一种基于视觉底层特征的图像质量评价方法

把视觉底层特征概念引入到客观图像质量评价中,提出了一种基于不同图像视觉底层特征的质量评价方法。在基于Itti计算模型和视觉底层特征最佳权重的基础上,对4种类型图像提取底层视觉特征显著图,利用特征最佳权重值,组合归一化形成视觉计算显著图,通过直方图相似度计算分析各显著图。实验结果与主观评价结果具有较好的一致性,且优于基于传统Itti模型和SSIM模型的图像质量评价方法。不同类型的图像需要充分考虑各特征的权重大小,使其能真实反映视觉感兴趣区域的特征属性,更好地评价失真图像的质量。     

基于GAN的半监督遥感图像场景分类

针对遥感图像背景复杂及有监督场景分类算法无法利用无标签数据的问题,提出一种基于生成对抗网络的半监督遥感图像场景分类方法.首先,引入谱归一化残差块代替传统生成对抗网络中的二维卷积,利用残差块的跳跃连接解决梯度消失问题;其次,引入特征融合思想,将浅层特征与深层特征进行融合,从而减少特征损失;最后,在生成对抗网络的判别器中加...     

两级透射-反射聚光分频电热联产系统设计和分析

在传统聚光条件下的太阳能光伏发电系统中,由于太阳光中存在所有波段的光子,而其中只有一部分能够被太阳电池用来发电,其余的部分进入太阳电池之后非但不会被用于发电,反而会变成热量使太阳电池升温,从而使电池光电转换效率下降．本文设计了一种聚光且具有分频功能的太阳能电热联产系统,利用线聚焦菲涅尔透镜和光谱选择性透过涂层改善太阳电池表面的入射光环境,在聚光的同时将不利于光伏发电的太阳光波段反射并加以收集利用．分析结果表明,与相同条件下传统的只进行聚光的光伏系统相比,两级透射一反射聚光分频电热联产系统具有更高的太阳能利用效率．     

太阳能辅助燃煤发电系统蓄热运行策略优化

太阳能辅助燃煤发电已经被证明是一种有效利用太阳能的发电方式。与纯太阳能光热发电系统不同,太阳能辅助燃煤互补发电系统(下简称互补发电系统)中采用不同的蓄热运行策略将对互补系统的性能产生显著影响。本文针对槽式互补发电系统,建立了槽式太阳能集热场以及互补系统的数学模型,采用了真实的气象数据进行仿真模拟,研究分析了互补发电系统的年性能,得出了不同太阳能倍数、蓄热小时数对互补系统的太阳能发电成本LCOE的影响规律,并据此优化蓄热运行策略。其结果表明:三种策略中,削峰填谷策略是最适合互补发电系统的运行策略,在0.5蓄热小时数、1.2太阳能倍数下,其太阳能发电成本取得极小值,为0.064$/kWh。     

紫外光通信中基于大气散射理论的传输模型

在研究单次散射模型的基础上, 针对单次散射模型不能对天气变化对紫外光信号造成的影响做出模拟的不足, 结合大气散射理论构建了紫外光传输的二次散射模型。研究了瑞利散射和米氏(Mie)散射在四种典型天气条件下的散射相函数, 仿真得出了紫外光被大气中的粒子散射后的能量分布情况, 将其引入二次散射模型, 并确定了各种天气条件下的散射粒子浓度后对紫外光通信系统做出性能仿真。计算结果表明, 二次散射模型可以仿真不同的天气条件下的紫外光通信系统的性能, 从仿真结果上验证了非直视通信的可实现性。并得出, 在雨、雾天气下, 紫外光信号衰减剧烈, 接收仰角不可过大; 在天气晴好时, 能更好的实现紫外光非直视通信, 接收仰角可达到180°。长距离通信时, 天气状况变化对通信性能影响更大。     

基于图像融合的动态轮廓线跟踪新方法

红外与可见光传感器是目标跟踪识别系统中常用的两种传感器,对这两种传感器图像进行融合能有效提高系统跟踪检测的准确性。将动态轮廓线模型与图像融合结合,在特征搜索过程中利用特征点准确地完成了图像配准,同时使用了一种新的特征级融合方法,将两种图像中目标轮廓的B样条曲线控制点进行实时微分耦合。这种耦合将Curwen提出的微分耦合机制作了改进,利用图像配准把刚性硬模板改变为实时的变换模板并推导了融合后动态轮廓线的新的动力学方程。这种融合利用了红外图像目标轮廓信息约束可见光图像中动态轮廓线的收敛形状,有效地提高了可见光图像目标跟踪的准确性。对运动人手序列图像的对比跟踪实验表明,这种融合使得可见光图像中动态轮廓线平均跟踪误差减小了60．25％。     

