Pub Date : 2025-12-01Epub Date: 2025-06-18DOI: 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.
{"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":"2025-12-01","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}
Pub Date : 2025-12-01Epub Date: 2025-06-24DOI: 10.1016/j.aiia.2025.06.007
Xiangyu Zhao , Fuzhen Sun , Jinlong Li , Dongfeng Zhang , Qiusi Zhang , Zhongqiang Liu , Changwei Tan , Hongxiang Ma , Kaiyi Wang
Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security. The advent of Genomic Selection heralds a new epoch in breeding, characterized by its capacity to harness whole-genome variation for genomic prediction. This approach transcends the need for prior knowledge of genes associated with specific traits. Nonetheless, the vast dimensionality of genomic data juxtaposed with the relatively limited number of phenotypic samples often leads to the “curse of dimensionality”, where traditional statistical, machine learning, and deep learning methods are prone to overfitting and suboptimal predictive performance. To surmount this challenge, we introduce a unified Variational auto-encoder based Multi-task Genomic Prediction model (VMGP) that integrates self-supervised genomic compression and reconstruction with multiple prediction tasks. This approach provides a robust solution, offering a formidable predictive framework that has been rigorously validated across public datasets for wheat, rice, and maize. Our model demonstrates exceptional capabilities in multi-phenotype and multi-environment genomic prediction, successfully navigating the complexities of cross-population genomic selection and underscoring its unique strengths and utility. Furthermore, by integrating VMGP with model interpretability, we can effectively triage relevant single nucleotide polymorphisms, thereby enhancing prediction performance and proposing potential cost-effective genotyping solutions. The VMGP framework, with its simplicity, stable predictive prowess, and open-source code, is exceptionally well-suited for broad dissemination within plant breeding programs. It is particularly advantageous for breeders who prioritize phenotype prediction yet may not possess extensive knowledge in deep learning or proficiency in parameter tuning.
{"title":"VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants","authors":"Xiangyu Zhao , Fuzhen Sun , Jinlong Li , Dongfeng Zhang , Qiusi Zhang , Zhongqiang Liu , Changwei Tan , Hongxiang Ma , Kaiyi Wang","doi":"10.1016/j.aiia.2025.06.007","DOIUrl":"10.1016/j.aiia.2025.06.007","url":null,"abstract":"<div><div>Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security. The advent of Genomic Selection heralds a new epoch in breeding, characterized by its capacity to harness whole-genome variation for genomic prediction. This approach transcends the need for prior knowledge of genes associated with specific traits. Nonetheless, the vast dimensionality of genomic data juxtaposed with the relatively limited number of phenotypic samples often leads to the “curse of dimensionality”, where traditional statistical, machine learning, and deep learning methods are prone to overfitting and suboptimal predictive performance. To surmount this challenge, we introduce a unified Variational auto-encoder based Multi-task Genomic Prediction model (VMGP) that integrates self-supervised genomic compression and reconstruction with multiple prediction tasks. This approach provides a robust solution, offering a formidable predictive framework that has been rigorously validated across public datasets for wheat, rice, and maize. Our model demonstrates exceptional capabilities in multi-phenotype and multi-environment genomic prediction, successfully navigating the complexities of cross-population genomic selection and underscoring its unique strengths and utility. Furthermore, by integrating VMGP with model interpretability, we can effectively triage relevant single nucleotide polymorphisms, thereby enhancing prediction performance and proposing potential cost-effective genotyping solutions. The VMGP framework, with its simplicity, stable predictive prowess, and open-source code, is exceptionally well-suited for broad dissemination within plant breeding programs. It is particularly advantageous for breeders who prioritize phenotype prediction yet may not possess extensive knowledge in deep learning or proficiency in parameter tuning.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 829-842"},"PeriodicalIF":8.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534365","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}
Pub Date : 2025-12-01Epub Date: 2025-06-11DOI: 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 = 0.9238 ± 0.0346, RMSEp = 0.1746 ± 0.0401. For oil content, = 0.9602 ± 0.0180 and RMSEp = 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 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.
