首页期刊导航|Computers and Electronics in Agriculture
期刊信息/Journal information
Computers and Electronics in Agriculture
Elsevier Science Publishers
Computers and Electronics in Agriculture

Elsevier Science Publishers

0168-1699

Computers and Electronics in Agriculture/Journal Computers and Electronics in AgricultureSCIEIISTP
正式出版
收录年代

    Chlorophyll detector development based on snapshot-mosaic multispectral image sensing and field wheat canopy processing

    Tang W.Zhao R.Li M.Sun H....
    15页
    查看更多>>摘要：? 2022 Elsevier B.V.To achieve rapid nondestructive detection of chlorophyll content in crops in a field environment, we designed a new lightweight device based on a snapshot-mosaic imaging sensor given the sensitive properties of chlorophyll in the red-edge to near-infrared band (700–900 nm) and the advantages of imaging spectroscopy in environmental noise separation. The hardware part of the device includes a spectral camera based on a snapshot-mosaic sensor, a main control unit, a network module, a storage module, a power supply module, and a display and remote-control device. The software part was written using the Qt library and the C++ programming language. It includes the connection and initialization of the sensor, the control of the exposure time, the display of the image in real time, the acquisition and storage, and the calculation of the reflectance. The sensor was tested and calibrated to evaluate the sensor performance. Experimental results show that the different channels of the sensor have an excellent linear relationship for light intensity changes and can be used to measure reflected radiation from crop leaves in a field environment after calibration. At the same time, field experiments on wheat were conducted. A dark channel filtering method for 25 channels of the developed device was proposed to effectively eliminate the scattered light interference from the crop canopy in the spectral images. The background interference was effectively eliminated by background segmentation. Partial least squares regression (PLSR) method was used for modeling after preprocessing and band screening of the spectral data. The model achieved high accuracy with RC2 of 0.87, RV2 of 0.79, and RMSE of 3.94 mg/L. As a result, the system combined the proposed model with the developed device can effectively eliminate the interference of soil background and scattered light caused by the complex structure of crop canopy, and improve the accuracy of diagnosis. So that the system has potential in the crop growth variation analysis.
      原文链接:
    • NSTL
    • Elsevier

    Quantifying the accuracies of six 30-m cropland datasets over China: A comparison and evaluation analysis

    Ge Q.Zhang C.Dong J.
    14页
    查看更多>>摘要：? 2022 Elsevier B.V.With the development of remote sensing technology, more and more fine-resolution cropland datasets have emerged as powerful tools for agriculture planning and food security evaluation. But questions about their accuracy and reliability must be answered before using them, making evaluations necessary. So far, little attention has been paid to the performance of fine-resolution (e.g., 30 m) and cropland-specific products at continental or regional scales. This study implemented a comparison analysis and accuracy assessment for six cropland products with a 30-m resolution in China circa 2015, including FROM-GLC, GLC_FCS, CLCD, AGLC, GFSAD, GLAD. Their similarities and disparities were delineated at national, provincial, meridional, and zonal scales. 33,713 ground truth points were then collected through visual interpretation of Google Earth images and from existing available validation datasets, to evaluate the pixel-wise accuracy of them across China. In terms of spatial consistency, high agreement among the six products could be found in North China Plain and Northeast China, and low agreement was found in Southern, Southwest, and Northwest China. Topography including elevation and slope were important factors influencing spatial consistency. As for provincial area accuracy, CLCD and AGLC were most correlated with statistical data (r2 > 0.9), followed by GLAD (0.88) and AGLC (0.87). FROM-GLC had the lowest correlation (r2 = 0.37) with statistics. The relative area differences between each product and statistics also demonstrated that CLCD had the best area accuracies in most provinces. By contrast, GLC_FCS had a severe overestimation and FROM-GLC suffered from a large underestimation of cropland area. Last, the pixel-wise validation results indicated that CLCD and GLAD had the highest overall accuracy (OA) of 0.88, followed by AGLC (0.85) and GFSAD (0.84). FROM-GLC and GLC_FCS had the lowest OAs of less than 0.70. The comparison and evaluation results in this study can provide insights into the national and provincial performances of these fine-resolution cropland products and give valuable references for guiding data usage and help to improve future land use/cover mapping.
      原文链接:
    • NSTL
    • Elsevier

    Development and evaluation of a pneumatic finger-like end-effector for cherry tomato harvesting robot in greenhouse

