.56, with the highest overall R² being 0.69. The highest R² for QY01 and ZY03 varieties was 0.56 and 0.78, respectively. Under high- and low-nitrogen conditions, the highest R² was 0.64 and 0.67, respectively. At a planting density of 36,000 plants per mu, the highest R² was 0.81. This study has improved the accuracy of estimating rapeseed AGB.