Search

Apple fruits can be easily damaged, and bruises occur on peels during harvest, transportation and storage, which could decrease fruit quality. This paper proposed an apple bruise grading method based on hyperspectral imaging (HSI). The spectral information of sound apples (Yantai Fuji 8) was first captured using a hyperspectral reflectance imaging device (386-1016 nm). These apples were then mechanically damaged by the same impact forces, and the bruised regions were exposed to room temperature for at most 120 min. The spectral data of the bruised apples at four different exposure times (30 min, 60 min, 90 min and 120 min) were obtained. The spectral data were preprocessed using Procrustes analysis (PA) to enable a more diverse distribution of the spectra among different patterns. To both accurately maintain the spectral information of different patterns and reduce the dimensions of the spectra, piecewise nonlinear curve fitting (PWCF) was presented using the least squares algorithm, where the resultant fitting coefficients from different spectral intervals were catenated into a low-dimension feature descriptor. The feature descriptors were then fed to an error-correction output coding-based support vector machine (ECOC-SVM) to grade the bruised apples. To further evaluate the performance of the presented PWCF, conventional algorithms, including the successive projections algorithm (SPA), genetic algorithm (GA), principal component analysis (PCA) and kernel principal component analysis (KPCA), were introduced for comparison. Experimental results showed that the proposed method obtained the best grading accuracy (97.33%) compared to the other methods.

Locating picking points plays an important role in robotic litchi harvesting in orchards. However, the localisation accuracy can easily be affected by unstructured growing environments with variable illumination conditions and the unpredictable growing shapes of weight-bearing stems carrying litchi clusters. A computer-vision-based method is proposed to locate acceptable picking points for litchi clusters. To improve the illumination distributions of weakly illuminated images while leaving those of well-illuminated images unchanged, an iterative retinex algorithm was developed. Then, the litchi regions are segmented by combining red/green chromatic mapping and Otsu thresholding in the RGB colour space. By incorporating both local spatial and local hue-level intensity relationships, the hue component in the HSV colour space is re-constructed to filter the noise, and the stem regions are segmented in accordance with the distributed intervals of hue-level intensity. Finally, based on the connection and position relationship among the segmented litchi and stem regions, the structural distribution of the corners generated via Harris corner detection is analysed to locate the picking points. More than 97% of the pixels within litchi regions are correctly segmented after illumination compensation, and an improvement of 7% in the number of correctly segmented pixels within stem regions is achieved with the re-construction of the hue-level intensity. The overall performance of the proposed method was evaluated on test images with high illumination diversity, and accuracy greater than 83% in locating litchi picking points was achieved, showing better performance than three similar frameworks that do not incorporate our proposed procedures.

Late blight and early blight are the most destructive diseases for potatoes. It is valuable to distinguish diseases and their degrees of infection on potato leaves for timely prevention. This study investigated an accurate recognition method for detecting the disease type and degree of infection from potato leaf images. To segment the leaf from the images efficiently and accurately, an automatic scheme for the graph-cut algorithm is developed. The seeds of the foreground were extracted by Otsu thresholding, and the seeds of the background were extracted by color statistical thresholding on a* and b* components. To remove the backgrounds that have similar color as the infected patch, the superpixels that neighbor the outline of the leaf will be iteratively eliminated when their entropies are far from those of the major part of the leaf. Then, the color features were extracted from the individual channels of the L*a*b* on the refined region of interest (ROI), and the texture features were extracted using a local binary pattern (LBP). Finally, four classifiers based on the k-nearest neighbor (k-NN), support vector machine (SVM), artificial neural network (ANN) and random forest (RF) methods were adopted to evaluate the performance for recognition of potato disease. The performance of the proposed method was evaluated on 2840 images of healthy and diseased potato leaves. The segmentation results showed that the average intersection over union (IoU) was 93.70% for the five classes. For disease classification, the SVM classifier achieved the highest overall accuracy of 97.4% compared with k-NN, ANN and RF. For the degree of infection classification, and the SVM classifier achieved the highest overall accuracy of 91.0%. To enhance the classification performance, a combination of six types of features was evaluated. The results showed that SVM achieved the highest overall accuracy of 92.1% with the combinations of a local binary pattern (LBP) on the a* component, LBP on the b* component, the color histogram on the L* component, and the color histogram on the a* component.

