-
src
说明： ORB-SLAM 基本延续了 PTAM 的算法框架,但对框架中的大部分组件都做了改进, 归纳起来主要有 4 点:
ORB-SLAM 选用了 ORB 特征, 基于 ORB 描述量的特征匹配和重定位, 都比 PTAM 具有更好的视角不变性。此外, 新增三维点的特征匹配效率更高, 因此能更及时地扩展场景。扩展场景及时与否决定了后续帧是否能稳定跟踪。ORBSLAM 加入了循环回路的检测和闭合机制, 以消除误差累积。系统采用与重定位相同的方法来检测回路(匹配回路两侧关键帧上的公共点), 通过方位图 (Pose Graph) 优化来闭合回路。PTAM 需要用户指定 2 帧来初始化系统, 2 帧间既要有足够的公共点, 又要有足够的平移量. 平移运动为这些公共点提供视差 (Parallax) , 只有足够的视差才能三角化出精确的三维位置。ORB-SLAM 通过检测视差来自动选择初始化的 2 帧。PTAM 扩展场景时也要求新加入的关键帧提供足够的视差, 导致场景往往难以扩展. ORB-SLAM 采用一种更鲁棒的关键帧和三维点的选择机制——先用宽松的判断条件尽可能及时地加入新的关键帧和三维点, 以保证后续帧的鲁棒跟踪; 再用严格的判断条件删除冗余的关键帧和不稳定的三维点，以保证 BA 的效率和精度。(Orb-slam basically continues the algorithm framework of PTAM, but most of the components in the framework have been improved, which mainly includes four points:)
- 2020-06-11 23:43:54下载
- 积分：1
-
main
模糊图像的去模糊处理，主要有利用hough变换估计模糊方向，利用radon变换估计模糊长度。(Blurred image deblurring process, mainly using the estimated blurring direction hough transform, radon transform using the estimated blur length.)
- 2017-04-11 13:27:50下载
- 积分：1
-
watermarkmatlab
matlab嵌入水印源程序
在matlab中实现数字水印的嵌入，提取和检测(Matlab source watermark embedded in Matlab achieve digital watermark embedding and extraction and detection)
- 2006-06-01 10:12:20下载
- 积分：1
-
gmm
混合高斯模型使用K（基本为3到5个） 个高斯模型来表征图像中各个像素点的特征,在新一帧图像获得后更新混合高斯模型,用当前图像中的每个像素点与混合高斯模型匹配,如果成功则判定该点为背景点, 否则为前景点。通观整个高斯模型，他主要是有方差和均值两个参数决定，,对均值和方差的学习,采取不同的学习机制,将直接影响到模型的稳定性、精确性和收敛性。由于我们是对运动目标的背景提取建模，因此需要对高斯模型中方差和均值两个参数实时更新。为提高模型的学习能力,改进方法对均值和方差的更新采用不同的学习率 为提高在繁忙的场景下,大而慢的运动目标的检测效果,引入权值均值的概念,建立背景图像并实时更新,然后结合权值、权值均值和背景图像对像素点进行前景和背景的分类。(Gaussian mixture model using K (essentially 3-5) Gaussian model to characterize the features of each pixel in the image, in the image of the new frame for updated Gaussian mixture model, with each pixel in the image with a Gaussian mixture current model matching, if successful, determined that the point of the background points, otherwise the former attraction. Throughout the entire Gaussian model, he mainly has two parameters determine the variance and the mean, the mean and variance of the study, to take a different learning mechanism, will directly affect the stability, accuracy and convergence model. Since we are moving object extraction of the background modeling, so the need for the Gaussian model variance and mean two parameters real-time updates. In order to improve the learning ability of the model, an improved method for updating the mean and variance of different learning rates to improve in the busy scene, large and slow moving object detection results, the introduction of)
- 2014-03-25 09:01:12下载
- 积分：1
-
mean-shift
基于meanshift/camshift的视频运动目标跟踪实现，通过鼠标手动选择跟踪目标。基于HSV空间模型，可手动调节H S V的阈值，显示前景、背景、反响投影图。开发工具是VS2008、OPENCV.(Based meanshift/camshift video moving target tracking achieved manually using the mouse to select the target track. HSV space model, you can manually adjust the threshold HSV, showing foreground, background, reaction projection. Development tools are VS2008, OPENCV)
- 2014-05-06 16:20:51下载
- 积分：1
-
adpmedian
自适应中值滤波程序
自己根据mathworks网站的源程序
改进而来
非常详细 拿来即可用(Adaptive median filter in accordance with the procedures themselves MathWorks Web site to improve from a very detailed source code can be used with)
- 2008-06-07 14:17:30下载
- 积分：1
-
wavelet_fusion
小波分析用于图像融合，图像融合是将统一对象的两个或更多的图像合成在一幅图像中。(Wavelet analysis for image fusion, image fusion is to unify two or more objects in an image image synthesis.)
- 2020-11-17 21:19:39下载
- 积分：1
-
array2
能够提取一幅图片的不变矩特征值，方便大家学习图像识别方面的开发技术(Able to extract a picture of the moment invariant features of value, to facilitate learning in the development of image recognition technology)
- 2011-07-16 11:03:02下载
- 积分：1
-
遥感图像分类工具箱Active-Learning
遥感图像分类工具箱，包含多种基于支持向量机分类器的主动学习算法(active learning toolbox, used for remote sensing data classification, includes most popular svm-based active learning algorithms.)
- 2013-05-11 14:03:27下载
- 积分：1
-
Ncut
Ncut的文献及matlab源代码。基于图的分割非常好的一个算法(Ncut literature and matlab source code. Graph-Based Segmentation Algorithm for a very good)
- 2010-11-30 18:56:36下载
- 积分：1
