Artificial Intelligence in Agriculture最新文献_第5页

Two-year remote sensing and ground verification: Estimating chlorophyll content in winter wheat using UAV multi-spectral imagery 两年遥感与地面验证：利用无人机多光谱影像估算冬小麦叶绿素含量

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-11-05 DOI: 10.1016/j.aiia.2025.10.017

Wenjie Ai , Guofeng Yang , Zhongren Li , Jiawei Du , Lingzhen Ye , Xuping Feng , Xiangping Jin , Yong He

Leaf chlorophyll content serves as a critical biophysical indicator for characterizing wheat growth status. Traditional measurement using a SPAD meter, while convenient, is hampered by its localized sampling, low efficiency, and destructive nature, making it unsuitable for high-throughput field applications. To overcome these constraints, this research developed a novel approach for assessing canopy SPAD values in winter wheat by leveraging multispectral imagery obtained from an unmanned aerial vehicle (UAV). The generalizability of this methodology was rigorously evaluated through a replication experiment conducted in a subsequent growing season. Throughout the study, canopy reflectance data were acquired across key phenological stages and paired with synchronized ground-based SPAD measurements to construct stage-specific estimation models. The acquired multispectral images were processed to remove soil background interference, from which 17 distinct vegetation indices and 8 texture features were subsequently extracted. An in-depth examination followed, aiming to clarify the evolving interplay of these features with SPAD values throughout growth phases. Among the vegetation indices, the Modified Climate Change Canopy Vegetation Index (MCCCI) displayed a “rise-and-decline” pattern across the season, aligning with the crop's intrinsic growth dynamics and establishing it as a robust and phonologically interpretable proxy. Texture features, particularly contrast and entropy, demonstrated notable associations with SPAD values, reaching their peak strength during the booting stage. Comparative evaluation of various predictive modeling techniques revealed that a Support Vector Regression (SVR) model integrating both vegetation indices and texture features yielded the highest estimation accuracy. This integrated model outperformed models based solely on spectral or textural data, improving estimation accuracy by 23.81 % and 22.48 %, respectively. The model's strong generalization capability was further confirmed on the independent validation dataset from the second year (RMSE = 2.54, R² = 0.748). In summary, this study establishes an effective and transferable framework for non-destructively monitoring chlorophyll content in winter wheat canopies using UAV data.

叶片叶绿素含量是表征小麦生长状况的重要生物物理指标。使用SPAD仪表进行传统测量虽然方便，但由于其局部采样、低效率和破坏性，使其不适合高通量现场应用。为了克服这些限制，本研究开发了一种利用无人机（UAV）获得的多光谱图像来评估冬小麦冠层SPAD值的新方法。通过在随后的生长季节进行的重复实验，严格评估了该方法的普遍性。在整个研究过程中，获取了关键物候阶段的冠层反射率数据，并与同步的地面SPAD测量数据配对，构建了特定阶段的估算模型。对获取的多光谱图像进行去除土壤背景干扰的处理，提取出17种不同的植被指数和8种纹理特征。随后进行了深入的研究，旨在阐明这些特征在整个生长阶段与SPAD值之间不断变化的相互作用。在植被指数中，修正气候变化冠层植被指数（MCCCI）在整个季节中呈现出“上升-下降”的模式，与作物的内在生长动态一致，并建立了一个稳健的、可在音系上解释的指标。纹理特征，特别是对比度和熵，与SPAD值有显著的相关性，在启动阶段达到峰值。通过对各种预测建模技术的比较评估，发现结合植被指数和纹理特征的支持向量回归（SVR）模型的估计精度最高。该综合模型的估计精度分别提高了23.81%和22.48%，优于单纯基于光谱和纹理数据的模型。在第二年的独立验证数据集上进一步证实了模型较强的泛化能力（RMSE = 2.54, R2 = 0.748）。综上所述，本研究为利用无人机数据无损监测冬小麦冠层叶绿素含量建立了一个有效且可转移的框架。

{"title":"Two-year remote sensing and ground verification: Estimating chlorophyll content in winter wheat using UAV multi-spectral imagery","authors":"Wenjie Ai , Guofeng Yang , Zhongren Li , Jiawei Du , Lingzhen Ye , Xuping Feng , Xiangping Jin , Yong He","doi":"10.1016/j.aiia.2025.10.017","DOIUrl":"10.1016/j.aiia.2025.10.017","url":null,"abstract":"<div><div>Leaf chlorophyll content serves as a critical biophysical indicator for characterizing wheat growth status. Traditional measurement using a SPAD meter, while convenient, is hampered by its localized sampling, low efficiency, and destructive nature, making it unsuitable for high-throughput field applications. To overcome these constraints, this research developed a novel approach for assessing canopy SPAD values in winter wheat by leveraging multispectral imagery obtained from an unmanned aerial vehicle (UAV). The generalizability of this methodology was rigorously evaluated through a replication experiment conducted in a subsequent growing season. Throughout the study, canopy reflectance data were acquired across key phenological stages and paired with synchronized ground-based SPAD measurements to construct stage-specific estimation models. The acquired multispectral images were processed to remove soil background interference, from which 17 distinct vegetation indices and 8 texture features were subsequently extracted. An in-depth examination followed, aiming to clarify the evolving interplay of these features with SPAD values throughout growth phases. Among the vegetation indices, the Modified Climate Change Canopy Vegetation Index (MCCCI) displayed a “rise-and-decline” pattern across the season, aligning with the crop's intrinsic growth dynamics and establishing it as a robust and phonologically interpretable proxy. Texture features, particularly contrast and entropy, demonstrated notable associations with SPAD values, reaching their peak strength during the booting stage. Comparative evaluation of various predictive modeling techniques revealed that a Support Vector Regression (SVR) model integrating both vegetation indices and texture features yielded the highest estimation accuracy. This integrated model outperformed models based solely on spectral or textural data, improving estimation accuracy by 23.81 % and 22.48 %, respectively. The model's strong generalization capability was further confirmed on the independent validation dataset from the second year (RMSE = 2.54, R<sup>2</sup> = 0.748). In summary, this study establishes an effective and transferable framework for non-destructively monitoring chlorophyll content in winter wheat canopies using UAV data.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 480-494"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579035","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

YOLO-light-pruned: A lightweight model for monitoring maize seedling count and leaf age using near-ground and UAV RGB images YOLO-light-pruned：基于近地和无人机RGB图像监测玉米幼苗数和叶龄的轻量级模型

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-10-02 DOI: 10.1016/j.aiia.2025.10.002

Tiantian Jiang , Liang Li , Zhen Zhang , Xun Yu , Yanqin Zhu , Liming Li , Yadong Liu , Yali Bai , Ziqian Tang , Shuaibing Liu , Yan Zhang , Zheng Duan , Dameng Yin , Xiuliang Jin

