The detection and counting of fruit tree canopies are important for orchard management, yield estimation, and phenotypic analysis. Previous research has shown that most fruit tree canopy detection methods are based on the use of traditional computer vision algorithms or machine learning methods to extract shallow features such as color and contour, with good results. However, due to the lack of robustness of these features, most methods are hardly adequate for the recognition and counting of fruit tree canopies in natural scenes. Other studies have shown that deep learning methods can be used to perform canopy detection. However, the adhesion and occlusion of fruit tree canopies, as well as background noise, limit the accuracy of detection. Therefore, to improve the accuracy of fruit tree canopy recognition and counting in real-world scenarios, an improved YOLOv4 (you only look once v4) is proposed, using a dataset produced from fruit tree canopy UAV imagery, combined with the Mobilenetv3 network, which can lighten the model and increase the detection speed, combined with the CBAM (convolutional block attention module), which can increase the feature extraction capability of the network, and combined with ASFF (adaptively spatial feature fusion), which enhances the multi-scale feature fusion capability of the network. In addition, the K-means algorithm and linear scale scaling are used to optimize the generation of pre-selected boxes, and the learning strategy of cosine annealing is combined to train the model, thus accelerating the training speed of the model and improving the detection accuracy. The results show that the improved YOLOv4 model can effectively overcome the noise in an orchard environment and achieve fast and accurate recognition and counting of fruit tree crowns while lightweight the model. The mAP reached 98.21%, FPS reached 96.25 and F1-score reached 93.60% for canopy detection, with a significant reduction in model size; the average overall accuracy (AOA) reached 96.73% for counting. In conclusion, the YOLOv4-Mobilenetv3-CBAM-ASFF-P model meets the practical requirements of orchard fruit tree canopy detection and counting in this study, providing optional technical support for the digitalization, refinement, and smart development of smart orchards.

Unmanned Aerial Vehicle (UAV) spray has been used for efficient and adaptive pesticide applications with its low costs. However, droplet drift is the main problem for UAV spray and will induce pesticide waste and safety concerns. Droplet size and deposition distribution are both highly related to droplet drift and spray effect, which are determined by the nozzle. Therefore, it is necessary to propose an evaluating method for a specific UAV spray nozzles. In this paper, four machine learning methods (REGRESS, least squares support vector machines (LS-SVM), extreme learning machine, and radial basis function neural network (RBFNN)) were applied for quantitatively evaluating one type of UAV spray nozzle (TEEJET XR110015VS), and the case of twin nozzles was investigated. The results showed REGRESS and LS-SVM are good candidates for droplet size evaluation with the coefficient of determination in the calibration set above 0.9 and root means square errors of the prediction set around 2 µm. RBFNN achieved the best performance for the evaluation of deposition distribution and showed its potential for determining the droplet size of overlapping area. Overall, this study proved the accuracy and efficiency of using the machine learning method for UAV spray nozzle evaluation. Additionally, the study demonstrated the feasibility of using machine learning model to predict the droplet size in the overlapping area of twin nozzles.

Accurate monitoring of rice phenology is critical for crop management, cultivars breeding, and yield estimating. Previously, research for phenology detection relied on time-series data and orthomosaic and manually plotted regions, which are difficult to automate. This study presented a novel approach for extracting and mapping phenological traits directly from the unmanned aerial vehicle (UAV) photograph sequence. First, a multi-stage rice field segmentation dataset containing four growth stages and 2600 images, namely PaddySeg, was built. Moreover, an efficient Ghost Bilateral Network (GBiNet) was proposed to generate trait masks. To locate the trait of each pixel, we introduced direct geo-locating (DGL) and incremental sparse sampling (ISS) techniques to eliminate redundant computation. According to the results on PaddySeg, the proposed GBiNet with 91.50% mean-Intersection-over-Union (mIoU) and 41 frames-per-second (FPS) speed outperformed the baseline model (90.95%, 36 FPS), while the fastest GBiNet_t reached 62 FPS which was 1.7 times faster than the baseline model, BiSeNetV2. Additionally, the measured average DGL deviation was less than 1% of the relative height. Finally, the mapping of rice phenology was achieved by interpolation on trait value–location pairs. The proposed approach demonstrated great potential for automatic rice phenology stage surveying and mapping.

Efficient and quick yield prediction is of great significance for ensuring world food security and crop breeding research. The rapid development of unmanned aerial vehicle (UAV) technology makes it more timely and accurate to monitor crops by remote sensing. The objective of this study was to explore the method of developing a novel yield index (YI) with wide adaptability for yield prediction by fusing vegetation indices (VIs), color indices (CIs), and texture indices (TIs) from UAV-based imagery. Six field experiments with 24 varieties of rice and 21 fertilization methods were carried out in three experimental stations in 2019 and 2020. The multispectral and RGB images of the rice canopy collected by the UAV platform were used to rebuild six new VIs and TIs. The performance of VI-based YI (MAPE = 13.98%) developed by quadratic nonlinear regression at the maturity stage was better than other stages, and outperformed that of CI-based (MAPE = 22.21%) and TI-based (MAPE = 18.60%). Then six VIs, six CIs, and six TIs were fused to build YI by multiple linear regression and random forest models. Compared with heading stage (R² = 0.78, MAPE = 9.72%) and all stage (R² = 0.59, MAPE = 22.21%), the best performance of YI was developed by random forest with fusing VIs + CIs + TIs at maturity stage (R² = 0.84, MAPE = 7.86%). Our findings suggest that the novel YI proposed in this study has great potential in crop yield monitoring.