Artificial Intelligence in Agriculture最新文献_第5页

Recognizing and localizing chicken behaviors in videos based on spatiotemporal feature learning 基于时空特征学习的视频鸡行为识别与定位

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-21 DOI: 10.1016/j.aiia.2025.06.006

Yilei Hu , Jinyang Xu , Zhichao Gou , Di Cui

Timely acquisition of chicken behavioral information is crucial for assessing chicken health status and production performance. Video-based behavior recognition has emerged as a primary technique for obtaining such information due to its accuracy and robustness. Video-based models generally predict a single behavior from a single video segment of a fixed duration. However, during periods of high activity in poultry, behavior transition may occur within a video segment, and existing models often fail to capture such transitions effectively. This limitation highlights the insufficient temporal resolution of video-based behavior recognition models. This study presents a chicken behavior recognition and localization model, CBLFormer, which is based on spatiotemporal feature learning. The model was designed to recognize behaviors that occur before and after transitions in video segments and to localize the corresponding time interval for each behavior. An improved transformer block, the cascade encoder-decoder network (CEDNet), a transformer-based head, and weighted distance intersection over union (WDIoU) loss were integrated into CBLFormer to enhance the model's ability to distinguish between different behavior categories and locate behavior boundaries. For the training and testing of CBLFormer, a dataset was created by collecting videos from 320 chickens across different ages and rearing densities. The results showed that CBLFormer achieved a [email protected]:0.95 of 98.34 % on the test set. The integration of CEDNet contributed the most to the performance improvement of CBLFormer. The visualization results confirmed that the model effectively captured the behavioral boundaries of chickens and correctly recognized behavior categories. The transfer learning results demonstrated that the model is applicable to chicken behavior recognition and localization tasks in real-world poultry farms. The proposed method handles cases where poultry behavior transitions occur within the video segment and improves the temporal resolution of video-based behavior recognition models.

及时获取鸡的行为信息对评估鸡的健康状况和生产性能至关重要。基于视频的行为识别由于其准确性和鲁棒性而成为获取此类信息的主要技术。基于视频的模型通常从固定时长的单个视频片段中预测单个行为。然而，在家禽的高活动期间，行为转变可能发生在视频片段中，现有模型通常无法有效捕捉这种转变。这一限制突出了基于视频的行为识别模型的时间分辨率不足。提出了一种基于时空特征学习的鸡行为识别与定位模型CBLFormer。该模型旨在识别视频片段中过渡前后发生的行为，并为每个行为定位相应的时间间隔。将改进的变压器块、级联编码器-解码器网络（CEDNet）、基于变压器的磁头和加权距离交联（WDIoU）损失集成到CBLFormer中，以增强模型区分不同行为类别和定位行为边界的能力。为了训练和测试CBLFormer，通过收集320只鸡不同年龄和饲养密度的视频，创建了一个数据集。结果表明，CBLFormer在98.34%的测试集中实现了[email protected]:0.95。集成CEDNet对CBLFormer的性能提升贡献最大。可视化结果证实，该模型有效捕获了鸡的行为边界，正确识别了鸡的行为类别。迁移学习结果表明，该模型适用于现实家禽养殖场中鸡的行为识别和定位任务。该方法处理了家禽行为在视频片段内发生转变的情况，并提高了基于视频的行为识别模型的时间分辨率。

{"title":"Recognizing and localizing chicken behaviors in videos based on spatiotemporal feature learning","authors":"Yilei Hu , Jinyang Xu , Zhichao Gou , Di Cui","doi":"10.1016/j.aiia.2025.06.006","DOIUrl":"10.1016/j.aiia.2025.06.006","url":null,"abstract":"<div><div>Timely acquisition of chicken behavioral information is crucial for assessing chicken health status and production performance. Video-based behavior recognition has emerged as a primary technique for obtaining such information due to its accuracy and robustness. Video-based models generally predict a single behavior from a single video segment of a fixed duration. However, during periods of high activity in poultry, behavior transition may occur within a video segment, and existing models often fail to capture such transitions effectively. This limitation highlights the insufficient temporal resolution of video-based behavior recognition models. This study presents a chicken behavior recognition and localization model, CBLFormer, which is based on spatiotemporal feature learning. The model was designed to recognize behaviors that occur before and after transitions in video segments and to localize the corresponding time interval for each behavior. An improved transformer block, the cascade encoder-decoder network (CEDNet), a transformer-based head, and weighted distance intersection over union (WDIoU) loss were integrated into CBLFormer to enhance the model's ability to distinguish between different behavior categories and locate behavior boundaries. For the training and testing of CBLFormer, a dataset was created by collecting videos from 320 chickens across different ages and rearing densities. The results showed that CBLFormer achieved a [email protected]:0.95 of 98.34 % on the test set. The integration of CEDNet contributed the most to the performance improvement of CBLFormer. The visualization results confirmed that the model effectively captured the behavioral boundaries of chickens and correctly recognized behavior categories. The transfer learning results demonstrated that the model is applicable to chicken behavior recognition and localization tasks in real-world poultry farms. The proposed method handles cases where poultry behavior transitions occur within the video segment and improves the temporal resolution of video-based behavior recognition models.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 816-828"},"PeriodicalIF":8.2,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FGPointKAN++ point cloud segmentation and adaptive key cutting plane recognition for cow body size measurement fgpointkan++点云分割和自适应关键切割平面识别的奶牛体型测量

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-18 DOI: 10.1016/j.aiia.2025.06.003

Guoyuan Zhou , Wenhao Ye , Sheng Li , Jian Zhao , Zhiwen Wang , Guoliang Li , Jiawei Li

Accurate and efficient body size measurement is essential for health assessment and production management in modern animal husbandry. In order to realize the segmentation of the point clouds at the pixel-level and the accurate calculation of body size for the dairy cows in different postures, a segmentation model (FGPointKAN++) and an adaptive key cutting plane recognition (AKCPR) model are developed. FGPointKAN++ introduces FGE module and KAN that enhance local feature extraction and geometric consistency, significantly improving dairy cow part segmentation accuracy. The AKCPR utilizes adaptive plane fitting and dynamic orientation calibration to optimize the key body size measurement. The dairy cow body size parameters are then calculated based on the plane geometry features. The experimental results show that mIoU scores of 82.92 % and 83.24 % for the dairy cow pixel-level point cloud segmentation results. The calculated Mean Absolute Percentage Errors (MAPE) of Wither Height (WH), Body Width (BW), Chest Circumference (CC) and Abdominal Circumference (AC) are 2.07 %, 3.56 %, 2.24 % and 1.42 %, respectively. This method enables precise segmentation and automatic body size measurement of dairy cows in various walking postures, showing considerable potential for practical applications. It provides technical support for unmanned, intelligent, and precision farming, thereby enhancing animal welfare and improving economic efficiency.