Maize seedling count and leaf age are critical indicators of early growth status, essential for effective field management and breeding variety selection. Traditional field monitoring methods are time-consuming, labor-intensive, and prone to subjective errors. Recently, deep learning-based object detection models have gained attention in crop seedling counting. However, many of these models exhibit high computational complexity and implementation costs, making field deployment challenging. Moreover, maize leaf age monitoring in field environments is barely investigated. Therefore, this study proposes two lightweight models, YOLOv8n-Light-Pruned (YOLOv8n-LP) and YOLOv11n-Light-Pruned (YOLOv11n-LP), for monitoring maize seedling count and leaf age in field RGB images. Our proposed models are improved from YOLOv8n and YOLOv11n by incorporating the DAttention mechanism, an improved BiFPN, an EfficientHead, and layer-adaptive magnitude-based pruning. The improvement in model complexity and model efficiency was significant, with the number of parameters reduced by over 73 % and model efficiency upgraded by up to 42.9 % depending on the device computation power. High accuracy was achieved in seedling counting (YOLOv8n-LP/ YOLOv11n-LP: AP = 0.968/0.969, R² = 0.91/0.94, rRMSE = 6.73 %/5.59 %), with significantly reduced model size (YOLOv8n-LP/ YOLOv11n-LP: parameters = 0.8 M/0.7 M, trained model size = 1.8 MB/1.7 MB). The robustness was validated across datasets with varying leaf ages (rRMSE = 4.07 % – 7.27 %), resolutions (rRMSE = 3.06 % – 6.28 %), seedling compositions (rRMSE = 1.09 % – 9.29 %), and planting densities (rRMSE = 3.38 % – 10.82 %). Finally, by integrating plant counting and leaf age estimation, the proposed models demonstrated high accuracy in leaf age detection using near-ground images (YOLOv8n-LP/ YOLOv11n-LP: rRMSE = 5.73 %/7.54 %) and UAV images (rRMSE = 9.24 %/14.44 %). The results demonstrate that the proposed models excel in detection accuracy, deployment efficiency, and adaptability to complex field environments, providing robust support for practical applications in precision agriculture.

玉米幼苗数和叶龄是玉米早期生长状况的重要指标，对田间有效管理和选育品种至关重要。传统的现场监测方法耗时长、劳动强度大，而且容易出现主观误差。近年来，基于深度学习的目标检测模型在农作物幼苗计数中得到了广泛关注。然而，这些模型中的许多都具有较高的计算复杂性和实施成本，使得现场部署具有挑战性。此外，对田间环境下玉米叶龄监测的研究很少。因此，本研究提出了YOLOv8n-Light-Pruned （YOLOv8n-LP）和YOLOv11n-Light-Pruned （YOLOv11n-LP）两种轻量级模型，用于田间RGB图像中玉米幼苗数和叶龄的监测。我们提出的模型是在YOLOv8n和YOLOv11n的基础上改进的，采用了注意力机制、改进的BiFPN、effenhead和基于层的自适应幅度修剪。模型复杂性和模型效率的提高是显著的，参数数量减少了73%以上，模型效率提高了42.9%，具体取决于设备的计算能力。结果表明，YOLOv8n-LP/ YOLOv11n-LP: AP = 0.968/0.969, R2 = 0.91/0.94, rRMSE = 6.73% / 5.59%，模型尺寸显著减小（YOLOv8n-LP/ YOLOv11n-LP：参数= 0.8 M/0.7 M，训练模型尺寸= 1.8 MB/1.7 MB）。在不同叶龄（rRMSE = 4.07% - 7.27%）、分辨率（rRMSE = 3.06% - 6.28%）、幼苗组成（rRMSE = 1.09% - 9.29%）和种植密度（rRMSE = 3.38% - 10.82%）的数据集上验证了该方法的稳健性。最后，通过整合植物计数和叶龄估计，所提出的模型在近地图像（YOLOv8n-LP/ YOLOv11n-LP: rRMSE = 5.73% / 7.54%）和无人机图像（rRMSE = 9.24% / 14.44%）的叶龄检测中显示出较高的精度。结果表明，该模型具有较好的检测精度、部署效率和对复杂野外环境的适应性，为精准农业的实际应用提供了强有力的支持。

{"title":"YOLO-light-pruned: A lightweight model for monitoring maize seedling count and leaf age using near-ground and UAV RGB images","authors":"Tiantian Jiang , Liang Li , Zhen Zhang , Xun Yu , Yanqin Zhu , Liming Li , Yadong Liu , Yali Bai , Ziqian Tang , Shuaibing Liu , Yan Zhang , Zheng Duan , Dameng Yin , Xiuliang Jin","doi":"10.1016/j.aiia.2025.10.002","DOIUrl":"10.1016/j.aiia.2025.10.002","url":null,"abstract":"<div><div>Maize seedling count and leaf age are critical indicators of early growth status, essential for effective field management and breeding variety selection. Traditional field monitoring methods are time-consuming, labor-intensive, and prone to subjective errors. Recently, deep learning-based object detection models have gained attention in crop seedling counting. However, many of these models exhibit high computational complexity and implementation costs, making field deployment challenging. Moreover, maize leaf age monitoring in field environments is barely investigated. Therefore, this study proposes two lightweight models, YOLOv8n-Light-Pruned (YOLOv8n-LP) and YOLOv11n-Light-Pruned (YOLOv11n-LP), for monitoring maize seedling count and leaf age in field RGB images. Our proposed models are improved from YOLOv8n and YOLOv11n by incorporating the DAttention mechanism, an improved BiFPN, an EfficientHead, and layer-adaptive magnitude-based pruning. The improvement in model complexity and model efficiency was significant, with the number of parameters reduced by over 73 % and model efficiency upgraded by up to 42.9 % depending on the device computation power. High accuracy was achieved in seedling counting (YOLOv8n-LP/ YOLOv11n-LP: AP = 0.968/0.969, R<sup>2</sup> = 0.91/0.94, rRMSE = 6.73 %/5.59 %), with significantly reduced model size (YOLOv8n-LP/ YOLOv11n-LP: parameters = 0.8 M/0.7 M, trained model size = 1.8 MB/1.7 MB). The robustness was validated across datasets with varying leaf ages (rRMSE = 4.07 % – 7.27 %), resolutions (rRMSE = 3.06 % – 6.28 %), seedling compositions (rRMSE = 1.09 % – 9.29 %), and planting densities (rRMSE = 3.38 % – 10.82 %). Finally, by integrating plant counting and leaf age estimation, the proposed models demonstrated high accuracy in leaf age detection using near-ground images (YOLOv8n-LP/ YOLOv11n-LP: rRMSE = 5.73 %/7.54 %) and UAV images (rRMSE = 9.24 %/14.44 %). The results demonstrate that the proposed models excel in detection accuracy, deployment efficiency, and adaptability to complex field environments, providing robust support for practical applications in precision agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 164-186"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324222","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

