Query：
学者姓名：郑书河
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
本发明提供了一种基于机器视觉的茶园智能精准喷药系统及喷药方法，属于茶园机械技术领域，所述方法包括：步骤S1：构建茶叶病害检测模型；步骤S2：采集茶园现场图片；步骤S3：将步骤S2采集的茶园现场图片传输至NVIDIA Jetson Orin Nano主控系统上，并通过步骤S1得到的检测模型进行检测，判断是否有病虫害发生：如果有，则计算出病虫害发生的位置后进行喷药处理。实现茶园病虫害的精准识别，以及精准喷药。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 郑书河 , 黄伟良 , 陈洪彬 et al. 基于机器视觉的茶园智能精准喷药系统及喷药方法 : CN202510751300.1[P]. | 2025-06-06 . |
| MLA | 郑书河 et al. "基于机器视觉的茶园智能精准喷药系统及喷药方法" : CN202510751300.1. | 2025-06-06 . |
| APA | 郑书河 , 黄伟良 , 陈洪彬 , 李梦 , 赖镇辉 , 陈龙彬 et al. 基于机器视觉的茶园智能精准喷药系统及喷药方法 : CN202510751300.1. | 2025-06-06 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
近年来，随着果穗收获技术日趋成熟，劳动力成本的增加和畜牧业大力发展，穗茎兼收收获机需求逐步增加。在分析现有同类机型的基础上，设计了4YZJ-4型玉米穗茎兼收收获机，该机能够一次性完成果穗收获、茎秆收获和根茬处理等作业。采用双层割台完成果穗和茎秆同时收获，动刀盘刀片人字形排列可有效提高切碎质量降低功耗，收获机配置了专用草箱既可独自完成茎秆回收，也可满足跟车回收作业需求。通过大面积田间试验验证，结果表明：总损失率为3.2%,果穗含杂率为0.88%,苞叶剥净率为92%,秸秆长度合格率为93.9%,生产率为0.4～0.8 hm
Keyword ：
双层割台 双层割台 玉米收获机 玉米收获机 茎穗兼收 茎穗兼收
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 邸志峰 , 姜伟 , 李娜 et al. 4YZJ-4型玉米茎穗兼收收获机设计与试验 [J]. | 农业装备与车辆工程 , 2025 , 63 (03) : 1-5 . |
| MLA | 邸志峰 et al. "4YZJ-4型玉米茎穗兼收收获机设计与试验" . | 农业装备与车辆工程 63 . 03 (2025) : 1-5 . |
| APA | 邸志峰 , 姜伟 , 李娜 , 张华 , 崔中凯 , 周进 et al. 4YZJ-4型玉米茎穗兼收收获机设计与试验 . | 农业装备与车辆工程 , 2025 , 63 (03) , 1-5 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Carrots are a widely consumed vegetable around the world. They come in several varieties, each with their distinct quality traits. This study uses hyperspectral imaging to identify and predict soluble solids content (SSC) in three carrot cultivars using machine learning-based spectral analysis. After preprocessing the raw spectra, we constructed a partial least squares regression (PLSR) model to predict SSC using the preprocessed full spectra. iPLS and competitive adaptive reweighted sampling (CARS) methods were compared for variable selection. To differentiate carrots from three orchards, we developed four classification models: CARS-LDA, iPLS-LDA, iPLSKNN, and CARS-KNN. Results indicated that both CARS-LDA and iPLS achieved effective wavelength selection for the Fuzhou A carrot cultivar, with the CARS-LDA model demonstrating the highest predictive capability, reflected by a relative prediction deviation (RPD) value of 2.72. In terms of accuracy, specificity, sensitivity, and precision, the CARS-KNN model was the best. This study underscores the potential of hyperspectral imaging coupled with machine learning methodologies to reliably predict and distinguish between various carrot cultivars, thereby contributing significantly to improvements in food safety and quality control standards in the agricultural sector.
