Crop disease diagnosis is of great significance to crop yield and agricultural production. Deep learning methods have become the main research direction to solve the diagnosis of crop diseases. This paper proposed a deep convolutional neural network that integrates an attention mechanism, which can better adapt to the diagnosis of a variety of tomato leaf diseases. The network structure mainly includes residual blocks and attention extraction modules. The model can accurately extract complex features of various diseases. Extensive comparative experiment results show that the proposed model achieves the average identification accuracy of 96.81% on the tomato leaf diseases dataset. It proves that the model has significant advantages in terms of network complexity and real-time performance compared with other models. Moreover, through the model comparison experiment on the grape leaf diseases public dataset, the proposed model also achieves better results, and the average identification accuracy of 99.24%. It is certified that add the attention module can more accurately extract the complex features of a variety of diseases and has fewer parameters. The proposed model provides a high-performance solution for crop diagnosis under the real agricultural environment.

Agrochemical application is an important tool in the agricultural industry for the protection of crops. Agrochemical application with conventional sprayers results in the waste of applied agrochemicals, which not only increases financial losses but also contaminates the environment. Targeted agrochemical sprayers using smart control systems can substantially decrease the chemical input, weed control cost, and destructive environmental contamination. A variable rate spraying system was developed using deep learning methods for the development of new models to classify weeds and to accurately spray on desired weeds target. Laboratory and field experiments were conducted to assess the sprayer performance for weed classification and precise spraying of the target weeds using three classification CNNs (Convolutional Neural Networks) models. The DCNNs models (AlexNet, VGG-16, and GoogleNet) were trained using a dataset containing a total of 12,443 images captured from the strawberry field (4200 images with spotted spurge, 4265 images with Shepherd’s purse, and 4178 strawberry plants). The VGG-16 model attained higher values of precision, recall and F1-score as compared to AlexNet and GoogleNet. Additionally VGG-16 model recorded higher percentage of completely sprayed weeds target (CS = 93%) values. Overall in all experiments, VGG-16 performed better than AlexNet and GoogleNet for real-time weeds target classification and precision spraying. The experiments results revealed that the Sprayer performance decreased with the increase of sprayer traveling speed above 3 km/h. Experimental results recommended that the sprayer with the VGG-16 model can achieve high performance that makes it more ideal for a real-time spraying application. It is concluded that the advanced variable rate spraying system has the potential for spot application of agrochemicals to control weeds in a strawberry field. It can reduce the crop input costs and the environmental pollution risks.

Plant health is the basis of agricultural development. Plant diseases are a major factor for crop losses in agriculture. Plant diseases are difficult to diagnose correctly, and the manual disease diagnosis process is time consuming. For this reason, it is highly desirable to automatically identify the diseases in strawberry plants to prevent loss of crop quality. Deep learning (DL) has recently gained popularity in image classification and identification due to its high accuracy and fast learning. In this research, deep learning models were used to identify the leaf scorch disease in strawberry plants. Four convolutional neural networks (SqueezeNet, EfficientNet-B3, VGG-16 and AlexNet) CNN models were trained and tested for the classification of healthy and leaf scorch disease infected plants. The performance accuracy of EfficientNet-B3 and VGG-16 was higher for the initial and severe stage of leaf scorch disease identification as compared to AlexNet and SqueezeNet. It was also observed that the severe disease (leaf scorch) stage was correctly classified more often than the initial stage of the disease. All the trained CNN models were integrated with a machine vision system for real-time image acquisition under two different lighting situations (natural and controlled) and identification of leaf scorch disease in strawberry plants. The field experiment results with controlled lightening arrangements, showed that the model EfficientNet-B3 achieved the highest classification accuracy, with 0.80 and 0.86 for initial and severe disease stages, respectively, in real-time. AlexNet achieved slightly lower validation accuracy (0.72, 0.79) in comparison with VGGNet and EfficientNet-B3. Experimental results stated that trained CNN models could be used in conjunction with variable rate agrochemical spraying systems, which will help farmers to reduce agrochemical use, crop input costs and environmental contamination.