    Zhang F.Zhang J.Yuan T.Yin J....
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.This paper presents the development and evaluation of a pneumatic finger-like end-effector for cherry tomato harvesting robot. The end-effector is pneumatically controlled and has the capability of picking cherry tomatoes continuously and steadily. The end-effector is compact in overall structure, which consists of finger-like clamping finger, rotating and telescopic cylinders, and RGB-D camera, etc. Another important feature is that the clamping finger uses a combination of clamping and rotating and has good adaptability in dense operating environments. Further, a hand-picking dynamic measurement system is developed to measure and analyze the applied force and disturbance for simplified picking methods during picking. The hand-picking test shows that both the applied force and the disturbance are smaller for rotating compared to pulling, so the method of rotating is chosen for the design of the end-effector in this study. The field test shows the average cycle time of picking single cherry tomato is 6.4 s. The harvest success rates for pickable cherry tomatoes in different directions are 84% (right), 83.3% (back), 79.8% (left), and 69.4% (front), respectively. The failure cases are analyzed and collision and localization failure are the main causes of unsuccessful picking during picking.
      原文链接:
    • NSTL
    • Elsevier

    A visual identification method for the apple growth forms in the orchard

    Lv J.Lu W.Yang B.Zou L....
    9页
    查看更多>>摘要：? 2022 Elsevier B.V.The work aimed at the visual identification of the growth forms of fruits to facilitate the subsequent use of different harvesting mechanisms for different growth forms of fruits by robots. The improved YOLOv5 deep learning algorithm was used to propose a visual identification method for the growth forms of apples in the orchard. Specifically, the feature extraction module of the YOLOv5 algorithm imitated the BiFPN model to propose the BiFPN-S structure. The spread of features and feature reuse were enhanced to better fit features. The improved algorithm was called YOLOv5-B. The network SiLU activation function was replaced with the ACON-C activation function to improve its network performance. The COCO data set was used to pre-train the network, and then the data set of the work was trained by the transfer learning method. After the training, the generated optimal model was applied for the visual-identification test of the growth of apple fruits. The results showed that the improved algorithm model considered high accuracy and real-time performance, with the map reaching 98.4% and the F1 value of 0.928. The average accuracy of identifying the growth forms of apples for the test set was 98.45%, and the processing speed was 71 FPS.
      原文链接:
    • NSTL
    • Elsevier

    Improved estimation of canopy water status in maize using UAV-based digital and hyperspectral images

    Meiyan S.Qizhou D.ShuaiPeng F.Baoguo L....
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.The estimation of water status of maize is important for evaluating crop growth and conducting precision irrigation. The development of unmanned aerial vehicles (UAVs) equipped with sensor technologies provides high-quality data for estimating maize water status. Only a few studies have been conducted on the estimation of maize equivalent water thickness (EWT) and fuel moisture content (FMC) using UAV hyperspectral images. This study aimed to estimate the leaf and canopy water status of maize inbred lines using UAV digital and hyperspectral data. Leaf area index (LAI) is required to obtain canopy water indicators, canopy equivalent water thickness (EWTc), and canopy fuel moisture content (FMCc). However, obtaining the LAI from remote sensing images requires the support of samples or prior knowledge. The LAI is positively correlated with canopy coverage (CC), which can be extracted accurately from UAV images. Therefore, for EWTc and FMCc, this study aimed to use the CC instead of the LAI to construct and test new canopy water indicators in order to improve the convenience of UAV imaging technology in monitoring maize water status. The results showed that, after the introduction of CC, two indicators, revised canopy equivalent water thickness (r-EWTc) and revised canopy fuel moisture content (r-FMCc), were both sensitive to the difference vegetation index (DVI) derived from UAV hyperspectral images. The r-FMCc was the most effective of the six water indicators used in this study, and the Pearson's correlation coefficient (r) with DVI was 0.93. The results indicate that the CC extracted directly from UAV digital images is suitable to replace LAI, and helps improve the data availability for estimating canopy water status. The UAV hyperspectrum can accurately estimate the water status in maize inbred lines, which is helpful for further application of UAV data in breeding.
      原文链接:
    • NSTL
    • Elsevier

    Advances in the estimations and applications of critical nitrogen dilution curve and nitrogen nutrition index of major cereal crops. A review