Keyword ：
Carrot classification Carrot classification CARS-K-NN model CARS-K-NN model Feature wavelength selection Feature wavelength selection Hyperspectral imaging Hyperspectral imaging Machine learning techniques Machine learning techniques Partial least squares regression Partial least squares regression Soluble solid content Soluble solid content
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Arcel, Mulowayi Mutombo , Bin, Chen Long , Shen, Zhen Hui et al. Exploring the power of advanced spectral imaging and multivariate analysis for distinguishing similar carrot cultivars [J]. | JOURNAL OF FOOD COMPOSITION AND ANALYSIS , 2025 , 142 . |
| MLA | Arcel, Mulowayi Mutombo et al. "Exploring the power of advanced spectral imaging and multivariate analysis for distinguishing similar carrot cultivars" . | JOURNAL OF FOOD COMPOSITION AND ANALYSIS 142 (2025) . |
| APA | Arcel, Mulowayi Mutombo , Bin, Chen Long , Shen, Zhen Hui , Nyimbo, Witness Joseph , Turay, Mark Bayo , Zheng, Shu He . Exploring the power of advanced spectral imaging and multivariate analysis for distinguishing similar carrot cultivars . | JOURNAL OF FOOD COMPOSITION AND ANALYSIS , 2025 , 142 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
【目的】获取生态茶园土壤与开沟触土部件相互作用的离散元仿真模型参数，建立生态茶园的“土壤-绿肥根茬秸秆-开沟触土部件”离散元仿真模型，为生态茶园触土部件离散元仿真研究提供依据。【方法】采用物理下落堆积、斜面滚动试验与离散元仿真联合方案，基于Hertz-Mindlin with Bonding接触模型，对土壤颗粒间及土壤-开沟触土部件材料(65 Mn钢)接触参数进行标定。以土壤下落堆积角、土壤颗粒斜面滚动距离为评价指标，以静摩擦系数、滚动摩擦系数和恢复系数为试验因素，应用Box-Behnken的响应面优化方法，确定土壤堆积角与土球斜面滚动距离的回归模型。【结果】模型优化处理后，土壤颗粒之间的静摩擦系数、滚动摩擦系数和恢复系数分别为1.017、0.089和0.222。土壤-开沟部件的静摩擦系数、滚动摩擦系数和恢复系数分别为0.279、0.104和0.487。仿真标定结果与物理试验的相对误差为0.68%和0.98%。基于标定参数建立生态茶园“土壤—绿肥根茬秸秆-开沟触土部件”离散元仿真模型，通过仿真试验与田间试验对比分析，开沟深度和开沟宽度的最大相对误差分别为8.15%和6.36%。【结论】标定优化后的参数与物理试验的相对误差小，建立的生态茶园“土壤-绿肥根茬秸秆-开沟触土部件”离散元仿真模型的可靠性与有效性较高。
Keyword ：
参数标定 参数标定 土壤 土壤 旋耕开沟 旋耕开沟 生态茶园 生态茶园 离散元法 离散元法
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈龙彬 , 陈凌霄 , 郑书河 . 生态茶园“土壤-绿肥根茬秸秆-开沟触土部件”离散元模型建立与验证 [J]. | 福建农林大学学报(自然科学版) , 2025 , 54 (03) : 420-431 . |
| MLA | 陈龙彬 et al. "生态茶园“土壤-绿肥根茬秸秆-开沟触土部件”离散元模型建立与验证" . | 福建农林大学学报(自然科学版) 54 . 03 (2025) : 420-431 . |
| APA | 陈龙彬 , 陈凌霄 , 郑书河 . 生态茶园“土壤-绿肥根茬秸秆-开沟触土部件”离散元模型建立与验证 . | 福建农林大学学报(自然科学版) , 2025 , 54 (03) , 420-431 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
【目的】提出一种机械臂路径规划算法，以解决多自由度机械臂在大棚采摘作业中路径规划速度慢、路径成本高等问题，为采摘机械臂高效作业提供依据。【方法】基于Informed RRT
Keyword ：
改进Informed RRT 改进Informed RRT 路径规划 路径规划 采摘机械臂 采摘机械臂
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 郑泽斌 , 郑书河 , 翁武雄 et al. 基于改进Informed RRT*算法的大棚采摘机械臂路径规划 [J]. | 福建农林大学学报(自然科学版) , 2025 , 54 (02) : 279-288 . |
| MLA | 郑泽斌 et al. "基于改进Informed RRT*算法的大棚采摘机械臂路径规划" . | 福建农林大学学报(自然科学版) 54 . 02 (2025) : 279-288 . |
| APA | 郑泽斌 , 郑书河 , 翁武雄 , 林添良 , 郭雷 . 基于改进Informed RRT*算法的大棚采摘机械臂路径规划 . | 福建农林大学学报(自然科学版) , 2025 , 54 (02) , 279-288 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Accurate identification of tomato fruit stalks is critical for end-effectors to perform precise cutting operations, which contributes to enhanced harvesting efficiency and reduced reliance on manual labor. However, actual field environments may compromise the accuracy of tomato fruit stalks identification. To address this issue, this study proposes an improved GCD-YOLO model based on YOLOv8n. Specifically, GAM is integrated into the YOLOv8 backbone network, the original Neck is replaced with CCFM, and Dyhead is adopted as the detection head for tomato fruit stalks identification. The results show that the different improvement modules can effectively enhance the feature extraction ability of the model, thus improving the detection accuracy of the GCD-YOLO model for tomato fruit