Effective maize and weed detection plays an important role in farmland management, which helps to improve yield and save herbicide resources. Due to their convenience and high resolution, Unmanned Aerial Vehicles (UAVs) are widely used in weed detection. However, there are some challenging problems in weed detection: (i) the cost of labeling is high, the image contains many plants, and annotation of the image is time-consuming and labor-intensive; (ii) the number of maize is much larger than the number of weed in the field, and this imbalance of samples leads to decreased recognition accuracy; and (iii) maize and weed have similar colors, textures, and shapes, which are difficult to identify when an UAV flies at a comparatively high altitude. To solve these problems, we propose a new weed detection framework in this paper. First, to balance the samples and reduce the cost of labeling, a lightweight model YOLOv4-Tiny was exploited to detect and mask the maize rows so that it was only necessary to label weeds on the masked image. Second, the improved YOLOv4 was used as a weed detection model. We introduced the Meta-ACON activation function, added the Convolutional Block Attention Module (CBAM), and replaced the Non-Maximum Suppression (NMS) with Soft Non-Maximum Suppression (Soft-NMS). Moreover, the distributions and counts of weeds were analyzed, which was useful for variable herbicide spraying. The results showed that the total number of labels for 1000 images decrease by half, from 33,572 to 17,126. The improved YOLOv4 had a mean average precision (mAP) of 86.89%.

Light traps have been widely used for automatic monitoring of pests in the field as an alternative to time-consuming and labor-intensive manual investigations. However, the scale variation, complex background and dense distribution of pests in light-trap images bring challenges to the rapid and accurate detection when utilizing vision technology. To overcome these challenges, in this paper, we put forward a lightweight pest detection model, AgriPest-YOLO, for achieving a well-balanced between efficiency, accuracy and model size for pest detection. Firstly, we propose a coordination and local attention (CLA) mechanism for obtaining richer and smoother pest features as well as reducing the interference of noise, especially for pests with complex backgrounds. Secondly, a novel grouping spatial pyramid pooling fast (GSPPF) is designed, which enriches the multi-scale representation of pest features via fusing multiple receptive fields of different scale features. Finally, soft-NMS is introduced in the prediction layer to optimize the final prediction results of overlapping pests. We evaluated the performance of our method on a large scale multi pest image dataset containing 24 classes and 25k images. Experimental results show that AgriPest-YOLO achieves end-to-end real-time pest detection with high accuracy, obtaining 71.3% mAP on the test dataset, outperforming the classical detection models (Faster RCNN, Cascade RCNN, Dynamic RCNN,YOLOX and YOLOv4) and lightweight detection models (Mobilenetv3-YOLOv4, YOLOv5 and YOLOv4-tiny), meanwhile our method demonstrates better balanced performance in terms of model size, detection speed and accuracy. The method has good accuracy and efficiency in detecting multi-class pests from light-trap images which is a key component of pest forecasting and intelligent pest monitoring technology.

Unmanned Aerial Vehicle (UAV) spray has been used for efficient and adaptive pesticide applications with its low costs. However, droplet drift is the main problem for UAV spray and will induce pesticide waste and safety concerns. Droplet size and deposition distribution are both highly related to droplet drift and spray effect, which are determined by the nozzle. Therefore, it is necessary to propose an evaluating method for a specific UAV spray nozzles. In this paper, four machine learning methods (REGRESS, least squares support vector machines (LS-SVM), extreme learning machine, and radial basis function neural network (RBFNN)) were applied for quantitatively evaluating one type of UAV spray nozzle (TEEJET XR110015VS), and the case of twin nozzles was investigated. The results showed REGRESS and LS-SVM are good candidates for droplet size evaluation with the coefficient of determination in the calibration set above 0.9 and root means square errors of the prediction set around 2 µm. RBFNN achieved the best performance for the evaluation of deposition distribution and showed its potential for determining the droplet size of overlapping area. Overall, this study proved the accuracy and efficiency of using the machine learning method for UAV spray nozzle evaluation. Additionally, the study demonstrated the feasibility of using machine learning model to predict the droplet size in the overlapping area of twin nozzles.

In recent years, more and more deep neural network methods have been used in the forecasting research of multivariate time series. Comparing to the traditional methods such as autoregressive models, methods based on neural networks have achieved superior results. However, the sequence data comes from all aspects, and the data contains long-term and short-term models, which is not a small challenge for data prediction research. We builds a model based on a deep neural network, and uses a convolutional network and a recurrent network in the long-term sequence data input and short-term sequence data input of the model. Convolutional networks are mainly used to extract short-term patterns in sequence data, and recurrent networks are mainly used to extract long-term patterns in sequence data. In addition, in order to solve the problem that the output of the neural network is not sensitive to the change of the input scale, we also added an autoregressive network to the model. When constructing the input of the model, we use the corresponding period characteristics to construct the two input of the model for different datasets: long-term historical data and short-term historical data. Our model has achieved better results than traditional prediction models on four public data sets: out of 32 indicators in 8 methods, 24 optimal results have been achieved.

In precision agriculture, effective monitoring of corn pest regions is crucial to developing early scientific prevention strategies and reducing yield losses. However, complex backgrounds and small objects in real farmland bring challenges to accurate detection. In this paper, we propose an improved model based on YOLOv4 that uses contextual information and attention mechanism. Firstly, a context priming module with simple architecture is designed, where effective features of different layers are fused as additional context features to augment pest region feature representation. Secondly, we propose a multi-scale mixed attention mechanism (MSMAM) with more focus on pest regions and reduction of noise interference. Finally, the mixed attention feature-fusion module (MAFF) with MSMAM as the kernel is applied to selectively fuse effective information from additional features of different scales and alleviate the inconsistencies in their fusion. Experimental results show that the improved model performs better in different growth cycles and backgrounds of corn, such as corn in vegetative 12th, the vegetative tasseling stage, and the overall dataset. Compared with the baseline model (YOLOv4), our model achieves better average precision (AP) by 6.23%, 6.08%, and 7.2%, respectively. In addition, several comparative experiments were conducted on datasets with different corn growth cycles and backgrounds, and the results verified the effectiveness and usability of the proposed method for such tasks, providing technical reference and theoretical research for the automatic identification and control of pests.