Blueberry is among the fruits with high economic gains for orchard farmers. Identification of blueberry fruits with different maturities has economic significance to help orchard farmers plan pesticide application, estimate yield, and conduct harvest operations efficiently. Vision systems for automated orchard yield estimation have received growing attention toward fruit identification with different maturity stages. However, due to interfering factors such as varying outdoor illuminations, similar colors with the surrounding canopy, imaging distance, and occlusion in natural environments, it remains a serious challenge to develop reliable visual methods for identifying blueberry fruits with different maturities. This study constructed a YOLO-BLBE (Blueberry) model combined with an innovative I-MSRCR (Improved MSRCR (Multi-Scale Retinex with Color Restoration)) method to accurately identify blueberry fruits with different maturities. The color feature of blueberry fruit in the original image was enhanced by the I-MSRCR algorithm, which was improved based on the traditional MSRCR algorithm by adjusting the proportion of color restoration factors. The GhostNet model embedded by the CA (coordinate attention) mechanism module replaced the original backbone network of the YOLOv5s model to form the backbone of the YOLO-BLBE model. The BIFPN (Bidirectional Feature Pyramid Network) structure was applied in the neck network of the YOLO-BLBE model, and Alpha-EIOU was used as the loss function of the model to determine and filter candidate boxes. The main contributions of this study are as follows: (1) The I-MSRCR algorithm proposed in this paper can effectively amplify the color differences between blueberry fruits of different maturities. (2) Adding the synthesized blueberry images processed by the I-MSRCR algorithm to the training set for training can improve the model’s recognition accuracy for blueberries of different maturity levels. (3) The YOLO-BLBE model achieved an average identification accuracy of 99.58% for mature blueberry fruits, 96.77% for semi-mature blueberry fruits, and 98.07% for immature blueberry fruits. (4) The YOLO-BLBE model had a size of 12.75 MB and an average detection speed of 0.009 s.

Reasonably formulating the strawberry harvesting sequence can improve the quality of harvested strawberries and reduce strawberry decay. Growth information based on drone image processing can assist the strawberry harvesting, however, it is still a challenge to develop a reliable method for object identification in drone images. This study proposed a deep learning method, including an improved YOLOv8 model and a new image-processing framework, which could accurately and comprehensively identify mature strawberries, immature strawberries, and strawberry flowers in drone images. The improved YOLOv8 model used the shuffle attention block and the VoV–GSCSP block to enhance identification accuracy and detection speed. The environmental stability-based region segmentation was used to extract the strawberry plant area (including fruits, stems, and leaves). Edge extraction and peak detection were used to estimate the number of strawberry plants. Based on the number of strawberry plants and the distribution of mature strawberries, we draw a growth chart of strawberries (reflecting the urgency of picking in different regions). The experiment showed that the improved YOLOv8 model demonstrated an average accuracy of 82.50% in identifying immature strawberries, 87.40% for mature ones, and 82.90% for strawberry flowers in drone images. The model exhibited an average detection speed of 6.2 ms and a model size of 20.1 MB. The proposed new image-processing technique estimated the number of strawberry plants in a total of 100 images. The bias of the error for images captured at a height of 2 m is 1.1200, and the rmse is 1.3565; The bias of the error for the images captured at a height of 3 m is 2.8400, and the rmse is 3.0199. The assessment of picking priorities for various regions of the strawberry field in this study yielded an average accuracy of 80.53%, based on those provided by 10 experts. By capturing images throughout the entire growth cycle, we can calculate the harvest index for different regions. This means farmers can not only obtain overall ripeness information of strawberries in different regions but also adjust agricultural strategies based on the harvest index to improve both the quantity and quality of fruit set on strawberry plants, as well as plan the harvesting sequence for high-quality strawberry yields.

The precise detection of diseases is crucial for the effective treatment of pear trees and to improve their fruit yield and quality. Currently, recognizing plant diseases in complex backgrounds remains a significant challenge. Therefore, a lightweight CCG-YOLOv5n model was designed to efficiently recognize pear leaf diseases in complex backgrounds. The CCG-YOLOv5n model integrates a CA attention mechanism, CARAFE up-sampling operator, and GSConv into YOLOv5n. It was trained and validated using a self-constructed dataset of pear leaf diseases. The model size and FLOPs are only 3.49 M and 3.8 G, respectively. The mAP@0.5 is 92.4%, and the FPS is up to 129. Compared to other lightweight indicates that the models, the experimental results demonstrate that the CCG-YOLOv5n achieves higher average detection accuracy and faster detection speed with a smaller computation and model size. In addition, the robustness comparison test CCG-YOLOv5n model has strong robustness under various lighting and weather conditions, including frontlight, backlight, sidelight, tree shade, and rain. This study proposed a CCG-YOLOv5n model for accurately detecting pear leaf diseases in complex backgrounds. The model is suitable for use on mobile terminals or devices.

