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

    Development and performance evaluation of a guide vane inclination automatic control system for corn threshing unit based on feedrate monitoring

    Fan C.Zhang D.Yang L.Cui T....
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.The crop threshing process and the material movement speed are difficult to control with the fluctuation of feedrate in the longitudinal axial flow threshing unit, which results in the decline of threshing performance. We developed a corn threshing unit with an electric-hydraulic top cover guide vane inclination automatic control system based on the feedrate to overcome these problems. The optimal control model of feedrate and guide vane inclination was established for the control system: When the feedrates were 6, 8, and 10 kg/s, the optimal guide vane inclinations were 22°, 24°and 26°, respectively. Taking the constant guide vane inclination (20°) as the control group, the operational performance of the automatic control system of guide vane inclination was evaluated. The test bench results showed that the steady-state response time was 0.15 s, and the error was maintained within 0.27°, the control algorithm can meet the design requirement. Moreover, results demonstrated that the threshing unit with control system outperformed the one with the constant guide vane inclination, with the average torque range of the threshing rotor axis, average peak torque, the broken grain rate (BGR)、the unthreshed grain rate (UGR) and the grain-entrainment loss rate (EGR) decreasing by 17.39%, 19.03%, 1.63%, 0.06%, and 0.19%, respectively. Thus it can be seen that corresponding to different feedrates conditions, a proper guide vane inclination from the threshing unit with the developed automatic control system could obtain better working quality than the results with constant guide vane inclination.
      原文链接:
    • NSTL
    • Elsevier

    A Machine Learning approach to reconstruct cloudy affected vegetation indices imagery via data fusion from Sentinel-1 and Landsat 8

    dos Santos E.P.da Silva D.D.Dias R.L.S.do Amaral C.H....
    12页
    查看更多>>摘要：? 2022 Elsevier B.V.A way to reconstruct optical sensor-derived images allowing cloud-free vegetation monitoring is proposed in this paper. The motivation is the influence that clouds have on optical remote sensing of tropical regions, which hinders Earth observation systems because their presence reduces imaging frequency. To circumvent that problem, a machine learning model-based integration methodology for the fusion of Landsat 8 and Sentinel-1 data is proposed herein. Sentinel-1 constellation has mounted Synthetic aperture radar (SAR) sensors are used because the imaging is not affected by clouds due to microwave spectrum characteristics. To study the problem and predict both the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI), three algorithms were selected: multivariate linear regression, multivariate adaptive regression splines, and random forest (RF). Two testing strategies were also chosen: k-Fold cross-validation for hyperparameter tuning of the model and holdout testing to assess the generalization ability of the model. The SAR covariables were employed to feed the algorithms, including selected SAR vegetation indices; in addition, environmental data, such as land use and land cover (LULC), the date, and position of the samples were used. The predictions from the NDVI and EVI produced good results, namely, similar Willmott's agreement index (d) values that ranged from ～0.64 to 0.96. The best-fitted model was the RF, which was used to reconstruct the NDVI images and produced good results that agreed well with the predictions (d index from 0.58 to 0.87) and spatial patterns. The results obtained show that the integration of radar and environmental covariables with optical vegetation indices can allow vegetation monitoring that is free of gaps due to clouds.
      原文链接:
    • NSTL
    • Elsevier

    Two-stage method based on triplet margin loss for pig face recognition

    Wang Z.Liu T.
    15页
    查看更多>>摘要：? 2022 Elsevier B.V.In recent years, as the scale of breeding farms has become increasingly larger, to improve animal welfare and increase farm output, an increasing number of farms have proposed the idea of precision feeding for individual animals. Therefore, how to accurately identify a single animal individually and provide a targeted breeding program for it has become the focus. We have designed and evaluated a lightweight pig face recognition model based on a deep convolutional neural network algorithm, which can achieve a high pig face recognition rate in complex environments. This is a two-stage convolutional neural network model. The first stage is responsible for pig face detection. Based on the EfficientDet-D0 model, we show an improved average precision for pig face detection from 90.7% to 99.1% by employing a dataset sampling technique. The second stage is responsible for pig face classification, using six classification models, including ResNet-18, ResNet-34, DenseNet-121, Inception-v3, AlexNet, and VGGNet-19, as the backbone and proposes an improved method based on the triplet margin loss function. To strengthen the network performance, the multitask learning method enables the network to effectively cluster the features of the feature extractor layer. Then, the k-nearest neighbor algorithm is used to replace the fully connected layer with a large number of parameters to classify the features. These improved models have a maximum classification accuracy of 96.8% for 28 pigs. The parameters of these improved models are reduced to 4.32% of the original at most. Finally, the two-stage model including EfficientDet-d0 and DenseNet 121 has a mean average precision value of 91.35% for face recognition of 28 pigs. Compared with the EfficientDet-d0 network trained by the one-stage method, the mean average precision value is improved by 28%. In addition, we reorganized the original dataset and performed 10-fold cross-validation, and the mAP value was 94.04%.
      原文链接:
    • NSTL
    • Elsevier

