Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only Once)-based method to detect wheat spikes accurately in UAV images and solve spike error detection and miss detection caused by occlusion conditions. The proposed method introduces data cleaning and data augmentation to improve the generalization ability of the detection network. The network is rebuilt by adding a microscale detection layer, setting prior anchor boxes, and adapting the confidence loss function of the detection layer based on the IoU (Intersection over Union). These refinements improve the feature extraction for small-sized wheat spikes and lead to better detection accuracy. With the confidence weights, the detection boxes in multiresolution images are fused to increase the accuracy under occlusion conditions. The result shows that the proposed method is better than the existing object detection algorithms, such as Faster RCNN, Single Shot MultiBox Detector (SSD), RetinaNet, and standard YOLOv5. The average accuracy (AP) of wheat spike detection in UAV images is 94.1%, which is 10.8% higher than the standard YOLOv5. Thus, the proposed method is a practical way to handle the spike detection in complex field scenarios and provide technical references for field-level wheat phenotype monitoring.

To improve the efficiency and effectiveness of mosaicking unmanned aerial vehicle (UAV) images, we propose in this paper a rapid mosaicking method based on scale-invariant feature transform (SIFT) for mosaicking UAV images used for crop growth monitoring. The proposed method dynamically sets the appropriate contrast threshold in the difference of Gaussian (DOG) scale-space according to the contrast characteristics of UAV images used for crop growth monitoring. Therefore, this method adjusts and optimizes the number of matched feature point pairs in UAV images and increases the mosaicking efficiency. Meanwhile, based on the relative location relationship of UAV images used for crop growth monitoring, the random sample consensus (RANSAC) algorithm is integrated to eliminate the influence of mismatched point pairs in UAV images on mosaicking and to keep the accuracy and quality of mosaicking. Mosaicking experiments were conducted by setting three types of UAV images in crop growth monitoring: visible, near-infrared, and thermal infrared. The results indicate that compared to the standard SIFT algorithm and frequently used commercial mosaicking software, the method proposed here significantly improves the applicability, efficiency, and accuracy of mosaicking UAV images in crop growth monitoring. In comparison with image mosaicking based on the standard SIFT algorithm, the time efficiency of the proposed method is higher by 30%, and its structural similarity index of mosaicking accuracy is about 0.9. Meanwhile, the approach successfully mosaics low-resolution UAV images used for crop growth monitoring and improves the applicability of the SIFT algorithm, providing a technical reference for UAV application used for crop growth and phenotypic monitoring.

Climate change and anthropogenic activities, including agricultural irrigation have significantly altered the global and regional hydrological cycle. However, human-induced modification to the natural environment is not well represented in land surface models (LSMs). In this study, we utilize microwave-based soil moisture products to aid the detection of under-represented irrigation processes throughout China. The satellite retrievals used in this study include passive microwave observations from the Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) and its successor AMSR2, active microwave observations from the Advanced Scatterometer (ASCAT), and the blended multi-sensor soil moisture product from the European Space Agency (i.e., ESA CCI product). We first conducted validations of the three soil moisture retrievals against in-situ observations (collected from the nationwide agro-meteorological network) in irrigated areas in China. It is found that compared to the conventional Spearman’s rank correlation and Pearson correlation coefficients, entropy-based mutual information is more suitable for evaluating soil moisture anomalies induced by irrigation. In general, around 60% of uncertainties in the anomaly of “ground truth” time series can be resolved by soil moisture retrievals, with ASCAT outperforming the others. Following this, the potential utility of soil moisture retrievals in mapping irrigation patterns in China is investigated by examining the difference in probability distribution functions (detected by two-sample Kolmogorov-Smirnov test) between soil moisture retrievals and benchmarks of the numerical model ERA-Interim without considering the irrigation process. Results show that microwave remote sensing provides a promising alternative to detect the under-represented irrigation process against the reference LSM ERA-Interim. Specifically, the highest performance in detecting irrigation intensity is found when using ASCAT in Huang-Huai-Hai Plain, followed by advanced microwave scanning radiometer (AMSR) and ESA CCI. Compared to ASCAT, the irrigation detection capabilities of AMSR exhibit higher discrepancies between descending and ascending orbits, since the soil moisture retrieval algorithm of AMSR is based on surface temperature and, thus, more affected by irrigation practices. This study provides insights into detecting the irrigation extent using microwave-based soil moisture with aid of LSM simulations, which has great implications for numerical model development and agricultural managements across the country.