The effects of adding CeO2 nanoparticles on the formation and growth of interfacial intermetallic compounds (IMCs) between Sn-0.3Ag-0.7Cu-xCeO2 (x = 0, 0.05, 0.1, 0.15, 0.2, 0.3 wt%) (SAC0307-xCeO2) solders and Cu substrates during reflow soldering were investigated. Scanning electron microscopy (SEM) was used to observe the microstructural evolution of the solder joints and measure the thickness and grain size of the intermetallic layers. The results show that the thicknesses and grain sizes of the IMCs decrease with CeO2 nanoparticle addition to the SAC0307 solder and that these parameters decrease significantly at a particle concentration of approximately 0.15 wt%. At higher concentrations, the thicknesses and grain sizes of the IMCs increase slightly. The growth exponents for the IMC layers and grains are determined by curve fitting to study the growth kinetics of the IMCs during reflow soldering. The results reveal that the growth exponents of the IMC layers range from 0.335 to 0.374 and those of the IMC grains range from 0.302 to 0.318, thus suggesting that the growth of the IMCs is controlled by the combined kinetic processes of atomic interdiffusion, interfacial reactions, and grain ripening. These data also show that among the tested solders, the SAC0307–0.15CeO2 solder joint has the smallest growth rate and exhibits the most significant effects in IMC growth suppression and grain size refinement. Based on the theories of heterogeneous nucleation and adsorption, a mechanism for reducing the IMC growth rate by the addition of CeO2 nanoparticles to the SAC0307 solder is proposed.

Cultivar identification of seeds is important for crop yield and quality. To study the impact of different features expressions and classification methods on cultivar identification, the performance of the feature expressions and classification algorithms affecting the accuracy of cultivar identification was evaluated by image processing techniques. A total of 448 samples of seeds from seven cultivars of sweet corn, namely, Orlando, Beiyasi, Jingketian 183, Jingtian 218, Suitian 1, CT76 and Lilixiangtian, were evaluated. The color, shape and texture features of the seeds were extracted from the images, and the class separability criterion was adopted to evaluate the separability of the features of the embryo side, nonembryo side and both of them combined. The results indicate that the class separability based on the features of the embryo side was higher than that based on the nonembryo side and both of them combined. Based on the embryo-side optical feature data, dimensionality reduction was conducted by two feature selection methods (stepwise discriminant analysis (SDA) and genetic algorithm (GA)) and two feature extraction methods (principal component analysis (PCA) and kernel principal component analysis (KPCA)). Performance evaluation of the feature reductions was conducted by constructing k-nearest neighbor (K-NN), na&iuml, ve Bayes (NB), linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Compared to the PCA and KPCA algorithms, the SDA and GA algorithms were more conducive to the cultivar classification of sweet corn seeds, the critical features selected specifically by the SDA, K-NN, NB, LDA and SVM classifiers achieved the best classification accuracies (81.43%, 82.86%, 90%, and 87.14%, respectively). Analysis of variance (ANOVA) revealed that the approach for optical feature selection had a more significant effect on the identification of sweet corn seed cultivars than did the classifiers. Therefore, based on the optical images of the embryo side and the key features obtained by the feature selection method, a classification model was constructed for the accurate and nondestructive classification of different sweet corn seed cultivars.

Due to the variable illumination conditions and occlusion produced by neighbouring fruits and other background participants, vision systems are important in accurately and reliably detecting mature citrus in natural orchard environments for automatic fruit picking applications. A robust citrus fruit detection method based on a monocular vision system was proposed. An adaptive enhanced red and green chromatic map was generated from an illumination-compensated image, which was obtained using block-based local homomorphic filtering. Otsu thresholding, morphology operation, marker-controlled watershed transform and convex hull operation methods were then used in combination to locate potential citrus regions from the chromatic map. Local texture information was extracted from the potential regions using local binary patterns and fed to a histogram intersection kernel-based support vector machine to make the final decision. The performance of the proposed method was evaluated on 127 test images captured in two citrus orchards on both sunny and cloudy days. Under strict PASCAL criteria, the recall rate of correctly detected citrus was greater than 0.86, with 13 false detections.