{"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":"2025-12-01","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}
Pub Date : 2025-12-01Epub Date: 2025-04-04DOI: 10.1016/j.aiia.2025.03.007
Jiang Pin , Tingfeng Guo , Minzi Xv , Xiangjun Zou , Wenwu Hu
This paper describes the design, algorithm development, and experimental verification of a precise spray perception system based on LiDAR were presented to address the issue that the navigation line extraction accuracy of self-propelled sprayers during field operations is low, resulting in wheels rolling over the ridges and excessive pesticide waste. A data processing framework was established for the precision spray perception system. Through data preprocessing, adaptive segmentation of crops and ditches, extraction of navigation lines and crop positioning, which were derived from the original LiDAR point cloud species. Data collection and analysis of the field environment of cabbages in different growth cycles were conducted to verify the stability of the precision spraying system. A controllable constant-speed experimental setup was established to compare the performance of LiDAR and depth camera in the same field environment. The experimental results show that at the self-propelled sprayer of speeds of 0.5 and 1 ms−1, the maximum lateral error is 0.112 m in a cabbage ridge environment with inter-row weeds, with an mean absolute lateral error of 0.059 m. The processing speed per frame does not exceed 43 ms. Compared to the machine vision algorithm, this method reduces the average processing time by 122 ms. The proposed system demonstrates superior accuracy, processing time, and robustness in crop identification and navigation line extraction compared to the machine vision system.
{"title":"Fast extraction of navigation line and crop position based on LiDAR for cabbage crops","authors":"Jiang Pin , Tingfeng Guo , Minzi Xv , Xiangjun Zou , Wenwu Hu","doi":"10.1016/j.aiia.2025.03.007","DOIUrl":"10.1016/j.aiia.2025.03.007","url":null,"abstract":"<div><div>This paper describes the design, algorithm development, and experimental verification of a precise spray perception system based on LiDAR were presented to address the issue that the navigation line extraction accuracy of self-propelled sprayers during field operations is low, resulting in wheels rolling over the ridges and excessive pesticide waste. A data processing framework was established for the precision spray perception system. Through data preprocessing, adaptive segmentation of crops and ditches, extraction of navigation lines and crop positioning, which were derived from the original LiDAR point cloud species. Data collection and analysis of the field environment of cabbages in different growth cycles were conducted to verify the stability of the precision spraying system. A controllable constant-speed experimental setup was established to compare the performance of LiDAR and depth camera in the same field environment. The experimental results show that at the self-propelled sprayer of speeds of 0.5 and 1 ms<sup>−1</sup>, the maximum lateral error is 0.112 m in a cabbage ridge environment with inter-row weeds, with an mean absolute lateral error of 0.059 m. The processing speed per frame does not exceed 43 ms. Compared to the machine vision algorithm, this method reduces the average processing time by 122 ms. The proposed system demonstrates superior accuracy, processing time, and robustness in crop identification and navigation line extraction compared to the machine vision system.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 686-695"},"PeriodicalIF":8.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254490","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}
Pub Date : 2025-12-01Epub Date: 2025-05-31DOI: 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.
{"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":"2025-12-01","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}
Pub Date : 2025-12-01Epub Date: 2025-05-30DOI: 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 (), angular deviation () and the lateral deviation () 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.
{"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":"2025-12-01","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}
Pub Date : 2025-12-01Epub Date: 2025-03-22DOI: 10.1016/j.aiia.2025.03.005
Alberto Carraro , Mattia Pravato , Francesco Marinello , Francesco Bordignon , Angela Trocino , Gerolamo Xiccato , Andrea Pezzuolo
Precision Livestock Farming (PLF) emerges as a promising solution for revolutionising farming by enabling real-time automated monitoring of animals through smart technologies. PLF provides farmers with precise data to enhance farm management, increasing productivity and profitability. For instance, it allows for non-intrusive health assessments, contributing to maintaining a healthy herd while reducing stress associated with handling. In the poultry sector, image analysis can be utilised to monitor and analyse the behaviour of each hen in real time. Researchers have recently used machine learning algorithms to monitor the behaviour, health, and positioning of hens through computer vision techniques. Convolutional neural networks, a type of deep learning algorithm, have been utilised for image analysis to identify and categorise various hen behaviours and track specific activities like feeding and drinking. This research presents an automated system for analysing laying hen movement using video footage from surveillance cameras. With a customised implementation of object tracking, the system can efficiently process hundreds of hours of videos while maintaining high measurement precision. Its modular implementation adapts well to optimally exploit the GPU computing capabilities of the hardware platform it is running on. The use of this system is beneficial for both real-time monitoring and post-processing, contributing to improved monitoring capabilities in precision livestock farming.
