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

    A 3D grape bunch reconstruction pipeline based on constraint-based optimisation and restricted reconstruction grammar

    Xin B.Whitty M.
    14页
    查看更多>>摘要：? 2022 Elsevier B.V.Phenotypic traits of grapevines are known to be closely related to grapevine yield, wine flavour and sensitivity to disease. Traditional phenotyping methods based on manual measurements face the bottleneck of intensely repetitive and time consuming measurement. As viticulturists turning their focus to the 3D automatic phenotyping domain, existing work on grape bunch phenotyping indicates deficiencies in incomplete reconstruction information, poor element coincidence with the ground truth and poor performance under field conditions. To this end, the proposed work introduces a novel reconstruction pipeline by dividing it into sub-problems of visible-berry-related reconstruction and invisible element prediction. By taking a 2D image of the target bunch as the only sensor input, visible berries are detected using image processing algorithms. With the detected berry information, their morphological positions are predicted, from which internodes that are associated with the detected berries are derived. Parameters of derived internodes are then estimated employing constraint-based optimisation theory, from which the visible-berry-related reconstruction is able to be achieved. Invisible element prediction is then conducted by filling elements according to a Restricted Reconstruction Grammar (RRG). A fully reconstructed bunch model is finally presented. Compared with existing work, the proposed grape bunch reconstruction pipeline achieved an improvement in quantity estimation of rachis internodes, tertiary internodes and pedicels, whose percentage errors were indicated as 21.2, 42.2 and 31.2% respectively. A better performance was also revealed in length estimations of secondary internodes and pedicels with percentage errors of 3.5 and 0.5%. This may largely facilitate related studies on disease control of grape bunches since internode numbers and lengths are closely related to bunch compactness which is the indicator of disease sensitivity. Especially, the proposed reconstruction pipeline shows an promising improvement in element coincidence with F1 scores of 0.90, 0.77, 0.45, 0.43 for respective element types. Knowing that element coincidence may influence the inner space utilisation of a bunch, the proposed work provides a better option for 3D grape bunch phenotyping.
      原文链接:
    • NSTL
    • Elsevier

    Deep Learning-based query-count forecasting using farmers’ helpline data

    Godara S.Toshniwal D.
    12页
    查看更多>>摘要：? 2022 Elsevier B.V.Forecasting the nationwide demand for agriculture-related help plays a crucial role in supporting the decision-making activities of the agri-sector. In this direction, the article presents an artificial intelligence-based framework for predicting the agriculture-related query-calls count in the nation's farmers-helpline network. The present work utilizes advanced data mining techniques to operate on the available dataset. The dataset utilized for the study includes over 1.3 million query-call logs accumulated from the “Kisan Call Center”, a farmers’ helpline network administered by the Ministry of Agriculture, Government of India. Moreover, to validate the proposed framework, we process data corresponding to the top-five rice-producing states of India. In addition, the study compares the forecasting performance of four Machine Learning and Deep Learning-based models, i.e., Support Vector Regression, Multi-layer Perceptron, Long Short-Term Memory Networks, and Gated Recurrent Units. The experimental results convey that the proposed framework is useful for predicting trends in farmers’ problems. Furthermore, the framework is valuable in developing fully automated AI-based systems connected with the data servers of the Kisan Call Centers and providing the forecast in a mechanized manner.
      原文链接:
    • NSTL
    • Elsevier

    Monitoring crop phenology with street-level imagery using computer vision

    d'Andrimont R.Yordanov M.Martinez-Sanchez L.van der Velde M....
    14页
    查看更多>>摘要：? 2022 The Author(s)Street-level imagery holds a significant potential to scale-up in-situ data collection. This is enabled by combining the use of cheap high-quality cameras with recent advances in deep learning compute solutions to derive relevant thematic information. We present a framework to collect and extract crop type and phenological information from street level imagery using computer vision. Monitoring crop phenology is critical to assess gross primary productivity and crop yield. During the 2018 growing season, high-definition pictures were captured with side-looking action cameras in the Flevoland province of the Netherlands. Each month from March to October, a fixed 200-km route was surveyed collecting one picture per second resulting in a total of 400,000 geo-tagged pictures. At 220 specific parcel locations, detailed on the spot crop phenology observations were recorded for 17 crop types (including bare soil, green manure, and tulips): bare soil, carrots, green manure, grassland, grass seeds, maize, onion, potato, summer barley, sugar beet, spring cereals, spring wheat, tulips, vegetables, winter barley, winter cereals and winter wheat. Furthermore, the time span included specific pre-emergence parcel stages, such as differently cultivated bare soil for spring and summer crops as well as post-harvest cultivation practices, e.g. green manuring and catch crops. Classification was done using TensorFlow with a well-known image recognition model, based on transfer learning with convolutional neural network (MobileNet). A hypertuning methodology was developed to obtain the best performing model among 160 models. This best model was applied on an independent inference set discriminating crop type with a Macro F1 score of 88.1% and main phenological stage at 86.9% at the parcel level. Potential and caveats of the approach along with practical considerations for implementation and improvement are discussed. The proposed framework speeds up high quality in-situ data collection and suggests avenues for massive data collection via automated classification using computer vision.
      原文链接:
    • NSTL
    • Elsevier