Transformer short-circuit accident caused by external short-circuit fault is analyzed and the basic parameters and process structure of transformer are introduced. The process and treatment of fault are expounded. The fault type is simulated and the fault degree is calculated quantitatively. By analyzing the results of fault recording, protection action, electrical test and gas chromatography test, the basic cause and fault location of transformer fault are determined and the corresponding preventive measures are put forward.

The segmentation of citrus trees in a natural orchard environment is a key technology for achieving the fully autonomous operation of agricultural unmanned aerial vehicles (UAVs). Therefore, a tree segmentation method based on monocular machine vision technology and a support vector machine (SVM) algorithm are proposed in this paper to segment citrus trees precisely under different brightness and weed coverage conditions. To reduce the sensitivity to environmental brightness, a selective illumination histogram equalization method was developed to compensate for the illumination, thereby improving the brightness contrast for the foreground without changing its hue and saturation. To accurately differentiate fruit trees from different weed coverage backgrounds, a chromatic aberration segmentation algorithm and the Otsu threshold method were combined to extract potential fruit tree regions. Then, 14 color features, five statistical texture features, and local binary pattern features of those regions were calculated to establish an SVM segmentation model. The proposed method was verified on a dataset with different brightness and weed coverage conditions, and the results show that the citrus tree segmentation accuracy reached 85.27% &plusmn, 9.43%, thus, the proposed method achieved better performance than two similar methods.

The morphological evolution and growth kinetics of interfacial Cu6Sn5 and Cu3Sn intermetallic compound (IMC) layers between Cu substrates and Sn-0.3Ag-0.7Cu-xMn (x = 0 wt.%, 0.02 wt.%, 0.05 wt.%, 0.1 wt.%, and 0.15 wt.%) (SAC0307-xMn) solders were investigated. After ageing, the uneven scallop-like morphology of Cu6Sn5 transforms into a layer-like morphology, and the Cu3Sn morphology remains layer-like. Kirkendall voids at the Cu/Cu3Sn interface and in the Cu3Sn layer are observed at high ageing temperatures. The Cu6Sn5 layer predominantly governs the growth of the total IMC layer at low ageing temperatures, whereas the Cu3Sn layer primarily influences the total IMC layer at high ageing temperatures. The growth of the Cu6Sn5 and Cu3Sn layers fits a power–law relationship with an exponent between 0.44 and 0.82, indicating that IMC growth is primarily controlled by diffusion but may also be affected by interfacial reactions. The activation energies and interdiffusion coefficients of the Cu6Sn5 and Cu3Sn layers were determined. The addition of Mn nanoparticles strongly affected the growth of the Cu6Sn5 layer but weakly impacted the growth of the Cu3Sn layer, particularly at low ageing temperatures. Adding Mn nanoparticles to the SAC0307 solder can evidently increase the activation energy of the Cu6Sn5 layer, reduce the atomic diffusion rate, and inhibit the excessive growth of the Cu6Sn5 IMC.

Purpose The purpose of this paper is to investigate of the effects of Mn nanoparticle addition on the wettability, microstructure and microhardness of SAC0307-xMn(np) (SAC: Sn–Ag–Cu; x = 0, 0.02, 0.05, 0.1 and 0.3 Wt.%) composite solders. Design/methodology/approach The SAC0307-xMn(np) composite solders were prepared by mechanically mixing different weight percentages of Mn nanopowders into the SAC0307 solder paste with rosin flux. In this study, the wettability of the solders was studied using contact angle and spread ratio methods. Afterward, the microstructure of the solders was investigated using scanning electron microscopy, energy-dispersive X-ray spectroscopy and X-ray diffractometry. Moreover, the microhardness of the solders was studied. Findings The wetting process of SAC0307-xMn(np) composite solders was found to experience four stages. Adding a small amount of Mn nanoparticles (x = 0.05 Wt.%) could improve the wettability compared to Mn-free solder. Beyond this level, the wettability deteriorated. The addition of Mn nanoparticles significantly refined the size and spacing of Ag3Sn grains in the solder matrix. When 0.1 Wt.% Mn nanoparticles was added, both the average size of the Ag3Sn grains and the spacing between the Ag3Sn grains decreased significantly and approached minimum values. Beyond this amount, the size and spacing between Ag3Sn grains increased slightly but remained smaller than those in the Mn-free solder matrix. The refined Ag3Sn grains increased the microhardness of the Mn-containing composite solders by 6-25 per cent, in good agreement with the prediction of the classic theory of dispersion strengthening. Originality/value The paper demonstrates that Mn nanoparticle addition could improve the SAC0307-xMn(np) solder wettability and reduce the grain size and spacing between Ag3Sn grains. The enhancement of the solder microhardness shows good correlation with the microstructure.

