A CNN-Based Single-Stage Occlusion Real-Time Target Detection Method

Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.

Target acquisition performance in the presence of JPEG image compression

This paper presents an investigation on the effect of JPEG compression on the similarity between the target image and the background,where the similarity is further used to determine the degree of clutter in the image.Four new clutter metrics based on image quality assessment are introduced,among which the Haar wavelet-based perceptual similarity index,known as HaarPSI,provides the best target acquisition prediction results.It is shown that the similarity between the target and the background at the boundary between visually lossless and visually lossy compression does not change significantly compared to the case when an uncompressed image is used.In future work,through subjective tests,it is necessary to check whether this presence of compression at the threshold of just noticeable differences will affect the human target acquisition performance.Similarity values are compared with the results of subjective tests of the well-known target Search_2 database,where the degree of agreement between objective and subjective scores,measured through linear correlation,reached a value of 90%.

Depolarization Degree to Determine Dihedral Attribute of Radar Target

This paper investigates the ability of the depolarization degree, derived from the characteristic polarization states at the resonant frequency set, to identify corner or swept, i.e. dihedral, changes in same-class targets by a metallic wire example. A well-estimated depolarization degree requires a robust extraction of the fundamental target resonance set in two orthogonal sets of fully co-polarized and cross-polarized polarization channels, then finding the null polarization states using the Lagrangian method. Such depolarization degree per resonance mode has the potential to form a robust feature set because it is relatively less sensitive to onset ambiguity, invariant to rotation, and could create a compact, recognizable, and separable distribution in the proposed feature space. The study was limited to two targets with two swept changes of fifteen degrees within normal incidence;under a supervised learning approach, the results showed that the identification rate converging to upper-bound (100%) for a signal-to-noise ratio above 20 dB and lower-bound around (50%) below −10 dB.

基于Real-Time Windows Target状态观测器的实验开发

在Matlab/Simulink中应用Real-Time Windows Target模块重构状态观测器的实时仿真模型,采用该方法开发的实验系统既便于实现,又能和实际物理系统良好对接,有利于学生掌握状态观测器的相关知识和促进对Matlab的了解和应用。给出的应用实例验证了方法的可行性。

Design and operation strategies of the system for destroying time-sensitive target based on system effectiveness

To improve the effect of destroying time-sensitive target （TST）, a method of operational effectiveness evaluation is presented and some influential factors are analyzed based on the combat flow of system for destroying TST. Considering the possible operation modes of the system, a waved operation mode and a continuous operation mode are put forward at first. At the same time, some relative formulas are modified. In examples, the influential factors and operation modes are analyzed based on the system effectiveness. From simulation results, some design and operation strategies of the system for destroying time sensitive targets are concluded, which benefit to the improvement of the system effectiveness.

On the Trade-off between Power Consumption and Time Synchronization Quality for Moving Targets under Large-Scale Fading Effects in Wireless Sensor Networks

In this work we find a lower bound on the energy required for synchronizing moving sensor nodes in a Wireless Sensor Network (WSN) affected by large-scale fading, based on clock estimation techniques. The energy required for synchronizing a WSN within a desired estimation error level is specified by both the transmit power and the required number of messages. In this paper we extend our previous work introducing nodes’ movement and the average message delay in the total energy, including a comprehensive analysis on how the distance between nodes impacts on the energy and synchronization quality trade-off under large-scale fading effects.

Impacts of space-time-frequency synchronization errors onwide-band target echo characteristics of bistatic/multistatic radar

Bistatic/multistatic radar has great potential advantages over its monostatic counterpart. However, the separation of a transmitter and a receiver leads to difficulties in locating the target position accurately and guaranteeing space-timefrequency synchronization of the transmitter and the receiver.The error model of space-time-frequency synchronization in a motion platform of bistatic/multistatic radar is studied. The relationship between the space synchronization error and the transmitter platform position, receiver platform position, moving state, and beam pointing error, is analyzed. The effect of space synchronization error on target echo power is studied. The target scattering characteristics are restructured by many separate scattering centers of the target in high frequency regions. Based on the scattering centers model of the radar target, this radar target echo model and the simulation method are discussed. The algorithm of bistatic/multistatic radar target echo accurately reflects the scattering characteristics of the radar target, pulse modulation speciality of radar transmitting signals, and spacetime-frequency synchronization error characteristics between the transmitter station and the receiver station. The simulation of bistatic radar is completed in computer, and the results of the simulation validate the feasibility of the method.