Early detection of wheat powdery mildew: A multi-source in situ remote sensing approach enabled by stacked ensemble learning 小麦白粉病的早期检测：基于堆叠集成学习的多源原位遥感方法

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-10-02 DOI: 10.1016/j.aiia.2025.10.004

Li Song , Jiliang Zhao , Yahui Li , Linru Liu , Jianzhao Duan , Li He , Yonghua Wang , Tiancai Guo , Wei Feng

Powdery mildew seriously hinders photosynthesis and nutrient accumulation in wheat, and its early detection holds the key to enhancing control efficacy. In this research, solar-induced chlorophyll fluorescence (SIF) parameters were derived from radiance and reflectance data, while vegetation indices (VI) were computed using reflectance. A suite of feature selection methods, including shadow feature (Boruta), feature selection (ReliefF), minimum redundancy maximum correlation (mRMR), and random forest (RF). Models were developed on the back propagation (BP) neural network, support vector regression (SVR), and partial least squares regression (PLSR). Furthermore, a stacking ensemble strategy was adopted, utilizing RF and decision tree (DT) algorithms as meta-models to integrate the predictions from base models. The findings revealed that the Boruta method selected a well-balanced number of feature parameters with normalized weights. The multi-source model (SIF + VI) is superior to the single-source model (SIF or VI). The BP model exhibited high accuracy in wheat disease monitoring, particularly during the initial infection phases. The multi-regressor stacked with RF ensemble model (MRSRF) generally surpassed the multi-regressor stacked with DT ensemble model (MRSDT), especially in the initial infection stage, where the MRSRF model's average R² was 13.03 % higher than that of the BP model. To validate these conclusions, reflectance data simulated by the PROSAIL model (PROSPECT and SAIL) were utilized. The Boruta-MRSRF model demonstrated exceptional advantages in early detection, achieving an R² greater than 0.90 at all infection stages. This study provides effective ideas and methods for the active prevention and control of crop diseases, which are of great significance for ensuring agricultural production.

白粉病严重阻碍小麦光合作用和养分积累，早期发现白粉病是提高防治效果的关键。在本研究中，太阳诱导的叶绿素荧光（SIF）参数来源于辐射和反射率数据，而植被指数（VI）则来源于反射率数据。一套特征选择方法，包括阴影特征（Boruta）、特征选择（ReliefF）、最小冗余最大相关（mRMR）和随机森林（RF）。基于BP神经网络、支持向量回归（SVR）和偏最小二乘回归（PLSR）建立模型。此外，采用层叠集成策略，利用RF和DT算法作为元模型对基础模型的预测进行集成。结果表明，Boruta方法选择了一个很好的平衡数量的特征参数与归一化的权重。多源模型（SIF + VI）优于单源模型（SIF或VI）。BP模型在小麦病害监测中具有较高的准确性，特别是在感染初期。RF集成模型（MRSRF）叠加的多回归量总体优于DT集成模型（MRSDT），特别是在感染初期，MRSRF模型的平均R2比BP模型高13.03%。为了验证这些结论，利用PROSAIL模型（PROSPECT和SAIL）模拟的反射率数据。Boruta-MRSRF模型在早期检测方面表现出卓越的优势，在所有感染阶段的R2均大于0.90。本研究为积极防治作物病害提供了有效的思路和方法，对保障农业生产具有重要意义。

{"title":"Early detection of wheat powdery mildew: A multi-source in situ remote sensing approach enabled by stacked ensemble learning","authors":"Li Song , Jiliang Zhao , Yahui Li , Linru Liu , Jianzhao Duan , Li He , Yonghua Wang , Tiancai Guo , Wei Feng","doi":"10.1016/j.aiia.2025.10.004","DOIUrl":"10.1016/j.aiia.2025.10.004","url":null,"abstract":"<div><div>Powdery mildew seriously hinders photosynthesis and nutrient accumulation in wheat, and its early detection holds the key to enhancing control efficacy. In this research, solar-induced chlorophyll fluorescence (SIF) parameters were derived from radiance and reflectance data, while vegetation indices (VI) were computed using reflectance. A suite of feature selection methods, including shadow feature (Boruta), feature selection (ReliefF), minimum redundancy maximum correlation (mRMR), and random forest (RF). Models were developed on the back propagation (BP) neural network, support vector regression (SVR), and partial least squares regression (PLSR). Furthermore, a stacking ensemble strategy was adopted, utilizing RF and decision tree (DT) algorithms as meta-models to integrate the predictions from base models. The findings revealed that the Boruta method selected a well-balanced number of feature parameters with normalized weights. The multi-source model (SIF + VI) is superior to the single-source model (SIF or VI). The BP model exhibited high accuracy in wheat disease monitoring, particularly during the initial infection phases. The multi-regressor stacked with RF ensemble model (MRSRF) generally surpassed the multi-regressor stacked with DT ensemble model (MRSDT), especially in the initial infection stage, where the MRSRF model's average R<sup>2</sup> was 13.03 % higher than that of the BP model. To validate these conclusions, reflectance data simulated by the PROSAIL model (PROSPECT and SAIL) were utilized. The Boruta-MRSRF model demonstrated exceptional advantages in early detection, achieving an R<sup>2</sup> greater than 0.90 at all infection stages. This study provides effective ideas and methods for the active prevention and control of crop diseases, which are of great significance for ensuring agricultural production.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 124-138"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145264763","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

SCLFormer: A synergistic convolution-linear attention transformer for hyperspectral image classification of mechanical damage in maize kernels SCLFormer：一种用于玉米籽粒机械损伤高光谱图像分类的协同卷积-线性注意转换器

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-11-27 DOI: 10.1016/j.aiia.2025.11.010

Yiqiang Zheng , Jun Fu , Fengshuang Liu , Haiming Zhao , Jindai Liu

Classifying mechanical damage in maize kernels using hyperspectral imaging is crucial for food security and loss reduction. Existing methods are constrained by high computational complexity and limited precision in detecting subtle damages, such as pericarp damage and kernel cracks. To address these challenges, we introduce a novel algorithm, the Synergistic Convolution and Linear Attention Transformer (SCLFormer). By replacing traditional softmax attention with linear attention, we reduce computational complexity from quadratic to linear, thereby enhancing efficiency. Integrating convolutional operations into the encoder enriches local prior information for global feature modeling, improving classification accuracy. SCLFormer achieves an overall accuracy of 97.08 % in classifying maize kernel damage, with over 85 % accuracy for cracked kernel and pericarp damage. Compared to softmax attention, SCLFormer reduces training and testing times by 355.27 s (16.86 %) and 0.71 s (23.67 %), respectively. Additionally, we propose a modular hyperspectral image-level classification framework that can integrate existing pixel-level feature extraction networks to achieve classification accuracies exceeding 80 %, demonstrating the framework's scalability. SCLFormer, serving as the framework's dedicated feature extraction component, provides a robust solution for maize kernel damage classification and exhibits substantial potential for broader spatial-scale applications. This framework establishes a novel technical paradigm for hyperspectral image-wise classification of other agricultural products.

