Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

不同孔形下豆类透筛效果对比及圆筒筛优化

以大豆为对象,推导了筛孔透筛区域的面积计算公式,对比了不同孔型圆筒筛的大豆透筛效果,得出大豆在正方形筛孔的圆筒筛中透筛效果最好,并通过仿真计算对其进行了验证。在此基础上对正方形筛孔的圆筒筛进行优化,用筛分比和除杂比计算筛分效果,通过正交仿真试验分析得到不同工艺参数对圆筒筛的豆类筛分效果的影响次序,并得出最佳工艺参数为圆筒倾角5°、圆筒转速16r/min、进料速度14t/h、筛孔边长9mm,该条件下筛分效果为0.935,比原始模型提高了3.89%。     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

无源光网络标准发展及关键技术研究

无源光网络(Passive Optical Network,PON)作为当今接入网的主要技术解决方案,具有带宽使用效率高、传输距离远、抗干扰能力强等特点.通过研究PON技术的发展动态,本文首先归纳了各种PON技术的产生背景和应用特点,整理出各技术间的连接关系及主要标准;其次介绍了PON技术的帧结构,并对带宽、波长、传输模式等PON技术的主要参数进行了汇总;然后将国内外研究热点进行划分,围绕媒体访问控制协议、帧结构、动态带宽分配算法、节能机制等关键技术,阐述了其研究现状及在PON中的重要作用;最后对PON技术的发展趋势进行了展望.     

基于特征融合的中文简历解析方法研究

针对基于规则和统计的传统中文简历解析方法效率低、成本高、泛化能力差的缺点，提出一种基于特征融合的中文简历解析方法，即级联Word2Vec生成的词向量和用BLSTM（Bidirectional Long Short-Term Memory）建模字序列生成的词向量，然后再结合BLSTM和CRF（Conditional Random Fields）对中文简历进行解析（BLSTM-CRF）。为了提高中文简历解析的效率，级联包含字序列信息的词向量和用Word2Vec生成的词向量，融合成一个新的词向量表示；再由BLSTM强大的学习能力融合词的上下文信息，输出所有可能标签序列的分值给CRF层；再由CRF引入标签之间约束关系求解最优序列。利用梯度下降算法训练神经网络，使用预先训练的词向量和Dropout优化神经网络，最终完成对中文简历的解析工作。实验结果表明，所提的特征融合方法优于传统的简历解析方法。     

On Cost Aware Cloudlet Placement for Mobile Edge Computing

As accessing computing resources from the remote cloud inherently incurs high end-to-end (E2E) delay for mobile users, cloudlets, which are deployed at the edge of a network, can potentially mitigate this problem. Although some research works focus on allocating workloads among cloudlets, the cloudlet placement aiming to minimize the deployment cost (i.e., consisting of both the cloudlet cost and average E2E delay cost) has not been addressed effectively so far. The locations and number of cloudlets have a crucial impact on both the cloudlet cost in the network and average E2E delay of users. Therefore, in this paper, we propose the Cost Aware cloudlet PlAcement in moBiLe Edge computing (CAPABLE) strategy, where both the cloudlet cost and average E2E delay are considered in the cloudlet placement. To solve this problem, a Lagrangian heuristic algorithm is developed to achieve the suboptimal solution. After cloudlets are placed in the network, we also design a workload allocation scheme to minimize the E2E delay between users and their cloudlets by considering the user mobility. The performance of CAPABLE has been validated by extensive simulations.      

Structural,morphological, dielectric and magnetic properties of Zn-Zr co-doping yttrium iron garnet

In this study, yttrium iron garnet co-doped with Zn and Zr atoms with a chemical formula Y₃Zn_xZr_xFe_(5−2x)O₁₂ (x = 0.0-0.3) has been successfully prepared by the solid-state reaction method. The effects of doping concentration on the microstructure, crystal structure, magnetic properties, and dielectric properties of Y₃Zn_xZr_xFe_(5−2x)O₁₂ were investigated. The microstructure analysis indicates that co-doping of YIG with Zn and Zr can effectively reduce the grain size of the ceramic. The crystal structure results reveal that the doping concentration of Zn–Zr has substantial influence on the lattice parameters of YIG, such as, increases the lattice constant, crystal cell size, and interplanar spacing. However, the second phase of ZrO₂ appears once x ≥ 0.15. Additionally, the dielectric properties of YIG ferrite can be regulated using this Zn–Zr co-doping method. Zn–Zr co-doping can improve the dielectric stability and reduce the dielectric loss at high temperature. The magnetization measurement shows that the saturation magnetization is stabilized at x < 0.15, and the magnetic loss is decreased with the increase in the doping concentration. Overall, the findings show that the ceramic with x = 0.1 exhibits better properties included high saturation magnetization (24.607 emu/g), low magnetic loss (0.0025 @ 1 MHz), and relatively low dielectric loss (496 @ 400°C).     

基于图像增强的去雾快速算法的FPGA实现

基于图像增强方法，本文提出了一种使用亮度映射的图像去雾快速算法。此算法通过调整室外多雾场景图像的对比度，提高了雾中物体的辨识度。算法的复杂度低、处理延迟小，实时性高，利于FPGA的实现。实现时不需外存储器，延时为ns级，并提供了强度调节接口，以适应较广的应用环境。