Processing pepper planting and processing have become an important red pillar industry in Xinjiang. With the continuous growth of processing pepper planting areas in Xinjiang, diseases and pests are increasing year by year. The aim of this study was to compare the droplet deposition and control efficiency of unmanned aerial vehicle (UAV) and electric air-pressure knapsack (EAP) sprayers on a processing pepper field. The UAV sprayer had a poor droplet coverage rate, droplet density, and deposition uniformity, but displayed the best deposition (1.01 μg/cm², which was 98% more than the EAP sprayer). The control efficacy of the UAV sprayer on processing pepper fields with Phytophthora capsici and aphids was slightly lower than that of the EAP sprayer. When the UAV sprayer was used to control processing pepper diseases and pests, it could reduce the pesticide dosage on the premise of ensuring the control effect. Further study of the residue of high concentration pesticides in pepper fruit and environment sprayed by UAVs are needed.

Maize small leaf spot (Bipolaris maydis) is one of the most important diseases of maize. The severity of the disease cannot be accurately identified, the cost of pesticide application increases every year, and the agricultural ecological environment is polluted. Therefore, in order to solve this problem, this study proposes a novel deep learning network DISE-Net. We designed a dilated-inception module instead of the traditional inception module for strengthening the performance of multi-scale feature extraction, then embedded the attention module to learn the importance of interchannel relationships for input features. In addition, a dense connection strategy is used in model building to strengthen channel feature propagation. In this paper, we constructed a data set of maize small leaf spot, including 1268 images of four disease grades and healthy leaves. Comparative experiments show that DISE-Net with a test accuracy of 97.12% outperforms the classical VGG16 (91.11%), ResNet50 (89.77%), InceptionV3 (90.97%), MobileNetv1 (92.51%), MobileNetv2 (92.17%) and DenseNet121 (94.25%). In addition, Grad-Cam network visualization also shows that DISE-Net is able to pay more attention to the key areas in making the decision. The results showed that the DISE-Net was suitable for the classification of maize small leaf spot in the field.

Defoliant spraying is an important aspect of mechanized cotton harvesting. Fully and uniformly spraying defoliant could improve the quality of defoliation and reduce the impurity content in cotton. Improving the coverage of defoliant droplets in the middle and lower layers of cotton and ensuring the full and even dispersion of droplets in the cotton canopy are essentially in increasing the defoliation effect. In this study, we assessed the effect of aviation spray adjuvants on droplet deposition, defoliation, boll opening and defoliant retention in cotton leaves sprayed by an unmanned aerial vehicle (UAV). The results showed that adding aviation spray adjuvants could significantly improve the defoliant droplet deposition. Fifteen days after spraying, the defoliation rate was 80.31% and the boll opening was 90.61%. The defoliation rate increased by 3.12–34.62% and the boll opening rate increased by 6.67–29.56% after the addition of aviation spray adjuvants. Using a vegetable oil adjuvant could significantly increase the droplet coverage rate and the retention of defoliants in cotton leaves.

Atrazine is one of the most widely used herbicides in weed management. However, the widespread use of atrazine has concurrently accelerated the evolution of weed resistance mechanisms. Resistant weeds were identified early to contribute to crop protection in precision agriculture before visible symptoms of atrazine application to weeds in actual field environments. New developments in unmanned aerial vehicle (UAV) platforms and sensor technologies promote cost-effective data collection by collecting multi-modal data at very high spatial and spectral resolution. In this study, we obtained multispectral and RGB images using UAVs, increased available information with the help of image fusion technology, and developed a weed spectral resistance index, WSRI = (RE-R)/(RE-B), based on the difference between susceptible and resistant weed biotypes. A deep convolutional neural network (DCNN) was applied to evaluate the potential for identifying resistant weeds in the field. Comparing the WSRI introduced in this study with previously published vegetation indices (VIs) shows that the WSRI is better at classifying susceptible and resistant weed biotypes. Fusing multispectral and RGB images improved the resistance identification accuracy, and the DCNN achieved high field accuracies of 81.1% for barnyardgrass and 92.4% for velvetleaf. Time series and weed density influenced the study of weed resistance, with 4 days after application (4DAA) identified as a watershed timeframe in the study of weed resistance, while different weed densities resulted in changes in classification accuracy. Multispectral and deep learning proved to be effective phenotypic techniques that can thoroughly analyze weed resistance dynamic response and provide valuable methods for high-throughput phenotyping and accurate field management of resistant weeds.

