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.

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.

Cropland extraction has great significance in crop area statistics, intelligent farm machinery operations, agricultural yield estimates, and so on. Semantic segmentation is widely applied to remote sensing image cropland extraction. Traditional semantic segmentation methods using convolutional networks result in a lack of contextual and boundary information when extracting large areas of cropland. In this paper, we propose a boundary enhancement segmentation network for cropland extraction in high-resolution remote sensing images (HBRNet). HBRNet uses Swin Transformer with the pyramidal hierarchy as the backbone to enhance the boundary details while obtaining context. We separate the boundary features and body features from the low-level features, and then perform a boundary detail enhancement module (BDE) on the high-level features. Endeavoring to fuse the boundary features and body features, the module for interaction between boundary information and body information (IBBM) is proposed. We select remote sensing images containing large-scale cropland in Yizheng City, Jiangsu Province as the Agricultural dataset for cropland extraction. Our algorithm is applied to the Agriculture dataset to extract cropland with mIoU of 79.61%, OA of 89.4%, and IoU of 84.59% for cropland. In addition, we conduct experiments on the DeepGlobe, which focuses on the rural areas and has a diversity of cropland cover types. The experimental results indicate that HBRNet improves the segmentation performance of the cropland.

Effectively monitoring pest-infested areas by computer vision is essential in precision agriculture in order to minimize yield losses and create early scientific preventative solutions. However, the scale variation, complex background, and dense distribution of pests bring challenges to accurate detection when utilizing vision technology. Simultaneously, supervised learning-based object detection heavily depends on abundant labeled data, which poses practical difficulties. To overcome these obstacles, in this paper, we put forward innovative semi-supervised pest detection, PestTeacher. The framework effectively mitigates the issues of confirmation bias and instability among detection results across different iterations. To address the issue of leakage caused by the weak features of pests, we propose the Spatial-aware Multi-Resolution Feature Extraction (SMFE) module. Furthermore, we introduce a Region Proposal Network (RPN) module with a cascading architecture. This module is specifically designed to generate higher-quality anchors, which are crucial for accurate object detection. We evaluated the performance of our method on two datasets: the corn borer dataset and the Pest24 dataset. The corn borer dataset encompasses data from various corn growth cycles, while the Pest24 dataset is a large-scale, multi-pest image dataset consisting of 24 classes and 25k images. Experimental results demonstrate that the enhanced model achieves approximately 80% effectiveness with only 20% of the training set supervised in both the corn borer dataset and Pest24 dataset. Compared to the baseline model SoftTeacher, our model improves mAP_@0.5 (mean Average Precision) at 7.3 compared to that of SoftTeacher at 4.6. This method offers theoretical research and technical references for automated pest identification and management.

In recent years, remote sensing analysis has gained significant attention in visual analysis applications, particularly in segmenting and recognizing remote sensing images. However, the existing research has predominantly focused on single-period RGB image analysis, thus overlooking the complexities of remote sensing image capture, especially in highly vegetated land parcels. In this paper, we provide a large-scale vegetation remote sensing (VRS) dataset and introduce the VRS-Seg task for multi-modal and multi-temporal vegetation segmentation. The VRS dataset incorporates diverse modalities and temporal variations, and its annotations are organized using the Vegetation Knowledge Graph (VKG), thereby providing detailed object attribute information. To address the VRS-Seg task, we introduce VRSFormer, a critical pipeline that integrates multi-temporal and multi-modal data fusion, geometric contour refinement, and category-level classification inference. The experimental results demonstrate the effectiveness and generalization capability of our approach. The availability of VRS and the VRS-Seg task paves the way for further research in multi-modal and multi-temporal vegetation segmentation in remote sensing imagery.