一种融合MRF分割与数学形态学的道路提取算法

针对高分辨率合成孔径雷达（Synthetic Aperture Radar, SAR）图像中道路目标难以有效提取的问题,提出一种融合马尔可夫随机场（Markov Random Field, MRF）分割与数学形态学处理的高分辨率SAR图像道路提取算法。该算法首先利用直方图均衡化和增强Lee滤波对SAR图像进行预处理,实现道路的边缘增强,抑制相干斑噪声;进而利用基于条件迭代模式（Iterated Conditional Mode, ICM）的MRF对SAR图像中的道路目标进行初分割;再用数学形态学填充空洞,平滑道路边缘;最后,基于道路的几何特征,使用偏心率、矩阵度、复杂度等因子去除虚警,从而提取出道路目标。利用该文算法对两块实际高分辨率SAR图像进行道路目标提取,均可以取得90%以上的正确道路提取率,表明本文算法具有较高的道路提取精度。     

Effect of scavenge port angles on flow distribution and performance of swirl-loop scavenging in 2-stroke aircraft diesel engine

Swirl-Loop Scavenging (SLS) improves the performance of 2-stroke aircraft diesel engine because the involved swirl may not only benefit the scavenging process, but also facilitate the fuel atomization and combustion. The arrangement of scavenge port angles greatly influences in-cylinder flow distribution and swirl intensity, as well as the performance of the SLS engine. However, the mechanism of the effect and visualization experiment are rarely mentioned in the literature. To further investigate the SLS, Particle Image Velocimetry (PIV) experiment and Computational Fluid Dynamics (CFD) simulation are adopted to obtain its swirl distribution characteristics, and the effect of port angles on scavenging performance is discussed based on engine fired cycle simulation. The results illustrate that Reynolds Stress Turbulence model is accurate enough for in-cylinder flow simulation. Tangential and axial velocity distribution of the flow, as well as the scavenging performance, are mainly determined by geometric scavenge port angles α_geom and β_geom. For reinforcement of scavenging on cross-sections and meridian planes, α_geom value of 27° and β_geom value of 60° are preferred, under which the scavenging efficiency reaches as high as 73.7%. Excessive swirl intensity has a negative effect on SLS performance, which should be controlled to a proper extent.     

基于图像的经纬仪测量目标快速瞄准技术

电子经纬仪是一种高精度的测角仪器,由多台高精度电子经纬仪构成的测量系统可以实现三维坐标测量,用于对大型工业产品的几何检测。但经纬仪在测量过程中仍然需要人工瞄准目标,存在速度慢、效率低、人为因素影响大等不足。实现经纬仪自动照准目标功能将是一个新的发展方向。提出一种基于图像的自动瞄准技术,通过在经纬仪上安装一台相机获取待测目标点的图像,利用图形目标识别技术获取目标点图像坐标,依据相机与经纬仪的空间关系可以获得各目标点相对于经纬仪的初始角度,从而实现目标点的快速概略定位,理论推导及实验证明本方法能够准确有效的获得目标点的概略位置。     

基于Contourlet与HIS变换的SAR与多光谱影像融合方法

为了提高SAR影像的解译水平,本文利用Contourlet变换在影像表述上能够弥补小波变换不能有效捕捉二维空间实体的特点,提出了一种基于Contourlet与HIS变换的SAR与多光谱影像融合方法。实验选取了一组TM 多光谱影像与ERS-2 SAR影像进行融合研究,并将融合结果与基于HIS变换、DWT结合HIS变换融合方法的融合结果进行视觉比较与统计分析。结果表明,无论是目视比较还是统计分析,本文方法都很好的将SAR影像的空间细节与多光谱影像的色彩信息集成到了一起,显著地提高了SAR影像的解译水平,相对于基于HIS、DWT+HIS变换的融合方法获得了更好质量的融合影像。     

联合变换相关法测量空间相机像移的抗噪性研究

为了研究使用联合变换相关器测量空间相机像移时噪声对测量精度的影响,分别对相关器加入背景噪声和图像噪声,通过仿真得到5种不同处理方法在不同噪声水平下的测量误差,并利用搭建的实验平台验证了使用联合变换相关法测量空间相机像移的有效性。结果表明,相比于其它相关器处理方法,使用功率谱相减并以0值为阈值二值化的方法得到的像移测量精度较高,即使对于SNR=1的输入图像,在含有背景噪声时,像移测量误差不大于0.12个像元,完全满足空间相机的使用要求。     

