A field-based apple detection and grading device was developed and used to detect and grade apples in the field using a deep learning framework. Four features were selected for apple grading, namely, size, color, shape, and surface defects, and detection algorithms were designed to discriminate between the four features using machine vision and other methods. Then, the four apple features were fused, and a support vector machine (SVM) was used for infield apple grading into three grades: first-grade fruit, second-grade fruit, and other-grade fruit. The results showed that for a single index, the accuracy of detecting the apple size, the fruit shape, the color, and the surface defects, were 99.04%, 97.71%, 98%, and 95.85%. The grading accuracies for the first-grade fruit, second-grade fruit, other-grade fruit, and the average grading accuracy based on multiple features were 94.55%, 95.71%, 100%, and 95.49%, respectively. The field experiment showed that the average grading accuracy was 94.12% when the feeding interval of the apples was less than 1.5 s and the walking speed did not exceed 0.5 m/s, meeting the accuracy requirements of field-based apple grading.

With the increase of labor cost and the development of agricultural mechanization, standardized orchards suitable for autonomous operations of agricultural machinery will be a future development trend of the fruit-planting industry. For field-planting processes of standardized orchards, autonomous navigation of orchard vehicles in complex environments is the foundation of mechanized and intelligent field operations. In order to realize autonomous driving and path-tracking of vehicles in complex standardized orchards that involve much noise and interference between rows of fruit trees, an automatic navigation system was designed for orchard vehicles, based on 2D lasers. First, considering the agronomic requirements for orchard planting such as plant spacing, row spacing and trunk diameter, different filtering thresholds were established to eliminate discrete points of 2D laser point cloud data effectively. Euclidean clustering algorithm and the important geometric theorems of three points collinearity was used to extract the central feature points of the trunk, as the same time, navigation path was fitted based on the least square method. Secondly, an automatic navigation control algorithm was designed, and the fuzzy control was used to realize the dynamic adjustment of the apparent distance of the pure pursuit model. Finally, the reliability of the proposed approach was verified by simulation using MATLAB/Simulink, and field tests were carried out based on electric agricultural vehicle. Experimental results show that the method proposed in this study can effectively improve the precision of automatic navigation in complex orchard environment and realize the autonomous operation of orchard vehicles.

Rapid and accurate crop chlorophyll content estimation is crucial for guiding field management and improving crop yields. This study explored the potential for potato chlorophyll content estimation based on unmanned aerial vehicle (UAV) multispectral imagery. To search the optimal estimation method, three parts of research were conducted as following. First, a combination of support vector machines (SVM) and a gaussian mixture model (GMM) thresholding method was proposed to estimate fractional vegetation cover (FVC) during the potato growing period, and the proposed method produced efficient estimates of FVC; among all the selected vegetation indices (VIs), the soil adjusted vegetation index (SAVI) had the highest accuracy. Second, the recursive feature elimination (RFE) algorithm was utilized to screen the VIs and texture features derived from multispectral images: three Vis, including modified simple ratio (MSR), ratio vegetation index (RVI) and normalized difference vegetation index (NDVI); three texture features, including correlation in the NIR band (corr-NIR), correlation in the red-edge band (corr-Red-edge) and homogeneity in the NIR band (hom-NIR), showed higher contribution to chlorophyll content estimation. Finally, a stacking model was constructed with K-Nearest Neighbor (KNN), a light gradient boosting machine (light-GBM), SVM algorithm as the base model and linear fitting as the metamodel, and four machine learning algorithms (SVM, KNN, light-GBM and stacking) were used to build the chlorophyll content estimation model suitable for different growing seasons. The results were: (1) The performance of the estimation model could be improved based on both VIs and texture features over using single-type features, and the stacking algorithm yielded the highest estimation accuracy with an R² value of 0.694 and an RMSE value of 0.553; (2) When FVC was added, the estimation model accuracy was further improved, and the stacking algorithm also produced the highest estimation accuracy with R² value of 0.739, RMSE value of 0.511 (3) When comparing modeling algorithms, stacking algorithms had greater advantages in the estimation chlorophyll content with potato plants than using single machine learning algorithms. This study indicates that taking into account the combination of VIs reflecting spectral characteristics, texture features reflecting spatial information and the FVC reflecting canopy structure properties can accomplish higher chlorophyll content estimation accuracy, and the stacking algorithm can integrate the advantages of a single machine learning model, with great potential for estimation of potato chlorophyll content.