The effects of operation height and tree shape on droplet deposition in citrus trees using an unmanned aerial vehicle (UAV) were investigated in this study. When the operation height was 1.2 m and the flight speed was 3.5 m s−1, the droplet density and droplet coverage rate were maximized in all the canopies. The droplets exhibited the most uniform distribution (CV = 32.44%) in the lower layer of inverted triangle-shaped trees. The droplet density in the lower layer of inverted triangle-shaped trees was 48.04% higher than that in triangle-shaped trees. There was no statistically significant difference between the middle and lower layers of inverted triangle-shaped trees. The uniformity of the droplet deposition distribution was studied in six parts of the citrus trees at an operation height of 1.2 m. The results indicated that the front, middle, rear, left and centre parts displayed uniform distributions, but the right part of the inverted triangle-shaped trees did not. This difference might have been caused by a deviated flight route due to manual control error or by droplet drift from the wind originating from the right.

We used finite element analysis (FEA) and the Taguchi method to investigate the reliability of a four-tier die-stacked system-in-package (SiP) structure and to achieve the optimal design of the SiP structure under thermal cycling. A finite element model of a four-tier die-stacked SiP structure was developed to simulate the thermal stress distribution in the stacked die during the thermal cycling test. Scanning electron microscopy (SEM) was used to observe the failure sites of the SiP structure. The results show that the thermal stress is concentrated in the top die and that the maximum thermal stress occurs at the outmost four corners of the bottom of the top die. A micro-crack appears in the top die, and the crack starts from the bottom of the die close to the corner of die 4. Nine geometric parameters of the SiP structure were chosen as the variable factors, and the volume-averaged maximum thermal stress Δ σ max was chosen as the quality factor. An L12(29) orthogonal array was applied in a Taguchi experiment to estimate the effects of the nine factors and to reveal the optimal design of a four-tier die-stacked SiP structure based on the results of the thermal cycling test. The thickness of the top die has an important effect on the reliability; more than 21.2% of the volume-averaged maximum thermal stress is reduced using the optimal design.

Color cast of the UAV imagery is inevitable due to the temperature and illuminance changes during the UAV flight. Since color is an important feature in crop monitoring, color cast often produces misleading inference in estimation of crop stress, nutrient, and productivity. Therefore, color calibration is a necessary step to remove the negative effects of color variation for UAV based crop monitoring. Nowadays, the state of art color calibration methods usually use the semantic correspondences for accurate color transfer. However, the mainstream color calibration methods ignore the integration of semantic segmentation and style transfer, and suffer the problem of semantic mismatch. To address this problem, this study proposed a multi decoder architecture that builds the integration of sematic segmentation and style transfer for the color transfer in an end to end mode. Also, this paper introduced an Crop Oriented adaptive instance normalization (AdaIN) method to estimate the color cast in the crop areas, and used that estimated information for color calibration over the whole image area with a local to global attention mechanism. Each proposed module was evaluated in ablation study to test its effectiveness, respectively. Also, the proposed method was evaluated on several crop types and compared with the state of art methods. Experimental results showed that our proposed method achieved state of art or close to state of art performance in all metrics. The research of this work is expected to obtain a general framework to remove the color cast of UAV imagery for crop monitoring, which may build a good foundation for the following data interpretation. Our dataset and codes are can be downloaded at http://github.com/huanghsheng/deep-color-calibration .