太阳能燃气轮机与卡林那循环联合的热发电系统

本文提出了一种带间冷回热的太阳能燃气轮机与卡林那循环组成的联合循环发电系统,对其热力性能进行了分析,并研究了关键运行参数对热力性能影响。塔式太阳能接收器将经过间冷压缩的压缩空气加热至1000℃用以驱动燃气轮机做功。卡林那循环用以回收燃气余热发电。基于蔡睿贤的比较法,推导出了该系统太阳能热发电效率的简明解析式。结果表明,当燃气轮机入口温度为1000℃时,该系统的(火用)效率和太阳能热发电效率分别可达到29%和27.5%,比太阳能燃气-蒸汽联合循环分别高1.8%和1.6%。该系统的提出,为提高太阳能热发电系统的太阳能热发电效率提供了一种方法,并且对太阳能热发电耗水大的问题提供了一个解决途径。     

全卷积网络多层特征融合的飞机快速检测

针对传统飞机检测方法准确率低、虚警率高、速度慢等问题,提出一种全卷积神经网络多层特征融合的飞机快速检测方法。将浅层和深层的特征经过采样后在同一尺度进行融合,以缓解由于深层特征图维度过低造成的对小目标表达不足的问题;修改区域提取时的选框尺寸以适应实际图像中飞机的尺寸特征;用卷积层代替全连接层以减少网络参数并适应不同大小的输入图像;复用区域提取网络和检测网络的卷积层和学习的特征参数以保证检测的高效性。仿真结果表明,与典型的飞机检测方法相比,所提方法在测试集上取得了更高的准确率和更低的虚警率,同时大大加快了检测速度。     

基于雷达反射率图像特征的冰雹暴雨识别

为了实现冰雹暴雨天气的识别与分类,提出了一种基于雷达反射率图像特征的自动识别方法.对雷达回波反射率图像中冰雹回波区域和暴雨回波区域的图像特征进行提取,通过分析冰雹暴雨间单一特征的差异性和不同特征之间的分类互补性,确定了识别冰雹暴雨的有效图像特征(包括强度特征和纹理特征).将提取出的样本有效特征与探空数据(0℃和~20℃温度层高度)结合,利用粗糙集理论进行数据挖掘,进而建立了冰雹暴雨天气的客观识别模型.通过对362个测试样本的测试与统计,冰雹击中率达到93.29%,暴雨的击中率达到89.27%,并且两者均具有较低的误警率.实验结果与传统PUP系统比较,表明利用雷达反射率图像特征实现对冰雹暴雨天气的识别与分类具有较好的效果.     

太阳能分频利用电热联产初步研究

本文对太阳能聚光分频利用电热联产的机理进行了探讨,给出了太阳能光谱有效能函数以及太阳能聚光分频利用电热联产的设计方案,并对该系统进行了热力性能分析,发电投资和成本比较.结果表明,对30倍聚光分频的光伏/光热系统,光伏发电效率约0.095,250～280℃热量利用效率0.14,折算为电的总发电效率为0.139;与普通光伏发电系统相比,单位面积硅光电池发电功率提高约16倍,投资成本仅0.33倍,每千瓦时的发电上网成本可从3.52元降到0.84元,考虑税收后的上网成本将从5.1元降到1.18元.     

Design,manufacture and testing of a closed cycle thermosyphon rankine engine

The Thermosyphon Rankine Engine (TSR) is a recent concept for power generation using solar or other available low grade heat sources. The basis of the engine is the modification of a heat pipe, with its excellent heat and mass transfer characteristics, to incorporate a turbine, thereby making the system into a Rankine Cycle Engine.The TSR is directed towards power production from solar ponds, geothermal energy and heat produced by solar collectors, as well as for waste heat utilisation for electrical power generation.A theoretical formulation and results from experiments on prototype units are presented. Based on the results, it is concluded that the TSR engine may play an important role for conversion into electrical energy of thermal energy produced by conventional solar collectors, geothermal sources and waste heat.     