Accurate fruit segmentation in images is the prerequisite and key step for precision agriculture. In this article, aiming at the segmentation of grape cluster with different varieties, 3 state-of-the-art semantic segmentation networks, i.e., Fully Convolutional Network (FCN), U-Net, and DeepLabv3+ applied on six different datasets were studied. We investigated: (1) the segmentation performance difference of the 3 studied networks; (2) The impact of different input representations on segmentation performance; (3) The effect of image enhancement method to improve the poor illumination of images and further improve the segmentation performance; (4) The impact of the distance between grape clusters and camera on segmentation performance. The experiment results show that compared with FCN and U-Net the DeepLabv3+ combined with transfer learning is more suitable for the task with an intersection over union (IoU) of 84.26%. Five different input representations, namely RGB, HSV, L*a*b, HHH, and YCrCb obtained different IoU, ranging from 81.5% to 88.44%. Among them, the L*a*b got the highest IoU. Besides, the adopted Histogram Equalization (HE) image enhancement method could improve the model’s robustness against poor illumination conditions. Through the HE preprocessing, the IoU of the enhanced dataset increased by 3.88%, from 84.26% to 88.14%. The distance between the target and camera also affects the segmentation performance, no matter in which dataset, the closer the distance, the better the segmentation performance was. In a word, the conclusion of this research provides some meaningful suggestions for the study of grape or other fruit segmentation.

For high-speed robotic cut-and-catch harvesting, efficient trellis grape recognition and picking point positioning are crucial factors. In this study, a new method for the rapid positioning of picking points based on synchronous inference for multi-grapes was proposed. Firstly, a three-dimensional region of interest for a finite number of grapes was constructed according to the “eye to hand” configuration. Then, a feature-enhanced recognition deep learning model called YOLO v4-SE combined with multi-channel inputs of RGB and depth images was put forward to identify occluded or overlapping grapes and synchronously infer picking points upwards of the prediction boxes of the multi-grapes imaged completely in the three-dimensional region of interest (ROI). Finally, the accuracy of each dimension of the picking points was corrected, and the global continuous picking sequence was planned in the three-dimensional ROI. The recognition experiment in the field showed that YOLO v4-SE has good detection performance in various samples with different interference. The positioning experiment, using a different number of grape bunches from the field, demonstrated that the average recognition success rate is 97% and the average positioning success rate is 93.5%; the average recognition time is 0.0864 s; and the average positioning time is 0.0842 s. The average positioning errors of the x, y, and z directions are 2.598, 2.012, and 1.378 mm, respectively. The average positioning error of the Euclidean distance between the true picking point and the predicted picking point is 7.69 mm. In field synchronous harvesting experiments with different fruiting densities, the average recognition success rate is 97%; the average positioning success rate is 93.606%; and the average picking success rate is 92.78%. The average picking speed is 6.18 $\mathrm{s}\times {\mathrm{bunch}}^{-1}$, which meets the harvesting requirements for high-speed cut-and-catch harvesting robots. This method is promising for overcoming time-consuming harvesting caused by the problematic positioning of the grape stem.

Rapid and accurate grape leaf disease diagnosis is of great significance to its yield and quality of grape. In this paper, aiming at the identification of grape leaf diseases, a fast and accurate detection method based on fused deep features, extracted from a convolutional neural network (CNN), plus a support vector machine (SVM) is proposed. In the research, based on an open dataset, three types of state-of-the-art CNN networks, three kinds of deep feature fusion methods, seven species of deep feature layers, and a multi-class SVM classifier were studied. Firstly, images were resized to meet the input requirements of the CNN network; then, the deep features of the input images were extracted via the specific deep feature layer of the CNN network. Two kinds of deep features from different networks were then fused using different fusion methods to increase the effective classification feature information. Finally, a multi-class SVM classifier was trained with the fused deep features. The experimental results on the open dataset show that the fused deep features with any kind of fusion method can obtain a better classification performance than using a single type of deep feature. The direct concatenation of the Fc1000 deep feature extracted from ResNet50 and ResNet101 can achieve the best classification result compared with the other two fusion methods, and its F1 score is 99.81%. Furthermore, the SVM classifier trained using the proposed method can achieve a classification performance comparable to that of using the CNN model directly, but the training time is less than 1 s, which has an advantage over spending tens of minutes training a CNN model. The experimental results indicate that the method proposed in this paper can achieve fast and accurate identification of grape leaf diseases and meet the needs of actual agricultural production.