In order to explore water distribution in sprinkler irrigation systems under dynamic water pressure, an irrigation test was conducted in a sprinkler irrigation system equipped with the Hunter MP2000 full circular rotator ray sprinkler under “trapezoidal” waveform pressure to explore the influencing factors such as basic water pressure, dynamic pressure period, and the sprinkler combination spacing. The result shows that the basic pressure, sprinkler combination spacing, and their interaction significantly affected the coefficient of variation, average intensity, and coefficient of uniformity. The normalized comprehensive evaluation indexes were selected as the measurement standards. The optimal factor combination was found to be the basic pressure of 250 kPa, the dynamic pressure period of 200 s, and the sprinkler combination spacing of 6 m, and the corresponding evaluation index values were 0.08, 10.54 mm/h, and 93.20%, respectively. The uniformity coefficient was increased by 6.54% compared with the constant pressure of the same flow rate. Compared with the constant pressure of the same flow rate, the sprinkler area and the average intensity increased by 39.67% and decreased by 8.62% when the basic pressure was 250 kPa and the dynamic pressure period was 200 s. The average uniformity coefficient increased by 11.76% at the combined spacing of 6.0, 6.5, 7.0, 7.5, and 8.0 m. The results provide a theoretical basis for sprinkler irrigation decisions under dynamic pressure.

Online rapid detection of a fertilizer solution’s type and concentration is crucial for intelligent water and fertilizer machines to realize intellectual precision variable fertilization. In this paper, a cylindrical capacitance sensor was designed based on the dielectric properties of the fertilizer solution, and an online rapid detection method of fertilizer type and concentration was proposed based on the characteristic frequency response mode. Three fertilizer solutions, potassium chloride, calcium superphosphate, and urea, were used as test objects. Ten concentrations of each fertilizer solution in the 10~100 g/L range were taken as the test fertilizer solution. Then, under the action of a series of sine wave excitation signals from 1 kHz to 10 MHz, the sensor’s amplitude-frequency/phase-frequency response data were obtained. The detection strategy of ‘first type, then concentration’ was adopted to realize rapid online detection of fertilizer type and concentration. Experimental results indicated that the maximum relative error of the sensor stability test was 0.72%, and the maximum error of concentration detection was 7.26%. Thus, the intelligent water and fertilizer machine can give feedback on the information of a fertilizer solution in real-time during the process of precise variable fertilization, thus improving the intelligence of water and fertilizer machines.

Rapid detection of fertilizer solutions is essential for improving water-fertilizer integration systems. However, existing detection methods are hindered by high costs, complexity, and slow response times, making real-time monitoring challenging. To solve these issues, we developed a qualitative-quantitative model that leverages machine learning (ML) algorithms based on the dielectric frequency response to detect the type and concentration of seven fertilizer solutions (N, P, K, PN, PK, NK, and NPK). Each fertilizer had unique dielectric frequency features, with different fluctuation, peak numbers, and maximum peaks. A linear relationship was also observed between the dielectric features (gain or phase shift) and fertilizer concentration within a specific frequency band. Following a "qualitative first, then quantitative" strategy, a qualitative-quantitative model was constructed using these results, including one classification model and seven concentration prediction models. For identifying solution types, the random forests (RF) algorithm was selected as the optimal qualitative model, with an accuracy of 98.57%. For detecting solution concentrations, seven optimal models were identified with R² values exceeding 0.98 and RMSE values below 0.4%, each incorporating the observed linear relationships mentioned above and different ML algorithms. Notably, the least squares support vector machine (LSSVM) and BP regression models outperformed the partial least squares regression (PLSR) model. These results demonstrated that the developed qualitative-quantitative model effectively integrates dielectric features with ML algorithms to accurately detect fertilizer solution components. This model can provide can provide feedback on fertilizer in-formation, supporting rapid online identification of fertilizer components, significantly enhancing their water-fertilizer utilization efficiency.