准确、高效的体尺测量是现代畜牧业健康评价和生产管理的基础。为了实现点云的像素级分割和奶牛不同姿态体型的精确计算，开发了fgpointkan++分割模型和自适应关键切割平面识别（AKCPR）模型。fgpointkan++引入FGE模块和KAN，增强局部特征提取和几何一致性，显著提高奶牛部位分割精度。AKCPR利用自适应平面拟合和动态方向校准来优化关键体尺寸测量。然后根据平面几何特征计算奶牛体型参数。实验结果表明，奶牛像素级点云分割的mIoU分数分别为82.92%和83.24%。臀高（WH）、体宽（BW）、胸围（CC）和腹围（AC）的平均绝对百分比误差（MAPE）分别为2.07%、3.56%、2.24%和1.42%。该方法可实现奶牛不同行走姿势的精确分割和体型自动测量，具有较大的实际应用潜力。为无人化、智能化、精准化农业提供技术支持，从而提高动物福利，提高经济效益。

{"title":"FGPointKAN++ point cloud segmentation and adaptive key cutting plane recognition for cow body size measurement","authors":"Guoyuan Zhou , Wenhao Ye , Sheng Li , Jian Zhao , Zhiwen Wang , Guoliang Li , Jiawei Li","doi":"10.1016/j.aiia.2025.06.003","DOIUrl":"10.1016/j.aiia.2025.06.003","url":null,"abstract":"<div><div>Accurate and efficient body size measurement is essential for health assessment and production management in modern animal husbandry. In order to realize the segmentation of the point clouds at the pixel-level and the accurate calculation of body size for the dairy cows in different postures, a segmentation model (FGPointKAN++) and an adaptive key cutting plane recognition (AKCPR) model are developed. FGPointKAN++ introduces FGE module and KAN that enhance local feature extraction and geometric consistency, significantly improving dairy cow part segmentation accuracy. The AKCPR utilizes adaptive plane fitting and dynamic orientation calibration to optimize the key body size measurement. The dairy cow body size parameters are then calculated based on the plane geometry features. The experimental results show that mIoU scores of 82.92 % and 83.24 % for the dairy cow pixel-level point cloud segmentation results. The calculated Mean Absolute Percentage Errors (MAPE) of Wither Height (WH), Body Width (BW), Chest Circumference (CC) and Abdominal Circumference (AC) are 2.07 %, 3.56 %, 2.24 % and 1.42 %, respectively. This method enables precise segmentation and automatic body size measurement of dairy cows in various walking postures, showing considerable potential for practical applications. It provides technical support for unmanned, intelligent, and precision farming, thereby enhancing animal welfare and improving economic efficiency.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 783-801"},"PeriodicalIF":8.2,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application of artificial intelligence in insect pest identification - A review 人工智能在害虫识别中的应用综述

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-16 DOI: 10.1016/j.aiia.2025.06.005

Sourav Chakrabarty , Chandan Kumar Deb , Sudeep Marwaha , Md. Ashraful Haque , Deeba Kamil , Raju Bheemanahalli , Pathour Rajendra Shashank

The increasing danger of insect pests to agriculture and ecosystems calls for quick, and precise diagnosis. Conventional techniques that depend on human observation and taxonomic knowledge are frequently labour-intensive and time-consuming. Incorporating artificial intelligence (AI) into detection has emerged as an effective approach in agriculture, including entomology. AI-based detection methods use machine learning, deep learning algorithms, and computer vision techniques to automate and improve the identification of insects. Deep learning algorithms, such as convolutional neural networks (CNNs), are primarily used for AI-powered insect pest identification by categorizing insects based on their visual features through image-based classification methodology. These methods have revolutionized insect identification by analyzing large databases of insect images and identifying distinct patterns and features linked to different species. AI-powered systems can improve insect pest identification by utilizing other data modalities. However, there are obstacles to overcome, such as the scarcity of high-quality labelled datasets and scalability and affordability issues. Despite these challenges, there is significant potential for AI-powered insect pest identification and pest management. Cooperation among researchers, practitioners, and policymakers is necessary to utilize AI in pest management fully. AI technology is transforming the field of entomology by enabling high-precision identification of insect pests, leading to more efficient and eco-friendly pest management strategies. This can enhance food safety and reduce the need for continuous insecticide spraying, ensuring the purity and safety of the food supply chains. This review updates AI-powered insect pest identification, covering its significance, methods, challenges, and prospects.

害虫对农业和生态系统的危害日益增加，需要快速和准确的诊断。依靠人类观察和分类学知识的传统技术往往是劳动密集型和耗时的。将人工智能（AI）纳入检测已成为包括昆虫学在内的农业领域的有效方法。基于人工智能的检测方法使用机器学习、深度学习算法和计算机视觉技术来自动化和改进昆虫的识别。深度学习算法，如卷积神经网络（cnn），主要用于人工智能驱动的害虫识别，通过基于图像的分类方法，根据昆虫的视觉特征对昆虫进行分类。这些方法通过分析大型昆虫图像数据库，识别与不同物种相关的不同模式和特征，彻底改变了昆虫鉴定。人工智能驱动的系统可以通过利用其他数据模式来改进害虫识别。然而，还有一些障碍需要克服，例如高质量标记数据集的稀缺性以及可扩展性和可负担性问题。尽管存在这些挑战，人工智能驱动的害虫识别和害虫管理仍有巨大的潜力。研究人员、从业者和政策制定者之间的合作是充分利用人工智能进行有害生物防治的必要条件。人工智能技术正在改变昆虫学领域，实现对害虫的高精度识别，从而实现更高效、更环保的害虫管理策略。这可以提高食品安全，减少连续喷洒杀虫剂的需要，确保食品供应链的纯度和安全性。本文综述了人工智能害虫识别的意义、方法、挑战和前景。