{"title":"A new tool to improve the computation of animal kinetic activity indices in precision poultry farming","authors":"Alberto Carraro , Mattia Pravato , Francesco Marinello , Francesco Bordignon , Angela Trocino , Gerolamo Xiccato , Andrea Pezzuolo","doi":"10.1016/j.aiia.2025.03.005","DOIUrl":"10.1016/j.aiia.2025.03.005","url":null,"abstract":"<div><div>Precision Livestock Farming (PLF) emerges as a promising solution for revolutionising farming by enabling real-time automated monitoring of animals through smart technologies. PLF provides farmers with precise data to enhance farm management, increasing productivity and profitability. For instance, it allows for non-intrusive health assessments, contributing to maintaining a healthy herd while reducing stress associated with handling. In the poultry sector, image analysis can be utilised to monitor and analyse the behaviour of each hen in real time. Researchers have recently used machine learning algorithms to monitor the behaviour, health, and positioning of hens through computer vision techniques. Convolutional neural networks, a type of deep learning algorithm, have been utilised for image analysis to identify and categorise various hen behaviours and track specific activities like feeding and drinking. This research presents an automated system for analysing laying hen movement using video footage from surveillance cameras. With a customised implementation of object tracking, the system can efficiently process hundreds of hours of videos while maintaining high measurement precision. Its modular implementation adapts well to optimally exploit the GPU computing capabilities of the hardware platform it is running on. The use of this system is beneficial for both real-time monitoring and post-processing, contributing to improved monitoring capabilities in precision livestock farming.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 659-670"},"PeriodicalIF":8.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253342","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}
Pub Date : 2025-12-01Epub Date: 2025-06-21DOI: 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.
{"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":"2025-12-01","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}
Pub Date : 2025-12-01Epub Date: 2025-05-28DOI: 10.1016/j.aiia.2025.05.003
Evans K. Wiafe, Kelvin Betitame, Billy G. Ram, Xin Sun
As precision agriculture evolves, unmanned ground vehicles (UGVs) have become an essential tool for improving weed management techniques, offering automated and targeted methods that obviously reduce the reliance on manual labor and blanket herbicide applications. Several papers on UGV-based weed control methods have been published in recent years, yet there is no explicit attempt to systematically study these papers to discuss these weed control methods, UGVs adopted, and their key components, and how they impact the environment and economy. Therefore, the objective of this study was to present a systematic review that involves the efficiency and types of weed control methods deployed in UGVs, including mechanical weeding, targeted herbicide application, thermal/flaming weeding, and laser weeding in the last 2 decades. For this purpose, a thorough literature review was conducted, analyzing 68 relevant articles on weed control methods for UGVs. The study found that the research focus on using UGVs in mechanical weeding has been more dominant, followed by target or precision spraying/ chemical weeding, with hybrid weeding systems quickly emerging. The effectiveness of UGVs for weed control is hinged on the accuracy of their navigation and weed detection technologies, which are influenced heavily by environmental conditions, including lighting, weather, uneven terrain, and weed and crop density. Also, there is a shift from using traditional machine learning (ML) algorithms to deep learning neural networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), for weed detection algorithm development due to their potential to work in complex environments. Finally, trials of most UGVs have limited documentation or lack extensive trials under various conditions, such as varying soil types, crop fields, topography, field geometry, and annual weather conditions. This review paper serves as an in-depth update on UGVs in weed management for farmers, researchers, robotic technology industry players, and AI enthusiasts, helping to further foster collaborative efforts to develop new ideas and advance this revolutionary technique in modern agriculture.
{"title":"Technical study on the efficiency and models of weed control methods using unmanned ground vehicles: A review","authors":"Evans K. Wiafe, Kelvin Betitame, Billy G. Ram, Xin Sun","doi":"10.1016/j.aiia.2025.05.003","DOIUrl":"10.1016/j.aiia.2025.05.003","url":null,"abstract":"<div><div>As precision agriculture evolves, unmanned ground vehicles (UGVs) have become an essential tool for improving weed management techniques, offering automated and targeted methods that obviously reduce the reliance on manual labor and blanket herbicide applications. Several papers on UGV-based weed control methods have been published in recent years, yet there is no explicit attempt to systematically study these papers to discuss these weed control methods, UGVs adopted, and their key components, and how they impact the environment and economy. Therefore, the objective of this study was to present a systematic review that involves the efficiency and types of weed control methods deployed in UGVs, including mechanical weeding, targeted herbicide application, thermal/flaming weeding, and laser weeding in the last 2 decades. For this purpose, a thorough literature review was conducted, analyzing 68 relevant articles on weed control methods for UGVs. The study found that the research focus on using UGVs in mechanical weeding has been more dominant, followed by target or precision spraying/ chemical weeding, with hybrid weeding systems quickly emerging. The effectiveness of UGVs for weed control is hinged on the