利用高光谱成像技术对玉米籽粒机械损伤进行分类对粮食安全和减少损失至关重要。现有方法在检测果皮损伤和果仁裂纹等细微损伤时，计算量大、精度低。为了解决这些挑战，我们引入了一种新的算法，即协同卷积和线性注意力转换器（SCLFormer）。通过将传统的softmax注意力替换为线性注意力，将计算复杂度从二次型降低到线性型，从而提高了效率。将卷积运算集成到编码器中，丰富了全局特征建模的局部先验信息，提高了分类精度。SCLFormer对玉米籽粒损伤分类的总体准确率为97.08%，对裂粒和果皮损伤分类的准确率超过85%。与softmax相比，SCLFormer的训练和测试时间分别减少了355.27 s（16.86%）和0.71 s（23.67%）。此外，我们提出了一个模块化的高光谱图像级分类框架，该框架可以集成现有的像素级特征提取网络，实现超过80%的分类精度，证明了框架的可扩展性。SCLFormer作为该框架的专用特征提取组件，为玉米籽粒损伤分类提供了一个强大的解决方案，并显示出更广泛的空间尺度应用潜力。该框架为其他农产品的高光谱图像分类建立了一种新的技术范式。

{"title":"SCLFormer: A synergistic convolution-linear attention transformer for hyperspectral image classification of mechanical damage in maize kernels","authors":"Yiqiang Zheng , Jun Fu , Fengshuang Liu , Haiming Zhao , Jindai Liu","doi":"10.1016/j.aiia.2025.11.010","DOIUrl":"10.1016/j.aiia.2025.11.010","url":null,"abstract":"<div><div>Classifying mechanical damage in maize kernels using hyperspectral imaging is crucial for food security and loss reduction. Existing methods are constrained by high computational complexity and limited precision in detecting subtle damages, such as pericarp damage and kernel cracks. To address these challenges, we introduce a novel algorithm, the Synergistic Convolution and Linear Attention Transformer (SCLFormer). By replacing traditional softmax attention with linear attention, we reduce computational complexity from quadratic to linear, thereby enhancing efficiency. Integrating convolutional operations into the encoder enriches local prior information for global feature modeling, improving classification accuracy. SCLFormer achieves an overall accuracy of 97.08 % in classifying maize kernel damage, with over 85 % accuracy for cracked kernel and pericarp damage. Compared to softmax attention, SCLFormer reduces training and testing times by 355.27 s (16.86 %) and 0.71 s (23.67 %), respectively. Additionally, we propose a modular hyperspectral image-level classification framework that can integrate existing pixel-level feature extraction networks to achieve classification accuracies exceeding 80 %, demonstrating the framework's scalability. SCLFormer, serving as the framework's dedicated feature extraction component, provides a robust solution for maize kernel damage classification and exhibits substantial potential for broader spatial-scale applications. This framework establishes a novel technical paradigm for hyperspectral image-wise classification of other agricultural products.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 565-577"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145693322","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

Development of an enhanced hybrid attention YOLOv8s small object detection method for phenotypic analysis of root nodules 一种用于根瘤表型分析的增强杂交注意YOLOv8s小目标检测方法的开发

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-07-21 DOI: 10.1016/j.aiia.2025.07.001

Ya Zhao , Wen Zhang , Liangxiao Zhang , Xiaoqian Tang , Du Wang , Qi Zhang , Peiwu Li

Nodule formation and their involvement in biological nitrogen fixation are critical features of leguminous plants, with phenotypic characteristics closely linked to plant growth and nitrogen fixation efficiency. However, the phenotypic analysis of root nodules remains technically challenging due to their small size, weak texture, dense clustering, and occlusion. To address these challenges, this study constructed a scanner-based imaging platform and optimized data acquisition conditions for high-resolution, high-consistency root nodule images under field conditions. In addition, A hybrid small-object detection method, SCO-YOLOv8s, was proposed, integrating Swin Transformer and CBAM attention mechanisms into the YOLOv8s framework to enhance global and local feature representation. Furthermore, an Otsu segmentation-based post-processing module was incorporated to validate and refine detection results based on geometric features, boundary sharpness, and image entropy, effectively reducing false positives and enhancing robustness in complex scenes. Using this integrated approach, over 3375 nodules were identified from a single plant sample in under 1 min, with extracted phenotypic features such as diameter, color, and texture. A total of 10,879 high-quality annotated images were collected from 39 peanut varieties across 14 provinces and 31 soybean varieties across 12 provinces in China, addressing the current lack of large-scale datasets for legume root nodules. The SCO-YOLOv8s model achieved a precision of 97.29 %, a mAP of 98.23 %, and an overall identification accuracy of 95.83 %. This integrated approach provides a practical and scalable solution for high-throughput nodule phenotyping, and may contribute to a deeper understanding of nitrogen fixation mechanisms.

根瘤形成及其参与生物固氮是豆科植物的重要特征，其表型特征与植物生长和固氮效率密切相关。然而，由于根瘤体积小、质地弱、密集聚集和闭塞，根瘤的表型分析在技术上仍然具有挑战性。为了应对这些挑战，本研究构建了一个基于扫描仪的成像平台，并优化了现场条件下高分辨率、高一致性根瘤图像的数据采集条件。此外，提出了一种混合小目标检测方法SCO-YOLOv8s，该方法将Swin Transformer和CBAM注意机制集成到YOLOv8s框架中，增强了全局和局部特征表征。此外，采用基于Otsu分割的后处理模块，基于几何特征、边界清晰度和图像熵对检测结果进行验证和细化，有效减少误报，增强复杂场景下的鲁棒性。利用这种综合方法，在不到1分钟的时间内从单个植物样本中鉴定出超过3375个根瘤，并提取了直径、颜色和纹理等表型特征。共收集了中国14个省39个花生品种和12个省31个大豆品种的10879张高质量的注释图像，解决了目前缺乏大规模豆科根瘤数据集的问题。SCO-YOLOv8s模型的识别精度为97.29%，mAP为98.23%，总体识别精度为95.83%。这种综合方法为高通量根瘤表型分析提供了一种实用且可扩展的解决方案，并可能有助于更深入地了解固氮机制。

