Monitoring maize emergence quality is crucial for predicting yield, guiding precise management, and enhancing agricultural productivity and sustainability. Previous studies have highlighted the significant potential of UAV-RGB images and deep learning algorithms in evaluating maize plant counting (PC), plant spacing (PS), emergence rate (ER), and emergence uniformity (EU), respectively. However, a predominant limitation in these studies is their reliance on detected rectangular bounding boxes (RBB) and the associated geometric centers for quantifying emergence-related parameters. This approach tends to falter when confronted with the irregular growth orientations and diverse morphological attributes of maize plants, thereby compromising the accuracy and robustness of the estimations. To address this issue, this study builds a high-quality UAV-RGB dataset covering the V2 to V4 growth stages of maize seedlings and proposes a novel multi-task learning approach based on our YOLO11-Mamba framework. This methodology is committed to accurately detecting maize seedlings with oriented bounding boxes (OBB) and precisely pinpointing their centroids with key points (KP). Meanwhile, the Mamba Attention (MA) module, which combines a structured spatial model (SSM) and an independent spatial attention mechanism, is conducive to enhancing the state-of-the-art (SOTA) YOLO11′s adaptability to local features and global dependencies. The results indicate that multi-task YOLO11-Mamba outperforms YOLO11 in detecting maize seedlings, achieving a 2.1% improvement in OBB's AP50 and a 2.9% promotion in KP's mAP. Furthermore, the R2 for estimated PC, ER, PS, and EU is 0.915, 0.915, 0.908, and 0.754, respectively, demonstrating impressive performance in estimating maize emergence quality. Finally, a whole-field mapping is conducted to comprehensively demonstrate PC, ER, PS, and EU under different growth cycles based on multi-task YOLO11-Mamba. This study provides a smart and practical framework for the precise monitoring and management of maize in the early seedling stage. The dataset and code will be open-sourced at https://www.github.com/AG-WDS/MSQE.

To address the challenges of slow response, low efficiency in manual field inspection, and frequent missed detection of lodging areas in traditional monitoring of wheat lodging disasters, this study proposes a drone-based wheat lodging inspection method leveraging an improved Mask-RT-DETR model and edge computing. Considering the complex characteristics of wheat lodging in aerial images-such as diverse stem bending angles, severe occlusion within plant populations, and complicated background interference-three key improvements are introduced to the Mask-RT-DETR model. First, a bottleneck convolutional kernel optimization module is designed, employing 1 x 1 channel compression and 3 x 3 depthwise separable convolutions to enhance the extraction of spectral features at stem fracture points. Second, a Cascaded Group-wise Attention (CGA) module is embedded into the Transformer decoder to strengthen the spatial correlation modeling of stem inclination angles and canopy density. By combining multi-head attention mechanisms with a cascaded group strategy, CGA reduces computational load while improving feature representation. Third, the localization loss function is upgraded to Focal-EIoU Loss (Focal Efficient Intersection over Union Loss), which, together with a dynamic sample matching strategy, enhances regression accuracy of lodging bounding boxes and reduces model parameters while preserving multi-scale feature fusion capability. A dataset is constructed using field imagery collected by a drone platform equipped with high-resolution RGB and multispectral sensors. Experimental results show that, compared to the original model, the improved model achieves a 6.7 percentage point increase in precision and reaches a detection speed of 63.2 FPS. In cross-model comparative experiments, the proposed method outperforms Faster R-CNN, SSD, YOLO series models, and the original Mask-RT-DETR in precision (P), recall (R), mean average precision (mAP), and F1-score, achieving a lodging detection accuracy of 97.2 %. To evaluate edge computing performance, the model is deployed on a Jetson Orin Nano embedded device. After acceleration with TensorRT, it achieves 96.3 % accuracy, 96.5 % recall, and a real-time detection speed of 32.0 FPS, satisfying the requirements for real-time, high-accuracy field monitoring. The results demonstrate that the improved model maintains a lightweight architecture while significantly enhancing detection accuracy, providing an effective technical solution for drone-based wheat lodging inspection that balances detection performance and computational efficiency.

