摘要：
The theoretical minimum driving power expression for the optical switch based on VO2 thin film is given out in this paper, which is obtained from the phase transition characteristics and thermal structure of the VO2 thin film, and it reveals some key parameters to decide its value. According to the theoretical expression, a kind of simple thermal structure fabricated with a low phase transition VO2 thin film is proposed for low power-consumption optical switch. This kind of optical switch is compact and fast while requiring only a simple driving circuit, and the VO2 thin film is deposited by using reactive ion beam sputtering method and formed by post-annealing process, which is compatible with IC process.
通讯机构：
[Zongyu Huang; Huating Liu] S;School of Physics and Optoelectronic, Hunan Key Laboratory for Micro-Nano Energy Materials and Devices, Xiangtan University, Hunan, People’s Republic of China<&wdkj&>Hunan Key Laboratory of Two-Dimensional Materials, Hunan University, Changsha, People’s Republic of China<&wdkj&>School of Physics and Optoelectronic, Hunan Key Laboratory for Micro-Nano Energy Materials and Devices, Xiangtan University, Hunan, People’s Republic of China<&wdkj&>School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, People’s Republic of China
摘要：
We present a statistical study on dense molecular gas tracers of HCN (4-3), HCO+ (4-3) lines and molecular tracers of [C I], and CO observations for a sample of 26 infrared bright star-forming (SF) galaxies. We investigate the dependence of dense gas star formation efficiency traced by HCN (4-3), HCO+ (4-3) (that is L-IR/L-HCN(') (4-3), and LIR/L-HCO+(')(4-3)), and luminosity ratio of L-HCN(')(4-3)/L-HCO+(')(4-3) on [C I]-CO ratios of L-[C (')(I] (1-0))/LCO (1-0), L[C I](2-1)'/L-CO (1-0()') and L-[C I](2-1)(')/L-[C I] (1-0)(') (hereafter R-[CI]) which are sensitive to interstellar medium conditions. Our findings show that both LIR/L ' HCN (4-3) and LIR/L ' HCO+ (4-3) have moderate correlations with L '[C I](2-1)/L ' CO (1-0) and R[CI], while L ' HCN(4-3)/L ' HCO+ (4-3) does not show any significant correlations with any of the [C I]-CO ratios. We compare the L ' HCN (4-3)/L ' HCO+ (4-3) ratios of AGN and SF galaxies, and find that although the higher L ' HCN (4-3)/L ' HCO+ (4-3) ratios are mainly found in AGN, the majority of the L ' HCN (4-3)/L ' HCO+ (4-3) values in SF galaxies are comparable to those in AGN. Based on our findings, it appears that the L ' HCN (4-3)/L ' HCO+ (4-3) ratio may not be a reliable indicator of the presence of an AGN, although further investigation is needed to confirm this conclusion.
摘要：
Electrochemical conversion of CO2 into CO, powered by renewable electricity, offers one means to address the need for the storage of intermittent renewable energy. However, it is challenging because the competing HER is hard to avoid, which significantly compromises the selectivity to CO and reduces the efficiency of CO2RR de -vices. This study reports a cooperative catalyst design of metal-molecule catalyst interfaces with the goal of high local concentration of CO2 and stabilizing the intermediate, which improves the electrosynthesis of CO. The strategy is implemented by functionalizing the silver surface with cobalt (II)-complexes to promote the selective electrolysis of CO2 to CO. We report a CO2-to-CO Faradaic efficiency of 98.5 % and a partial current density of 16.52 mA cm-2 at -1.1 V vs. RHE. Mechanism studies reveal that the catalytic performance of the Ag/Co(bpy)32+ correlates with the metal-molecule interaction, which provide new opportunities for construction and design of high-efficient catalysts toward CO2 reduction.