{"title":"Application of artificial intelligence in insect pest identification - A review","authors":"Sourav Chakrabarty , Chandan Kumar Deb , Sudeep Marwaha , Md. Ashraful Haque , Deeba Kamil , Raju Bheemanahalli , Pathour Rajendra Shashank","doi":"10.1016/j.aiia.2025.06.005","DOIUrl":"10.1016/j.aiia.2025.06.005","url":null,"abstract":"<div><div>The increasing danger of insect pests to agriculture and ecosystems calls for quick, and precise diagnosis. Conventional techniques that depend on human observation and taxonomic knowledge are frequently labour-intensive and time-consuming. Incorporating artificial intelligence (AI) into detection has emerged as an effective approach in agriculture, including entomology. AI-based detection methods use machine learning, deep learning algorithms, and computer vision techniques to automate and improve the identification of insects. Deep learning algorithms, such as convolutional neural networks (CNNs), are primarily used for AI-powered insect pest identification by categorizing insects based on their visual features through image-based classification methodology. These methods have revolutionized insect identification by analyzing large databases of insect images and identifying distinct patterns and features linked to different species. AI-powered systems can improve insect pest identification by utilizing other data modalities. However, there are obstacles to overcome, such as the scarcity of high-quality labelled datasets and scalability and affordability issues. Despite these challenges, there is significant potential for AI-powered insect pest identification and pest management. Cooperation among researchers, practitioners, and policymakers is necessary to utilize AI in pest management fully. AI technology is transforming the field of entomology by enabling high-precision identification of insect pests, leading to more efficient and eco-friendly pest management strategies. This can enhance food safety and reduce the need for continuous insecticide spraying, ensuring the purity and safety of the food supply chains. This review updates AI-powered insect pest identification, covering its significance, methods, challenges, and prospects.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 44-61"},"PeriodicalIF":12.4,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

EU-GAN: A root inpainting network for improving 2D soil-cultivated root phenotyping EU-GAN：改善二维土壤栽培根系表型的根染网络

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-11 DOI: 10.1016/j.aiia.2025.06.004

Shangyuan Xie , Jiawei Shi , Wen Li , Tao Luo , Weikun Li , Lingfeng Duan , Peng Song , Xiyan Yang , Baoqi Li , Wanneng Yang

Beyond its fundamental roles in nutrient uptake and plant anchorage, the root system critically influences crop development and stress tolerance. Rhizobox enables in situ and nondestructive phenotypic detection of roots in soil, serving as a cost-effective root imaging method. However, the opacity of the soil often results in intermittent gaps in the root images, which reduces the accuracy of the root phenotype calculations. We present a root inpainting method built upon Generative Adversarial Networks (GANs) architecture In addition, we built a hybrid root inpainting dataset (HRID) that contains 1206 cotton root images with real gaps and 7716 rice root images with generated gaps. Compared with computer simulation root images, our dataset provides real root system architecture (RSA) and root texture information. Our method avoids cropping during training by instead utilizing downsampled images to provide the overall root morphology. The model is trained using binary cross-entropy loss to distinguish between root and non-root pixels. Additionally, Dice loss is employed to mitigate the challenge of imbalanced data distribution Additionally, we remove the skip connections in U-Net and introduce an edge attention module (EAM) to capture more detailed information. Compared with other methods, our approach significantly improves the recall rate from 17.35 % to 35.75 % on the test dataset of 122 cotton root images, revealing improved inpainting capabilities. The trait error reduction rates (TERRs) for the root area, root length, convex hull area, and root depth are 76.07 %, 68.63 %, 48.64 %, and 88.28 %, respectively, enabling a substantial improvement in the accuracy of root phenotyping. The codes for the EU-GAN and the 8922 labeled images are open-access, which could be reused by researchers in other AI-related work. This method establishes a robust solution for root phenotyping, thereby increasing breeding program efficiency and advancing our understanding of root system dynamics.

根系除了在养分吸收和植物锚定方面的基本作用外，还对作物的发育和抗逆性具有重要影响。Rhizobox使土壤中根系的原位和无损表型检测成为一种经济有效的根系成像方法。然而，土壤的不透明性经常导致根系图像出现间歇性间隙，从而降低了根系表型计算的准确性。此外，我们建立了一个混合根绘制数据集（HRID），该数据集包含1206张具有真实间隙的棉花根图像和7716张具有生成间隙的水稻根图像。与计算机模拟根图像相比，我们的数据集提供了真实的根系统架构（RSA）和根纹理信息。我们的方法在训练过程中避免了裁剪，而是利用下采样图像来提供整体的根形态。该模型使用二元交叉熵损失进行训练，以区分根像素和非根像素。此外，我们还利用骰子损失来缓解数据分布不平衡的挑战。此外，我们还消除了U-Net中的跳过连接，并引入了边缘注意模块（EAM）来捕获更详细的信息。与其他方法相比，在122张棉花根图像的测试数据集上，我们的方法将召回率从17.35%显著提高到35.75%，表明我们的方法提高了涂漆能力。根面积、根长、凸包皮面积和根深的性状误差减少率分别为76.07%、68.63%、48.64%和88.28%，显著提高了根表型的准确性。EU-GAN和8922标记图像的代码是开放获取的，研究人员可以在其他人工智能相关工作中重复使用。该方法建立了一个可靠的根系表型分析解决方案，从而提高了育种计划的效率，并促进了我们对根系动力学的理解。