{"title":"Development of an enhanced hybrid attention YOLOv8s small object detection method for phenotypic analysis of root nodules","authors":"Ya Zhao , Wen Zhang , Liangxiao Zhang , Xiaoqian Tang , Du Wang , Qi Zhang , Peiwu Li","doi":"10.1016/j.aiia.2025.07.001","DOIUrl":"10.1016/j.aiia.2025.07.001","url":null,"abstract":"<div><div>Nodule formation and their involvement in biological nitrogen fixation are critical features of leguminous plants, with phenotypic characteristics closely linked to plant growth and nitrogen fixation efficiency. However, the phenotypic analysis of root nodules remains technically challenging due to their small size, weak texture, dense clustering, and occlusion. To address these challenges, this study constructed a scanner-based imaging platform and optimized data acquisition conditions for high-resolution, high-consistency root nodule images under field conditions. In addition, A hybrid small-object detection method, SCO-YOLOv8s, was proposed, integrating Swin Transformer and CBAM attention mechanisms into the YOLOv8s framework to enhance global and local feature representation. Furthermore, an Otsu segmentation-based post-processing module was incorporated to validate and refine detection results based on geometric features, boundary sharpness, and image entropy, effectively reducing false positives and enhancing robustness in complex scenes. Using this integrated approach, over 3375 nodules were identified from a single plant sample in under 1 min, with extracted phenotypic features such as diameter, color, and texture. A total of 10,879 high-quality annotated images were collected from 39 peanut varieties across 14 provinces and 31 soybean varieties across 12 provinces in China, addressing the current lack of large-scale datasets for legume root nodules. The SCO-YOLOv8s model achieved a precision of 97.29 %, a mAP of 98.23 %, and an overall identification accuracy of 95.83 %. This integrated approach provides a practical and scalable solution for high-throughput nodule phenotyping, and may contribute to a deeper understanding of nitrogen fixation mechanisms.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 12-43"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722714","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

Transfer learning-based soybean LAI estimations by integrating PROSAIL, UAV, and PlanetScope imagery 整合PROSAIL、UAV和PlanetScope图像的基于迁移学习的大豆LAI估计

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-11-02 DOI: 10.1016/j.aiia.2025.10.018

Qing Li , Yanan Wei , Dalei Hao , Weijian Yu , Yelu Zeng

Accurate Leaf Area Index (LAI) estimations at the soybean plot scale is achievable using high-resolution Unmanned Aerial Vehicle (UAV) imagery and field measurement samples. However, the limited coverage of UAV flights restricts large-scale remote sensing monitoring in expansive soybean fields. This study leverages the broad coverage and 3-m resolution of PlanetScope satellite imagery to extend LAI prediction from UAV to satellite scales through transfer learning, using UAV-scale LAI estimates as a benchmark to validate cross-scale consistency. To address this challenge, this study proposed the LAI-TransNet, a two-stage transfer learning framework designed for precise and scalable soybean LAI prediction across large areas, demonstrating its effectiveness in cross-scale monitoring. In Stage 1, a UAV-scale benchmark is established using PROSAIL-simulated UAV reflectance data (UAV-Sim) and field-measured soybean LAI. Traditional machine learning, deep learning, and transfer learning models are trained on a hybrid UAV-Sim and field-measured dataset (UAV-Sim_Measured), with the transfer learning model CNN-TL, fine-tuned using pre-trained weights derived from UAV-Sim, achieving the highest accuracy (R² = 0.81, RMSE = 0.64 m²/m², rRMSE = 11.5 %). In Stage 2, LAI-TransNet is developed by fine-tuning the CNN-TL model on PlanetScope simulated data (PS-Sim), preprocessed via cross-domain mapping to align UAV and satellite spectral features. Real PlanetScope imagery is corrected for reflectance consistency with reference to UAV imagery spectral profiles. LAI-TransNet outperforms other deep learning models trained directly on PS-Sim (R² = 0.69 vs. 0.60–0.63), ensuring robust cross-scale consistency. By bridging UAV and satellite scales, LAI-TransNet enables large-scale soybean LAI monitoring, enhancing precision agriculture management through improved monitoring with the PlanetScope imagery.

利用高分辨率无人机（UAV）图像和实地测量样本，可以在大豆地块尺度上实现精确的叶面积指数（LAI）估算。然而，无人机飞行覆盖范围有限，限制了大面积大豆田的大规模遥感监测。本研究利用PlanetScope卫星图像的广泛覆盖范围和3米分辨率，通过迁移学习将LAI预测从无人机尺度扩展到卫星尺度，以无人机尺度LAI估计为基准验证跨尺度一致性。为了应对这一挑战，本研究提出了LAI- transnet，这是一个两阶段迁移学习框架，旨在精确和可扩展地预测大面积的大豆LAI，证明了其在跨尺度监测中的有效性。第一阶段，利用prosail模拟无人机反射率数据（UAV- sim）和大豆LAI实测数据，建立无人机尺度基准。传统的机器学习、深度学习和迁移学习模型在UAV-Sim和现场测量数据集（UAV-Sim_Measured）上进行训练，迁移学习模型CNN-TL使用来自UAV-Sim的预训练权值进行微调，达到了最高的精度（R2 = 0.81, RMSE = 0.64 m2/m2, rRMSE = 11.5%）。在第二阶段，ai - transnet是通过在PlanetScope模拟数据（PS-Sim）上微调CNN-TL模型来开发的，并通过跨域映射进行预处理，以对准无人机和卫星的光谱特征。真实的PlanetScope图像与无人机图像光谱轮廓的反射率一致性进行了校正。ai - transnet优于直接在PS-Sim上训练的其他深度学习模型（R2 = 0.69 vs. 0.60-0.63），确保了鲁棒的跨尺度一致性。通过连接无人机和卫星尺度，LAI- transnet实现了大规模的大豆LAI监测，通过改进PlanetScope图像的监测，加强了精准农业管理。

{"title":"Transfer learning-based soybean LAI estimations by integrating PROSAIL, UAV, and PlanetScope imagery","authors":"Qing Li , Yanan Wei , Dalei Hao , Weijian Yu , Yelu Zeng","doi":"10.1016/j.aiia.2025.10.018","DOIUrl":"10.1016/j.aiia.2025.10.018","url":null,"abstract":"<div><div>Accurate Leaf Area Index (LAI) estimations at the soybean plot scale is achievable using high-resolution Unmanned Aerial Vehicle (UAV) imagery and field measurement samples. However, the limited coverage of UAV flights restricts large-scale remote sensing monitoring in expansive soybean fields. This study leverages the broad coverage and 3-m resolution of PlanetScope satellite imagery to extend LAI prediction from UAV to satellite scales through transfer learning, using UAV-scale LAI estimates as a benchmark to validate cross-scale consistency. To address this challenge, this study proposed the LAI-TransNet, a two-stage transfer learning framework designed for precise and scalable soybean LAI prediction across large areas, demonstrating its effectiveness in cross-scale monitoring. In Stage 1, a UAV-scale benchmark is established using PROSAIL-simulated UAV reflectance data (UAV-Sim) and field-measured soybean LAI. Traditional machine learning, deep learning, and transfer learning models are trained on a hybrid UAV-Sim and field-measured dataset (UAV-Sim_Measured), with the transfer learning model CNN-TL, fine-tuned using pre-trained weights derived from UAV-Sim, achieving the highest accuracy (<em>R</em><sup>2</sup> = 0.81, RMSE = 0.64 m<sup>2</sup>/m<sup>2</sup>, rRMSE = 11.5 %). In Stage 2, LAI-TransNet is developed by fine-tuning the CNN-TL model on PlanetScope simulated data (PS-Sim), preprocessed via cross-domain mapping to align UAV and satellite spectral features. Real PlanetScope imagery is corrected for reflectance consistency with reference to UAV imagery spectral profiles. LAI-TransNet outperforms other deep learning models trained directly on PS-Sim (<em>R</em><sup>2</sup> = 0.69 vs. 0.60–0.63), ensuring robust cross-scale consistency. By bridging UAV and satellite scales, LAI-TransNet enables large-scale soybean LAI monitoring, enhancing precision agriculture management through improved monitoring with the PlanetScope imagery.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 365-380"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527909","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 perspective analysis of imaging-based monitoring systems in precision viticulture: Technologies, intelligent data analyses and research challenges 精准葡萄栽培中基于成像的监测系统的视角分析：技术、智能数据分析和研究挑战