stalks. The GCD-YOLO model achieves a detection precision of 94.4% and an mAP@50 of 91.7% for tomato fruit stalks, significantly outperforming YOLOv8n, SSD, Faster R-CNN, YOLOv5n, RT-DETR, YOLOv9t, YOLOv11n and YOLOv12n. Furthermore, the GCD-YOLO model was deployed on an NVIDIA Jetson Orin Nano for field experiments. Experimental results demonstrate that the GCD-YOLO model delivers outstanding detection performance on edge devices, achieving an inference speed of 26.24FPS in actual field environments. The research findings contribute to the development of smart agriculture and facilitate the implementation of machine vision in tomato harvesting applications.
Keyword ：
Deep learning Deep learning Edge device deployment Edge device deployment Machine vision Machine vision Tomato fruit stalks Tomato fruit stalks YOLOv8 YOLOv8
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Weng, Wuxiong , Lai, Zhenhui , Cui, Zheming et al. GCD-YOLO: A deep learning network for accurate tomato fruit stalks identification in unstructured environments [J]. | SMART AGRICULTURAL TECHNOLOGY , 2025 , 12 . |
| MLA | Weng, Wuxiong et al. "GCD-YOLO: A deep learning network for accurate tomato fruit stalks identification in unstructured environments" . | SMART AGRICULTURAL TECHNOLOGY 12 (2025) . |
| APA | Weng, Wuxiong , Lai, Zhenhui , Cui, Zheming , Chen, Zhixiong , Chen, Hongbin , Lin, Tianliang et al. GCD-YOLO: A deep learning network for accurate tomato fruit stalks identification in unstructured environments . | SMART AGRICULTURAL TECHNOLOGY , 2025 , 12 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Aiming at the problems of low success rate and high seedling injury rate of automatic vegetable transplanting, this study focused on cabbage substrate block seedlings and developed a progressive push-out automatic seedling device controlled by a PLC system. Based on the friction mechanical properties of seedlings-tray during seedling taking, the collision rebound theoretical analysis of substrate block seedling delivery and the finite element simulation analysis of the seedling taking mechanism were carried out to determine the conditions for stable seedling taking and delivery of the device and the working parameters of the key mechanisms. To evaluate individual parameter effects, a test bench was built, and the effective ranges key factors were subsequently determined. Three key experimental factors, the inclination angle of the limit guide plate, the seedling separation channel width, and the seedling separation cylinder pressure, were investigated using an L9(3(4)) orthogonal array design with blockage rate and breakage rate as evaluation metrics. The range and variance analysis methods were employed to determine the relative significance of each factor's influence on the performance indicators. The optimal parameters were determined as: the inclination angle of the limiting guide plate was 3.5 degrees, the width of the seedling separation channel was 50 mm, and the pressure of the seedling separation cylinder was 0.6 MPa. Under these conditions, the seedling taking effect was significantly improved: the blockage rate was 2.46%, the breakage rate was 3.18%, and the seedling taking success rate was 94.36%. The optimal parameter combination was verified by the experiment: the average blockage rate was 3.23%, the average breakage rate was 3.68%, and the average success rate was 93.09%. Compared with the orthogonal experiment, the relative success rate error was 1.27%, indicating that the device has high stability. This study will provide reference for the design of automatic vegetable transplanters.