{"title":"EU-GAN: A root inpainting network for improving 2D soil-cultivated root phenotyping","authors":"Shangyuan Xie , Jiawei Shi , Wen Li , Tao Luo , Weikun Li , Lingfeng Duan , Peng Song , Xiyan Yang , Baoqi Li , Wanneng Yang","doi":"10.1016/j.aiia.2025.06.004","DOIUrl":"10.1016/j.aiia.2025.06.004","url":null,"abstract":"<div><div>Beyond its fundamental roles in nutrient uptake and plant anchorage, the root system critically influences crop development and stress tolerance. Rhizobox enables in situ and nondestructive phenotypic detection of roots in soil, serving as a cost-effective root imaging method. However, the opacity of the soil often results in intermittent gaps in the root images, which reduces the accuracy of the root phenotype calculations. We present a root inpainting method built upon Generative Adversarial Networks (GANs) architecture In addition, we built a hybrid root inpainting dataset (HRID) that contains 1206 cotton root images with real gaps and 7716 rice root images with generated gaps. Compared with computer simulation root images, our dataset provides real root system architecture (RSA) and root texture information. Our method avoids cropping during training by instead utilizing downsampled images to provide the overall root morphology. The model is trained using binary cross-entropy loss to distinguish between root and non-root pixels. Additionally, Dice loss is employed to mitigate the challenge of imbalanced data distribution Additionally, we remove the skip connections in U-Net and introduce an edge attention module (EAM) to capture more detailed information. Compared with other methods, our approach significantly improves the recall rate from 17.35 % to 35.75 % on the test dataset of 122 cotton root images, revealing improved inpainting capabilities. The trait error reduction rates (TERRs) for the root area, root length, convex hull area, and root depth are 76.07 %, 68.63 %, 48.64 %, and 88.28 %, respectively, enabling a substantial improvement in the accuracy of root phenotyping. The codes for the EU-GAN and the 8922 labeled images are open-access, which could be reused by researchers in other AI-related work. This method establishes a robust solution for root phenotyping, thereby increasing breeding program efficiency and advancing our understanding of root system dynamics.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 770-782"},"PeriodicalIF":8.2,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving accuracy and generalization in single kernel oil characteristics prediction in maize using NIR-HSI and a knowledge-injected spectral tabtransformer 利用NIR-HSI和知识注入谱表转换器提高玉米单粒油特性预测的准确性和泛化性

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-11 DOI: 10.1016/j.aiia.2025.05.007

Anran Song , Xinyu Guo , Weiliang Wen , Chuanyu Wang , Shenghao Gu , Xiaoqian Chen , Juan Wang , Chunjiang Zhao

Near-infrared spectroscopy hyperspectral imaging (NIR-HSI) is widely used for seed component prediction due to its non-destructive and rapid nature. However, existing models often suffer from limited generalization, particularly when trained on small datasets, and there is a lack of effective deep learning (DL) models for spectral data analysis. To address these challenges, we propose the Knowledge-Injected Spectral TabTransformer (KIT-Spectral TabTransformer), an innovative adaptation of the traditional TabTransformer specifically designed for maize seeds. By integrating domain-specific knowledge, this approach enhances model training efficiency and predictive accuracy while reducing reliance on large datasets. The generalization capability of the model was rigorously validated through ten-fold cross-validation (10-CV). Compared to traditional machine learning methods, the attention-based CNN (ACNNR), and the Oil Characteristics Predictor Transformer (OCP-Transformer), the KIT-Spectral TabTransformer demonstrated superior performance in oil mass prediction, achieving

R_{p}^{2}

= 0.9238 ± 0.0346, RMSE_p = 0.1746 ± 0.0401. For oil content,

R_{p}^{2}

= 0.9602 ± 0.0180 and RMSE_p = 0.5301 ± 0.1446 on a dataset with oil content ranging from 0.81 % to 13.07 %. On the independent validation set, our model achieved

R^{2}

values of 0.7820 and 0.7586, along with RPD values of 2.1420 and 2.0355 in the two tasks, highlighting its strong prediction capability and potential for real-world application. These findings offer a potential method and direction for single seed oil prediction and related crop component analysis.

近红外光谱高光谱成像（NIR-HSI）因其无损、快速等优点被广泛应用于种子成分预测。然而，现有模型通常泛化有限，特别是在小数据集上训练时，并且缺乏用于光谱数据分析的有效深度学习（DL）模型。为了解决这些挑战，我们提出了知识注入光谱TabTransformer (KIT-Spectral TabTransformer)，这是一种专门为玉米种子设计的传统TabTransformer的创新改编。通过集成领域特定知识，该方法提高了模型训练效率和预测准确性，同时减少了对大型数据集的依赖。通过10倍交叉验证（10-CV）严格验证了模型的泛化能力。与传统的机器学习方法、基于注意力的CNN （attention-based CNN， ACNNR）和油特性预测变压器（Oil characteristic Predictor Transformer, OCP-Transformer）相比，KIT-Spectral TabTransformer在油质量预测方面表现出更优异的性能，Rp2= 0.9238±0.0346,RMSEp = 0.1746±0.0401。在含油量为0.81% ~ 13.07%的数据集上，Rp2= 0.9602±0.0180,RMSEp = 0.5301±0.1446。在独立验证集上，我们的模型在两个任务中的R2值分别为0.7820和0.7586，RPD值分别为2.1420和2.0355，显示出了较强的预测能力和实际应用潜力。这些发现为单粒种子油脂预测及相关作物成分分析提供了潜在的方法和方向。

{"title":"Improving accuracy and generalization in single kernel oil characteristics prediction in maize using NIR-HSI and a knowledge-injected spectral tabtransformer","authors":"Anran Song , Xinyu Guo , Weiliang Wen , Chuanyu Wang , Shenghao Gu , Xiaoqian Chen , Juan Wang , Chunjiang Zhao","doi":"10.1016/j.aiia.2025.05.007","DOIUrl":"10.1016/j.aiia.2025.05.007","url":null,"abstract":"<div><div>Near-infrared spectroscopy hyperspectral imaging (NIR-HSI) is widely used for seed component prediction due to its non-destructive and rapid nature. However, existing models often suffer from limited generalization, particularly when trained on small datasets, and there is a lack of effective deep learning (DL) models for spectral data analysis. To address these challenges, we propose the Knowledge-Injected Spectral TabTransformer (KIT-Spectral TabTransformer), an innovative adaptation of the traditional TabTransformer specifically designed for maize seeds. By integrating domain-specific knowledge, this approach enhances model training efficiency and predictive accuracy while reducing reliance on large datasets. The generalization capability of the model was rigorously validated through ten-fold cross-validation (10-CV). Compared to traditional machine learning methods, the attention-based CNN (ACNNR), and the Oil Characteristics Predictor Transformer (OCP-Transformer), the KIT-Spectral TabTransformer demonstrated superior performance in oil mass prediction, achieving <span><math><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></math></span>= 0.9238 ± 0.0346, RMSE<sub>p</sub> = 0.1746 ± 0.0401. For oil content, <span><math><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></math></span>= 0.9602 ± 0.0180 and RMSE<sub>p</sub> = 0.5301 ± 0.1446 on a dataset with oil content ranging from 0.81 % to 13.07 %. On the independent validation set, our model achieved <span><math><msup><mi>R</mi><mn>2</mn></msup></math></span> values of 0.7820 and 0.7586, along with RPD values of 2.1420 and 2.0355 in the two tasks, highlighting its strong prediction capability and potential for real-world application. These findings offer a potential method and direction for single seed oil prediction and related crop component analysis.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 802-815"},"PeriodicalIF":8.2,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144470916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rapid detection and visualization of physiological signatures in cotton leaves under Verticillium wilt stress 黄萎病胁迫下棉花叶片生理特征的快速检测与可视化