    Basic motion behavior recognition of single dairy cow based on improved Rexnet 3D network

    Ma S.Zhang Q.Li T.Song H....
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.Basic motion behaviors of dairy cows (lying, standing and walking) contain abundant health information. However, to monitor these behaviors accurately and efficiently by using camera-based methods remains challenging. In this study, time dimension was added to extend the Rexnet to Rank eXpansion Network 3D algorithm (Rexnet 3D) network to realize non-contact and automatic recognition of dairy cows’ basic motion behaviors. A total of 406 videos containing 256,500 frames of dairy cows in different scenes and postures were collected and tested. Six different networks including Resnet101, Mobilev2, Mobilev3, Shufflev2, C3D and S3D were selected to validate the performance of the proposed network. The average number of frames recognized per second (ANFR), FLOPs and Networks Weight were used to evaluate the performance of the method. Experimental results showed that behavior recognition accuracy, ANFR, FLOPs and Networks Weight of the proposed method were 95.00%, 76.52 fps, 15.80 G and 14.30 M, respectively. Meanwhile, a total of 10 unedited videos with 1,722 s in total (43,065 frames) were collected to verify the effectiveness in real environment. The results showed that the accuracy of the proposed method was higher when the sampling interval was five frames and the accuracy of the specific three basic motion behaviors was 91.02%, and the ANFR was 101.02 fps. In general, these findings indicated that it was feasible to use a designed network for accurate recognition of cows’ basic motion behaviors. The network could provide necessary reference for improving the precision breeding and health welfare of dairy cows.
      原文链接:
    • NSTL
    • Elsevier

    A computationally efficient model for granular material piling in a container

    Liu Z.Jiang C.Evans J.T.Dhamankar S....
    9页
    查看更多>>摘要：? 2022 Elsevier B.V.This paper describes the development of a novel computationally efficient model to simulate the granular material piling process inside a container. The model computes both the granular material profile inside the container and spillage amount and location out of the container based on the cart geometry, impact location and orientation of flow of the grain transmitted into the container. The performance and utility of the grain fill model strategy is demonstrated via simulation of the grain piling process inside a grain cart during agricultural combine harvester grain unloading from the combine into a tractor-driven grain cart. The simulation demonstrates that the model can simulate both the grain profile change and spillage in real time. Experimental data collected from a benchmark system with LiDAR was used to quantify the model accuracy during grain unloading. The experimental results show that the model can achieve 0.2-m accuracy during a corn unloading process from an empty to a full grain cart.
      原文链接:
    • NSTL
    • Elsevier

    Developing an automatic conjunctive surface-groundwater operating system for sustainable agricultural water distribution

    Askari Fard A.Hashemy Shahdany S.M.Javadi S.Maestre J.M....
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.Groundwater extraction from aquifers is the primary approach for supplying agricultural water demand due to the inadequate, unfair, and unreliable distribution of surface water (SW) systems. In this regard, the present study developed an automated operating system for conjunctive surface and groundwater (GW) resources. By centralized model predictive control (CMPC), an automated SW distribution system was developed in MATLAB and integrated with the groundwater modeling system (GMS) to provide an intelligent SW-GW conjunctive operating system in water scarcity scenarios. A controversial irrigation district in central Iran is selected as the test case in Iran. GW extraction from active tube-wells in the SW distribution system's territory includes 39%, 21%, 40% deep, semi-deep, and shallow. Besides, about 65% of energy consumption is related to over-exploitation in deep wells. The notable point of automating the SW system is the high capability of CMPC to control fluctuations in all canal reaches so that the dependability and adequacy of water distribution become reasonable even under severe scenarios. Intelligent SW-GW operating system led to an uprise of 0.1–2.2, 0.2–3.2, 0.4–3.9, 0.7–6.9, 1.5–9.1, and 3.8–13.5 m in the aquifer water level, respectively, within 12, 2, 36, 48, 60, and 120 months. Besides, Water extraction reduction from the aquifer after one year is about 16%, and the reduction of annual energy consumption is around 81%. The proposed method enables authorities to promote the SW distribution in practical, implementable, and step-by-step planning to reduce GW extraction from tube-wells based on actual water reduction potential.
      原文链接:
    • NSTL
    • Elsevier

    Biophysical parameter estimation of crops from polarimetric synthetic aperture radar imagery with data-driven polynomial chaos expansion and global sensitivity analysis

