共查询到20条相似文献，搜索用时 31 毫秒
1.
提出了一种基于先检测、后滤波的椒盐噪声滤除GPU实现算法。该算法首先依据椒盐噪声的特征,将图像像素分为噪声和信号,然后对噪声像素作标准中值滤波,如果中值为信号,则用中值代替噪声像素灰度值;如果中值为噪声,则取中值邻域,如果中值邻域为信号,则用它代替噪声像素灰度值;否则扩大邻域窗口,重复算法。但随着图像规模的增大,在CPU上执行的时间显著增加。分析并利用图形处理器（GPU）的并行处理特征,并在GPU上实现了本文算法。实验结果表明所提出的算法较经典的自适应中值滤波算法有较好的去噪效果和边缘保护能力,并且随着图像规模的增大,算法执行时间较CPU可以提高最多3个数量级。 相似文献
2.
Non-Rigid Medical Image Registration with Joint Histogram Estimation Based on Mutual Information 总被引：1，自引：0，他引：1
A mutual information-based non-rigid medical image registration algorithm is presented. An approximate function of Hanning windowed sinc is used as kernel function of partial volume (PV) interpolation to estimate the joint histogram, which is the key to calculating the mutual information. And a new method is proposed to compute the gradient of mutual information with respect to the model parameters. The transformation of object is modeled by a free-form deformation (FFD) based on B-splines. The experiments on 3D synthetic and real image data show that the algorithm can converge at the global optimum and restrain the emergency of local extreme. 相似文献
3.
Medical image registration is the process of finding ageometric transformation between two image-based coordi-nate systems that have the same patient-based coordinates ,i .e .the same anatomic locations .The registered multi-mo-dality images lead to impro… 相似文献
4.
This paper introduces a new enhancement method for multi-spectral satellite remote sensing imagery, based on principal component
analysis (PCA) and intensity-hue-saturation (IHS) transformations. The PCA and the IHS transformations are used to separate
the spatial information of the multi-spectral image into the first principal component and the intensity component, respectively.
The enhanced image is obtained by replacing the intensity component of the IHS transformation with the first principal component
of the PCA transformation, and undertaking the inverse IHS transformation. The objective of the proposed method is to make
greater use of the spatial and spectral information contained in the original multi-spectral image. On the basis of the visual
and statistical analysis results of the experimental study, we can conclude that the proposed method is an ideal new way for
multi-spectral image quality enhancement with little color distortion. It has potential advantages in image mapping optimization,
object recognition, and weak information sharpening. 相似文献
5.
为提高三维场景实时阴影渲染性能,通过图形硬件编程方法,采用HLSL实现Shadow Map。实验表明,GPU的渲染速度远远大于CPU,在计算负载由传统的CPU转移到GPU处理之后,算法的运行效率得到明显提升。 相似文献
6.
提出了一种能有效实现物体表面三维图像数据配准的算法.该算法利用了三维数据采集时的三维点的阵列信息,这些三维点的阵列信息在采集原始三维数据时可以很容易获得,同时,还利用了三维数据矢量/顶点相似特征作为数据匹配的基础.采用迭代最小均方误差算法来自适应优化变换矩阵参数.这些方法可以有效地提高三维图像配准的性能,加快匹配过程的运算速度.实验结果表明该算法可以获得较好的配准后三维图像的主观效果.尽管该方法主要针对人头模型,但经过少许修改后即可适用于其他物体. 相似文献
7.
黄铜城 《邵阳学院学报(社会科学版)》2001,23(2):13-18
对图象几何变换、图象配准及其二者之间的关系进行了深入的研究与探讨,得出了"对于两帧来自同一视点具有不同内在参数的重叠图象之间的关系可用二维平面投影变换模型来描述"的结论,并给出了具体证明. 相似文献
8.