关键词：
semantic understanding;neural networks;optical music recognition;YOLOv5;digital code
摘要：
Symbolic semantic understanding of staff images is an important technological support to achieve "intelligent score flipping". Due to the complex composition of staff symbols and the strong semantic correlation between symbol spaces, it is difficult to understand the pitch and duration of each note when the staff is performed. In this paper, we design a semantic understanding system for optical staff symbols. The system uses the YOLOv5 to implement the optical staff's low-level semantic understanding stage, which understands the pitch and duration in natural scales and other symbols that affect the pitch and duration. The proposed note encoding reconstruction algorithm is used to implement the high-level semantic understanding stage. Such an algorithm understands the logical, spatial, and temporal relationships between natural scales and other symbols based on music theory and outputs digital codes for the pitch and duration of the main notes during performances. The model is trained with a self-constructed SUSN dataset. Experimental results with YOLOv5 show that the precision is 0.989 and that the recall is 0.972. The system's error rate is 0.031, and the omission rate is 0.021. The paper concludes by analyzing the causes of semantic understanding errors and offers recommendations for further research. The results of this paper provide a method for multimodal music artificial intelligence applications such as notation recognition through listening, intelligent score flipping, and automatic performance.
通讯机构：
[Jia, PF ] G;Guangxi Univ sity, Sch Elect Engn, Nanning 530004, Peoples R China.;Guangxi Univ sity, Guangxi Key Lab Intelligent Control & Maintenance, Nanning 530004, Peoples R China.
关键词：
Air discharge components;Cr-MoS2(001) monolayer;density functional theory (DFT);gas sensing
摘要：
Air discharge characteristic gas detection is considered as one of the most reliable methods in fault diagnosis of air switchgear. Based on the first-principles of density functional theory, the adsorption and sensing properties of transition metal (Cr) modified MoS2(001) monolayer on three air discharge characteristic gases (CO, NO, and NO2) are analyzed. First, the Cr-doped MoS2(001) monolayer model is obtained by modeling and analyzing different doping sites, and the subsequent density functional theory (DFT) calculation is done. Based on this model, many kinds of adsorption structures were constructed and optimized. The parameters of adsorption structure, adsorption energy, and adsorption distance were obtained. Furthermore, the differential charge density (DCD), state density, response performance, and adsorption performance of the system were analyzed. The results show that Cr-MoS2(001) monolayer has good adsorption performance to three gases. CO gas molecules can be rapidly desorbed from Cr-MoS2(001) monolayer surface at room temperature. Cr-MoS2(001) monolayer has the potential as a low-power gas sensor material for detecting CO characteristic gases and a solid adsorbent material for cleaning NO and NO2 gases. This work provides theoretical guidance for the development of MoS2-based sensors for detecting characteristic gases in air discharge.
通讯机构：
[Lixia Xiao] D;[Zhengcai Xia] W;Wuhan National High Magnetic Field Center, Huazhong University of Science and Technology, Wuhan 430074, China<&wdkj&>Department of Physical Sciences, Wenhua College, Wuhan 430074, China
摘要：
The honeycomb single-crystal compound Na2Ni2TeO6 has been synthesized successfully, and its magnetization behavior under a pulsed high magnetic field has been investigated. At TN similar to 27 K, Na2Ni2TeO6 undergoes a paramagnetic (PM) to antiferromagnetic (AFM) phase transition with both the magnetic field parallel to the c-axis (B parallel to c) and the magnetic field perpendicular to the c-axis (B perpendicular to c). For B parallel to c and T = 2 K, a field-induced spin-reorientation transition is observed at B parallel to c1 similar to 10.95 T and reached the canted AFM phase; as the magnetic field increases to B parallel to c2 similar to 49.5 T, the spin is almost completely polarized and the PM state reached. For B perpendicular to c and T = 4.2 K, a spin-reorientation transition was observed at B perpendicular to c similar to 53.5 T. Moreover, with the increase of temperature, the transition critical field moves to lower field regions, and with the increase of magnetic field, the critical temperature moves to the lower region. The Na2Ni2TeO6 single crystal shows obvious magnetic anisotropy, and the magnetic anisotropy does not disappear until the magnetic field is up to 56 T. Our experimental results confirm the uniaxial magnetocrystalline anisotropy related to the Ising-like spin configuration. Based on the temperature dependence of magnetization measurements, a complete magnetic phase diagram of Na2Ni2TeO6 was drawn.