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-09-09 DOI: 10.1016/j.aiia.2025.08.001

Annaclaudia Bono , Cataldo Guaragnella , Tiziana D'Orazio

This paper presents a comprehensive review of recent advancements in intelligent monitoring systems within the precision viticulture sector. These systems have the potential to make agricultural production more efficient and ensure the adoption of sustainable practices to increase food production and meet growing global demand while maintaining high-quality standards. The review examines core components of non-destructive imaging-based monitoring systems in vineyards, focusing on sensors, tasks, and data processing methodologies. Particular emphasis is placed on solutions designed for practical, in-field deployment. The analysis revealed that the most commonly used sensors are RGB cameras and that the most widespread analysis focuses on grape bunches, as they provide information on both the quality and quantity of the harvest. Regarding the image processing methods, it emerged that those based on deep learning are the most adopted. In addition, a detailed analysis highlights the main technical and practical limitations in real-world scenarios, such as the management of computational resources, the need for large datasets, and the difficulties in interpreting the results. The paper concludes with an in-depth discussion of the challenges and open research questions, providing insights into potential future directions for intelligent monitoring systems in precision viticulture. These include the continued exploration of sensors to balance ease of use and accuracy, the development of generalizable methods, experimentation in real-world scenarios, and collaboration between experts for practical solutions.

本文介绍了精密葡萄栽培领域智能监控系统的最新进展。这些系统有可能提高农业生产效率，并确保采用可持续做法，以增加粮食产量，满足日益增长的全球需求，同时保持高质量标准。该综述审查了葡萄园非破坏性成像监测系统的核心组成部分，重点是传感器、任务和数据处理方法。特别强调的是为实际的现场部署而设计的解决方案。分析显示，最常用的传感器是RGB相机，最广泛的分析集中在葡萄串上，因为它们提供了收获的质量和数量的信息。在图像处理方法方面，基于深度学习的方法被采用的最多。此外，详细分析强调了现实场景中的主要技术和实践限制，例如计算资源的管理，对大型数据集的需求以及解释结果的困难。最后，本文深入讨论了当前面临的挑战和开放的研究问题，并为精准葡萄栽培中智能监测系统的潜在未来发展方向提供了见解。其中包括对传感器的持续探索，以平衡易用性和准确性，开发可推广的方法，在现实世界场景中进行实验，以及专家之间的合作，以寻求实际的解决方案。

{"title":"A perspective analysis of imaging-based monitoring systems in precision viticulture: Technologies, intelligent data analyses and research challenges","authors":"Annaclaudia Bono , Cataldo Guaragnella , Tiziana D'Orazio","doi":"10.1016/j.aiia.2025.08.001","DOIUrl":"10.1016/j.aiia.2025.08.001","url":null,"abstract":"<div><div>This paper presents a comprehensive review of recent advancements in intelligent monitoring systems within the precision viticulture sector. These systems have the potential to make agricultural production more efficient and ensure the adoption of sustainable practices to increase food production and meet growing global demand while maintaining high-quality standards. The review examines core components of non-destructive imaging-based monitoring systems in vineyards, focusing on sensors, tasks, and data processing methodologies. Particular emphasis is placed on solutions designed for practical, in-field deployment. The analysis revealed that the most commonly used sensors are RGB cameras and that the most widespread analysis focuses on grape bunches, as they provide information on both the quality and quantity of the harvest. Regarding the image processing methods, it emerged that those based on deep learning are the most adopted. In addition, a detailed analysis highlights the main technical and practical limitations in real-world scenarios, such as the management of computational resources, the need for large datasets, and the difficulties in interpreting the results. The paper concludes with an in-depth discussion of the challenges and open research questions, providing insights into potential future directions for intelligent monitoring systems in precision viticulture. These include the continued exploration of sensors to balance ease of use and accuracy, the development of generalizable methods, experimentation in real-world scenarios, and collaboration between experts for practical solutions.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 62-84"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048407","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

STGMAE: A GNSS data-driven pre-training spatiotemporal graph masked autoencoder for agricultural machinery trajectory operation mode identification STGMAE: GNSS数据驱动的预训练时空图掩码自编码器，用于农业机械轨迹运行模式识别

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-10-24 DOI: 10.1016/j.aiia.2025.10.007

Tailai Chen , Weixin Zhai

Utilizing spatiotemporal features in massive amounts of trajectory data to identify the operation mode of agricultural machinery trajectories is a key task in precision agriculture. Most of the previous studies focuses narrowly on single-perspective feature extraction, neglecting comprehensive spatiotemporal information in trajectory data. To improve the accuracy of the task, this paper proposes a model called STGMAE. First, we propose a multilevel feature extraction method (MFE), which extracts motion and statistical features from the initial features via a motion feature extractor and a sliding time window, and then uses the spectral feature module (SFM) to capture the spectral information, which improves the representation of trajectory data. Next, to prevent information loss in long-range encoding, we design a pre-training network with serial encoding and parallel decoding. Specifically, the data are first modeled globally interactively via a multiscale wavelet projector (WMP), and then enter an adaptive graph isomorphic neural network (AGIN). In AGIN, semi-adaptive masked Laplace operator (SAMLO) is used to capture the correlation information between trajectory points, and then a passing mechanism is used to address the homogeneous relationships between trajectory points and heterogeneous relationships between trajectory graphs. Then, the original feature and graph structure are reconstructed from the two encoding nodes to realize self-supervised training. Eventually, we use the pre-trained weights on the real trajectory samples provided by the Key Laboratory of Agricultural Machinery Monitoring and Big Data Application, Ministry of Agriculture and Rural Affairs, which contains 219 trajectory samples (2,250,693 trajectory points). The experimental results show that for the paddy, corn, and wheat harvesting trajectory datasets, our model accuracies are 95.50 %, 95.32 %, and 95.36 %, respectively, and the F1 scores are 94.54 %, 92.09 %, and 93.79 %, respectively. Compared with existing state-of-the-art methods, our method achieves accuracies of 5.75 %, 4.47 %, and 5.03 % and F1 scores of 7.26 %, 4.85 %, and 6.65 %, respectively.