    A high-precision forest fire smoke detection approach based on ARGNet

    Zhan J.Hu Y.Zhou G.Cai W....
    18页
    查看更多>>摘要：? 2022 Elsevier B.V.The occurrence of forest fires can lead to ecological damage, property loss, and human casualties. Current forest fire smoke detection methods do not sufficiently consider the characteristics of smoke with high transparency and no clear edges and have low detection accuracy, which cannot meet the needs of complex aerial forest fire smoke detection tasks. In this paper, we propose Adjacent layer composite network based on a recursive feature pyramid with deconvolution and dilated convolution and global optimal nonmaximum suppression (ARGNet) for high-accuracy detection of forest fire smoke. First, the Adjacent layer composite network is proposed to enhance the extraction of smoke features with high transparency and no clear edges, and SoftPool in it is used to retain more feature information of smoke. Then, a recursive feature pyramid with deconvolution and dilated convolution (RDDFPN) is proposed to fuse shallow visual features and deep semantic information in the channel dimension to improve the accuracy of long-range aerial smoke detection. Finally, global optimal nonmaximum suppression (GO-NMS) sets the objective function to globally optimize the selection of anchor frames to adapt to the aerial photography of multiple smoke locations in forest fire scenes. The experimental results show that the ARGNet parametric number on the UAV-IoT platform is as low as 53.48 M, mAP reaches 79.03%, mAP50 reaches 90.26%, mAP75 reaches 82.35%, FPS reaches 122.5, and GFLOPs reaches 55.78. Compared with other mainstream methods, it has the advantages of real-time detection and high accuracy.
      原文链接:
    • NSTL
    • Elsevier

    Research on fish bait particles counting model based on improved MCNN

    Hou S.Liu J.Wang Y.An D....
    9页
    查看更多>>摘要：? 2022 Elsevier B.V.In intensive aquaculture, quantitative research on bait particles has important theoretical and practical significance for reducing breeding costs and realizing intelligent feeding, and can effectively reduce environmental pollution caused by excessive bait. However, the current methods based on acoustics and machine vision are difficult to count tiny or overlapped bait particles, resulting in low counting accuracy of model. In order to solve the above problems, this paper proposes a counting model for small bait particles, using MCNN as the basic network to achieve efficient and stable counting performance in aquaculture. The proposed model consists of two parts: a multi-column feature extractor and a density map generator. The multi-column feature extractor is used as the front-end network of model. By introducing multiple branches, convolution kernels with different size are used to extract feature information of different scales and adapt to the non-uniform bait particles. Thereby, the multi-scale problem caused by perspective variation of bait particles is solved. In addition, the density map generator is used as the back-end network of model. Instead of the 1 × 1 convolutional layer in the original MCNN, the density map generator takes advantage of transposed convolutional layer to restore the poor quality of the density map caused by the down-sample in the multi-column feature extraction network. Besides, the ReLU function is helpful to increase the fitting ability of the model. Moreover, in order to further improve the quality of the density map and the counting performance of the model, the Euclidean distance loss and the structural similarity loss are combined as the final loss function of the model. The fusion of loss is beneficial to solve the ambiguity of density map caused by the Euclidean loss function. As the experimental results showed, compared with the original MCNN network, the mean absolute error MAE of the proposed model is reduced by 69.35%, and the mean square error MSE is reduced by 70.87%. In summary, the proposed bait particles counting model has high counting accuracy and is more stable, it is in favor of providing theoretical support for intelligent feeding study in aquaculture.
      原文链接:
    • NSTL
    • Elsevier

    Key technologies of machine vision for weeding robots: A review and benchmark

    Li Y.Guo Z.Shuang F.Li X....
    16页
    查看更多>>摘要：? 2022 Elsevier B.V.Due to its obvious advantages in saving labor and pesticides, weeding robots are one of the key technologies for modern and sustainable agriculture and have attracted increasing attention from researchers and developers. Some papers on machine-vision-based weeding robots have been published in recent years, yet there is no clear attempt to systematically study these papers to discuss the components of a robotic weed control system, such as visual navigation, weed detection and directional weeding. In this paper, typical machine-vision-based weeding robots proposed or constructed in the last 30 years, together with a few open datasets for weed detection, are reviewed. Key technologies such as image preprocessing, image segmentation, navigation line extraction, and weed recognition based on machine learning (ML) or deep learning (DL) for weeding robots are discussed. To illustrate the application of DL algorithms to weed detection, this paper provides weed object detection results and a comparative analysis of eight baseline methods based on DL using a public dataset. The study found that there are still many issues that need to be addressed in each part of the robotic weeding control system. Because of environmental variation and system complexity, machine-vision-based weeding robots are still in their early stages. The results of the systematic review provide an understanding of innovative trends in the use of machine vision in weeding systems and references for future research on weeding robots.
      原文链接:
    • NSTL
    • Elsevier