Keyword ：
automatic seedling taking device automatic seedling taking device PLC control system PLC control system progressive push-out progressive push-out substrate block seedlings substrate block seedlings transplanter transplanter
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cui, Zhichao , Fu, Jingjing , Li, Jicheng et al. Design and test of the progressive push-out automatic seedling-taking device for vegetable substrate block seedlings [J]. | INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING , 2025 , 18 (4) : 89-100 . |
| MLA | Cui, Zhichao et al. "Design and test of the progressive push-out automatic seedling-taking device for vegetable substrate block seedlings" . | INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING 18 . 4 (2025) : 89-100 . |
| APA | Cui, Zhichao , Fu, Jingjing , Li, Jicheng , Ji, Haibo , Wu, Changhao , Zheng, Shuhe et al. Design and test of the progressive push-out automatic seedling-taking device for vegetable substrate block seedlings . | INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING , 2025 , 18 (4) , 89-100 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This research investigated the behavior of key nutritional elements specifically, titratable acidity (TA), and vitamin C within the xylem and cortex of carrots during various storage durations and temperatures. A hyperspectral imaging system captured 300 images across 472 wavebands ranging from 400 to 1000 nm. Regions of interest (ROIs) were defined to extract average spectra from these hyperspectral images (HSI). We developed two analytical models: support vector regression (SVR) and Partial Least Squares Discriminant Analysis (PLS-DA), to quantitatively analyze the relationships between pigment levels and spectral data. Uninformative Variable Elimination (UVE) and loading weights (LW) approaches were used to select effective wavelengths (EWs) for modeling. The reduction of vitamin C was found to be considerably influenced by changes in storage temperature and time, with comparable effects observed in the cortex and xylem. However, when compared to the cortex, TA showed a more milder increase in the xylem. This study concludes by highlighting the promise of HSI as an effective and non-destructive method for monitoring the chemical composition of carrot roots while they are being stored at different temperatures and times. These results are consistent with earlier studies on the quantitative evaluation of internal carrot quality and add to the body of existing information.
Keyword ：
Carrot storage Carrot storage Hyperspectral imaging Hyperspectral imaging Nutritional elements Nutritional elements Quantitative analysis model Quantitative analysis model Temperature and time effects Temperature and time effects
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Arcel, Mulowayi Mutombo , Meng, Li , Gatsi, Blessing et al. Optimizing nutrient retention in carrots during storage: A hyperspectral imaging approach [J]. | JOURNAL OF FOOD COMPOSITION AND ANALYSIS , 2025 , 146 . |
| MLA | Arcel, Mulowayi Mutombo et al. "Optimizing nutrient retention in carrots during storage: A hyperspectral imaging approach" . | JOURNAL OF FOOD COMPOSITION AND ANALYSIS 146 (2025) . |
| APA | Arcel, Mulowayi Mutombo , Meng, Li , Gatsi, Blessing , Shen, Zhen Hui , Murengami, Bryan Gilbert , Cui, Zhe ming et al. Optimizing nutrient retention in carrots during storage: A hyperspectral imaging approach . | JOURNAL OF FOOD COMPOSITION AND ANALYSIS , 2025 , 146 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