经直肠实时组织弹性成像引导靶向穿刺在前列腺癌诊断中的应用研究

目的 探讨经直肠实时组织弹性成像(transrectal real-time tissue elastography,TRTE)引导靶向穿刺诊断前列腺癌的临床应用价值。方法 选取2020年1月至2022年12月于郑州市第一人民医院就诊的可疑前列腺癌患者52例为研究对象,术前均行经直肠常规超声及TRTE检查评估前列腺病变的良恶性,对TRTE发现可疑病灶的28例患者行TRTE引导靶向穿刺(2针)+系统穿刺(8针),对TRTE未发现可疑病灶的24例患者行直肠常规超声引导系统穿刺(12针),分析TRTE诊断前列腺癌的效能及对比分析靶向穿刺与系统穿刺的穿刺阳性率。结果 本研究最终病理确诊前列腺癌25例,良性病变27例;TRTE诊断前列腺癌28例,良性病变24例,诊断的阳性预测值、阴性预测值分别为75.0%(21/28)、83.3%(20/24)。TRTE发现可疑病灶的28例患者,靶向穿刺共56针,诊断前列腺癌36针,阳性率64.29%(36/56),系统穿刺共224针,诊断前列腺癌89针,阳性率39.73%(89/224);靶向穿刺的前列腺癌穿刺阳性率显著高于系统穿刺(P<0.05)。结论 TRTE可较好地诊断前列腺癌,其引导靶向穿刺诊断前列腺癌的阳性率更高,可在减少穿刺针数的基础上最大限度提高穿刺阳性率。

中国式现代化视域下中国财政收入目标制演变研究

财政收入目标作为财政预算收入编制的基础,是财政政策相机调控的政策工具,亦是有为政府动员部署和调配资源的重要途径。中国财政收入目标制的发展阶段可划分为新中国成立初期财政收入目标考核确立前阶段(1949—1977年)、改革开放后财政收入目标考核萌发阶段(1978—1993年)、分税制后财政收入目标考核发展阶段(1994—1999年)、新世纪财政收入目标与预算绩效融合阶段(2000—2012年)及新时代财政融入国家治理体系阶段(2013年以来)等五个阶段,具有历史演进特征。根据1998—2020年相关数据,全国、省级和地市级三个层面的财政收入目标具有时空格局演变特征:就整体而言,中国财政收入目标具有很强的引导作用,体现了财政的主动性和目标意识;从区域来看,东部发达地区因为自身较大的经济体量,财政收入增速呈现正常的趋缓现象,财政收入目标总体上小于其他欠发达省份;而在区域内部,城市间财政收入目标差异分化较大,中部和西部地区城市所制定目标的水平会更高,目标的增长压力也更大,大部分城市的财政收入目标小于其实际经济增速,目标存在留有余地的空间;各省份和城市之间的收入目标差距均存在收敛效应。

太阳同步轨道遥感卫星快速目标访问计算方法

目标访问计算是指根据遥感卫星轨道和待观测目标的位置,计算遥感卫星对目标观测的时刻和姿态,是遥感卫星任务管控领域的重要基础技术之一。高效的目标访问计算方法可大幅提升卫星任务管控的时效性,对后续大规模遥感星座任务管控具有重要意义。利用太阳同步轨道卫星交点地方时不变的特点,快速估算出卫星经过目标的较短时间窗口,对时间窗口内的星历进行逐点计算,获取卫星对目标进行访问的最佳时刻。试验结果证明,该方法可大幅提升目标访问时间的计算效率。