    Cao W.Cao Q.Ata-UI-Karim S.T.Yoichiro K....
    14页
    查看更多>>摘要：? 2022 Elsevier B.V.Nitrogen (N) is one of the decisive elements for plant growth, crop biomass accumulation, and yield formation of cereal crops. However, managing N in crop production and comparing N use efficiency are challenging without prior knowledge of in-season crop N status. The development of critical N (Nc) dilution curves based on allometry between plant metabolic and structural compartments allows the estimation of crop N nutrition status by determining the N nutrition index (NNI). The purpose of this article is to review the research progress on the development of Nc curves in three major cereal crops (wheat, maize, and rice). The focus of this review paper is to compare the Nc curves of major cereals developed worldwide and to explain the differences in these Nc curve parameters in light of genotype through the management of environmental interactions. Additionally, this review provides an update on the most relevant methods for non-destructive estimation of the NNI of major cereal crops using various remote sensing technologies for large-scale applications. This review also sheds light on the applicability of Nc curve-based NNI for in-season crop N diagnosis, crop N requirement, crop grain yield, and quality prediction. Moreover, this review outlines future research directions to expand the impact of this approach on crop production.
      原文链接:
    • NSTL
    • Elsevier

    Changes in the effects of water and nitrogen management for potato under current and future climate conditions in the U.S

    Paff K.Fleisher D.Timlin D.
    16页
    查看更多>>摘要：? 2022A major portion of the United States’ potato (Solanum tuberosum, L.) production occurs in the state of Washington. Local intensive management practices involving heavy nitrogen and irrigation use can result in substantial resource loss due to sandy soils. It is important to examine the effects of nitrogen and water management practices under current climate conditions and how these effects may change in the future to develop best management practices. This study simulated the response of the Ranger Russet variety at two locations to three nitrogen (N) (168, 336, and 504 kg N/ha) and four irrigation (475, 645, 748, and 816 mm) rates using the USDA-ARS SPUDSIM potato model. The model was calibrated and evaluated using field data. Future weather was generated for two Representative Concentration Pathways (RCPs) (4.5 and 8.5) and four years (2030, 2050, 2070, and 2095). Management practices were evaluated based on whether yield, N, or water use was the priority. The highest yields were achieved when the highest input levels were used across all climate scenarios, but irrigation levels had minimal effect on yields for RCP 8.5 2070 and 2095. High input yields increased under RCP 4.5 as compared with historical values, though the yield increase was smaller for later years. High input yields increased initially for RCP 8.5 but decreased in later years. Water use was most efficient under low irrigation/high N treatments. N leaching decreased by as much as 83% for low irrigation/high N treatments, as compared to high irrigation/high N, though this also resulted in ≤ 23% yield reductions; however, this yield reduction decreased with increasing RCP and year. Nitrogen use efficiency was highest under high irrigation/low N conditions historically, and under low irrigation/low N in the future. More resource efficient management practices resulted in yield reductions, but the differences in yield between the most efficient practices and the highest yielding practices decreased as climate change became more severe. These results benefit growers by evaluating management options based on different goals and promoting environmental stewardship.
      原文链接:
    • NSTL
    • Elsevier

    Patch cropping- a new methodological approach to determine new field arrangements that increase the multifunctionality of agricultural landscapes

    Geistert J.Grahmann K.Bloch R.Bellingrath-Kimura S.D....
    15页
    查看更多>>摘要：? 2022Agricultural intensification decreased land cover complexity by converting small complex arable field geometries into large and simple structures which then were managed uniformly. These changes have led to a variety of negative environmental effects and influence ecosystem services. We present a novel small-scale and site-specific cropping system which splits a large field into small homogeneous sub-fields called ‘patches’ grouped in different yield potentials. A detailed workflow is presented to generate new spatially arranged patches with special focus on preprocessing and filtering of multi-year yield data, the variation in patch sizes and the adaptation of maximum working width to use available conventional farm equipment and permanent traffic lanes. The reduction of variance by the used cluster algorithm depends on the within-field heterogeneity. The patch size, the number of growing seasons (GS) used for clustering and the parallel shift of the patch structure along the permanent traffic lane resulted in a change in relative variance. Independent cross validation showed an increased performance of the classification algorithm with increasing number of GS used for clustering. The applied cluster analysis resulted in robust field segregation according to different yield potential zones and provides an innovative method for a novel cropping system.
      原文链接:
    • NSTL
    • Elsevier