通讯机构：
[Zongyu Huang] S;School of Physics and Optoelectronic, Hunan Key Laboratory for Micro-Nano Energy Materials and Devices, Xiangtan University, Hunan, People’s Republic of China<&wdkj&>Hunan Key Laboratory of Two-Dimensional Materials, Hunan University, Changsha, People’s Republic of China
关键词：
MoS2;WSe2 heterostructure;S vacancy;interlayer interaction;electronic and optical properties
摘要：
The van der Waals (vdWs) heterostructure retains some excellent properties of monolayer transition metal dichalcogenides (TMDs), and has a significant improvement in performance, which is anticipated to play an important role in optoelectronic devices. S vacancy and interlayer interaction act together to influence the properties of the system. In this work, based on first-principles calculations, the effect of S vacancy on the electronic and optical properties of the MoS2/WSe2 heterostructure were investigated. The calculation demonstrated that a single S vacancy introduces defect states between the conduction band minimum (CBM) and the Fermi level. For optical properties, the formed, built-in electric field of a heterostructure would prevent electron and hole recombination. Both systems show strong light absorption in the visible and ultraviolet regions. The absorption coefficient in the infrared regions of the defected MoS2/WSe2 heterostructure was larger than that of the perfect heterostructure. The defect states were influenced by interlayer distance. The defected MoS2/WSe2 heterostructure experienced a direct-gap semiconductor to metal, and the band gap decreased with decreasing layer distance. Also, all the systems showed strong light absorption in the visible and ultraviolet regions. As for the near-infrared region, light absorption of the defected MoS2/WSe2 heterostructure was more obvious as the interlayer distance decreased, while the smaller the layer distance, the more obvious was the absorption in the near-infrared region. In summary, S vacancy and interlayer interaction have important effects on the electronic structure and optical properties of the MoS2/WSe2 heterostructure, which is helpful for the design of multifunctional high-performance optoelectronic devices.
通讯机构：
[Huang, ZY ] X;Xiangtan Univ, Sch Phys & Optoelect, Hunan Key Lab Micronano Energy Mat & Devices, Xiangtan 411105, Hunan, Peoples R China.;Hunan Univ, Hunan Key Lab Two Dimens Mat, Changsha 410082, Peoples R China.
关键词：
strain engineering;Janus nanoribbons;electronic structures;magnetic moment
摘要：
Local strain, as a small degree and single direction strain method, can effectively regulate the structures and electronic properties of armchair Janus MoSSe nanoribbon, so that the system can be transformed from the original 0.467 eV indirect band gap into 0.259 eV (3-zig), 0.117 eV (3-arm), 0.080 eV (6-arm) and 0.139 eV (9-zig) direct band-gap semiconductor according to the different strain degrees and directions. Compared with traditional MoS2 and MoSe2 nanoribbons, Janus MoSSe nanoribbon shows relatively stable band structure under local strain. The structure and electronic properties of Janus MoSSe nanoribbon are anisotropic when the local strain is along different directions. Due to the broken mirror symmetry of the Janus system and the appearance of in-plane local polarization, the spin polarization effect of Janus nanoribbon under local strain is more remarkable. When the local strain degree C = 0.167 is along the zigzag direction and the local strain C ⩾ 0.056 is along the armchair direction, the Janus nanoribbon exhibits half-metallic properties and surprisingly induces a magnetic moment. For the local strain along the armchair direction, the total magnetic moment of the system can be up to 2.05 μB when C = 0.111. A local strain method is applied to the nanoribbon system, which can effectively regulate the geometric configuration and electronic structure without external doping, and introduce magnetism, providing the possibility for expanding nanoribbons as potential nanoelectronic and spintronic materials.