Interfacial intermetallic compound (IMC) growth between Cu substrates and low-Ag Sn-0.3Ag-0.7Cu-xMn (x = 0 wt.%, 0.02 wt.%, 0.05 wt.%, 0.1 wt.%, and 0.15 wt.%) (SAC0307-xMn) solders was investigated under different isothermal aging temperatures of 100°C, 150°C, and 190°C. Scanning electron microscopy (SEM) was employed to observe the microstructural evolution of the solder joints and measure the IMC layer thickness. The IMC phases were identified by energy-dispersive x-ray spectroscopy and x-ray diffraction. The results showed that a Cu6Sn5 IMC layer formed in the as-soldered solder joints, while a duplex structure consisting of a Cu6Sn5 IMC layer near the solder matrix and a Cu3Sn IMC layer was observed after isothermal aging. A considerable drop in the IMC layer thickness was observed when 0.1 wt.% Mn nanoparticles were added. Beyond this amount, the thickness of the IMC layer only slightly increases. Adding Mn nanoparticles can increase the activation energy and thus reduce the interdiffusion rates of the Sn and Cu atoms, which suppresses excessive IMC growth. The solder joint containing 0.1 wt.% Mn nanoparticles has the highest activation energy. SEM images revealed that the number of small particles precipitated in the channels between the Cu6Sn5 IMC layers increases with an increasing proportion of Mn nanoparticles. Based on the microstructural evolution of the solder joints, this study revealed that grain boundary pinning is one of the most important mechanisms for IMC growth inhibition when Mn nanoparticles are added.

Due to the change of illumination environment and overlapping conditions caused by the neighboring fruits and other background objects, the simple application of the traditional machine vision method limits the detection accuracy of lychee fruits in natural orchard environments. Therefore, this research presented a detection method based on monocular machine vision to detect lychee fruits growing in overlapped conditions. Specifically, a combination of contrast limited adaptive histogram equalization (CLAHE), red/blue chromatic mapping, Otsu thresholding and morphology operations were adopted to segment the foreground regions of the lychees. A stepwise method was proposed for extracting individual lychee fruit from the lychee foreground region. The first step in this process was based on the relative position relation of the Hough circle and an equivalent area circle (equal to the area of the potential lychee foreground region) and was designed to distinguish lychee fruits growing in isolated or overlapped states. Then, a process based on the three-point definite circle theorem was performed to extract individual lychee fruits from the foreground regions of overlapped lychee fruit clusters. Finally, to enhance the robustness of the detection method, a local binary pattern support vector machine (LBP-SVM) was adopted to filter out the false positive detections generated by background chaff interferences. The performance of the presented method was evaluated using 485 images captured in a natural lychee orchard in Conghua (Area), Guangzhou. The detection results showed that the recall rate was 86.66%, the precision rate was greater than 87% and the F1-score was 87.07%.

The maturity stage of bananas has a considerable influence on the fruit postharvest quality and the shelf life. In this study, an optical imaging based method was formulated to assess the importance of different external properties on the identification of four successive banana maturity stages. External optical properties, including the peel color and the local textural and local shape information, were extracted from the stalk, middle and tip of the bananas. Specifically, the peel color attributes were calculated from individual channels in the hue-saturation-value (HSV), the International Commission on Illumination (CIE) L*a*b* and the CIE L*ch color spaces, the textural information was encoded using a local binary pattern with uniform patterns (UP-LBP), and the local shape features were described by histogram of oriented gradients (HOG). Three classifiers based on the na&iuml, ve Bayes (NB), linear discriminant analysis (LDA) and support vector machine (SVM) algorithms were adopted to evaluate the performance of identifying banana fruit maturity stages using the different optical appearance features. The experimental results demonstrate that overall identification accuracies of 99.2%, 100% and 99.2% were achieved using color appearance features with the NB, LDA and SVM classifiers, respectively, overall accuracies of 92.6%, 86.8% and 93.4% were obtained using local textural features for the three classifiers, respectively, and overall accuracies of only 84.3%, 83.5% and 82.6% were obtained using local shape features with the three classifiers, respectively. Compared to the complicated calculation of both the local textural and local shape properties, the simplicity and high accuracy of the peel color property make it more appropriate for identifying banana fruit maturity stages using optical imaging techniques.