随着计算机技术的发展，三维重建技术作为一个新兴领域，越来越广泛用于人们的日常生活中。植物三维重建作为三维重建领域的一个分支，在农业生产、机器人定位、机器人定位、自然景观再现、研究植物生长状态、植物形态研究、电影游戏等多个领域都得到了应用。以白茶这一植物为例，以改进的运动恢复结构为基础进行三维重建。首先，使用直方图均衡化增加了图像的动态范围，再基于yolov5对白茶进行训练以减少背景对重建的影响，训练识别率达到90%以上，再基于运动恢复结构对白茶进行重建得到点云。由于初始点云具有大量噪声点，手动去除噪声点并基于Possion表面重建得到茶树精确三维模型。最后，通过对比不同帧采样、重建精度配置下的重建效率以及模型精度，得到三维重建的最佳重建策略。优化后的重建策略使得重建速度保持在5min以内，并保持了重建精度，为多视角三维重建技术在植物领域的三维重建提供了理论基础。
Keyword ：
图像分割 图像分割 白茶 白茶 直方图均衡化 直方图均衡化 系统优化 系统优化 运动恢复结构 运动恢复结构
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 冯睿鸣 , 郑书河 , 雷锦桂 . 基于改进的多视角茶树三维重建方法 [J]. | 计算机仿真 , 2025 , 42 (06) : 134-138,153 . |
| MLA | 冯睿鸣 et al. "基于改进的多视角茶树三维重建方法" . | 计算机仿真 42 . 06 (2025) : 134-138,153 . |
| APA | 冯睿鸣 , 郑书河 , 雷锦桂 . 基于改进的多视角茶树三维重建方法 . | 计算机仿真 , 2025 , 42 (06) , 134-138,153 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Intelligent detection of tomato seedling transplant quality represents a core technology for advancing agricultural automation. However, in practical applications, existing algorithms still face numerous technical challenges, particularly with prominent issues of false detections and missed detections during recognition. To address these challenges, we developed the ESG-YOLO object detection model and successfully deployed it on edge devices, enabling real-time assessment of tomato seedling transplanting quality. Our methodology integrates three key innovations: First, an EMA (Efficient Multi-scale Attention) module is embedded within the YOLOv8 neck network to suppress interference from redundant information and enhance morphological focus on seedlings. Second, the feature fusion network is reconstructed using a GSConv-based Slim-neck architecture, achieving a lightweight neck structure compatible with edge deployment. Finally, optimization employs the GIoU (Generalized Intersection over Union) loss function to precisely localize seedling position and morphology, thereby reducing false detection and missed detection. The experimental results demonstrate that our ESG-YOLO model achieves a mean average precision mAP of 97.4%, surpassing lightweight models including YOLOv3-tiny, YOLOv5n, YOLOv7-tiny, and YOLOv8n in precision, with improvements of 9.3, 7.2, 5.7, and 2.2%, respectively. Notably, for detecting key yield-impacting categories such as "exposed seedlings" and "missed hills", the average precision (AP) values reach 98.8 and 94.0%, respectively. To validate the model's effectiveness on edge devices, the ESG-YOLO model was deployed on an NVIDIA Jetson TX2 NX platform, achieving a frame rate of 18.0 FPS for efficient detection of tomato seedling transplanting quality. This model provides technical support for transplanting performance assessment, enabling quality control and enhanced vegetable yield, thus actively contributing to smart agriculture initiatives.
Keyword ：
edge device deployment edge device deployment ESG-YOLO ESG-YOLO tomato seedlings tomato seedlings transplanting quality detection transplanting quality detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Xinhui , Dong, Zhenfa , Wang, Can et al. ESG-YOLO: An Efficient Object Detection Algorithm for Transplant Quality Assessment of Field-Grown Tomato Seedlings Based on YOLOv8n [J]. | AGRONOMY-BASEL , 2025 , 15 (9) . |
| MLA | Wu, Xinhui et al. "ESG-YOLO: An Efficient Object Detection Algorithm for Transplant Quality Assessment of Field-Grown Tomato Seedlings Based on YOLOv8n" . | AGRONOMY-BASEL 15 . 9 (2025) . |
| APA | Wu, Xinhui , Dong, Zhenfa , Wang, Can , Zhu, Ziyang , Guo, Yanxi , Zheng, Shuhe . ESG-YOLO: An Efficient Object Detection Algorithm for Transplant Quality Assessment of Field-Grown Tomato Seedlings Based on YOLOv8n . | AGRONOMY-BASEL , 2025 , 15 (9) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