With the advancement of agricultural intelligence, dairy-cow farming has become a significant industry, and the application of computer vision technology in the automated monitoring of dairy cows has also attracted much attention. However, most of the images in the conventional detection dataset are high-quality images under normal lighting, which makes object detection very challenging in low-light environments at night. Therefore, this study proposed a night-time detection framework for cows based on an improved lightweight Zero-DCE (Zero-Reference Deep Curve Estimation) image enhancement network for low-light images. Firstly, the original feature extraction network of Zero-DCE was redesigned with an upsampling structure to reduce the influence of noise. Secondly, a self-attention gating mechanism was introduced in the skip connections of the Zero-DCE to enhance the network’s attention to the cow area. Then, an improved kernel selection module was introduced in the feature fusion stage to adaptively adjust the size of the receptive field. Finally, a depthwise separable convolution was used to replace the standard convolution of Zero-DCE, and an Attentive Convolutional Transformer (ACT) module was used to replace the iterative approach in Zero-DCE, which further reduced the computational complexity of the network and speeded up the inference. Four different object-detection models, YOLOv5, CenterNet, EfficientDet, and YOLOv7-tiny, were selected to evaluate the performance of the improved network and were tested on the night-time dataset before and after enhancement. Experimental results demonstrate that the detection performance of all models is significantly improved when processing night-time image samples through the enhanced Zero-DCE model. In summary, the improved lightweight Zero-DCE low-light enhancement network proposed in this study shows excellent performance, which can ensure that various object-detection models can quickly and accurately identify targets in low-light environments at night and are suitable for real-time monitoring in actual production environments.

Traffic sign recognition is an integral part of driver assistance systems play a crucial role in enhancing road safety. Due to a large number of challenging targets, such as occlusion, distortion, and small targets in actual scenes, existing methods still have bottlenecks in the accuracy of detection and recognition. Therefore, this paper proposes a real-time traffic sign recognition model based on scale sequence features (SSFs) and high-order spatial interactions (HOSIs) on the basis of YOLOv5. This model extracted scale-invariant SSF using a high-dimensional convolution on the underlying feature map to improve the detection effect of multi-scale targets. At the same time, recursive gated convolution modules are integrated into the feature pyramid network, expanding the interactions to arbitrary order and providing richer feature information for high-order convolutions. In addition, a cross-stage partial (CSP) structure is incorporated into the spatial pooling pyramid, which improves the structure’s performance without introducing excessive computational complexity. The experimental results show that the proposed model achieves 95.5

Seed vigor is a primary determinant of seed quality. Since the traditional methods detecting the seed vigor are time-consuming and costly, hyperspectral imaging technology in this study was used to develop a method that was rapid and nondestructive to detect the vigor of vegetable seeds. Hyperspectral images of two kinds of vegetable seeds, broad beans and hyacinth beans, were collected by measuring spectral reflectance from 400 to 1000 nm. The raw spectral data were first preprocessed with Savitzky-Golay (SG) smoothing and multiplicative scatter correction (MSC). And then, principal component analysis (PCA) and uninformative variable elimination (UVE) were carried out to select optimal wavelengths, and image features were also extracted simultaneously from RGB image that combined the central wavelengths at 660, 560 and 480 nm. Finally, support vector machines (SVM) and random forest (RF) model were employed to build the classification models based on spectral data, image data and the integrated data from both spectral and image data. The results showed that the SVM model had better classification performance and its accuracy achieved 83 to 91 %, when the spectral data were selected through UVE and combined with the image data. An integration of both spectral data and image data can improve the accuracy of the model compared to those used alone.

Aiming at the problem of low efficiency of manual counting of wheat scab spore microscopic images, we propose a counting algorithm for adhesion of wheat scabs spore based on contour angle-to-distance ratio. Specifically, the algorithm first improves the microscopic image quality of wheat scab spores utilizing Mean Shift and eliminates the influence of impurities and noise. Then, the adhesion of spores were screened by the Sobel operator and shape feature factor, and all adhesion spores were segmented according to the angle-to-distance ratio of spore contour, and finally, he spore count was completed. The experimental results show that this algorithm achieves an average accuracy of 93.1% in 313 wheat scab spore microscopic images, which is 7.9% higher than the traditional machine learning clustering algorithm. This algorithm can quickly and accurately calculate the number of wheat scab spores and can provide technical support for disease prevention and food security.