摘要：
Inspired by potential application prospects of spintronics and valleytronics, a novel heterobilayer Janus structure is designed by replacing the chalcogenide atomic layers in the original bilayer MoS2. Based on first-principles calculations, it is found that the SMoS/SeMoS structure exhibits a direct band-gap semiconductor and a typical type-II band alignment with longer carrier lifetime. The transition metal (TM) atom represented by V/Cr/Mn can be stably adsorbed on the heterobilayer Janus SMoS/SeMoS sheet and effectively introduce magnetic moments (m). The calculation results demonstrate that the most stable adsorption site of the TM atom is CX(A), and the TM (V/Cr/Mn) adatom modified SMoS/SeMoS system is converted into metal (V-) or half-metal (Cr/Mn-), respectively. Under the coupling of different indirect exchange interactions, the structure exhibits stable intrinsic anti-ferromagnetic interactions for V-SMoS/SeMoS and ferromagnetic ground state for Cr/Mn-SMoS/SeMoS, respectively, and the magnetic transition temperature (T c) reaches a high temperature or even room temperature. Moreover, the robust out-of-plane magnetocrystalline anisotropy energy ensures stable long-range magnetic order. Specifically, the combination of spin injection and strong spin–orbit coupling interaction effectively breaks the time-reversal symmetry, which leads to valley polarization of the system. Based on this, the biaxial strain can effectively regulate the electronic structure, magnetic properties and valley polarization of TM-SMoS/SeMoS nanosheets with double breaking of spatial-inversion and time-reversal symmetry.
摘要：
In response to the present epidemic situation, this work proposes an anti-coronavirus composite polymer coating with nano-Ag2MoO4 as the core component to reduce the potential safety hazards caused by excessive use of disinfectants. Nano-beta-Ag2MoO4 with mixed morphology was produced with industrialized preparation technology. Among them, oval nanoparticles are core components with antiviral properties, and long rod-shaped particles are used to identify whether the stirring process meets the standard. After x-ray diffraction and field emission scanning electron microscopy testing, nano-beta-Ag2MoO4 stored for 4 years still meets the design requirements in terms of purity, crystal phase, shape, and scale, which solves the problem of the long-term effect of core components. In the existing water-based paint production process, the mixing process and formula of nano-beta-Ag2MoO4 were explored, and the large-scale production process of anti-virus water-based paint was solved. Resistance tests against the HCoV-229E coronavirus showed that the anti-coronavirus activity rate of the nano-beta-Ag2MoO4 coating at a weight concentration of 200 ppm was 99.5% within 2 h, which verified the effectiveness of the composite polymer coating.
通讯机构：
[Zhang, C ] W;Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.