研究目的：利用数字图像测量技术对河流模型实验中的河床地形测晕研究。创新要点：以高质量的图像径向畸变校正为基础,依据多幅图像间 映射换算以及单幅图像灰度信息变换两方面的研究,来提取二维地形信息。研究方法：使用考虑残差的一阶误差传播的最大似然估计方法求解图像与地形坐标的映射变换参数;借助漫反射光照模型,通过适当假设,推导出地形高程与图像灰度、灰度梯度及太阳办向的关系式。重要结论：1．以Devernay基于直线的图像畸变校正方法为基础,通过使用更高精度的Canny边缘检测算子提取图像边缘,黄金分割法和二次插值法相结合的最优化方法求取畸变系数等,可以得到较好的校正效果,求算的畸变系数精度更高,求算过程更快;2．利用图像与地面间的透视投影关系方法求解地形高程小标,均匀并尽可能多地将控制点布置住控制区域内,使计算值更接近实测值,并满足河流演变实验的精度要求;3．通过推导关系式,理论上可以根据图像灰度、灰度梯度、太阳方向向晕算得地形高程。 相似文献
9.
吴振华 《实验室研究与探索》2011,30(9)
以HDV作为高清视频编码格式,采用CPU+GPU+I/O的构架,以及用千兆以太网和基于iSCSI的IP SAN作为网络结构,对如何构建适合高校教学的网络化高清非编室作了设计.以HDV为核心编码的非线性编辑系统既能满足当前仍有较大需求的标清节目制作,又能为高清节目制作做好充分地准备;CPU+ GPU+ I/O的构架有效利用CPU和GPU的处理能力,简化了非线性编辑系统,进一步降低了影视制作的门槛,从而有利于在高校和其他教育机构中推动影视技术教学;基于iSCSI的IP SAN的构架无论从成本上还是实施难度上,都极具竞争力,它基于成熟的以太网技术,随着万兆以太网的出现,它的应用将更为广泛. 相似文献
10.
三维彩色扫描系统及算法 总被引：2，自引：0，他引：2
提出了一种大尺寸 3D物体几何形状的扫描测量系统 ,该系统由一个线结构光源和一个彩色CCD摄像机组成 .CCD摄像机两次摄取被扫描物体的图像 ,首先从激光平面中获取被扫描物体的三维信息 ,然后将 3D物体的彩色信息和三维信息自动进行叠合 ,以获得 3D物体的真实模型 . 相似文献
11.
分析了光线跟踪渲染算法在GPU上实现的流程;设计了CUDA平台上基于BVH加速结构的光线跟踪渲染引擎,针对CUDA架构的特点重新设计了BVH遍历算法和间接反射计算算法;并在四个场景和两种分辨率下针对GPU和CPU实现进行了详细对比测试。通过分析实验结果,基于GPU加速的光线跟踪算法在不同复杂度的场景下相比其CPU实现都有较高的性能提升。 相似文献
12.
YUAN Zhen-ming WU Fei ZHUANG Yue-ting 《浙江大学学报(A卷英文版)》2006,7(4):549-555
INTRODUCTION Image registration plays an important role in the fusion of remote sensing, video panorama, medical image processing, etc. (Li et al., 1995; 2004; Brown, 1992; Belongie et al., 2001; Rui et al., 2001). More different than video panorama, the registration of multi-sensor image needs to align the multi-sensor images of the same scene from different sources (Rignot et al., 1991). Multi-sensor image registration is widely used in the fusion of panchromatic images with infrared i… 相似文献
13.
WU Xue-dong SONG Zhi-huan 《浙江大学学报(A卷英文版)》2007,8(10):1604-1613
Determination of relative three-dimensional (3D) position, orientation, and relative motion between two reference frames is an important problem in robotic guidance, manipulation, and assembly as well as in other fields such as photogrammetry. A solution to pose and motion estimation problem that uses two-dimensional (2D) intensity images from a single camera is de- sirable for real-time applications. The difficulty in performing this measurement is that the process of projecting 3D object features to 2D images is a nonlinear transformation. In this paper, the 3D transformation is modeled as a nonlinear stochastic system with the state estimation providing six degrees-of-freedom motion and position values, using line features in image plane as measuring inputs and dual quaternion to represent both rotation and translation in a unified notation. A filtering method called the Gaussian particle filter (GPF) based on the particle filtering concept is presented for 3D pose and motion estimation of a moving target from monocular image sequences. The method has been implemented with simulated data, and simulation results are provided along with comparisons to the extended Kalman filter (EKF) and the unscented Kalman filter (UKF) to show the relative advantages of the GPF. Simulation results showed that GPF is a superior alternative to EKF and UKF. 相似文献
14.