Fast and accurate assessment of wheat lodging holds significant importance for disaster prevention and agricultural insurance claim settlement. However, lodging detection is often influenced by the spatial and temporal heterogeneity of fields, leading to inconsistent lodging features in images captured at different times and locations. This inconsistency poses challenges for evaluating model performance and obtaining consistent results. In this study, we proposed a comprehensive lodging area detection model performance evaluation method for multi-year and multi-phenological periods. Three evaluation indicators-accuracy, potential, and stability-were introduced to assess model performance from different perspectives. Additionally, a weighted method is employed to combine the results of multiple experiments. To evaluate the performance of lodging area segmentation in wheat fields, we selected three feature adaptive models (CBAM-unet, SE-unet, and Swintransformer) along with the Unet model. The experimental results are as follows: (1) Swin-transformer achieved the highest weighted average accuracy (Acccp) of 83.53% among the four models evaluated. (2) Swin-transformer exhibited the highest upper limit of segmentation accuracy, reaching 97.98%. However, its average accuracy in the prediction experiment was 85% of the upper limit, suggesting potential for optimization. (3) CBAM-unet demonstrated the lowest overall weighted segmentation accuracy variance (35.92) compared to the other three models, indicating higher stability. Based on the experimental results it can be seen that our proposed method and model can address the challenge of evaluating lodging area detection models under spatial and temporal heterogeneity.

The utilization of unmanned aerial vehicle (UAV)-based imaging systems offers precise detection of plant diseases and aids in decision-making regarding fungicide applications to optimize disease control. This study employed a twin-lens multispectral camera mounted on a low-altitude UAV to capture imagery data from rice field plots that were treated with different fungicides. The objectives of this study were to assess the severity of narrow brown leaf spot (NBLS) caused by Cercospora janseana and to evaluate the efficacy of fungicide control. Eighteen color features and vegetation indices were extracted from RGB images, while nine color features and vegetation indices were extracted from multispectral images. Through correlation analysis, four spectral features, namely Lab-a, ExGR, VDVI, and g, were found to exhibit high correlations with disease severity. Specifically, RGB imagery had greater correlation coefficients (exceeding 0.95) for both ExGR and Lab-a features compared to multispectral imagery. A multifeature inversion modeling approach was employed, using support vector regression with the top four spectral features to predict NBLS severity. The results indicated R2 values were above 0.93 for all support vector regressions. Furthermore, the efficacies of ten different fungicide treatments were evaluated, with UAV imaging consistently aligning with ground truth rating data in terms of efficacy ranking. These results demonstrate the potential of UAV imagery for use as a valuable tool for NBLS detection and assessing fungicide efficacy, offering significant benefits in the management of NBLS, which is a globally important disease in rice.

The point cloud-based 3D model of forest helps to understand the growth and distribution pattern of trees, to improve the fine management of forestry resources. This paper describes the process of constructing a fine rubber forest growth model map based on 3D point clouds. Firstly, a multi-scale feature extraction module within the point cloud column is used to enhance the PointPillars learning capability. The Swin Transformer module is employed in the backbone to enrich the contextual semantics and acquire global features with the self-attention mechanism. All of the rubber trees are accurately identified and segmented to facilitate single-trunk localisation and feature extraction. Then, the structural parameters of the trunks calculated by RANSAC and IRTLS cylindrical fitting methods are compared separately. A growth model map of rubber trees is constructed. The experimental results show that the precision and recall of the target detection reach 0.9613 and 0.8754, respectively, better than the original network. The constructed rubber forest information map contains detailed and accurate trunk locations and key structural parameters, which are useful to optimise forestry resource management and guide the enhancement of mechanisation of rubber tapping.

Plant disease control has long been a critical issue in agricultural production and relies heavily on the identification of plant diseases, but traditional disease identification requires extensive experience. Most of the existing deep learning-based plant disease classification methods run on high-performance devices to meet the requirements for classification accuracy. However, agricultural applications have strict cost control and cannot be widely promoted. This paper presents a novel method for plant disease classification using a binary neural network with dual attention (DABNN), which can save computational resources and accelerate by using binary neural networks, and introduces a dual-attention mechanism to improve the accuracy of classification. To evaluate the effectiveness of our proposed approach, we conduct experiments on the PlantVillage dataset, which includes a range of diseases. The F1score and Accuracy of our method reach 99.39% and 99.4%, respectively. Meanwhile, compared to AlexNet and VGG16, the Computationalcomplexity of our method is reduced by 72.3% and 98.7%, respectively. The Paramssize of our algorithm is 5.4% of AlexNet and 2.3% of VGG16. The experimental results show that DABNN can identify various diseases effectively and accurately.