    Celik M.F.Erten E.
    12页
    查看更多>>摘要：? 2022 Elsevier B.V.Data-driven machine learning regression methods are easy to implement and applicable to a wide-range of data in biophysical parameter estimation and have become a common approach in the remote sensing field. Among the regression methods, polynomial chaos expansion (PCE) is one of the reliable and interesting ones due to its tight relationship with uncertainty quantification. One of the advantages of PCE is that global sensitivity analysis (GSA) with Sobol's method can be analytically computed from polynomial coefficients if the input space is statistically independent. However, most of the phenomena include dependent features either statistically or physically. Though the physical independence is provided between inputs, they must be statistically uncorrelated. Therefore, an independent and uncorrelated input space must be created before the regression analysis. In this paper, we performed PCE-based regression analysis for the estimation of biophysical parameters of crops. The study was conducted in the experimental fields of field pea, barley, canola, and oat of the AgriSAR2009 campaign. The input parameters of the regression model were formed by creating polarimetric features derived from RADARSAT-2 imagery. The estimated biophysical parameters were based on the discrete in situ measurements of leaf area index (LAI) and normalized difference vegetation index (NDVI), scattered semi-randomly in each crop field. We implemented neighbourhood component analysis (NCA) to create an independent and uncorrelated input space by eliminating correlations. Finally, we investigated the importance of features, which drive the PCE-based regression models applying GSA with Sobol's method. Besides the individual effects of each feature, their interactions were found significant.
      原文链接:
    • NSTL
    • Elsevier

    An improved YOLOv5 model based on visual attention mechanism: Application to recognition of tomato virus disease

    Li M.Bao Z.Li Y.Xu F....
    12页
    查看更多>>摘要：? 2022 Elsevier B.V.Traditional target detection methods cannot effectively screen key features, which leads to overfitting and produces a model with a weak generalization ability. In this paper, an improved SE-YOLOv5 network model is proposed for the recognition of tomato virus diseases. Images of tomato diseases in greenhouses were collected using a mobile phone, and the collected images were expanded. A squeeze-and-excitation (SE) module was added to a YOLOv5 model to realize the extraction of key features, using a human visual attention mechanism for reference. The trained network model was evaluated on the test set of tomato virus diseases. The accuracy was 91.07%, which was 7.12%, 17.85% and 8.91% higher than that of the Faster regions with convolutional neural network features (R-CNN) model, single-shot multiBox detector (SSD) model and YOLOv5 model, respectively. Meanwhile, the mean average precision (mAP@0.5) was 94.10%, which was 1.23%, 16.77% and 1.78% higher than that of the Faster R-CNN model, SSD model and YOLOv5 model. The proposed SE-YOLOv5 model can effectively detect regions of tomato virus disease, which provides disease identification and control theoretical research and technical support.
      原文链接:
    • NSTL
    • Elsevier

    The closed-open truck and loader routing problem for biomass transportation from satellite storage locations to a bioenergy plant

    An H.
    13页
    查看更多>>摘要：? 2022The complex daily operation and movement of costly machines transporting biomass to bioenergy plants can significantly affect the economic viability of the system. In particular, while a truck should have a closed route from/to the bioenergy plant, a mobile loader may have different departing and returning locations. This study formulated the closed-open routing of mobile machines as a mixed-integer linear programming model considering challenging modeling factors such as multi-trips, multi-visits, and synchronized loading operations. The formulated problem prescribes daily schedules for trucks and mobile loaders to minimize the total cost of transporting biomass from satellite storage locations to a bioenergy plant. A novel constructive heuristics-based method is developed in this research to solve the problem effectively for practical use. The numerical studies showed that the model correctly made operating schedules for real-life examples. The developed solution method outperformed the commercial solvers by reducing the total costs and finding feasible solutions in difficult cases, which the commercial solvers could not do. Further analysis at the branch-and-bound root node showed the effectiveness of the developed heuristics to strengthen the branch-and-bound procedure compared to the CPLEX heuristics-and-cuts.
      原文链接:
    • NSTL
    • Elsevier

    Automated detection of boundary line in paddy field using MobileV2-UNet and RANSAC

    He Y.Zhang X.Zhang Z.Fang H....
    13页
    查看更多>>摘要：? 2022 Elsevier B.V.The detection of boundary lines in farmlands is critical for precision agriculture and automatic navigation. This study proposed a novel method for automatic detection of boundary lines in paddy fields based on images acquired from a vision system. These images were collected from different environmental conditions with wheel marks, shadows, weeds, and uneven illumination in paddy fields. To alleviate the effect of this environmental noise on the detection of boundary lines, the proposed method was designed with the required robustness, which included two sequentially linked phases: farmland area segmentation and boundary line detection. For the segmentation of the farmland area, this study proposed an effective deep learning model, called MobileV2-UNet, which used modified inverted residual blocks and the dilated convolution to achieve the accurate segmentation of the farmland area and nonfarmland area. For the detection of farmland boundary lines, a multiboundary detection method based on the frame correlation and random sample consensus (RANSAC) algorithm was applied to detect the side boundary and end boundary, which could provide critical information for agricultural machinery steering. Results showed that the mean intersection over union (mIoU) for area segmentation reached 0.908, and the average angular and vertical errors for boundary line detection were 0.865° and 0.021, respectively. Moreover, the processing speed reached 8 frames per second, which could meet the real-time work demands of agricultural machinery.
      原文链接:
    • NSTL
    • Elsevier