搜索资源列表
SWImage
- The Swendsen-Wang Cuts algorithm is used to label atomic regions (superpixels) based on their intensity patterns using generative models in a Bayesian framework. The prior is based on areas of connected components, which provides a clean segmentation
subopt_anidiff_20110820
- 共分割代码，一种建立在图像过分割块的代码。本代码为MATLAB的，基于类似随机步的思想。-Co-segmentation code, which published in ICCV 2011.
thresh-iccv
- 一种基于自适应阈值的方法，用于change detection-Adaptive threshold based on the method for change detection
2009oral
- 10多篇ICCV 2009有关动作识别的 oral paper，很值得研究-More than 10 articles ICCV 2009 relevant actions identified oral paper, it is worth studying
PW_1.0.1
- 这个c程序实现几种2D和3D分割算法，这些算法可以参考下面这篇论文，程序的运行请查看README.txt-Camille Couprie, Leo Grady, Laurent Najman and Hugues Talbot , "Power Watersheds: A New Image Segmentation Framework Extending Graph Cuts, Random Walker and Optimal Spanning Forest", ICCV 09, 2009
paper
- 这是近几年计算机视觉领域的顶级会议 iccv和cvpr的关于图像跟踪的论文目录 对于涵如烟海的论文 这个目录能帮你更好的入门-This is the field of computer vision in recent years, the top conference iccv and cvpr papers on image tracking sea smoke catalog essay for the culvert this directory entry can help you b
chang09_ICCV
- 图像分割文章，是2009年的ICCV中的文章，效果不错，没源码-Image segmentation article 2009 ICCV article
2009-ICCV-Earth-Movers-Distances
- 快速计算基于描述子之间的匹配，改进的推土机算法-a new algorithm for a robust family of EarthMover’s Distances- EMDs with thresholded ground distances
kde_bg_v1.0
- 基于核密度估计的背景减法算法，拥有命令行界面的C++源代码。-kernel density estimation based background subtraction algorithm [1] with a command line interface. this algorithm is a somewhat improved version of [2]. the kmovingobjdetector class within the project is originally w
2011_11_iccv_hope
- 基于kinect的手势识别，主要优化了手部被遮挡情况下的三维模型还原。全英文，2011年iccv发表-Kinect-based gesture recognition, optimization of the hand is blocked in case of three-dimensional model reduction. The full English 2011 iccv published
LineMatch_LS
- 比较新的一个直线匹配算法，发表在ICCV上，效果很好，值得学习-A relatively new line matching algorithm, published in ICCV, the effect is very good, it is worth learning
LS_line_detion
- 比较新的一个直线特征提取算法，发表在ICCV上，LS匹配中所采用的方法，效果很好，值得学习-A relatively new line feature extraction algorithm, published in ICCV on, LS matching method used, the effect is very good, it is worth learning
Timofte-ICCV-2013
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution
Interactive-Image-Segmentation
- 交互式图像分割，是根据Yuri Boykov and Marie-Pierre Jolly的文章，用C++和OpenCV实现的-Automatic image segmentation is a hard problem and, is not flexible enough to be used for general segmentation. The objective of this project is to implement an interactive image segment
ComputerVision
- 基于投影M估计量的稳健回归方法，用于估计计算机视觉立体像对间的Fundamental Matrix。Fundamental Matrix，参考文献：H. Chen, P. Meer, Robust regression with projection based M-estimators. 9th International Conference on Computer Vision (ICCV), Nice, France, October 2003, 878-885.PS：这是作者11年前本
SaliencyICCV2013
- 2013年ICCV显著区域检测论文Efficient Salient Region Detection with Soft Image Abstraction源码-2013 ICCV salient region detection paper Efficient Salient Region Detection with Soft Image Abstraction Source
2013-ICCV-CASS-tracelasso
- 关于图像分割的文章，利用CASS-TRACE进行的图像处理，是数学方法，具有很好的价值-Articles about the image segmentation, image processing CASS-TRACE conducted mathematical methods, with good value
ICCV-Tutorial-on-Sparse-Coding
- ICCV会议的一个关于稀疏表示的教程，里面包含较为详细的理论知识，大牛的讲解让人通俗易懂-A ICCV meeting on tutorial sparse representation, which contains more detailed theoretical knowledge, to explain the straightaway
siftDemoV4
- SIFT，即尺度不变特征变换（Scale-invariant feature transform，SIFT），是用于图像处理领域的一种描述。这种描述具有尺度不变性，可在图像中检测出关键点，是一种局部特征描述子。[1] 该方法于1999年由David Lowe[2] 首先发表于计算机视觉国际会议（International Conference on Computer Vision，ICCV），2004年再次经David Lowe整理完善后发表于International journal of c
EDLinesTest
- EDLines是一种快速直线检测算子，2012年在ICCV上提出，也是目前处理直线检测最快的算法之一，该算法包含三个步骤：（1）边缘提取：利用Edge Drawing (ED)算法[28,29]从灰度图像中提取边缘片段；（2）线段检测：利用最小二乘法提取直线段；（3）线段确认：遵循Helmholtz定律，从已提取的直线段中摒弃虚假线段。EDLines算法的优越性得益于Edge Drawing (ED)算法能够从灰度图像中准确、快速、稳定地提取出光滑、完整的边缘片段。Edge Drawing (E