    An image restoration and detection method for picking robot based on convolutional auto-encoder

    Chen J.Zhang H.Wang Z.Wu J....
    13页
    查看更多>>摘要：? 2022 Elsevier B.V.At present, machine vision and deep learning theories have been widely used in fruit recognition and picking. However, in the process of identification and picking, there are often situations where the target is blocked, existing methods cannot accurately identify, or the identification accuracy rate is low. For improving the recognition rate of fruits under occlusion, this paper proposes an image restoration method based on a convolutional auto-encoder. This method first encodes the obstruction and then determines the general shape of the occluded fruit and compares the general shape with the coding part is combined to determine the area to be repaired. Finally, the area to be repaired is filled with pixels to realize the image repair and recognition of the occlusion map. The average repair rate of the method proposed in this paper is 95.96%, the restoration rate is 3.52% higher than the traditional convolution method, the L2 loss value is 0.63% lower than the traditional convolution method, the average detection accuracy of the restored fruits is 94.77%.
      原文链接:
    • NSTL
    • Elsevier

    Special report: AI Institute for next generation food systems (AIFS)

    Tagkopoulos I.Brown S.F.Liu X.Mason Earles J....
    6页
    查看更多>>摘要：? 2022 The Author(s)Artificial Intelligence (AI) has the potential to transform US food systems by targeting its biggest challenges: improving food yield, quality, and nutrition, decreasing resource consumption, increasing safety and traceability, and eliminating food waste. Despite big leaps in AI capacity, food systems present several challenges for the application and adoption of AI: (1) Food systems are highly diverse and biologically complex, (2) ground-truth data is sparse, costly, and privately held, and (3) human decisions and preferences are intricately linked to every stage of food system supply chains. To address these challenges and transform U.S. food systems, the AI Institute for Next Generation Food Systems (AIFS) aims to develop AI technologies and nurture the next generation of talent to produce and distribute more high-quality nutritious food with fewer resources. AIFS has six research clusters, including two Foundational Research Areas (Use-Inspired and Foundational AI, and Socioeconomics and Ethics) and four Application Research Areas spanning the entire food supply chain: Molecular Breeding, Agricultural Production, Food Processing and Distribution, and Nutrition. AIFS is developing generalizable, data efficient, and trustworthy AI solutions based on a knowledge-driven and human-in-the-loop learning paradigm designed to handle food system diversity and biological complexity, efficiently capture, and utilize food system data, and garner user trust via explainability, safety, privacy, and fairness.
      原文链接:
    • NSTL
    • Elsevier

    The influence of rotor downwash on spray distribution under a quadrotor unmanned aerial system

    Coombes M.Newton S.Knowles J.Garmory A....
    17页
    查看更多>>摘要：? 2022 Elsevier B.V.This paper investigates how sprays are influenced by rotor downwash produced by a quadrotor Unmanned Aerial System when crop spraying. Computational Fluid Dynamics simulations, using RANS modelling for the flow field and Lagrangian particle tracking for the spray, are conducted for several single-rotor and multi-rotor cases with the spray injected underneath the centre of the rotor. The rotor is modelled using a Blade Element actuator disc model. The accuracy of the computational approach is demonstrated by good agreement with experiment for both thrust and deposited spray pattern for a single rotor in an indoor environment. Both the experimental and computational results show that the peak in the spray distribution under a single rotor increases as rotor thrust increases, whilst increasing the rotor height above the ground causes this peak to decrease. The validated Computational Fluid Dynamics method is then used to simulate flight conditions for single-rotor and multi-rotor cases. These show the existence of a critical flight speed, above which the spray impinging on the ground no longer contains a notable peak. This behaviour is seen to be due to the streamtube detaching from the ground and no longer carrying the spray directly to the ground plane. Above this critical speed the spray is seen to become suspended in the air behind the Unmanned Aerial System. This behaviour makes realistic simulation more difficult, as details of the ambient turbulence conditions would be needed to model the subsequent spray transport. The reliance on turbulence to transport the spray is undesirable from a practical point of view due to the increased likelihood of significant spray drift.
      原文链接:
    • NSTL
    • Elsevier