基于深度学习的船舶辐射噪声识别研究

为了改善船舶辐射噪声识别系统的性能,进一步提高船舶辐射噪声识别的正确率,该文提出采用一种基于深度学习的船舶辐射噪声识别方法。该方法首先提取了船舶辐射噪声的频谱、梅尔倒谱系数等特征,将提取特征后的图像样本分别用于训练卷积神经网络和深度置信网络,再对船舶辐射噪声进行识别。通过文中所给实例,将深度学习和支持向量机两种识别方法的性能进行比较,得出深度学习方法可以有效地提高船舶辐射噪声识别正确率的初步结论。     

基于多核的车牌识别的架构实现

多核技术是现在提高芯片性能的主要方法。区别于传统以PC和DSP为核心的车牌识别系统,以FPGA为核心,利用SOPC技术构建了车牌识别多核处理器。给出了一种基于多核的车牌识别架构,在该多核处理器中,以3个Nios II 软核为主要处理器核处理车牌定位、字符特征识别提取及识别等处理,同时构建硬件加速器作为协处理器处理图像增强、边缘检测和膨胀、腐蚀等数学形态学处理。在CQ片上路由器基础上,构建了NOC用以实现片上多核通信。另外,为了保证路由器与多处理器核之间的快速、并行通信,加入了数据驱动模块。整个系统在Altera Cyclone IV FPGA上实现了车牌的识别。这种片上系统设计方法具有硬件设计灵活,可扩展性强等优点,能有效地降低系统软硬件设计的难度,缩短开发周期,并提高设计的可靠性。     

Development of an electronic stopping power model based on deep learning and its application in ion range prediction

Deep learning algorithm emerges as a new method to take the raw features from large dataset and mine their deep implicit relations, which is promising for solving traditional physical challenges. A particularly intricate and difficult challenge is the energy loss mechanism of energetic ions in solid, where accurate prediction of stopping power is a long-time problem. In this work, we develop a deep-learning-based stopping power model with high overall accuracy, and overcome the long-standing deficiency of the existing classical models by improving the predictive accuracy of stopping power for ultra-heavy ion with low energy, and the corresponding projected range. This electronic stopping power model, based on deep learning algorithm, could be hopefully applied for the study of ion-solid interaction mechanism and enormous relevant applications.     

Optimal Energy-Storage Configuration for Microgrids Based on SOH Estimation and Deep Q-Network

Energy storage is an important adjustment method to improve the economy and reliability of a power system. Due to the complexity of the coupling relationship of elements such as the power source, load, and energy storage in the microgrid, there are problems of insufficient performance in terms of economic operation and efficient dispatching. In view of this, this paper proposes an energy storage configuration optimization model based on reinforcement learning and battery state of health assessment. Firstly, a quantitative assessment of battery health life loss based on deep learning was performed. Secondly, on the basis of considering comprehensive energy complementarity, a two-layer optimal configuration model was designed to optimize the capacity configuration and dispatch operation. Finally, the feasibility of the proposed method in microgrid energy storage planning and operation was verified by experimentation. By integrating reinforcement learning and traditional optimization methods, the proposed method did not rely on the accurate prediction of the power supply and load and can make decisions based only on the real-time information of the microgrid. In this paper, the advantages and disadvantages of the proposed method and existing methods were analyzed, and the results show that the proposed method can effectively improve the performance of dynamic planning for energy storage in microgrids.     

Spiking Neural Network Based on Multi-Scale Saliency Fusion for Breast Cancer Detection

Deep neural networks have been successfully applied in the field of image recognition and object detection, and the recognition results are close to or even superior to those from human beings. A deep neural network takes the activation function as the basic unit. It is inferior to the spiking neural network, which takes the spiking neuron model as the basic unit in the aspect of biological interpretability. The spiking neural network is considered as the third-generation artificial neural network, which is event-driven and has low power consumption. It modulates the process of nerve cells from receiving a stimulus to firing spikes. However, it is difficult to train spiking neural network directly due to the non-differentiable spiking neurons. In particular, it is impossible to train a spiking neural network using the back-propagation algorithm directly. Therefore, the application scenarios of spiking neural network are not as extensive as deep neural network, and a spiking neural network is mostly used in simple image classification tasks. This paper proposed a spiking neural network method for the field of object detection based on medical images using the method of converting a deep neural network to spiking neural network. The detection framework relies on the YOLO structure and uses the feature pyramid structure to obtain the multi-scale features of the image. By fusing the high resolution of low-level features and the strong semantic information of high-level features, the detection precision of the network is improved. The proposed method is applied to detect the location and classification of breast lesions with ultrasound and X-ray datasets, and the results are 90.67% and 92.81%, respectively.     

