登录
首页 » matlab » saliency-object-or-region-detection

saliency-object-or-region-detection

于 2011-07-02 发布 文件大小:4138KB
0 206
下载积分: 1 下载次数: 614

代码说明:

  该文件夹包括代码及其对应的论文。其作用在于模拟人类视觉系统的生理特性--视觉注意机制,按照人眼观察外界的方式,检测视觉显著性物体和区域,并阐述了显著性区域的显著性密度和尺度之间的关系,可应用于生物视觉模拟、视觉目标检测、视觉目标跟踪、视觉智能监控,以及视觉生理学和视觉心理学等的研究中。(This document contains codes and the corresponding paper. The aim is to simulate a physiological characteristic of human visual system called visual attention mechanism. The code is used to detect salient objects or regions following the way human eye observes the world. The relation between density and scale of salient object/region is described. It has found widespread use in numerous applications such as biological vision simulation, visual object detection, visual object tracking, visual intelligent surveillance, visual physiological, and visual psychology.)

文件列表:

saliency object or region detection
...................................\CalcScaleSaliency.dll,28672,2005-09-21
...................................\Clustering.m,838,2011-02-04
...................................\drawcircle.m,137,2003-06-09
...................................\GoSalSca.asv,1274,2011-01-27
...................................\GoSalSca.m,1408,2011-01-28
...................................\imageSequence.m,2027,2011-01-28
...................................\parametersOfSaliencyDetection.m,612,2011-01-30
...................................\Saliency,Scale,image description.pdf,4299354,2011-01-27
...................................\SRGB2LMS.m,2336,2011-01-25
...................................\videoSequence.m,2088,2011-01-29

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • vibe_tom
    一种改进的VIBE运动目标检测算法,属于背景差分法,能对不同环境的目标进行检测,能消除鬼影。(The moving target detection algorithm VIBE belongs to background difference method. It can detect objects in different environments and eliminate ghosts.)
    2020-12-02 10:59:25下载
    积分:1
  • cs
    说明:  压缩传感理论的一个简单例子,首先对信号进行稀疏采样,然后利用MP算法对信号进行重建。(Compressed sensing theory of a simple example, first of all, the signal sparse sampling, and then use MP algorithm of signal reconstruction.)
    2009-01-14 13:49:38下载
    积分:1
  • SIFT
    图像检索中经典的SIFT方法matlab实现,由NTU的大牛撰写,做了些批注。(SIFT for image retrieval,feature extraction and matching)
    2020-12-30 15:29:00下载
    积分:1
  • CVPR12_SAS_code
    2012 CVPR 文章:Segmentation Using Superpixels A Bipartite Graph Partitioning Approach对应的代码(2012 CVPR paper:Segmentation Using Superpixels A Bipartite Graph Partitioning Approach)
    2013-05-15 20:07:16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
  • kjunzhi
    k均值聚类,聚为2类,结果显示散点图,红色十字表示聚类中心(K-means clustering, the class number is 2, and the results showed that the clustering center)
    2012-05-31 13:14:01下载
    积分:1
  • lans-patrec
    从一个模式识别toolbox中摘取的计算zernike不变矩的源代码,结果为图像的n阶m重zernike不变矩(From a pattern recognition toolbox extracted Zernike moment invariants calculation of the source code, the results of image re-n-order m Zernike moment invariants)
    2008-01-18 11:16:51下载
    积分:1
  • Axisch
    各个坐标系之间的坐标变化:地心大地坐标到地心空间大地直角系,地心系和测站系,测站系和测站系等之间的变化,旋转,平移。(Coordinate changes between the various coordinate systems: geocentric geodetic coordinate system to the geocentric Cartesian space earth, geocentric system and station lines, change the station, such as lines and lines between stations, rotation, translation)
    2013-12-31 23:31:40下载
    积分:1
  • C_V
    采用半隐式方案实现变分水平集图像分割方法(Active contour without edge, image segmentation)
    2013-07-10 17:51:22下载
    积分:1
  • lianxugaosiyasuo
    利用高斯金字塔原理进行连续的图像序列的压缩。需要将图像序列连续命名。输出为压缩图像。(Gaussian pyramid principle compress continuous image sequences. Need the image sequence continuously named. Output is compressed image)
    2015-01-27 11:57:30下载
    积分:1
  • 696516资源总数
  • 106914会员总数
  • 0今日下载