Computer Vision_33_SIFT: A novel point-matching algorithm based on fast sample consensus for image r

此部分是计算机视觉部分,主要侧重在底层特征提取,视频分析,跟踪,目标检测和识别方面等方面。对于自己不太熟悉的领域比如摄像机标定和立体视觉,仅仅列出上google上引用次数比较多的文献。有一些刚刚出版的文章,个人非常喜欢,也列出来了。

33. SIFT
关于SIFT,实在不需要介绍太多,一万多次的引用已经说明问题了。SURF和PCA-SIFT也是属于这个系列。后面列出了几篇跟SIFT有关的问题。
[1999 ICCV] Object recognition from local scale-invariant features
[2000 IJCV] Evaluation of Interest Point Detectors
[2006 CVIU] Speeded-Up Robust Features (SURF)
[2004 CVPR] PCA-SIFT A More Distinctive Representation for Local Image Descriptors
[2004 IJCV] Distinctive Image Features from Scale-Invariant Keypoints

[2009 GRSL] Robust scale-invariant feature matching for remote sensing image registration
[2010 IJCV] Improving Bag-of-Features for Large Scale Image Search
[2011 PAMI] SIFTflow Dense Correspondence across Scenes and its Applications

[2012 ECCV] KAZE Features

[2012 ICCV] ORB_An efficient alternative to SIFT or SURF

[2014 CVPR] TILDE: A Temporally Invariant Learned DEtector

[2014 TGRS] A novel coarse-to-fine scheme for automatic image registration based on SIFT and mutual information

[2015 GRSL] A novel point-matching algorithm based on fast sample consensus for image registration

[2015 GRSL] An efficient SIFT-based mode-seeking algorithm for sub-pixel registration of remotely sensed images

[2015 TGRS] SAR-SIFT: A SIFT-LIKE ALGORITHM FOR SAR IMAGES

[2016 ECCV] LIFT Learned Invariant Feature Transform

[2016 JVCIR] An Improved RANSAC based on the Scale Variation Homogeneity

[2017 GRSL] Remote Sensing Image Registration With Modified SIFT and Enhanced Feature Matching

[2017 CVPR] GMS :Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence

[2018 TIP] Fast Adaptive Bilateral Filtering

翻译

一种基于快速样本一致性的图像配准新算法

作者:Yue Wu, Wenping Ma, Maoguo Gong

 

摘要 -

 

 

 

 

 

 

 

 

上一篇:如何解决springboot参数传中文乱码


下一篇:使用JBOSS和Java以编程方式创建子域