太阳能热利用技术概况

太阳能是理想的可再生能源.太阳能热利用技术目前还处于发展时期.文章对太阳能热利用成熟技术、先进技术以及当前研究的中心问题进行了简要的概述.成熟技术部分主要包括热水器、太阳灶、太阳房等广为人们使用的太阳能热利用技术;先进技术部分主要阐述了尚处于研究试验阶段的高品位太阳能热利用技术,包括太阳能热发电、太阳能空调制冷、太阳能制氢、太阳能海水淡化及太阳能烟囱发电等;在当前研究的中心问题部分,主要论述了解决太阳能热利用的关键技术问题.     

多波段红外图像的海面舰船目标检测

现有的基于单个红外宽波段的海面舰船目标探测系统在面对复杂海天背景、岛岸背景、恶劣天气、亮带干扰或诱饵弹干扰等情况时,系统的探测率、虚警率、探测距离等性能指标均会受到严重的影响;为此,开展了基于多波段红外图像的海面舰船目标检测方法的研究。通过中波红外多波段数据采集系统实际采集107组五个中波红外波段的图像;波段1-5分别为3.7～4.8,3.7～4.1,4.4～4.8,3.7～3.9和4.65～4.75 μm;对多波段图像进行手动标注构建样本数据集,其中,正样本舰船目标298个,负样本非舰船目标353个。对于多波段红外图像,首先进行PCA降维并采用选择性搜索算法生成初始目标候选区域;针对候选区域中存在大量明显的非舰船目标区域的问题,利用积分图像计算候选区域的局部对比度,依据红外舰船目标的几何和灰度特征从初始目标候选区域中筛选出舰船目标可能性大的区域作为舰船目标候选区域。然后对舰船目标候选区域进行拓展以融入局部上下文信息,对于候选区域对应的5波段红外图像,分别提取每个波段图像的稠密SIFT特征,并将128维SIFT特征向量降为64维,融入SIFT特征的空间和波段位置分布信息得到新的特征向量,基于高斯混合模型对候选区域的特征向量集合进行编码融合得到舰船目标候选区域的费舍尔向量表示,最后利用线性SVM分类器识别出舰船目标。对多波段图像进行舰船目标候选区域生成实验,所提出的基于红外舰船目标的几何和灰度特征的约束方法可以有效地克服选择性搜索算法的不足,从初始目标候选区域中快速定位出舰船目标候选区域,对25组多波段图像进行实验,舰船目标候选区域生成的整体耗时为0.353 s,定位舰船目标区域耗时0.005 s。对100个正负样本进行目标识别测试,所提出的目标识别算法融合了目标的多波段图像特征信息,通过引入费舍尔向量挖掘了多波段图像梯度统计特征的深层次信息,算法的识别率达到了0.97,显著高于单波段红外图像的目标识别率。对25组多波段图像进行舰船目标检测实验,所提出的舰船目标检测方法能够在海天背景、岛岸背景以及亮带干扰等不同场景下完成海面舰船目标的检测工作,舰船目标定位准确,舰船目标召回率达到了0.95,每组多波段图像的平均检测耗时为1.33 s。研究结果表明,充分考虑海面舰船目标在红外图像中与局部海洋背景的辐射差异以及有效地融合舰船目标在多个红外波段图像中的辐射特征,可以增强舰船目标的可分性,提高舰船目标的识别率以及检测率,为基于多波段红外图像的海面舰船目标检测提供了新的技术支持。     

High performance computer methods applied to predictive spaceweather simulations

Taking advantage of the advent of massively parallel computers, sophisticated solution-adaptive techniques, and recent fundamental advances in basic numerical methods the authors have developed a high performance, adaptive-scale MHD code capable of resolving many of the critical processes in the Sun-Earth system which range over more than nine orders of magnitude. The development of such models are of increasing importance as the impact of space weather on vulnerable technological systems increases, and too, as the severity of space weather increases with the approach of solar maximum. There is an increasing need to develop physics-based, high performance models of the Sun-Earth system from the solar surface to the Earth's upper atmosphere which can operate faster than real time and which can provide reliable predictions of the near Earth space environment based upon solar observations and upstream solar wind measurements. They report on the status of the Michigan adaptive-scale MHD model, which is one effort whose goal is the development of an operational predictive space weather model