Jianyi Li Lanying Nie Zeyu Li Lijun Lin Lei Tang Jun Ouyang 《Anatomical sciences education》2012,5(6):330-339
Anatomical corrosion casts of human specimens are useful teaching aids. However, their use is limited due to ethical dilemmas associated with their production, their lack of perfect reproducibility, and their consumption of original specimens in the process of casting. In this study, new approaches with modern distribution of complex anatomical spatial information were explored to overcome these limitations through the digitalization of anatomical casts of human specimens through three‐dimensional (3D) reconstruction, rapid prototype production, and Web‐based 3D atlas construction. The corrosion cast of a lung, along with its associated arteries, veins, trachea, and bronchial tree was CT‐scanned, and the data was then processed by Mimics software. Data from the lung casts were then reconstructed into 3D models using a hybrid method, utilizing both “image threshold” and “region growing.” The fine structures of the bronchial tree, arterial, and venous network of the lung were clearly displayed and demonstrated their distinct relationships. The multiple divisions of bronchi and bronchopulmonary segments were identified. The 3D models were then uploaded into a rapid prototype 3D printer to physically duplicate the cast. The physically duplicated model of the lung was rescanned by CT and reconstructed to detect its production accuracy. Gross observation and accuracy detection were used to evaluate the duplication and few differences were found. Finally, Virtual Reality Modeling Language (VRML) was used to edit the 3D casting models to construct a Web‐based 3D atlas accessible through Internet Explorer with 3D display and annotation functions. Anat Sci Educ. © 2012 American Association of Anatomists. 相似文献
15.
尤瑞玲 《商丘师范学院学报》2008,24(12)
首先分析地理信息在人口普查和户籍管理中的作用,介绍了利用地理信息系统(GIS)技术,建立人口普查和户籍管理地理信息系统的试验成果,根据所获得的实际经验和我国的国情,提出了我国人口地理信息系统建设的研究方向和主要研究内容. 相似文献
16.
基于数字移相全息的图像重构 总被引：3，自引：0，他引：3
1IntroductionDifferent methods of holographic interferometry re-lated techniques have been used effectively for defectvisualisation in artwork diagnosis[1].Physical recon-struction of recorded wave fields though is of li mitedapplicability for on-field or… 相似文献
17.
针对PCB板缺陷检测中用传统SURF算法进行图像匹配精度不高的问题,提出一种生产工序中运动平台机械误差先验信息与SURF特征提取相结合的MSURF配准算法。通过提取计算SURF特征点,求出对应特征点对的距离;在PCB运动平台机械误差分析的基础上,依据先验阈值边界条件筛除异常匹配特征点对;求出两幅图像满足最小二乘拟合准则的映射关系,并将其用于图像配准。在机械运动误差0.05~0.10 mm范围内对42 mm×42 mm的PCB图像配准实验,结果表明:提出的图像配准方法速度快、精度高,适用于产线PCB缺陷检测。 相似文献
18.
胡顺波 《临沂师范学院学报》2009,31(6):126-131
在基于灰度的图像配准中,针对传统的空间均匀采样的多分辨率分析技术在低分辨率时会丢失重要边缘信息,从而产生较多局部极值点,导致误配准问题,通过使用基于灰度概率分布和其梯度信息的抽样方法,提出了非均匀空间采样的多分辨率分析技术．在人体脑部图像的刚体配准实验中应用非均匀多分辨率分析技术,实验结果表明,该非均匀多分辨率分析技术可以有效地减少局部极值点,并提高配准速度． 相似文献
19.
为了在三维超声成像中获得更多、更详细的位置信息,得到更准确的定位精度,采用机械臂夹持超声探头并利用L-M算法进行超声图像标定。标定过程中,通过将N线模板放在水槽中,从而得到更准确的定位装置接收器与超声图像之间的位置转换关系,利用六自由度机械臂控制超声探头水平移动扫描模板以获取超声图像,并利用区域提取与缺陷分割技术获得图像中的像素坐标,以及扫描点在模板中对应的实际坐标,最后运用L-M算法进行标定计算,获得所需的标定转换矩阵。实验结果证明,该方法简单易行且效率较高,提高了标定精度,可满足实际检测精度需求,避免了手动扫描误差,为后续三维重建奠定了基础。 相似文献