accuracy of their navigation and weed detection technologies, which are influenced heavily by environmental conditions, including lighting, weather, uneven terrain, and weed and crop density. Also, there is a shift from using traditional machine learning (ML) algorithms to deep learning neural networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), for weed detection algorithm development due to their potential to work in complex environments. Finally, trials of most UGVs have limited documentation or lack extensive trials under various conditions, such as varying soil types, crop fields, topography, field geometry, and annual weather conditions. This review paper serves as an in-depth update on UGVs in weed management for farmers, researchers, robotic technology industry players, and AI enthusiasts, helping to further foster collaborative efforts to develop new ideas and advance this revolutionary technique in modern agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 622-641"},"PeriodicalIF":8.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203295","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}
Pub Date : 2025-09-01Epub Date: 2025-04-08DOI: 10.1016/j.aiia.2025.03.006
Yuqing Yang , Chengguo Xu , Wenhao Hou , Alan G. McElligott , Kai Liu , Yueju Xue
Nursing behaviour and the calling-to-nurse sound are crucial indicators for assessing sow maternal behaviour and nursing status. However, accurately identifying these behaviours for individual sows in complex indoor pig housing is challenging due to factors such as variable lighting, rail obstructions, and interference from other sows' calls. Multimodal fusion, which integrates audio and visual data, has proven to be an effective approach for improving accuracy and robustness in complex scenarios. In this study, we designed an audio-visual data acquisition system that includes a camera for synchronised audio and video capture, along with a custom-developed sound source localisation system that leverages a sound sensor to track sound direction. Specifically, we proposed a novel transformer-based audio-visual multimodal fusion (TMF) framework for recognising fine-grained sow nursing behaviour with or without the calling-to-nurse sound. Initially, a unimodal self-attention enhancement (USE) module was employed to augment video and audio features with global contextual information. Subsequently, we developed an audio-visual interaction enhancement (AVIE) module to compress relevant information and reduce noise using the information bottleneck principle. Moreover, we presented an adaptive dynamic decision fusion strategy to optimise the model's performance by focusing on the most relevant features in each modality. Finally, we comprehensively identified fine-grained nursing behaviours by integrating audio and fused information, while incorporating angle information from the real-time sound source localisation system to accurately determine whether the sound cues originate from the target sow. Our results demonstrate that the proposed method achieves an accuracy of 98.42 % for general sow nursing behaviour and 94.37 % for fine-grained nursing behaviour, including nursing with and without the calling-to-nurse sound, and non-nursing behaviours. This fine-grained nursing information can provide a more nuanced understanding of the sow's health and lactation willingness, thereby enhancing management practices in pig farming.
{"title":"Transformer-based audio-visual multimodal fusion for fine-grained recognition of individual sow nursing behaviour","authors":"Yuqing Yang , Chengguo Xu , Wenhao Hou , Alan G. McElligott , Kai Liu , Yueju Xue","doi":"10.1016/j.aiia.2025.03.006","DOIUrl":"10.1016/j.aiia.2025.03.006","url":null,"abstract":"<div><div>Nursing behaviour and the calling-to-nurse sound are crucial indicators for assessing sow maternal behaviour and nursing status. However, accurately identifying these behaviours for individual sows in complex indoor pig housing is challenging due to factors such as variable lighting, rail obstructions, and interference from other sows' calls. Multimodal fusion, which integrates audio and visual data, has proven to be an effective approach for improving accuracy and robustness in complex scenarios. In this study, we designed an audio-visual data acquisition system that includes a camera for synchronised audio and video capture, along with a custom-developed sound source localisation system that leverages a sound sensor to track sound direction. Specifically, we proposed a novel transformer-based audio-visual multimodal fusion (TMF) framework for recognising fine-grained sow nursing behaviour with or without the calling-to-nurse sound. Initially, a unimodal self-attention enhancement (USE) module was employed to augment video and audio features with global contextual information. Subsequently, we developed an audio-visual interaction enhancement (AVIE) module to compress relevant information and reduce noise using the information bottleneck principle. Moreover, we presented an adaptive dynamic decision fusion strategy to optimise the model's performance by focusing on the most relevant features in each modality. Finally, we comprehensively identified fine-grained nursing behaviours by integrating audio and fused information, while incorporating angle information from the real-time sound source localisation system to accurately determine whether the sound cues originate from the target sow. Our results demonstrate that the proposed method achieves an accuracy of 98.42 % for general sow nursing behaviour and 94.37 % for fine-grained nursing behaviour, including nursing with and without the calling-to-nurse sound, and non-nursing behaviours. This fine-grained nursing information can provide a more nuanced understanding of the sow's health and lactation willingness, thereby enhancing management practices in pig farming.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 363-376"},"PeriodicalIF":8.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835177","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号