利用海量轨迹数据中的时空特征识别农机轨迹运行模式是精准农业的关键任务。以往的研究大多局限于单视角特征提取，忽略了轨迹数据中综合的时空信息。为了提高任务的准确性，本文提出了一种STGMAE模型。首先，我们提出了一种多层特征提取方法（MFE），该方法通过运动特征提取器和滑动时间窗从初始特征中提取运动特征和统计特征，然后使用光谱特征模块（SFM）捕获光谱信息，提高了轨迹数据的表征能力。其次，为了防止远程编码中的信息丢失，我们设计了一个串行编码和并行解码的预训练网络。具体而言，首先通过多尺度小波投影（WMP）对数据进行全局交互建模，然后输入自适应图同构神经网络（AGIN）。在AGIN中，采用半自适应掩模拉普拉斯算子（SAMLO）捕获轨迹点之间的相关信息，然后采用传递机制处理轨迹点之间的同质关系和轨迹图之间的异质关系。然后，从两个编码节点重构原始特征和图结构，实现自监督训练。最终，我们将预训练好的权值用于农业农村部农业机械监测与大数据应用重点实验室提供的真实轨迹样本，该样本包含219个轨迹样本（2,250,693个轨迹点）。实验结果表明，对于水稻、玉米和小麦的收获轨迹数据集，我们的模型准确率分别为95.50%、95.32%和95.36%，F1得分分别为94.54%、92.09%和93.79%。与现有最先进的方法相比，该方法的准确率分别为5.75%、4.47%和5.03%，F1分数分别为7.26%、4.85%和6.65%。

{"title":"STGMAE: A GNSS data-driven pre-training spatiotemporal graph masked autoencoder for agricultural machinery trajectory operation mode identification","authors":"Tailai Chen , Weixin Zhai","doi":"10.1016/j.aiia.2025.10.007","DOIUrl":"10.1016/j.aiia.2025.10.007","url":null,"abstract":"<div><div>Utilizing spatiotemporal features in massive amounts of trajectory data to identify the operation mode of agricultural machinery trajectories is a key task in precision agriculture. Most of the previous studies focuses narrowly on single-perspective feature extraction, neglecting comprehensive spatiotemporal information in trajectory data. To improve the accuracy of the task, this paper proposes a model called STGMAE. First, we propose a multilevel feature extraction method (MFE), which extracts motion and statistical features from the initial features via a motion feature extractor and a sliding time window, and then uses the spectral feature module (SFM) to capture the spectral information, which improves the representation of trajectory data. Next, to prevent information loss in long-range encoding, we design a pre-training network with serial encoding and parallel decoding. Specifically, the data are first modeled globally interactively via a multiscale wavelet projector (WMP), and then enter an adaptive graph isomorphic neural network (AGIN). In AGIN, semi-adaptive masked Laplace operator (SAMLO) is used to capture the correlation information between trajectory points, and then a passing mechanism is used to address the homogeneous relationships between trajectory points and heterogeneous relationships between trajectory graphs. Then, the original feature and graph structure are reconstructed from the two encoding nodes to realize self-supervised training. Eventually, we use the pre-trained weights on the real trajectory samples provided by the Key Laboratory of Agricultural Machinery Monitoring and Big Data Application, Ministry of Agriculture and Rural Affairs, which contains 219 trajectory samples (2,250,693 trajectory points). The experimental results show that for the paddy, corn, and wheat harvesting trajectory datasets, our model accuracies are 95.50 %, 95.32 %, and 95.36 %, respectively, and the F1 scores are 94.54 %, 92.09 %, and 93.79 %, respectively. Compared with existing state-of-the-art methods, our method achieves accuracies of 5.75 %, 4.47 %, and 5.03 % and F1 scores of 7.26 %, 4.85 %, and 6.65 %, respectively.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 439-457"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527922","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-scale feature alignment network for 19-class semantic segmentation in agricultural environments 农业环境下19类语义分割的多尺度特征对齐网络

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-11-22 DOI: 10.1016/j.aiia.2025.11.008

Zhi-xin Yao , Hao Wang , Zhi-jun Meng , Liang-liang Yang , Tai-hong Zhang

To improve environmental perception and ensure reliable agricultural machinery navigation during field transitions under unstructured farm road conditions, this study utilizes high-resolution RGB camera vision navigation technology to propose a Multi-Scale Feature Alignment Network (MSFA-Net) for 19-class semantic segmentation of agricultural environment, which includes information such as roads, pedestrians, and vehicles. MSFA-Net introduces two key innovations: the DASP module, which integrates multi-scale feature extraction with dual attention mechanisms (spatial and channel), and the MSFA architecture, which enables robust boundary extraction and mitigates interference from lighting variations and obstacles like vegetation. Compared to existing models, MSFA-Net uniquely combines efficient multi-scale feature extraction with real-time inference capabilities, achieving an mIoU of 84.46 % and an mPA of 96.10 %. For 512 × 512 input images, the model processes an average of 26 images/s on a GTX 1650Ti, with a boundary extraction error of less than 0.47 m within 20 m. These results indicate that the proposed MSFA-Net can significantly reduce navigation errors and improve the perception stability of agricultural machinery during field operations. Furthermore, the model can be exported to ONNX or TensorFlow Lite formats, facilitating efficient deployment on embedded devices and existing farm navigation systems.

为了提高农业机械在非结构化农田道路条件下的环境感知能力，保证农机导航的可靠性，本研究利用高分辨率RGB相机视觉导航技术，提出了一种多尺度特征对齐网络（MSFA-Net），对包括道路、行人、车辆等信息在内的农业环境进行19类语义分割。MSFA- net引入了两个关键的创新：DASP模块，它集成了具有双重注意机制（空间和通道）的多尺度特征提取；MSFA架构，它可以实现鲁棒的边界提取，并减轻光照变化和植被等障碍物的干扰。与现有模型相比，MSFA-Net独特地将高效的多尺度特征提取与实时推理能力相结合，实现了84.46%的mIoU和96.10%的mPA。对于512 × 512的输入图像，该模型在GTX 1650Ti上平均处理26张图像/s，在20 m范围内边界提取误差小于0.47 m。结果表明，本文提出的MSFA-Net能够显著降低导航误差，提高农机在野外作业中的感知稳定性。此外，该模型可以导出为ONNX或TensorFlow Lite格式，便于在嵌入式设备和现有农场导航系统上进行有效部署。