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-06 DOI: 10.1016/j.aiia.2025.06.002

Na Wu , Pan Gao , Jie Wu , Yun Zhao , Xing Xu , Chu Zhang , Erik Alexandersson , Juan Yang , Qinlin Xiao , Yong He

Verticillium wilt poses a severe threat to cotton growth and significantly impacts cotton yield. It is of significant importance to detect Verticillium wilt stress in time. In this study, the effects of Verticillium wilt stress on the microstructure and physiological indicators (SOD, POD, CAT, MDA, Chl_a, Chl_b, Chl_ab, Car) of cotton leaves were investigated, and the feasibility of utilizing hyperspectral imaging to estimate physiological indicators of cotton leaves was explored. The results showed that Verticillium wilt stress-induced alterations in cotton leaf cell morphology, leading to the disruption and decomposition of chloroplasts and mitochondria. In addition, compared to healthy leaves, infected leaves exhibited significantly higher activities of SOD and POD, along with increased MDA amounts, while chlorophyll and carotenoid levels were notably reduced. Furthermore, rapid detection models for cotton physiological indicators were constructed, with the R_p of the optimal models ranging from 0.809 to 0.975. Based on these models, visual distribution maps of the physiological signatures across cotton leaves were created. These results indicated that the physiological phenotype of cotton leaves could be effectively detected by hyperspectral imaging, which could provide a solid theoretical basis for the rapid detection of Verticillium wilt stress.

黄萎病严重威胁棉花生长，对棉花产量有显著影响。及时检测黄萎病菌的胁迫具有重要意义。本研究研究了黄萎病胁迫对棉花叶片微观结构和生理指标（SOD、POD、CAT、MDA、Chla、Chlb、Chlab、Car）的影响，探讨了利用高光谱成像技术估测棉花叶片生理指标的可行性。结果表明，黄萎病胁迫诱导棉花叶片细胞形态发生改变，导致叶绿体和线粒体的破坏和分解。此外，与健康叶片相比，侵染叶片SOD和POD活性显著升高，MDA含量显著升高，叶绿素和类胡萝卜素含量显著降低。建立了棉花生理指标的快速检测模型，最佳模型的Rp范围为0.809 ~ 0.975。基于这些模型，建立了棉花叶片生理特征的视觉分布图。以上结果表明，利用高光谱成像技术可以有效检测棉花叶片的生理表型，为快速检测黄萎病胁迫提供了坚实的理论基础。

{"title":"Rapid detection and visualization of physiological signatures in cotton leaves under Verticillium wilt stress","authors":"Na Wu , Pan Gao , Jie Wu , Yun Zhao , Xing Xu , Chu Zhang , Erik Alexandersson , Juan Yang , Qinlin Xiao , Yong He","doi":"10.1016/j.aiia.2025.06.002","DOIUrl":"10.1016/j.aiia.2025.06.002","url":null,"abstract":"<div><div>Verticillium wilt poses a severe threat to cotton growth and significantly impacts cotton yield. It is of significant importance to detect Verticillium wilt stress in time. In this study, the effects of Verticillium wilt stress on the microstructure and physiological indicators (SOD, POD, CAT, MDA, Chl<sub>a</sub>, Chl<sub>b</sub>, Chl<sub>ab</sub>, Car) of cotton leaves were investigated, and the feasibility of utilizing hyperspectral imaging to estimate physiological indicators of cotton leaves was explored. The results showed that Verticillium wilt stress-induced alterations in cotton leaf cell morphology, leading to the disruption and decomposition of chloroplasts and mitochondria. In addition, compared to healthy leaves, infected leaves exhibited significantly higher activities of SOD and POD, along with increased MDA amounts, while chlorophyll and carotenoid levels were notably reduced. Furthermore, rapid detection models for cotton physiological indicators were constructed, with the <em>R</em><sub><em>p</em></sub> of the optimal models ranging from 0.809 to 0.975. Based on these models, visual distribution maps of the physiological signatures across cotton leaves were created. These results indicated that the physiological phenotype of cotton leaves could be effectively detected by hyperspectral imaging, which could provide a solid theoretical basis for the rapid detection of Verticillium wilt stress.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 757-769"},"PeriodicalIF":8.2,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-camera fusion and bird-eye view location mapping for deep learning-based cattle behavior monitoring 基于深度学习的牛行为监测的多摄像机融合和鸟瞰图定位

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-06 DOI: 10.1016/j.aiia.2025.06.001

Muhammad Fahad Nasir , Alvaro Fuentes , Shujie Han , Jiaqi Liu , Yongchae Jeong , Sook Yoon , Dong Sun Park

Cattle behavioral monitoring is an integral component of the modern infrastructure of the livestock industry. Ensuring cattle well-being requires precise observation, typically using wearable devices or surveillance cameras. Integrating deep learning into these systems enhances the monitoring of cattle behavior. However, challenges remain, such as occlusions, pose variations, and limited camera viewpoints, which hinder accurate detection and location mapping of individual cattle. To address these challenges, this paper proposes a multi-viewpoint surveillance system for indoor cattle barns, using footage from four cameras and deep learning-based models including action detection and pose estimation for behavior monitoring. The system accurately detects hierarchical behaviors across camera viewpoints. These results are fed into a Bird's Eye View (BEV) algorithm, producing precise cattle position maps in the barn. Despite complexities like overlapping and non-overlapping camera regions, our system, implemented on a real farm, ensures accurate cattle detection and BEV-based projections in real-time. Detailed experiments validate the system's efficiency, offering an end-to-end methodology for accurate behavior detection and location mapping of individual cattle using multi-camera data.