Rapid detection and identification of Fusarium germinate spores play a vital role in the early prediction and effective management of wheat scab disease. This study proposed an improved Yolov5-ECA-ASFF target detection algorithm that addressed the challenges of small size and precise localization of spore image targets. The algorithm incorporated the attention mechanism module (ECA-Net) and adaptive feature fusion mechanism (ASFF) into the feature pyramid structure of YOLO, effectively tackling issues related to small size, limited characteristics, and unclear attributes of F. germinate spores. The results demonstrate that the proposed model achieved an average recognition accuracy of 98.57% for F. graminearum spores, surpassing the original Yolov5s algorithm’s mAP value by 6.8%. The proposed method outperformed other mainstream target detection networks like Yolov4 and Faster-RCNN. It also exhibited excellent recognition outcomes in scenarios involving multiple targets and complex backgrounds, while maintaining model robustness even when faced with similar appearance, morphology, and color characteristics of various scab spores. In conclusion, this method accurately detected and identified wheat scab spores in the presence of a variety of mixed spores, providing crucial technical support for automated detection of wheat scab spores and early prediction of wheat scab outbreaks under complex field environments.

How to strike a balance between detection speed and recognition accuracy has become a major challenge in real-time object detection. In this research, the YOLOv5 (You Only Look Once version 5) model was lightweight and optimized to improve the detection speed and accuracy of the network. To prune the backbone and neck are to simplify the network structure and reduce the parameters. The lightweight structure of the C3 module was designed and incorporated into the attention mechanism to improve the feature extraction capability of the network. For the public traffic sign dataset, the label assignment strategy and the loss function of YOLOv5 were refined to alleviate the imbalance between positive and negative samples and to better compute the loss, resulting in more stable and efficient training. Compared with other mainstream single-stage models, it achieves a better trade-off between speed and accuracy. With only 0.85 M parameters, 91.9% of mAP (mean average precision) and 360 FPS (frames per second) were achieved, which were 16.26% mAP and 26.67 FPS higher than the conventional YOLOv5n, respectively. The performance of our lightweight model in traffic sign detection far exceeds the most advanced achievements.

Soybean is an important food and oil crop in the world. It is of great significance to statics the planting scale accurately for optimizing the crop planting structure and world food security. The technology of accurately extracting the area of soybean planting areas at the field scale using UAV images combined with deep learning algorithms is important for the application. In this study, firstly, RGB images and multispectral images (RGN) were acquired simultaneously by the quad-rotor UAV DJ-Phantom4 Pro at a flying height of 200 m. And the features were extracted from the RGB and RGN images. Further, the fusion image of RGB + VIs and the fusion image of RGN + VIs were obtained by concatenating the band reflectivity of the original image with the calculated Vegetation Index (VI). Then, the soybean planting area was segmented from the feature fusion images by U-Net. And the accuracy of the two sensors was compared. The results showed that the Kappa coefficients obtained based on RGB image, RGN image, CME(the combination of CIVE, MExG, and ExGR), ODR(the combination of OSAVI, DVI, and RDVI), RGB + CME(the combination of RGB and CME), and RGN + ODR(the combination of RGN and ODR) were 0.8806, 0.9327, 0.8437, 0.9330, 0.9420, and 0.9238, respectively. The Kappa coefficient of the combination of the original image and the vegetation index was higher than the original image, indicating that the vegetation index calculation was beneficial to improving the soybean recognition accuracy of the U-Net model. Among them, the precision of the soybean planting area extracted from RGB + CME was the highest, and the Kappa coefficient was 0.9420. Finally, the soybean recognition accuracy of U-Net was compared with the results of DeepLabv3+, Random Forest, and Support Vector Machine. The accuracy of U-Net was the best. It can be concluded that this research proposed the method that was using U-Net trained the fusion image of the original image and vegetation index feature fusion image obtained by the UAV platform, which can effectively segment soybean planting areas. The conclusion of this work provided important technical support for farm level, family cooperatives, and other business entities to manage finely soybean planting and production at low cost.

