最大稳定极值区域
最大稳定极值区域(Maximally Stable Extremal Regions,簡稱MSER)是在计算机视觉领域中一种用于在图像中进行斑点检测的方法。这个方法由Matas等人[1]提出,用于在两个不同视角的图片中寻找对应关系。这种方法从图像中提取全面的元素对应关系,有助于宽基线匹配(wide-baseline matching),以及更好的立体匹配和物体识别算法。
特征检测 |
---|
典型角检测算法的输出 |
边缘检测 |
|
角检测 |
斑点检测 |
脊检测 |
霍夫变换 |
结构张量 |
仿射不变特征检测 |
|
特征描述 |
尺度空间 |
|
其他应用
- Shape Descriptors for Maximally Stable Extremal Regions
- Efficient Maximally Stable Extremal Region (MSER) Tracking
- N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions
- Video Google and Object Level Grouping for Video Shots
- Real-Time Extraction of Maximally Stable Extremal Regions on an FPGA
- Maximally Stable Colour Regions for Recognition and Matching
参见
- 斑点检测
- 特征检测
外部链接
- VLFeat, an open source computer vision library in C (with a MEX interface to MATLAB), including an implementation of MSER
- OpenCV, an open source computer vision library in C/C++, including an implementation of Linear Time MSER
- Detector Repeatabilty Study, Kristian Mikolajczyk Binaries (Win/Linux to compute MSER/HarrisAffine... . Binary used in his repeatability study.
参考文献
- J. Matas, O. Chum, M. Urban, and T. Pajdla. "Robust wide baseline stereo from maximally stable extremal regions." Proc. of British Machine Vision Conference, pages 384-396, 2002.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.