牛的行为监测是现代畜牧业基础设施的一个组成部分。确保牛的健康需要精确的观察，通常使用可穿戴设备或监控摄像头。将深度学习集成到这些系统中可以增强对牛行为的监控。然而，挑战仍然存在，如遮挡、姿势变化和摄像机视点有限，这些都阻碍了对单个牛的准确检测和定位。为了解决这些挑战，本文提出了一种用于室内牛棚的多视点监控系统，该系统使用来自四个摄像机的镜头和基于深度学习的模型，包括动作检测和姿态估计，用于行为监测。该系统准确地检测跨摄像机视点的分层行为。这些结果被输入到鸟瞰（BEV）算法中，在谷仓中生成精确的牛位置图。尽管像重叠和不重叠的摄像机区域这样的复杂性，我们的系统在一个真实的农场上实施，确保了准确的牛检测和基于bev的实时投影。详细的实验验证了系统的效率，提供了一种端到端的方法，可以使用多摄像头数据进行准确的行为检测和单个牛的位置映射。

{"title":"Multi-camera fusion and bird-eye view location mapping for deep learning-based cattle behavior monitoring","authors":"Muhammad Fahad Nasir , Alvaro Fuentes , Shujie Han , Jiaqi Liu , Yongchae Jeong , Sook Yoon , Dong Sun Park","doi":"10.1016/j.aiia.2025.06.001","DOIUrl":"10.1016/j.aiia.2025.06.001","url":null,"abstract":"<div><div>Cattle behavioral monitoring is an integral component of the modern infrastructure of the livestock industry. Ensuring cattle well-being requires precise observation, typically using wearable devices or surveillance cameras. Integrating deep learning into these systems enhances the monitoring of cattle behavior. However, challenges remain, such as occlusions, pose variations, and limited camera viewpoints, which hinder accurate detection and location mapping of individual cattle. To address these challenges, this paper proposes a multi-viewpoint surveillance system for indoor cattle barns, using footage from four cameras and deep learning-based models including action detection and pose estimation for behavior monitoring. The system accurately detects hierarchical behaviors across camera viewpoints. These results are fed into a Bird's Eye View (BEV) algorithm, producing precise cattle position maps in the barn. Despite complexities like overlapping and non-overlapping camera regions, our system, implemented on a real farm, ensures accurate cattle detection and BEV-based projections in real-time. Detailed experiments validate the system's efficiency, offering an end-to-end methodology for accurate behavior detection and location mapping of individual cattle using multi-camera data.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 724-743"},"PeriodicalIF":8.2,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review on enhancing agricultural intelligence with large language models 基于大语言模型的农业智能化研究进展

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-06-04 DOI: 10.1016/j.aiia.2025.05.006

Hongda Li , Huarui Wu , Qingxue Li , Chunjiang Zhao

This paper systematically explores the application potential of large language models (LLMs) in the field of agricultural intelligence, focusing on key technologies and practical pathways. The study focuses on the adaptation of LLMs to agricultural knowledge, starting with foundational concepts such as architecture design, pre-training strategies, and fine-tuning techniques, to build a technical framework for knowledge integration in the agricultural domain. Using tools such as vector databases and knowledge graphs, the study enables the structured development of professional agricultural knowledge bases. Additionally, by combining multimodal learning and intelligent question-answering (Q&A) system design, it validates the application value of LLMs in agricultural knowledge services. Addressing core challenges in domain adaptation, including knowledge acquisition and integration, logical reasoning, multimodal data processing, agent collaboration, and dynamic knowledge updating, the paper proposes targeted solutions. The study further explores the innovative applications of LLMs in scenarios such as precision crop management and market dynamics analysis, providing theoretical support and technical pathways for the development of agricultural intelligence. Through the technological innovation of large language models and their deep integration with the agricultural sector, the intelligence level of agricultural production, decision-making, and services can be effectively enhanced.

本文系统探讨了大型语言模型（large language models, LLMs）在农业智能领域的应用潜力，重点探讨了关键技术和实践路径。本研究的重点是法学硕士对农业知识的适应，从建筑设计、预培训策略和微调技术等基本概念开始，构建农业领域知识整合的技术框架。利用向量数据库和知识图谱等工具，本研究实现了专业农业知识库的结构化开发。通过多模态学习与智能问答系统设计相结合，验证法学硕士在农业知识服务中的应用价值。针对领域自适应中的知识获取与集成、逻辑推理、多模态数据处理、智能体协作和动态知识更新等核心挑战，提出了针对性的解决方案。研究进一步探索法学硕士在作物精准管理、市场动态分析等场景中的创新应用，为农业智能化发展提供理论支撑和技术路径。通过大语言模型的技术创新，与农业领域深度融合，有效提升农业生产、决策、服务的智能化水平。

{"title":"A review on enhancing agricultural intelligence with large language models","authors":"Hongda Li , Huarui Wu , Qingxue Li , Chunjiang Zhao","doi":"10.1016/j.aiia.2025.05.006","DOIUrl":"10.1016/j.aiia.2025.05.006","url":null,"abstract":"<div><div>This paper systematically explores the application potential of large language models (LLMs) in the field of agricultural intelligence, focusing on key technologies and practical pathways. The study focuses on the adaptation of LLMs to agricultural knowledge, starting with foundational concepts such as architecture design, pre-training strategies, and fine-tuning techniques, to build a technical framework for knowledge integration in the agricultural domain. Using tools such as vector databases and knowledge graphs, the study enables the structured development of professional agricultural knowledge bases. Additionally, by combining multimodal learning and intelligent question-answering (Q&A) system design, it validates the application value of LLMs in agricultural knowledge services. Addressing core challenges in domain adaptation, including knowledge acquisition and integration, logical reasoning, multimodal data processing, agent collaboration, and dynamic knowledge updating, the paper proposes targeted solutions. The study further explores the innovative applications of LLMs in scenarios such as precision crop management and market dynamics analysis, providing theoretical support and technical pathways for the development of agricultural intelligence. Through the technological innovation of large language models and their deep integration with the agricultural sector, the intelligence level of agricultural production, decision-making, and services can be effectively enhanced.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 671-685"},"PeriodicalIF":8.2,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MSNet: A multispectral-image driven rapeseed canopy instance segmentation network 一个多光谱图像驱动的油菜籽冠层实例分割网络