Object segmentation in deep learning has been recently used for the detection of Fusarium head blight (FHB), a worldwide disease in wheat. Such method, however, cannot detect the disease with high accuracy and is difficult to be used in labelling annotation. However, object detection network can solve the above problem. The object detection network has high detection accuracy and easy for labeling. Yolov5 is an advanced object detection network, but it can’t detect the neighboring wheat ears well. So in this study, a novel method was developed based on object detection network, feature extraction and classifier to overcome these disadvantages. We combined Yolov5 object detection network with distance intersection over union non maximum suppression (DIOU-NMS) to form an improved Yolov5 object detection network. The improved YoloV5 object detection network was employed to detect and record wheat ears in images collected from field plots at two locations over 2 years. Pre-segmentation was conducted for single individual wheat ear images using threshold segmentation; HSV and CMYK color spaces were used as the baseline in each wheat ear image for extracting comprehensive color feature (CCF). The Res-Net network was used for extracting each wheat ear’s high dimension feature (HDF). CCF and HDF were then merged as the comprehensive feature (CF) of each single wheat image. The random forest was used to classify wheat ear images into healthy wheat ears and diseased wheat ears by CF and then calculate the ratio of diseased wheat ears to total wheat ears as the level of damage caused by FHB. The results of performance evaluation of the proposed method in two different locations and years demonstrate its strong robustness in both time and spatial domains to effectively detect the levels of damage caused by FHB under the complex field background conditions. The average detection accuracy and detection time were 90.67% and 0.73 ms, respectively. The average accuracies of counting total wheat ears and diseased wheat ears were 96.16% and 81.66%, respectively. The improved YoloV5 method developed from this study can be used as a quick, efficient, and convenient tool for assessment of the levels of damage caused by FHB in wheat under field conditions.

The accurate extraction of wheat lodging areas can provide important technical support for post-disaster yield loss assessment and lodging-resistant wheat breeding. At present, wheat lodging assessment is facing the contradiction between timeliness and accuracy, and there is also a lack of effective lodging extraction methods. This study aims to propose a wheat lodging assessment method applicable to multiple Unmanned Aerial Vehicle (UAV) flight heights. The quadrotor UAV was used to collect high-definition images of wheat canopy at the grain filling and maturity stages, and the Unet network was evaluated and improved by introducing the Involution operator and Dense block module. The performance of the Improved_Unet was determined using the data collected from different flight heights, and the robustness of the improved network was verified with data from different years in two different geographical locations. The results of analyses show that (1) the Improved_Unet network was better than other networks (Segnet, Unet and DeeplabV3+ networks) evaluated in terms of segmentation accuracy, with the average improvement of each indicator being 3% and the maximum average improvement being 6%. The Improved_Unet network was more effective in extracting wheat lodging areas at the maturity stage. The four evaluation indicators, Precision, Dice, Recall, and Accuracy, were all the highest, which were 0.907, 0.929, 0.884, and 0.933, respectively; (2) the Improved_Unet network had the strongest robustness, and its Precision, Dice, Recall, and Accuracy reached 0.851, 0.892, 0.844, and 0.885, respectively, at the verification stage of using lodging data from other wheat production areas; and (3) the flight height had an influence on the lodging segmentation accuracy. The results of verification show that the 20-m flight height performed the best among the flight heights of 20, 40, 80 and 120 m evaluated, and the segmentation accuracy decreased with the increase of the flight height. The Precision, Dice, Recall, and Accuracy of the Improved_Unet changed from 0.907 to 0.845, from 0.929 to 0.864, from 0.884 to 0.841, and from 0.933 to 0.881, respectively. The results demonstrate the improved ability of the Improved-Unet to extract wheat lodging features. The proposed deep learning network can effectively extract the areas of wheat lodging, and the different height fusion models developed from this study can provide a more comprehensive reference for the automatic extraction of wheat lodging.