The detection of apple yield in complex orchards plays an important role in smart agriculture. Due to the large number of fruit trees in the orchard, improving the speed of apple detection has become one of the challenges of apple yield detection. Additional challenges in the detection of apples in complex orchard environments are vision obstruction by leaves, branches and other fruit, and uneven illumination. The YOLOv5 (You Only Look Once version 5) network structure has thus far been increasingly utilized for fruit recognition, but its detection accuracy and real-time detection speed can be improved. Thus, an upgraded lightweight apple detection method YOLOv5-PRE (YOLOv5 Prediction) is proposed for the rapid detection of apple yield in an orchard environment. The ShuffleNet and the GhostNet lightweight structures were introduced into the YOLOv5-PRE model to reduce the size of the model, and the CA (Coordinate Attention) and CBAM (Convolutional Block Attention Module) attention mechanisms were used to improve the detection accuracy of the algorithm. After applying this algorithm on PC with NVIDIA Quadro P620 GPU, and after comparing the results of the YOLOv5s (You Only Look Once version 5 small) and the YOLOv5-PRE models outputs, the following conclusions were obtained: the average precision of the YOLOv5-PRE model was 94.03%, which is 0.58% higher than YOLOv5s. As for the average detection time of a single image on GPU and CPU, it was 27.0 ms and 172.3 ms, respectively, which is 17.93% and 35.23% higher than YOLOV5s. Added to that, the YOLOv5-PRE model had a missed detection rate of 6.54% when being subject to back-light conditions, and a false detection rate of 4.31% when facing front-light conditions, which are 2.8% and 0.86% higher than YOLOv5s, respectively. Finally, the feature extraction process of the YOLOv5-PRE model was presented in the form of a feature map visualization, which enhances the interpretability of the model. Thus, the YOLOv5-PRE model is more suitable for transplanting into embedded devices and adapts well to different lighting conditions in the orchard, which provides an effective method and a theoretical basis for the rapid detection of apples in the process of rapid detection of apple yield.

The most common harvesting method of Lycium barbarum L. (L. barbarum) is manual harvesting, resulting in low efficiency and high cost. Meanwhile, the efficiency of vibration harvesting, which is considered an efficient mechanical harvesting method, can be significantly improved if the optimized resonance frequency of the shrub can be obtained. To vibration harvest fruit efficiently, a 3D model of the shrub was established based on measurements of the shape parameters, and material mechanics models of the branches were established based on physical tests. The modal analysis of the shrub based on finite element method (FEM) simulation was performed to obtain the range of resonance frequency, and the modal experiment of the shrub using acceleration sensors and an impact hammer was conducted to obtain the accurate resonance frequency. Based on the results of the modal analysis and experiment, the optimized resonance frequency was determined to be 2 Hz. The field experiment showed that the fruit fell off when the branches were vibrated at this frequency. The results provide the design basis for the efficient vibration harvesting of L. barbarum.

Investigating the interactions of granular fertilizers with various types of equipment is an essential part of agricultural research. A numerical technique simulating the mechanical behavior of granular assemblies has the advantage of data trackings, such as the trajectories, velocities, and transient forces of the particles at any stage of the test. The interaction parameters were calibrated to simulate responses of granular fertilizers in EDEM, a discrete element method (DEM) software. Without a proper calibration of the interaction parameters between the granular fertilizers and various materials, the simulations may not represent the real behavior of the granular fertilizers. Therefore, in this study, a strategy is presented to identify and select a set of DEM input parameters of granular fertilizers using the central composite design (CCD) to establish the nonlinear relationship between the dynamic macroscopic granular fertilizer properties and the DEM parameters. The determined interaction properties can be used to simulate granular fertilizers in EDEM.