Accurate wheat spike detection is crucial in wheat field phenotyping for precision farming. Advances in artificial intelligence have enabled deep learning models to improve the accuracy of detecting wheat spikes. However, wheat growth is a dynamic process characterized by important changes in the color feature of wheat spikes and the background. Existing models for wheat spike detection are typically designed for a specific growth stage. Their adaptability to other growth stages or field scenes is limited. Such models cannot detect wheat spikes accurately caused by the difference in color, size, and morphological features between growth stages. This paper proposes WheatNet to detect small and oriented wheat spikes from the filling to the maturity stage. WheatNet constructs a Transform Network to reduce the effect of differences in the color features of spikes at the filling and maturity stages on detection accuracy. Moreover, a Detection Network is designed to improve wheat spike detection capability. A Circle Smooth Label is proposed to classify wheat spike angles in drone imagery. A new micro-scale detection layer is added to the network to extract the features of small spikes. Localization loss is improved by Complete Intersection over Union to reduce the impact of the background. The results show that WheatNet can achieve greater accuracy than classical detection methods. The detection accuracy with average precision of spike detection at the filling stage is 90.1%, while it is 88.6% at the maturity stage. It suggests that WheatNet is a promising tool for detection of wheat spikes.

The number of seedlings is an important indicator that reflects the size of the wheat population during the seedling stage. Researchers increasingly use deep learning to detect and count wheat seedlings from unmanned aerial vehicle (UAV) images. However, due to the small size and diverse postures of wheat seedlings, it can be challenging to estimate their numbers accurately during the seedling stage. In most related works in wheat seedling detection, they label the whole plant, often resulting in a higher proportion of soil background within the annotated bounding boxes. This imbalance between wheat seedlings and soil background in the annotated bounding boxes decreases the detection performance. This study proposes a wheat seedling detection method based on a local annotation instead of a global annotation. Moreover, the detection model is also improved by replacing convolutional and pooling layers with the Space-to-depth Conv module and adding a micro-scale detection layer in the YOLOv5 head network to better extract small-scale features in these small annotation boxes. The optimization of the detection model can reduce the number of error detections caused by leaf occlusion between wheat seedlings and the small size of wheat seedlings. The results show that the proposed method achieves a detection accuracy of 90.1%, outperforming other state-of-the-art detection methods. The proposed method provides a reference for future wheat seedling detection and yield prediction.

Upscaling in situ soil moisture observations (ISMO) to multiscale pixel estimations with kriging is a key step in the comprehensive usage of ISMO and remote sensing (RS) soil moisture data. Scale effects occur and introduce uncertainties during upscaling processes because of spatial heterogeneity and the kriging method. A nested hierarchical scale series was established at the field level, and upscaled estimations at each scale were obtained by block kriging (BK) to illustrate multiscale ISMO upscaling processes. Those uncertainties were described with the results of comparison analysis against RS data, statistical analysis, and spatial trend surface analysis on multiscale estimations and were explained from the spatial heterogeneity perspective with a semivariogram analysis on ISMO. The results show that uncertainties exist and vary in multiscale upscaling processes, and the range of the empirical semivariogram could indicate scale effects. When the target scale is shorter than the range, BK maintains similar scale effects and global trends during upscaling processes, and the direct pixel estimation by BK is relatively close to the average of nested pixel estimations. This has great implications for understanding the kriging method in similar works.