A debris image tracking using optical flow algorithm

This study proposes a motion detection and object tracking technique for GEO debris in a sequence of images. A couple of techniques (called the “stacking method” and “line-identifying technique”) were recently proposed to address the same problem. Although these techniques are effective at detecting the debris position and motion in the image sequences, there are some issues concerned with computational load and assumed debris motion. This study derives a method to estimate motion vectors of objects in image sequence and finally detect the debris locations by using a computer vision technique called an optical flow algorithm. The new method detects these parameters in low computational time in a serial manner, which implies that it has an advantage to track not only linear but also nonlinear motion of GEO debris more easily than the previous methods. The feasibility of the proposed methods is validated using real and synthesized image sequences which contain some typical debris motions.     

一种基于图像的星体表面撞击坑自动提取方法

以星体表面的图像数据为基础,根据撞击坑的向阳面呈亮色调而背阳面呈暗色调的原理,提出了一种基于图像的星体表面撞击坑自动提取方法。该方法先用自适应双阈值分割法对星体表面的光学图像进行分割处理,获取图像中明暗区域的形状和位置信息;再用统计学原理分析明暗区域组成结构、像平面上光照方向,结合相关的约束条件来匹配同一撞击坑的明暗区域,同时拟合出撞击坑的外边缘并确定其半径、位置等信息。实验结果表明,该方法能够从常见的星体表面光学图像中快速、可靠地提取出撞击坑的中心位置和半径大小,具有较宽的普适应性和一定的应用价值。     

一种用于WorldView-2遥感图像的波段分组融合方法

针对WorldView-2卫星遥感图像,提出一种基于波段分组的多光谱图像与全色光图像融合新方法。该方法以全色光波段与多光谱各波段光谱响应的匹配特点为依据,首先将八波段多光谱图像分成两组,然后分别设计融合模型再进行分组融合,最终得到多光谱各波段的融合结果,分组策略简单、实用。实验结果表明,该方法在融合WorldView-2遥感图像时能够在提高空间分辨率和保持光谱信息方面达到更好的平衡,优于现有的几种融合方法。     

Aerial-BiSeNet: A real-time semantic segmentation network for high resolution aerial imagery

The aircraft system has recently gained its reputation as a reliable and efficient tool for sensing and parsing aerial scenes. However, accurate and fast semantic segmentation of high-resolution aerial images for remote sensing applications is still facing three challenges: the requirements for limited processing resources and low-latency operations based on aerial platforms, the balance between high accuracy and real-time efficiency for model performance, and the confusing objects with large intra-class variations and small inter-class differences in high-resolution aerial images. To address these issues, a lightweight and dual-path deep convolutional architecture, namely Aerial Bilateral Segmentation Network (Aerial-BiSeNet), is proposed to perform real-time segmentation on high-resolution aerial images with favorable accuracy. Specifically, inspired by the receptive field concept in human visual systems, Receptive Field Module (RFM) is proposed to encode rich multi-scale contextual information. Based on channel attention mechanism, two novel modules, called Feature Attention Module (FAM) and Channel Attention based Feature Fusion Module (CAFFM) respectively, are proposed to refine and combine features effectively to boost the model performance. Aerial-BiSeNet is evaluated on the Potsdam and Vaihingen datasets, where leading performance is reported compared with other state-of-the-art models, in terms of both accuracy and efficiency.     

基于第二代小波的序列图像超分辨率复原算法研究

介绍了第二代小波(SGWs)的基本原理和特点,在此基础上提出了低分辨率采样图像高分辨率 (HR)重建算法。它不但具有结构简单,逆变换容易,可扩展性好的优点,并且克服了第一代 小波(FGWs) 的不均匀采样和定义在有限区间上的难题,指出了小波变换时数据不规则性的 处理方法,并利用硬／软阈值对小波系数降噪,使得重构后的图像具有最佳的PSNR和最低的 重构误差。实验和仿真结果表明,与传统方法相比,该算法在提高了图像的分辨率同时PSNR 最多能提高3 dB左右。