关键词：
Contamination;Farming;Geographic information systems;Machine learning algorithms;Risk management;farmland protection;geographic information systems;heavy metals;machine learning algorithms;risk assessment;soil
摘要：
As a nationally protected land resource, farmland plays a crucial role in agriculture production and food safety, making the quality of soil and environmental health critically important. Therefore, studying the extent of soil heavy metal pollution in farmland is of great significance for understanding the growth environment of food crops and protecting agricultural land resources. This study addresses the challenge of accurately, quickly, and conveniently assessing the extent of soil heavy metal pollution across an entire research area using a limited number of soil samples. To tackle this issue, a novel soil heavy metal pollution risk hybrid intelligent evaluation model (HIEM) is proposed. The HIEM utilizes the Semi-Supervised Bayesian Regression (Semi-BR) model, trained through Bayesian Co-training, to predict the soil heavy metal content at unsampled points. It employs an improved Multiple Kernel Support Vector Machine (MKSVM) model to evaluate the pollution status of the soil. Additionally, Geographic Information System (GIS) techniques are employed for spatial analysis of the pollution situation in the research area. The study focuses on eight soil heavy metals: As, Cd, Cr, Hg, Pb, Zn, Cu, and Ni. The experimental verification of the model was conducted using field sampling data from the major agricultural areas of Huangpi and Xinzhou in Wuhan, Hubei Province, China. The experimental results show that the eastern region of Huangpi District is more severely contaminated, particularly the central area in the northeast, with moderate to high pollution levels. The hybrid intelligent evaluation model achieves an average accuracy of 96.66% in assessing single-factor pollution of the eight soil heavy metals and an overall evaluation accuracy of 97.42%. The hybrid intelligent evaluation model is able to accurately fit traditional single-factor index methods and Nemerow comprehensive pollution index method. The Geographic Information System representation reveals a consistent distribution trend of soil heavy metal pollution reflected by the hybrid intelligent evaluation model with the results obtained from single-factor index and Nemerow comprehensive pollution index evaluation, indicating the feasibility of using this evaluation method for assessing the risk of soil heavy metal pollution. The conclusion shows that the hybrid intelligent evaluation model needs at least 639 sets of sample data to achieve the highest accuracy when assessing the risk of soil heavy metal contamination in an area of about $3.7\times 10^{4}\,\,hm^{2}$ , and this paper provides a reference to solve the problem of realizing high-precision risk assessment of heavy metal contamination of agricultural soils in the case of small samples. This study is of great practical significance for soil pollution investigation, soil quality assessment and other practical work.
期刊：
Journal of Environmental Chemical Engineering,2023年11(6):111305 ISSN：2213-3437
通讯作者：
Chen, DC
作者机构：
[Zeng, Wu; Miao, Qing; Wu, Jiarui; Chen, Dachang; Li, Jie; Liu, Ke] Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.;[Xiao, Song] Wuhan Univ, Sch Elect Engn & Automat, Wuhan 430072, Peoples R China.;[Luo, Yi] Chinese Acad Sci, Inst Elect Engn, Beijing Int S&T Cooperat Base Plasma Sci & Energy, Beijing 100190, Peoples R China.
通讯机构：
[Chen, DC ] W;Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.
关键词：
Hazardous gas molecules;Main -group element atoms;GeSe monolayer;Adsorption;Sensor
摘要：
Currently, the identification of sensing materials that can selectively and rapidly respond to hazardous gases is urgent for safeguarding the environment and human life. The adsorption of hazardous gas molecules (NO, NO2, SO2, CO, and H2S) on the GeSe monolayer doped with single main-group element atom is investigated and compared based on first-principles density functional theory (DFT). NO2 has the highest adsorption energy and charge transfer adsorbed on both pristine GeSe and doped GeSe monolayer. At ambient temperature, for any doped GeSe monolayers adsorbing gas molecules (including H2O, O2, and N2), the occupation function value of NO2 is the highest. The analysis of density of states (DOS) and band structure indicates that NO2 interacts with different modified GeSe monolayers in terms of atomic orbitals. Moreover, Al-GeSe has the largest change of work function before and after the adsorption of NO2, meaning that Al-GeSe has the greatest response to NO2. current-voltage (I-V) characteristics demonstrate that Al-GeSe exhibits a remarkable current change after the adsorption of NO2. These results illustrate that Al-GeSe has a strong physical and chemical interaction with NO2, yielding a high response and selectivity, which is anticipated to be the optimal gas sensing material for NO2.
作者机构：
[Miao, Qing; Chen, Dachang; Zhao, Renchu; Liu, Ke; Zheng, Ziang] Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.;[Xiao, Beibei] Jiangsu Univ Sci & Technol, Sch Energy & Power Engn, Zhenjiang 212003, Peoples R China.
通讯机构：
[Chen, DC ] W;Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.