基于改进YOLOv8算法的实时细粒度植物病害检测

为解决现有识别方法在植物病害检测中遇到的密集分布、不规则形态、多尺度目标类别、纹理相似性等障碍,提出一种高性能的实时细粒度植物病害检测框架。首先,在YOLOv8主干网络和颈部设计两个新的残差块,增强特征提取和降低计算成本;其次,引入DenseNet层,并使用Hard-Swish函数作为主要激活函数,以提高模型的准确性;最后,设计PANet网络,用于保留细粒度的局部信息和改善特征融合。在不同的复杂环境下,对番茄植株的四种不同病害进行检测。试验结果表明,所提改进模型在检测准确性和速度上均优于现有模型的检测模型。当检测速度为71.23 FPS时,所提改进模型精确度为92.58%,召回率为97.59%,F_(1)分数为93.64%。为精准农业自动化提供有效的技术手段。

基于改进YOLOv4-tiny的果园复杂环境下桃果实实时识别

为实现果园复杂环境下的桃果实实时识别,提出一种基于YOLOv4-tiny的桃果实实时识别方法 YOLOv4-tinyPeach。通过在主干网络中引入卷积注意力模块CBAM,优化其通道维度和空间维度的特征信息;在颈部网络中添加大尺度浅层特征层,提高对小目标识别精度;采用双向特征金字塔网络BiFPN对不同尺度特征信息进行融合。通过训练和比较,YOLOv4-tiny-Peach模型在测试集下的平均精度AP为87.88%,准确率P为91.81%,召回率R为73.84%,F1值为81.85%,相比于改进前,AP提升5.46%,P提升2.29%,R提升4.09%,F1提升3.44%。为检验改进模型在果园复杂环境下的适应性,在不同数目、不同成熟期和遮挡的情况下对果实图像进行识别,并与原模型识别效果进行对比,结果表明改进模型在三种情况下的识别精度均高于原模型,尤其在大视场和未熟期场景下模型改进效果显著。YOLOv4-tiny-Peach模型占用内存为27.4 MB,识别速度为49.76 fps,适用于农业嵌入式设备。为果园复杂环境下的桃果实自动采摘提供实时精准的目标识别指导。

通信约束下UAV集群协同拦截任务分配算法

针对多无人机协同拦截多机动目标的任务分配问题,同时考虑到真实战场环境中存在的通信约束以及探测范围约束条件,本文提出了分步一致性拍卖算法(SCBAA)。首先,对真实战场环境中存在的通信约束以及探测范围约束等问题进行了描述分析,构建了多无人机协同拦截任务分配模型,设计了综合效能函数以及相应约束条件。其次,为解决多无人机协同打击单一目标的不平衡任务分配以及冲突消解问题,将原任务分配过程分为主要任务分配以及次要任务分配两部分,通过多次拍卖以及冲突消解实现多无人机对单一目标的任务分配。仿真结果表明,该算法可有效解决通信约束条件下的分布式多无人机协同拦截问题,并适应动态环境中任务分配对实时性的要求。

基于xPC Target的TIG焊PID控制实时仿真

为尝试在焊接过程控制研究中应用实时仿真方法,采用基于Matlab/Simulink的xPC Target模块搭建实时仿真平台,对TIG焊过程进行电流闭环PID控制实时仿真实验,实验中采用凑试法选择最优PID参数,对1.0、0.1Hz的方波及0.33 Hz的复杂波形进行在线控制仿真.由实验结果可知,基于Matlab/Simulink的xPC Target模块搭建的实时机系统可以在线仿真得到最优控制参数.