Natural rubber is an essential raw material for industrial products and plays an important role in social development. A variety of diseases can affect the growth of rubber trees, reducing the production and quality of natural rubber. Therefore, it is of great significance to automatically identify rubber leaf disease. However, in practice, different diseases have complex morphological characteristics of spots and symptoms at different stages and scales, and there are subtle interclass differences and large intraclass variation between the symptoms of diseases. To tackle these challenges, a group multi-scale attention network (GMA-Net) was proposed for rubber leaf disease image recognition. The key idea of our method is to develop a group multi-scale dilated convolution (GMDC) module for multi-scale feature extraction as well as a cross-scale attention feature fusion (CAFF) module for multi-scale attention feature fusion. Specifically, the model uses a group convolution structure to reduce model parameters and provide multiple branches and then embeds multiple dilated convolutions to improve the model’s adaptability to the scale variability of disease spots. Furthermore, the CAFF module is further designed to drive the network to learn the attentional features of multi-scale diseases and strengthen the disease features fusion at different scales. In this article, a dataset of rubber leaf diseases was constructed, including 2,788 images of four rubber leaf diseases and healthy leaves. Experimental results show that the accuracy of the model is 98.06%, which was better than other state-of-the-art approaches. Moreover, the model parameters of GMA-Net are only 0.65 M, and the model size is only 5.62 MB. Compared with MobileNetV1, V2, and ShuffleNetV1, V2 lightweight models, the model parameters and size are reduced by more than half, but the recognition accuracy is also improved by 3.86–6.1%. In addition, to verify the robustness of this model, we have also verified it on the PlantVillage public dataset. The experimental results show that the recognition accuracy of our proposed model is 99.43% on the PlantVillage dataset, which is also better than other state-of-the-art approaches. The effectiveness of the proposed method is verified, and it can be used for plant disease recognition.

An improved lightweight network (Improved YOLOv5s) was proposed based on YOLOv5s in this study to realise all-weather detection of dragon fruit in a complex orchard environment. A ghost module was introduced in the original YOLOv5s to realise the lightweight of the model. The coordinate attention mechanism was joined to make the model accurately locate and identify the dense dragon fruits. A bidirectional feature pyramid network was built to improve the detection effect of dragon fruit at different scales. SIoU loss function was adopted to improve the convergence speed during model training. The improved YOLOv5s model was used to detect a dragon fruit dataset collected in the natural environment. Results showed that the mean average precision (mAP), precision (P) and recall (R) of the model was 97.4%, 96.4% and 95.2%, respectively. The model size, parameters (Params) and floating-point operations (FLOPs) were 11.5 MB, 5.2 M and 11.4 G, respectively. Compared with the original YOLOv5s network, the model size, Params and FLOPs of the improved model was reduced by 20.6%, 18.75% and 27.8%, respectively. Meanwhile, the mAP of the improved model was improved by 1.1%. The results prove that the improved model had a more lightweight structure and better detection performance. Moreover, the average precision (AP) of the improved YOLOv5s for dragon fruit under the front light, back light, side light, cloudy day and night was 99.5%, 97.3%, 98.5%, 95.5% and 96.1%, respectively. The detection performance met the requirements of all-weather detection of dragon fruit and the improved model had good robustness. This study provides a theoretical basis and technical support for fruit monitoring based on unmanned aerial vehicle technology and intelligent picking based on picking robot technology.