关键词：
density functional theory;C4F7N;3d VIII atom;& gamma;-graphyne;gas sensor
摘要：
Recently, Heptafluoroisobutyronitrile (C4F7N) has received widespread attention in replacing one of the most greenhouse-insulating gas, SF6. However, gas leakage is incredibly harmful to the health of operational personnel and the security of industry production, and developing C4F7N detection technology is of great necessity. In this work, the adsorption properties, as well as the sensing performance of C4F7N on 3d VIII atom-decorated γ-graphyne (γ-GY), were theoretically discussed. The adsorption structures, adsorption energies, electron transfer, adsorption distance, electron distribution, and electronic properties were compared. The results show that the introduction of Fe and Co atom enhance the chemisorption of C4F7N, and the adsorption of C4F7N brings the maximum electron redistribution of Fe/γ-GY among three TM/γ-GY. Only the adsorption on Fe/γ-GY leads to the vanishing of the magnetic moment and creates a band gap. For three different modifications of γ-GY, the chemical interactions are highly related to the overlapping of transition metal 3d and N 2p orbitals in the density of states. The adsorption on Co/γ-GY causes the maximum change in work function from 5.06 eV to 5.26 eV. In addition, based on the band structure, work function, and desorption properties, the sensing properties of 3d VIII atom-decorated γ-GY were evaluated in order to promote the experimental exploration and development of high-performance C4F7N gas sensors.
通讯机构：
[Duo Zhang] S;School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430023, People's Republic of China
关键词：
electromagnetically induced grating;standing wave field;diffraction pattern and efficiency
摘要：
We proposed a theoretical scheme for two-dimensional (2D) electromagnetically induced grating (EIG) in a closed-loop four-level atomic system driven by a weak probe field, a traveling-wave control field, two orthogonal standing-wave fields and a microwave field. Due to low amplitude modulation accompanied with large phase modulation, EIG can be obtained and the probe energy can be diffracted into first-order and even high-order directions with high efficiency. The results show that the diffraction pattern and efficiency of the EIG could be adjusted effectively by the probe field detuning, the coherent field intensity, the interaction length. Meanwhile, the quantum interference between the amplitude modulation and phase modulation can be manipulated by the relative phase, which can be used to regulate the diffraction pattern and efficiency of the 2D EIG. Our scheme of 2D EIG may be useful in beam splitting and all-optical switching.
摘要：
Building roof segmentation is a key step in the process of 3-D building reconstruction using airborne light detection and ranging point cloud data. Voxel-based region growing is one of the most widely used methods to segment planes because of its high efficiency and easy implementation, but it is easy to omit roof planes due to the unreasonable voxel size and the complex roof structures. In addition, boundaries between adjacent roof planes are inaccurate. To solve the issues, a roof segmentation method using octree-based hybrid region growing and boundary neighborhood verification voting is proposed. First, an octree-based voxelization is performed on the raw building points to generate two basic units: planar voxels and individual points (i.e., points that are not in the planar voxels). Then, the hybrid region growing is conducted on these two basic units to segment coarse roof planes. A parameter-free boundary neighborhood verification voting strategy is used to assign the boundary points to the correct roof planes by verifying the neighborhoods of the boundary points and using reliable neighborhood information. Experimental results of four datasets, including two datasets provided by the International Society for Photogrammetry and Remote Sensing and two high-density datasets provided by OpenTopography, verify that roof planes can be successfully segmented by the proposed method with over 96.8% completeness and a minimum of 93.2% correctness. In addition, boundary points are assigned to the correct roof planes by the neighborhood verification voting strategy. Thus, the segmented roof planes can be used in various applications.
期刊：
JOURNAL OF ANIMAL PHYSIOLOGY AND ANIMAL NUTRITION,2023年107(1):228-237 ISSN：0931-2439
通讯作者：
Wan, LL;Ai, H
作者机构：
[Feng, Ke; Chen, Yan; Lu, Jianjian] Wuhan Polytech Univ, Sch Mech Engn, Wuhan, Peoples R China.;[Wan, Lili] Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430048, Peoples R China.;[Ai, Hui] Cent China Normal Univ, Sch Life Sci, Wuhan, Peoples R China.