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-31 DOI: 10.1016/j.aiia.2025.05.008

Yuang Yang, Xiaole Wang, Fugui Zhang, Zhenchao Wu, Yu Wang, Yujie Liu, Xuan Lv, Bowen Luo, Liqing Chen, Yang Yang

Precise detection of rapeseed and the growth of its canopy area are crucial phenotypic indicators of its growth status. Achieving accurate identification of the rapeseed target and its growth region provides significant data support for phenotypic analysis and breeding research. However, in natural field environments, rapeseed detection remains a substantial challenge due to the limited feature representation capabilities of RGB-only modalities. To address this challenge, this study proposes a dual-modal instance segmentation network, MSNet, based on YOLOv11n-seg, integrating both RGB and Near-Infrared (NIR) modalities. The main improvements of this network include three different fusion location strategies (frontend fusion, mid-stage fusion, and backend fusion) and the newly introduced Hierarchical Attention Fusion Block (HAFB) for multimodal feature fusion. Comparative experiments on fusion locations indicate that the mid-stage fusion strategy achieves the best balance between detection accuracy and parameter efficiency. Compared to the baseline network, the mAP50:95 improvement can reach up to 3.5 %. After introducing the HAFB module, the MSNet-H-HAFB model demonstrates a 6.5 % increase in mAP50:95 relative to the baseline network, with less than a 38 % increase in parameter count. It is noteworthy that the mid-stage fusion consistently delivered the best detection performance in all experiments, providing clear design guidance for selecting fusion locations in future multimodal networks. In addition, comparisons with various RGB-only instance segmentation models show that all the proposed MSNet-HAFB fusion models significantly outperform single-modal models in rapeseed count detection tasks, confirming the potential advantages of multispectral fusion strategies in agricultural target recognition. Finally, the MSNet was applied in an agricultural case study, including vegetation index level analysis and frost damage classification. The results show that ZN6–2836 and ZS11 were predicted as potential superior varieties, and the EVI2 vegetation index achieved the best performance in rapeseed frost damage classification.

油菜籽的生长状况及其冠层面积的精确检测是反映油菜籽生长状况的重要表型指标。实现油菜靶点及其生长区域的准确鉴定，为表型分析和育种研究提供了重要的数据支持。然而，在自然野外环境中，由于仅rgb模式的特征表示能力有限，油菜籽检测仍然是一个重大挑战。为了解决这一挑战，本研究提出了一种基于YOLOv11n-seg的双模态实例分割网络MSNet，该网络集成了RGB和近红外（NIR）模式。该网络的主要改进包括三种不同的融合定位策略（前端融合、中期融合和后端融合）和新引入的用于多模态特征融合的分层注意融合块（HAFB）。融合位置的对比实验表明，中期融合策略在检测精度和参数效率之间达到了最佳平衡。与基线网络相比，mAP50:95的改进可达3.5%。在引入HAFB模块后，MSNet-H-HAFB模型显示，相对于基线网络，mAP50:95增加了6.5%，参数数量增加了不到38%。值得注意的是，中期融合在所有实验中始终提供了最佳的检测性能，为未来多模态网络中融合位置的选择提供了明确的设计指导。此外，与各种仅rgb实例分割模型的比较表明，所提出的MSNet-HAFB融合模型在油菜籽计数检测任务中都明显优于单模态模型，证实了多光谱融合策略在农业目标识别中的潜在优势。最后，将MSNet应用于农业案例研究，包括植被指数水平分析和霜冻灾害分类。结果表明，ZN6-2836和ZS11被预测为潜在优势品种，EVI2植被指数在油菜籽冻害分类中表现最佳。

{"title":"MSNet: A multispectral-image driven rapeseed canopy instance segmentation network","authors":"Yuang Yang, Xiaole Wang, Fugui Zhang, Zhenchao Wu, Yu Wang, Yujie Liu, Xuan Lv, Bowen Luo, Liqing Chen, Yang Yang","doi":"10.1016/j.aiia.2025.05.008","DOIUrl":"10.1016/j.aiia.2025.05.008","url":null,"abstract":"<div><div>Precise detection of rapeseed and the growth of its canopy area are crucial phenotypic indicators of its growth status. Achieving accurate identification of the rapeseed target and its growth region provides significant data support for phenotypic analysis and breeding research. However, in natural field environments, rapeseed detection remains a substantial challenge due to the limited feature representation capabilities of RGB-only modalities. To address this challenge, this study proposes a dual-modal instance segmentation network, MSNet, based on YOLOv11n-seg, integrating both RGB and Near-Infrared (NIR) modalities. The main improvements of this network include three different fusion location strategies (frontend fusion, mid-stage fusion, and backend fusion) and the newly introduced Hierarchical Attention Fusion Block (HAFB) for multimodal feature fusion. Comparative experiments on fusion locations indicate that the mid-stage fusion strategy achieves the best balance between detection accuracy and parameter efficiency. Compared to the baseline network, the <em>mAP50:95</em> improvement can reach up to 3.5 %. After introducing the HAFB module, the MSNet-H-HAFB model demonstrates a 6.5 % increase in <em>mAP50:95</em> relative to the baseline network, with less than a 38 % increase in parameter count. It is noteworthy that the mid-stage fusion consistently delivered the best detection performance in all experiments, providing clear design guidance for selecting fusion locations in future multimodal networks. In addition, comparisons with various RGB-only instance segmentation models show that all the proposed MSNet-HAFB fusion models significantly outperform single-modal models in rapeseed count detection tasks, confirming the potential advantages of multispectral fusion strategies in agricultural target recognition. Finally, the MSNet was applied in an agricultural case study, including vegetation index level analysis and frost damage classification. The results show that ZN6–2836 and ZS11 were predicted as potential superior varieties, and the EVI2 vegetation index achieved the best performance in rapeseed frost damage classification.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 642-658"},"PeriodicalIF":8.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144231062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An autonomous navigation method for field phenotyping robot based on ground-air collaboration 基于地空协同的现场分型机器人自主导航方法