三维自适应固定时间多导弹协同制导律

针对三维空间内多导弹对机动目标同时攻击的问题,提出一种具有自适应律的三维多导弹固定时间协同制导律。建立三维空间导弹-目标动力学模型,以弹目视线方向和其垂直方向设计制导律,可保证剩余飞行时间和法向速度在固定时间内完成一致性收敛。采用自适应律来跟踪机动目标运动参数策略,提高多导弹系统的稳定性与对机动目标的打击精度。改进多导弹系统收敛条件,所设计的制导律具备了对攻击时间的约束能力。向制导律中加入饱和函数,避免因符号函数带来的系统抖振。通过仿真实验验证所提固定时间协同制导律的有效性及对抗通信拓扑切换的鲁棒性。实验结果表明:相较于对比文献所设计的制导律具有系统快速收敛以及高精度。

基于Matlab/xPC Target的实时仿真系统研究

利用Matlab RTW和xPC Target提供的实时仿真功能,可以完成某些实物在回路中的仿真。采用该种方式与传统方式相比,具有系统组建方便,成本低,开发周期短等特点。主要讨论了其实现方式和开发流程,并将其应用到弹载计算机仿真评估系统的设计中。

运动目标的多维度微运动特征提取研究

微多普勒特征提取作为一种常用的时频分析工具,对微动目标特征的提取重构具有重要意义.为了更好地研究多运动的微多普勒效应,提出了一种运动姿态分类方法.按照目标频移是否随时间变化可以将运动姿态分为频移时变运动和频移时不变运动.频移时变运动包括平移、翻滚和振动.针对这种运动应分析对比不同时间对应的瞬态频移,频移时不变运动主要为旋转运动.本文通过微多普勒效应理论结合电磁波频域模型,实现3D运动目标微动特性提取的仿真建立目标,分析不同环境条件例如晴天阴天、有无湍流对探测的影响,为后续实验研究奠定理论基础.开展基于收发同置系统的多特征运动目标的微多普勒频移探测实验,实验结果表明,不同目标位置上频移的幅度、正负性和谱线宽度旨在反演目标形状、运动姿态、运动方向和速度.利用FFTshift函数对一维数据进行解调分析,实现三维时间-频率-强度关系的研究.本研究实现了对目标宏观形状特性的测量以及微观运动信息的提取,为雷达探测和识别奠定基础.

“双碳”目标下抽水蓄能提升系统保供能力的技术经济性研究

本工作通过时序仿真模拟,对抽水蓄能在典型省级电网中的保供技术经济性进行量化分析。首先,根据典型省级电网未来电力规划数据,计算得出该省级电网2025年与2030年全年电力系统运行情况,结果表明系统在全年部分时段处于供电紧平衡状态,系统备用率不足10%,充裕性和安全性面临巨大挑战。其次,选取抽水蓄能与火电机组两种灵活性调节电源,对比分析新增两种调节电源下系统供电可靠性改善情况和两种方案的量化经济性,结果表明,以2030年该省级电网模拟结果为例,配置1200万千瓦抽水蓄能和火电机组均能够将该省级电网系统全年备用率提升10%以上,解决系统备用率不足问题,提升系统保供能力。考虑系统碳排放变化所产生的环境成本,抽水蓄能改善系统供电水平的年度综合成本低于同等水平下的火电机组,同时能够对新能源消纳水平的促进和碳排放水平的降低起到积极作用。最后,比较分析了抽水蓄能与锂离子电池储能对于提升系统供电可靠性的综合经济性,结果表明抽水蓄能对于改善系统供电可靠性和充裕性等方面的综合经济性优势显著。

多波束系统搜索水下失联目标的效能评估

针对当前运用多波束系统进行水下失联目标搜索时所布测线效能较低的问题,提出一种改进的测线布设方式。首先,分析并建立了典型测线布设方式的水下目标搜索耗时计算方法,然后对给定条件下搜索耗时的影响因素进行数值模拟计算,从而确定出多波束系统的不同波束开角、船舶长度、区域海水深度等不同因素影响下的测线布设最优方案。试验结果表明,小船作业时,采用梭织法与跨行法的搜索效率明显优于向心法与套行法,大船作业时,采用跨行法的搜索效率最优。这些结论有助于深入了解各因素之间的相互作用和影响规律,进而找出影响搜索效率的主要因素,并提出相应的改进措施和优化建议。