{"title":"Multi-scale feature alignment network for 19-class semantic segmentation in agricultural environments","authors":"Zhi-xin Yao , Hao Wang , Zhi-jun Meng , Liang-liang Yang , Tai-hong Zhang","doi":"10.1016/j.aiia.2025.11.008","DOIUrl":"10.1016/j.aiia.2025.11.008","url":null,"abstract":"<div><div>To improve environmental perception and ensure reliable agricultural machinery navigation during field transitions under unstructured farm road conditions, this study utilizes high-resolution RGB camera vision navigation technology to propose a Multi-Scale Feature Alignment Network (MSFA-Net) for 19-class semantic segmentation of agricultural environment, which includes information such as roads, pedestrians, and vehicles. MSFA-Net introduces two key innovations: the DASP module, which integrates multi-scale feature extraction with dual attention mechanisms (spatial and channel), and the MSFA architecture, which enables robust boundary extraction and mitigates interference from lighting variations and obstacles like vegetation. Compared to existing models, MSFA-Net uniquely combines efficient multi-scale feature extraction with real-time inference capabilities, achieving an mIoU of 84.46 % and an mPA of 96.10 %. For 512 × 512 input images, the model processes an average of 26 images/s on a GTX 1650Ti, with a boundary extraction error of less than 0.47 m within 20 m. These results indicate that the proposed MSFA-Net can significantly reduce navigation errors and improve the perception stability of agricultural machinery during field operations. Furthermore, the model can be exported to ONNX or TensorFlow Lite formats, facilitating efficient deployment on embedded devices and existing farm navigation systems.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 529-545"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623317","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 lightweight keypoint detection model-based method for strawberry recognition and picking point localization in multi-occlusion scenes 基于轻量级关键点检测模型的多遮挡场景草莓识别与采摘点定位方法

IF 12.4 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2026-03-01 Epub Date: 2025-10-24 DOI: 10.1016/j.aiia.2025.10.009

Dezhi Wang, Xiaochan Wang, Yinyan Shi, Xiaolei Zhang, Yanyu Chen, Jinming Zheng, Nan Liu

Strawberries grown on elevated stands usually suffer from fruit occlusion issues, which severely limit the implementation of strawberry recognition and picking point localization, and the embedded devices carried by strawberry picking robots have high requirements for model lightweighting, posing a dual challenge to the efficient execution of automated picking tasks by robots. To address this issue, this study proposes a method for strawberry recognition and picking point localization in multi-occlusion scenes based on a lightweight keypoint detection model. Firstly, a strawberry dataset covering no, slight, moderate, and heavy occlusion scenes is constructed. Then, a lightweight strawberry recognition and keypoint detection network, LS-net, is proposed. LS-net improves the spatial relationship modelling capability between strawberries and stems by integrating the lightweight MobileNetv4 backbone with the Mobile Grouped-Query Attention mechanism; improves the feature pyramid network using depthwise separable convolutions and incorporates an anchor-free decoupled head network to reduce computational complexity while maintaining detection accuracy; and introduces the Matrix Non-Maximum Suppression to optimize the processing of overlapping strawberries, which effectively reduces the false negative detections. Based on the keypoint detection results from LS-net, the picking point coordinates and stem pose are calculated after a series of processes such as region-of-interest extraction, binarization, and depth data alignment. The experimental results show that the accuracy of LS-net is 91.07 %, the mean average precision is 93.93 %, and the average pixel Euclidean distance is 4.79. By deploying LS-net to the embedded device, its frames per second reaches 78.2, and the success rates of 3D picking point localization and stem pose estimation are 84.07 % and 81.32 %, respectively. LS-net and related methods provide a visual recognition solution adapted to embedded devices for strawberry picking robots.

种植在高架架上的草莓通常存在果实遮挡问题，严重限制了草莓识别和采摘点定位的实现，并且草莓采摘机器人携带的嵌入式设备对模型轻量化要求很高，这对机器人高效执行自动化采摘任务提出了双重挑战。针对这一问题，本研究提出了一种基于轻量级关键点检测模型的多遮挡场景下草莓识别和采摘点定位方法。首先，构建草莓数据集，包括无、轻微、中度和重度遮挡场景。然后，提出了一种轻量级的草莓识别和关键点检测网络LS-net。LS-net通过集成轻量级MobileNetv4骨干网和移动分组查询关注机制，提高了草莓与茎的空间关系建模能力；使用深度可分离卷积改进特征金字塔网络，并结合无锚解耦头部网络，在保持检测精度的同时降低计算复杂度；引入矩阵非最大值抑制优化重叠草莓的处理，有效降低了假阴性检测。基于LS-net的关键点检测结果，经过感兴趣区域提取、二值化和深度数据对齐等一系列处理，计算提取点坐标和茎位姿。实验结果表明，LS-net的精度为91.07%，平均精度为93.93%，平均像元欧氏距离为4.79。将LS-net部署到嵌入式设备中，其帧数每秒达到78.2帧，3D拾取点定位和茎位估计的成功率分别为84.07%和81.32%。LS-net及其相关方法为草莓采摘机器人提供了一种适合嵌入式设备的视觉识别解决方案。

{"title":"A lightweight keypoint detection model-based method for strawberry recognition and picking point localization in multi-occlusion scenes","authors":"Dezhi Wang, Xiaochan Wang, Yinyan Shi, Xiaolei Zhang, Yanyu Chen, Jinming Zheng, Nan Liu","doi":"10.1016/j.aiia.2025.10.009","DOIUrl":"10.1016/j.aiia.2025.10.009","url":null,"abstract":"<div><div>Strawberries grown on elevated stands usually suffer from fruit occlusion issues, which severely limit the implementation of strawberry recognition and picking point localization, and the embedded devices carried by strawberry picking robots have high requirements for model lightweighting, posing a dual challenge to the efficient execution of automated picking tasks by robots. To address this issue, this study proposes a method for strawberry recognition and picking point localization in multi-occlusion scenes based on a lightweight keypoint detection model. Firstly, a strawberry dataset covering no, slight, moderate, and heavy occlusion scenes is constructed. Then, a lightweight strawberry recognition and keypoint detection network, LS-net, is proposed. LS-net improves the spatial relationship modelling capability between strawberries and stems by integrating the lightweight MobileNetv4 backbone with the Mobile Grouped-Query Attention mechanism; improves the feature pyramid network using depthwise separable convolutions and incorporates an anchor-free decoupled head network to reduce computational complexity while maintaining detection accuracy; and introduces the Matrix Non-Maximum Suppression to optimize the processing of overlapping strawberries, which effectively reduces the false negative detections. Based on the keypoint detection results from LS-net, the picking point coordinates and stem pose are calculated after a series of processes such as region-of-interest extraction, binarization, and depth data alignment. The experimental results show that the accuracy of LS-net is 91.07 %, the mean average precision is 93.93 %, and the average pixel Euclidean distance is 4.79. By deploying LS-net to the embedded device, its frames per second reaches 78.2, and the success rates of 3D picking point localization and stem pose estimation are 84.07 % and 81.32 %, respectively. LS-net and related methods provide a visual recognition solution adapted to embedded devices for strawberry picking robots.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 316-341"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465549","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