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-30 DOI: 10.1016/j.aiia.2025.05.005

Zikang Zhang , Zhengda Li , Meng Yang , Jiale Cui , Yang Shao , Youchun Ding , Wanneng Yang , Wen Qiao , Peng Song

High-throughput phenotyping collection technology is important in affecting the efficiency of crop breeding. This study introduces a novel autonomous navigation method for phenotyping robots that leverages ground-air collaboration to meet the demands of unmanned crop phenotypic data collection. The proposed method employs a UAV equipped with a Real-Time Kinematic (RTK) module for the construction of high-precision Field maps. It utilizes SegFormor-B0 semantic segmentation models to detect crop rows, and extracts key coordinate points of these rows, and generates navigation paths for the phenotyping robots by mapping these points to actual geographic coordinates. Furthermore, an adaptive controller based on the Pure Pursuit algorithm is proposed, which dynamically adjusts the steering angle of the phenotyping robot in real-time, according to the distance (

d

), angular deviation (

α

) and the lateral deviation (

e_{y}

) between the robot's current position and its target position. This enables the robot to accurately trace paths in field environments. The results demonstrate that the mean absolute error (MAE) of the proposed method in extracting the centerline of potted plants area's rows is 2.83 cm, and the cropland's rows is 4.51 cm. The majority of global path tracking errors stay within 2 cm. In the potted plants area, 99.1 % of errors lie within this range, with a mean absolute error of 0.62 cm and a maximum error of 2.59 cm. In the cropland, 72.4 % of errors remain within this range, with a mean absolute error of 1.51 cm and a maximum error of 4.22 cm. Compared with traditional GNSS-based navigation methods and single vision methods, this method shows significant advantages in adapting to the dynamic growth of crops and complex field environments, which not only ensures that the phenotyping robot accurately travels along the crop rows during field operations to avoid damage to the crops, but also provides an efficient and accurate means of data acquisition for crop phenotyping.

高通量表型收集技术是影响作物育种效率的重要技术之一。本研究介绍了一种新型的表型机器人自主导航方法，该方法利用地空协作来满足无人作物表型数据收集的需求。该方法采用一种配备实时运动学（RTK）模块的无人机来构建高精度的野外地图。它利用SegFormor-B0语义分割模型检测作物行，提取这些行的关键坐标点，并将这些点映射到实际地理坐标，为表型机器人生成导航路径。在此基础上，提出了一种基于Pure Pursuit算法的自适应控制器，根据机器人当前位置与目标位置之间的距离(d)、角度偏差（α）和横向偏差（ey），实时动态调整表型机器人的转向角度。这使机器人能够在现场环境中准确地跟踪路径。结果表明，该方法提取盆栽区行中心线的平均绝对误差（MAE）为2.83 cm，农田行中心线的平均绝对误差为4.51 cm。大多数全局路径跟踪误差保持在2cm以内。在盆栽区域，99.1%的误差在此范围内，平均绝对误差为0.62 cm，最大误差为2.59 cm。在农田中，72.4%的误差保持在该范围内，平均绝对误差为1.51 cm，最大误差为4.22 cm。与传统的基于gnss的导航方法和单视觉方法相比，该方法在适应作物的动态生长和复杂的田间环境方面具有明显的优势，不仅保证了表型机器人在田间作业中准确地沿着作物行移动，避免对作物造成损害，而且为作物表型分析提供了一种高效、准确的数据采集手段。

{"title":"An autonomous navigation method for field phenotyping robot based on ground-air collaboration","authors":"Zikang Zhang , Zhengda Li , Meng Yang , Jiale Cui , Yang Shao , Youchun Ding , Wanneng Yang , Wen Qiao , Peng Song","doi":"10.1016/j.aiia.2025.05.005","DOIUrl":"10.1016/j.aiia.2025.05.005","url":null,"abstract":"<div><div>High-throughput phenotyping collection technology is important in affecting the efficiency of crop breeding. This study introduces a novel autonomous navigation method for phenotyping robots that leverages ground-air collaboration to meet the demands of unmanned crop phenotypic data collection. The proposed method employs a UAV equipped with a Real-Time Kinematic (RTK) module for the construction of high-precision Field maps. It utilizes SegFormor-B0 semantic segmentation models to detect crop rows, and extracts key coordinate points of these rows, and generates navigation paths for the phenotyping robots by mapping these points to actual geographic coordinates. Furthermore, an adaptive controller based on the Pure Pursuit algorithm is proposed, which dynamically adjusts the steering angle of the phenotyping robot in real-time, according to the distance (<span><math><mi>d</mi></math></span>), angular deviation (<span><math><mi>α</mi></math></span>) and the lateral deviation (<span><math><msub><mi>e</mi><mi>y</mi></msub></math></span>) between the robot's current position and its target position. This enables the robot to accurately trace paths in field environments. The results demonstrate that the mean absolute error (MAE) of the proposed method in extracting the centerline of potted plants area's rows is 2.83 cm, and the cropland's rows is 4.51 cm. The majority of global path tracking errors stay within 2 cm. In the potted plants area, 99.1 % of errors lie within this range, with a mean absolute error of 0.62 cm and a maximum error of 2.59 cm. In the cropland, 72.4 % of errors remain within this range, with a mean absolute error of 1.51 cm and a maximum error of 4.22 cm. Compared with traditional GNSS-based navigation methods and single vision methods, this method shows significant advantages in adapting to the dynamic growth of crops and complex field environments, which not only ensures that the phenotyping robot accurately travels along the crop rows during field operations to avoid damage to the crops, but also provides an efficient and accurate means of data acquisition for crop phenotyping.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 610-621"},"PeriodicalIF":8.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144194569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0