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.

Late blight, caused by phytophthora infestans, is a devastating disease in potato production. In severe cases, this can lead to potato crop failure. To rapidly detect potato late blight, in this study, a deep learning model was developed to discriminate the degree of potato leaf diseases with high recognition accuracy and a fast inference speed. It constructed a total of seven categories of potato leaf disease datasets in single and complex backgrounds, which were augmented using data enhancement method increase to increase the number of images to 7039. In this study, the performance of the pre-trained model for fine-grained classification of potato leaf diseases was evaluated comprehensively in terms of accuracy, inference speed, and the number of parameters. The ShuffleNetV2 2× model with better generalization ability and faster inference speed was selected and improved. Three improvement strategies were proposed: introducing an attention module, reducing the depth of the network, and reducing the number of 1 × 1 convolutions. Their effects on the performance of the underlying model were explored through experiments, and the best form of improvement was determined. The loss function of the improved model converged to 0.36. This was compared to the base model, which was reduced by 34.5%. In the meantime, the improved model reduced the number of parameters, FLOPs, and model size by approximately 23%, increased classification accuracy by 0.85%, and improved CPU inference speed by 25%. Deploying the improved model to the embedded device, the overall classification precision was 94%, and the average time taken to detect a single image was 3.27 s. The method provided critical technical support for the automatic identification of potato late blight.

Our research focuses on winter jujube trees and is conducted in a greenhouse environment in a structured orchard to effectively control various growth conditions. The development of a robotic system for winter jujube harvesting is crucial for achieving mechanized harvesting. Harvesting winter jujubes efficiently requires accurate detection and location. To address this issue, we proposed a winter jujube detection and localization method based on the MobileVit-Large selective kernel-GSConv-YOLO (MLG-YOLO) model. First, a winter jujube dataset is constructed to comprise various scenarios of lighting conditions and leaf obstructions to train the model. Subsequently, the MLG-YOLO model based on YOLOv8n is proposed, with improvements including the incorporation of MobileViT to reconstruct the backbone and keep the model more lightweight. The neck is enhanced with LSKblock to capture broader contextual information, and the lightweight convolutional technology GSConv is introduced to further improve the detection accuracy. Finally, a 3-dimensional localization method combining MLG-YOLO with RGB-D cameras is proposed. Through ablation studies, comparative experiments, 3-dimensional localization error tests, and full-scale tree detection tests in laboratory environments and structured orchard environments, the effectiveness of the MLG-YOLO model in detecting and locating winter jujubes is confirmed. With MLG-YOLO, the mAP increases by 3.50%, while the number of parameters is reduced by 61.03% in comparison with the baseline YOLOv8n model. Compared with mainstream object detection models, MLG-YOLO excels in both detection accuracy and model size, with a mAP of 92.70%, a precision of 86.80%, a recall of 84.50%, and a model size of only 2.52 MB. The average detection accuracy in the laboratory environmental testing of winter jujube reached 100%, and the structured orchard environmental accuracy reached 92.82%. The absolute positioning errors in the X, Y, and Z directions are 4.20, 4.70, and 3.90 mm, respectively. This method enables accurate detection and localization of winter jujubes, providing technical support for winter jujube harvesting robots.

Late blight caused by Phytophthora infestans is a destructive disease in potato production, which can lead to crop failure in severe cases. This study combined visible/near-infrared (Vis/NIR) spectroscopy with machine learning (ML) and chemometric methods for rapid detection of potato late blight. The determination of disease severity was accomplished by two methods directly or indirectly based on differences in reflectance. One approach was to utilize ML algorithms to build a model that directly reflects the relationship between disease level and spectral reflectance. Another method was to first use partial least squares to construct a predictive model of internal physicochemical values, such as relative chlorophyll content (SPAD) and peroxidase (POD) activity, and then use an ML model to classify disease levels based on the predicted values. The classification accuracy based on these two methods could reach up to 99 and 95%, respectively. The changes in physicochemical values during the development of disease were further investigated. Regression models for fitting changes in SPAD value and POD activity were developed based on temperature and incubation time, with determination coefficients of 0.961 and 0.997, respectively. The prediction of epidemic period was realized by combining regression and classification models based on physicochemical values with an accuracy of 88.5%. It is demonstrated that rapid non-destructive determination of physicochemical values based on Vis/NIR spectroscopy for potato late blight detection is feasible. Furthermore, it is possible to guide the control of disease throughout the epidemic period.

Automatic machine vision-based defect detection has been successfully applied to many industrial visual inspection applications. However, automatic steel surface defect detection is still a challenging task due to diverse defect categories, low-contrast between defect and complex texture background. To address these challenges, a chained atrous spatial pyramid pooling network (CASPPNet) is proposed for steel surface defect detection. In CASPPNet, chained atrous spatial pyramid pooling is designed to enlarge receptive field and obtain enrich semantic information. An improved global attention feature fusion module is introduced to achieve feature interaction and salience. Moreover, residual boundary refinement block is introduced to get more complete defect boundary. Comparative experimental results verify that our method is superior to the state-of-the-art segmentation methods on public accessible SD-saliency-900 datasets and can meet the requirement of real-time online detection (the detection efficiency is at over 47 FPS on a single GPU).