Infrared-Visible Image Fusion Based on Semantic Guidance and Visual Perception

Infrared-visible fusion has great potential in night-vision enhancement for intelligent vehicles. The fusion performance depends on fusion rules that balance target saliency and visual perception. However, most existing methods do not have explicit and effective rules, which leads to the poor contrast and saliency of the target. In this paper, we propose the SGVPGAN, an adversarial framework for high-quality infrared-visible image fusion, which consists of an infrared-visible image fusion network based on Adversarial Semantic Guidance (ASG) and Adversarial Visual Perception (AVP) modules. Specifically, the ASG module transfers the semantics of the target and background to the fusion process for target highlighting. The AVP module analyzes the visual features from the global structure and local details of the visible and fusion images and then guides the fusion network to adaptively generate a weight map of signal completion so that the resulting fusion images possess a natural and visible appearance. We construct a joint distribution function between the fusion images and the corresponding semantics and use the discriminator to improve the fusion performance in terms of natural appearance and target saliency. Experimental results demonstrate that our proposed ASG and AVP modules can effectively guide the image-fusion process by selectively preserving the details in visible images and the salient information of targets in infrared images. The SGVPGAN exhibits significant improvements over other fusion methods.     

A Novel Drinking Category Detection Method Based on Wireless Signals and Artificial Neural Network

With the continuous improvement of people’s health awareness and the continuous progress of scientific research, consumers have higher requirements for the quality of drinking. Compared with high-sugar-concentrated juice, consumers are more willing to accept healthy and original Not From Concentrated (NFC) juice and packaged drinking water. At the same time, drinking category detection can be used for vending machine self-checkout. However, the current drinking category systems rely on special equipment, which require professional operation, and also rely on signals that are not widely used, such as radar. This paper introduces a novel drinking category detection method based on wireless signals and artificial neural network (ANN). Unlike past work, our design relies on WiFi signals that are widely used in life. The intuition is that when the wireless signals propagate through the detected target, the signals arrive at the receiver through multiple paths and different drinking categories will result in distinct multipath propagation, which can be leveraged to detect the drinking category. We capture the WiFi signals of detected drinking using wireless devices; then, we calculate channel state information (CSI), perform noise removal and feature extraction, and apply ANN for drinking category detection. Results demonstrate that our design has high accuracy in detecting drinking category.     

Non-Destructive Detection of Moldy Walnuts Based on Hyperspectral Imaging Technology

Walnuts with their shells are a popular agricultural product in China. However, mildew from growth can sometimes be processed into foods. It is difficult to visually determine which walnuts have mildew without breaking the shells. A non-destructive method for detecting walnuts with mildew was studied by combining spectral data with image information. A total of 120 “Lüling” walnuts with shells were used for the mildew experiment. The characteristics of the spectral data from six surfaces of all samples were collected in the range of 370–1042 nm on days 0, 15, and 30. The spectrum was pretreated using SNV, and the feature bands were extracted using PCA and modeled using a support vector machine (SVM). The results show that the overall classification accuracy was 93%, with an of accuracy of 100% for INEN walnuts (normal internally and externally). The accuracy for IMEM walnuts (mildew internally and externally) reached 87.29%. There was an accuracy of 78.6% for IMEN walnuts (mildew internally and normal externally). The non-destructive detection of mildewed walnuts can be undertaken using hyperspectral imaging technology, which provides a new technique for exploring the mechanisms of walnuts with mildew.     

Crystal Structure of Human CD47 in Complex with Engineered SIRPα.D1(N80A)

Background: Targeting the CD47/SIRPα signaling pathway represents a novel approach to enhance anti-tumor immunity. However, the crystal structure of the CD47/SIRPα has not been fully studied. This study aims to analyze the structure interface of the complex of CD47 and IMM01, a novel recombinant SIRPα-Fc fusion protein. Methods: IMM01-Fab/CD47 complex was crystalized, and diffraction images were collected. The complex structure was determined by molecular replacement using the program PHASER with the CD47-SIRPαv2 structure (PDB code 2JJT) as a search model. The model was manually built using the COOT program and refined using TLS parameters in REFMAC from the CCP4 program suite. Results: Crystallization and structure determination analysis of the interface of IMM01/CD47 structure demonstrated CD47 surface buried by IMM01. Comparison with the literature structure (PDB ID 2JJT) showed that the interactions of IMM01/CD47 structure are the same. All the hydrogen bonds that appear in the literature structure are also present in the IMM01/CD47 structure. These common hydrogen bonds are stable under different crystal packing styles, suggesting that these hydrogen bonds are important for protein binding. In the structure of human CD47 in complex with human SIRPα, except SER66, the amino acids that form hydrogen bonds are all conserved. Furthermore, comparing with the structure of PDB ID 2JJT, the salt bridge interaction from IMM01/CD47 structure are very similar, except the salt bridge bond between LYS53 in IMM01 and GLU106 in CD47, which only occurs between the B and D chains. However, as the side chain conformation of LYS53 in chain A is slightly different, the salt bridge bond is absent between the A and C chains. At this site between chain A and chain C, there are a salt bridge bond between LYS53 (A) and GLU104 (C) and a salt bridge bond between HIS56 (A) and GLU106 (C) instead. According to the sequence alignment results of SIRPα, SIRPβ and SIRPγ in the literature of PDB ID 2JJT, except ASP100, the amino acids that form common salt bridge bonds are all conserved. Conclusion: Our data demonstrated crystal structure of the IMM01/CD47 complex and provides a structural basis for the structural binding interface and future clinical applications.     

基于数字地图的二维电波传播问题仿真

为快速预测二维地理环境下的电磁环境特性,应用二维抛物方程模型对电磁环境进行仿真。为了得到真实有效的地形数据,研究了从GeoTiff中抽取网格点上地理信息的方法,并利用双线性插值法计算了任意位置处的高程值。同时研究了地球表面两点之间计算距离的方法,将该方法的计算结果与GIS软件结果进行对比,验证了该方法的可靠性。在标准大气环境下,利用二维抛物方程模型仿真分析了不同距离处不同高度的电波传播传播因子的变化情况,为预测真实地理环境中的电波传播特性提供了一种有效的方法。     

基于TL494开关电源的设计

开关电源主回路将输入的15VAC电压整流滤波所得的直流电压通过升压斩波电路,变换为25-30VDC输出。主控制器为PIC16F877A单片机。整个系统由整流滤波电路、DC-DC变换器、控制电路、按键显示等模块组成。主控制器和TL494以闭环形式控制DC-DC变换电路,实现输出电压稳定可调。该电源还具有过流保护、自恢复、软启动和短路报警功能。     

Enhanced enzymatic hydrolysis of poplar bark by combined use of gamma ray and dilute acid for bioethanol production

Pretreatment of poplar bark with a combination of sulfuric acid (3%, w/w, H₂SO₄) and gamma irradiation (0–1000 kGy) was performed in an attempt to enhance enzymatic hydrolysis for bioethanol production. The yields of reducing sugar were slightly increased with an increasing irradiation dose, ranging from 35.4% to 51.5%, with a 56.1% reducing sugar yield observed after dilute acid pretreatment. These results clearly showed that soluble sugars were released faster and to a greater extent in dilute acid-pretreated poplar bark than in gamma irradiation-pretreated bark. When combined pretreatment was carried out, a drastic increase in reducing sugar yield (83.1%) was found compared with individual pretreatment, indicating the possibility of increasing the convertibility of poplar bark following combined pretreatment. These findings are likely associated with cellulose crystallinity, lignin modification, and removal of hemicelluloses.