基于单目视觉的三维重构相机技术研究

针对飞行器执行在轨服务获取空间多维图像的需求，提出了基于单目视觉的三维重构相机技术，利用基于亮度法体素着色原理实现空间目标的三维重构。搭建地面试验，设计模拟圆轨道和椭圆轨道多种试验，验证了在200 m范围内伴飞状态下,实现对目标的高分辨率三维重构图像，重构精度为0.105 m，为识别空间目标特征部位奠定技术基础。     

Evolution of turbulent boundary layer over a three-dimensional bump

A bump is typically used in the inlet system of an aircraft engine to compress the incoming airflow and to reduce boundary layer thickness developed over fuselage. In this work, the turbulent flow over a three-dimensional bump is experimentally studied. The bump model is mounted in a closed return wind tunnel operated at the nominal velocity 10 m/s, corresponding to a friction Reynolds number of 2300. The flow field upstream the bump, along the bump centerline and at two different spanwise plane...     

基于条件生成对抗模型的遥感卫星影像重建技术研究

为了快速侦察未知区域的地貌信息，遥感卫星可对特定区域进行扫描以获取遥感卫星影像。当卫星经过国外未知区域时，部分卫星无法针对某特定区域进行长时间的驻留扫描，本文提出一种基于条件生成对抗网络模型（Conditional Generative Adversarial Network，CGAN）进行网络训练，前期将某方法获取的区域轮廓地形信息作为CGAN网络的生成网络和鉴别网络中的条件约束信息，通过网络生成器与判别器在训练过程中互相博弈产生特定的输出集，有效地实现由单张电子轮廓图像到对应卫星遥感图像的端到端的非线性映射。本文通过原真实卫星遥感图像与生成卫星遥感图像进行四种对比误差计算，平均误差、均方误差与结构相似度均高于99%，峰值信噪比高于30 dB，生成的图像与原图像之间具备高相似度，实现了在获取坐标定位轮廓信息的先验条件下，对特定区域进行遥感卫星影像内容重建技术。     

Comparison of residual and dense neural network approaches for building extraction from high-resolution aerial images

Applications including change detection, disaster management, and urban planning require precise building information, and therefore automatic building extraction has become a significant research topic. With the improvements in sensor and satellite technologies, more data has become available, and with the increased computational power, deep learning methods have emerged as successful tools. In this study, U-Net and FPN architectures using four different backbones (ResNet-50, ResNeXt-50, SE-ResNext-50, and DenseNet-121), and an Attention Residual U-Net approach were used for building extraction from high-resolution aerial images. Two publicly available datasets, Inria Aerial Image Labeling Dataset and Massachusetts Buildings Dataset were used to train and test the models. According to the results, Attention Residual U-Net model has the highest F1 score with 0.8154, IoU score with 0.7102, and test accuracy with 94.51% on the Inria dataset. On the Massachusetts dataset, FPN Dense-Net-121 model has the highest F1 score with 0.7565 and IoU score with 0.6188, and Attention Residual U-Net model has the highest test accuracy with 92.43%. It has been observed that, FPN with DenseNet backbone can be a better choice when working with small size datasets. On the other hand, Attention Residual U-Net approach achieved higher success when a sufficiently large dataset is provided.     

采用局部约束线性编码的像素级舰船目标图像融合

为了提升视觉信息在低能见度条件下的适用性,提出了一种采用局部约束线性编码的像素级舰船目标图像融合方法.首先,采用K均值奇异值分解算法从海量的训练样本中完成过完备字典的学习.其次,在考虑着舰导引实时性任务需求的前提下,采用局部约束线性编码完成融合系数的非迭代求解,相较于压缩感知理论架构下的匹配追踪算法,极大地降低了计算复...     

Pose matters: Pose guided graph attention network for person re-identification

Person re-Identification (reID), aiming at retrieving a person across different cameras, has been playing a more and more important role in the construction of smart city and social security. For deep-learning-based reID methods, it has been proved that using local feature together with global feature could help to give robust representation for person retrieval. Human pose information can provide the locations of human skeleton to effectively guide the network to pay more attention to these key areas, and can also help to reduce the noise distractions from background or occlusions. Based on human pose, a Pose Guided Graph Attention (PGGA) network is proposed in this paper, which is a multi-branch architecture consisting of one branch for global feature and two branches for local key-point features. A graph attention convolution layer is carefully designed to re-assign the contribution weight of each extracted local feature by modeling the similarity relations. The experimental results demonstrate the effectiveness of our approach on discriminative feature learning. Our model achieves the state-of-the-art performance on several mainstream evaluation datasets. A plenty of ablation studies and different kinds of comparison experiments are conducted to prove the effectiveness of this work, including the tests on occluded datasets and cross-domain datasets. Moreover, we further design supplementary tests in practical scenario to indicate the advantage of our work in real-word applications.