通讯机构：
[Ai, H ] C;[Wan, LL ] W;Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430048, Peoples R China.;Cent China Normal Univ, Sch Life Sci, Wuhan, Peoples R China.
摘要：
The chicken is rich in various proteins, fatty acids, polysaccharides, trace elements, and other human essential nutrients that contribute to its high nutritional value. In this study, the expression levels of nutrition-related genes (acetyl-CoA acyltransferase, ACAA) of native chicken breeds were investigated. The level of GgalACAA1-2 transcripts expression in the liver of chicken was significantly higher than that of muscle and heart. Moreover, three protein extracts were isolated from the muscle, heart, and liver tissues from the chicken, and their nutritional function was evaluated in the present study. These protein extracts had excellent DPPH and hydroxyl radical scavenging capacities and exhibited significant superoxide anion scavenging ability. Moreover, the protein extracts of muscle tissue showed an important mouse splenocyte proliferation activity and could be used as an immunomodulator of natural origin. In addition, this report presented an automatic visual inspection of chicken viscera using the active contour algorithms and the image processing method for eviscerating by the parallel robot. The recognition and positioning rate of chicken viscera obtained by the proposed method could reach 96.45%. These methods provided basic data for automated poultry slaughter and segmentation, avoiding unnecessary health risks by a pathogenic microorganism, such as avian influenza, Newcastle disease virus, and coronavirus. Moreover, the internal organs of the chicken could be fully harvested by the image segmentation of automatic evisceration, which also facilitated the processing value of these internal organs as by-products of poultry.
摘要：
During the rice quality testing process, the precise segmentation and extraction of grain pixels is a key technique for accurately determining the quality of each seed. Due to the similar physical characteristics, small particles and dense distributions of rice seeds, properly analysing rice is a difficult problem in the field of target segmentation. In this paper, a network called SY-net, which consists of a feature extractor module, a feature pyramid fusion module, a prediction head module and a prototype mask generation module, is proposed for rice seed instance segmentation. In the feature extraction module, a transformer backbone is used to improve the ability of the network to learn rice seed features; in the pyramid fusion module and the prediction head module, a six-layer feature fusion network and a parallel prediction head structure are employed to enhance the utilization of feature information; and in the prototype mask generation module, a large feature map is used to generate high-quality masks. Training and testing were performed on two public datasets and one private rice seed dataset. The results showed that SY-net achieved a mean average precision (mAP) of 90.71% for the private rice seed dataset and an average precision (AP) of 16.5% with small targets in COCO2017. The network improved the efficiency of rice seed segmentation and showed excellent application prospects in performing rice seed quality testing.
摘要：
Aiming at the problems of uneven light reflectivity on the spherical surface and high similarity between the stems/calyxes and scars that exist in the detection of surface defects in apples, this paper proposed a defect detection method based on image segmentation and stem/calyx recognition to realize the detection and recognition of surface defects in apples. Preliminary defect segmentation results were obtained by eliminating the interference of light reflection inhomogeneity through adaptive bilateral filtering-based single-scale Retinex (SSR) luminance correction and using adaptive gamma correction to enhance the Retinex reflective layer, and later segmenting the Retinex reflective layer by using a region-growing algorithm. The texture features of apple surface defects under different image processing methods were analyzed based on the gray level co-occurrence matrix, and a support vector machine was introduced for binary classification to differentiate between stems/calyxes and scars. Deploying the proposed defect detection method into the embedded device OpenMV4H7Plus, the accuracy of stem/calyx recognition reached 93.7%, and the accuracy of scar detection reached 94.2%. It has conclusively been shown that the proposed defect detection method can effectively detect apple surface defects in the presence of uneven light reflectivity and stem/calyx interference.