为探讨无人机多源影像特征融合估测作物叶面积指数的能力,该研究以冬小麦为研究对象,利用多旋翼无人机搭载高清数码相机和UHD185成像光谱仪获取研究区冬小麦关键生育期(扬花期、灌浆期)的可见光和高光谱影像.综合考虑可见光、高光谱影像特征与冬小麦叶面积指数的相关性及影像特征重要性进行特征筛选,然后,以可见光植被指数、纹理特征、可见光植被指数+纹理特征、高光谱波段、高光谱植被指数及高光谱波段+植被指数分别作为输入变量构建多元线性回归、支持向量回归和随机森林回归的叶面积指数估测模型(单传感器数据源);以优选的两种影像特征结合支持向量回归、随机森林回归构建叶面积指数估测模型(两种传感器数据源),比较分析单源与多源影像特征监测冬小麦叶面积指数的性能.进一步地,考虑到小区土壤空间异质性会影响冬小麦叶面积指数估测结果,该研究探讨了不同影像采样面积下基于单源遥感数据构建的小麦叶面积指数估测模型精度.研究结果表明:在扬花期和灌浆期,使用两种影像优选特征构建的随机森林回归估测模型精度最佳,验证集决定系数分别为0.733和0.929,均方根误差为0.193和0.118.可见光影像采样面积分别为30％和50％,高光谱影像采样面积为65％时,基于单源影像特征构建的随机森林回归估测模型在扬花期和灌浆期效果最好.综上,该研究结果可为无人机遥感监测作物生理参数提供有价值的依据和参考.

Graph Neural Networks have been recently applied to 3D object detection in point clouds. The works, however, have the problem of insufficient detection accuracy for small objects and objects in complex backgrounds. Towards this end, a graph attention feature pyramid network is proposed for 3D point clouds object detection. Specifically, the network constructs a near-neighbors graph in a point cloud which is downsampled; and then, a graph attention feature pyramid network is designed to extract features of the point cloud at different levels; finally, a feature fusion module is employed to fuse the features before point classification and object detection. Compared with the benchmark network Point-GNN on the KITTI dataset, the detection accuracy of cars in complex scenes is improved by 2.53%, and the detection accuracy of pedestrian and cyclist categories in moderate scenes and complex scenes is improved by 5.17%. and 3.62%. The experiments show that the designed method is more effective for the detection of small objects and objects in complex backgrounds in 3D object detection.

The current driverless technology has great security risks. The traffic sign recognition technology equipped in the roof sensor is easily affected by light and occlusion, resulting in poor detection effect. To solve this problem, this paper proposes a traffic sign recognition model based on improved yolov4. According to the characteristics of weighted bidirectional feature pyramid network, a cross layer connection is added to the traditional yolov4 network, and the weight of the transferred feature map is adjusted in the process of feature fusion. This method can enhance the feature extraction ability of the network. The experimental results show that the proposed method can detect more types of traffic signs, the mAP of TT100K dataset reaches 87.85%, which is 1.03% higher than the traditional yolov4 algorithm, and the frame processing speed reaches 31.25fps, which meets the requirements of real-time detection.

The existing identification of wheat lodging based on unmanned aerial vehicle (UAV) is significantly dependent on the artificial ground annotation method, which exhibits low annotation accuracy and strong subjectivity, thus resulting in a low degree of separation for the annotated lodging area and the non-lodging area. To solve the problem of insufficient applicability of traditional annotation research to agricultural images, especially wheat field lodging images, a lodging annotation method in the study based on semi-automatic image segmentation algorithm was proposed. Firstly, a total of 101 farmlands with lodging occurred during the flowering, filling and mature period of wheat in 2019 and 2021 were segmented as the research objects. The above images were respectively changed into RGB and HSV color space and converted into four vegetation indexes, including excess-green (ExG), green leaf index (VEG), normalized green-red difference index (NGRDI), as well as red-green ratio index (GRRI). Secondly, lodging regions were extracted and modified from the image in accordance with color features. Lastly, the JM distance of lodging and non-lodging areas served as an index to examine the effect of image annotation for data analysis and evaluation of segmentation accuracy. The result of the experiment indicated that there was a very significant difference between the JM distance based on the annotation method proposed in this study and the result based on manual annotation. GRRI and ExG were the most suitable features for image annotation. The method proposed in this study had high generalization performance for the images captured in the three fertility periods in 2019 and 2021, and the images with poor image annotation results took up a small proportion. In brief, the lodging area annotation method proposed in this study increases the annotation accuracy by extracting lodging areas using a semi-automatic image segmentation algorithm. The proposed method outperforms the manual annotation method. Keywords: semi-automatic image annotation, wheat lodging, unmanned aerial vehicle, image processing, feature separability DOI: 10.33440/j.ijpaa.20220501.193 Citation: Zhang G, He F M, Yan H F, Xu H F, Pan Z G, Yang X Y, Zhang D Y, Li W F. Methodology of wheat lodging annotation based on semi-automatic image segmentation algorithm. Int J Precis Agric Aviat, 2022; 5(1): 47–53.