Over the next decade, the superfast 5G network will play a critical role in farming industries to improve the yields and quality of crops while using minimal labor. Smart and precision farming allows farmers to be more informed and productive. The advent of 5G will considerably change the nature of jobs in farming and agriculture. The internet of things (IoT)-based cloud computing service in the 5G network provides flexible and efficient solutions for smart farming. This will allow the automated operation of various unmanned agricultural machines for the plowing, planting, and management phases of crop farming and will ultimately achieve secure, reliable, environmentally friendly, and energy-efficient operations and enable unmanned farms. This paper provides a complete survey on 5G technology in the agricultural sector and discusses the need for and role of smart and precision farming; benefits of 5G; applications of 5G in precision farming such as real-time monitoring, virtual consultation and predictive maintenance, data analytics and cloud repositories; and future prospects.

The plant protection effect of an agricultural unmanned aerial vehicle (UAV) with multiple rotors is closely related to its speed and direction and the spatial and temporal distributions of the effective coverage of the downwash airflow. By combining compressible Reynolds-averaged Navier-Stokes (RANS) equations, the shear stress transport (SST) k - ω turbulence model, sliding grid technology and the Semi-Implicit Method for Pressure Linked Equations (SIMPLE) algorithm, this paper establishes a computational fluid dynamics (CFD) model of the downwash airflow of the quad-rotor agricultural UAV in hover and discusses the distribution of the downwash airflow in the spatial and temporal dimensions. The simulation results show that most areas of the downwash airflow tend to be stable within 4.5 s, and due to the downward flow characteristics after the stabilization, the z-direction (perpendicular to the ground) velocity of the downwash airflow directly under the rotor is the highest with a maximum value of −8.96 m/s, which accounts for the main part of the downwash flow. The rotor downwash airflow flows downward in spiral form and the phenomenon of “contraction and expansion” is obvious during the downwash flow. Closer to the ground, the coverage area of the z-direction velocity is larger, the pressure distribution is more uniform, and the airflow exhibits an “upwash” phenomenon due to the “ground effect”. The test and simulation values at test points from 1 m to 2.5 m and 0.75 m exhibit the same variation trend with maximum relative errors of 10% and 15%, and the numerical simulation is accurate.

The ripening growth kinetics of interfacial Cu6Sn5 grains between Cu substrates and Sn-3.0Ag-0.5Cu-xTiO2 (x = 0, 0.02, 0.05, 0.1, 0.3, and 0.6 wt %) (SAC305-xTiO2) solders were investigated. The results show that the Cu6Sn5 grain morphology is affected by the solder composition and the reflow time. The Cu6Sn5 grain size decreases upon addition of TiO2 and shows a significant decrease when the TiO2 nanoparticle fraction is increased to 0.1 wt %. At higher TiO2 nanoparticle fractions, the Cu6Sn5 grain size increases slightly. The growth of the Cu6Sn5 grains is mainly supplied by the flux of the interfacial reaction and the flux of ripening; the ripening flux plays a dominant role because it is approximately one order of magnitude greater than the interfacial reaction flux. The ripening growth of the Cu6Sn5 grains in the TiO2-containing solder joints is reduced more effectively than that of the Cu6Sn5 grains in the TiO2-free joint. For the SAC305/Cu and SAC305-0.6TiO2/Cu solder joints, the particle size distribution (PSD) of the Cu6Sn5 grains is well fit with the Marqusee and Ross (MR) model when the normalized size value of r/ is less than 1, and it is consistent with the flux-driven ripening (FDR) model when the value of r/ is greater than 1. On the other hand, for the SAC305-0.1TiO2/Cu solder joint, the Cu6Sn5 grains with a nearly hemispheric scallop shape and the PSD of the Cu6Sn5 grains show good agreement with the FDR model.

This paper presents an energy-efficient routing scheme for the in-network implementation of data regression modelling in wireless sensor networks (WSNs). With the kernel based distributed representation, a clustering based routing architecture is proposed to implement the distributed Gaussian elimination for solving the regression algebraic equation. In particular, the skeleton routing tree is built to coordinate the local computations associated with the clusters. The rest ramose nodes within each cluster are limited to contribute the corresponding local computations. Compared with the junction tree formation over all nodes, the notion of skeleton tree (ST) proposed here suppresses the redundant message passing among the ramose nodes with each cluster without deteriorating data modelling performance. Experimental results are reported to demonstrate the effectiveness of the proposed approach.