opencv关于特征点的descriptor

OpenCV 提供了10种特征检测方法：

• "FAST" – FastFeatureDetector
• "STAR" – StarFeatureDetector
• "SIFT" – SIFT (nonfree module)
• "SURF" – SURF (nonfree module)
• "ORB" – ORB
• "MSER" – MSER
• "GFTT" – GoodFeaturesToTrackDetector
• "HARRIS" – GoodFeaturesToTrackDetector with Harris detector enabled
• "Dense" – DenseFeatureDetector
• "SimpleBlob" – SimpleBlobDetector

OpenCV 中和 2D 特征检测相关的算法的头文件位于

• opencv\modules\features2d\include\opencv2\features2d.hpp，除SIFT、SURF以外的特征。
• opencv\modules\nonfree\include\opencv2\nonfree\features2d.hpp，只包含SIFT、SURF这两个受专利保护的特征，因此不是免费的（nonfree）。

我们来看具体的类
DescriptorExtractor 的子类都是描述子提取器，包含

• FREAK
• OpponentColorDescriptorExtractor
• BriefDescriptorExtractor

FeatureDetector 的子类都是特征检测器，包含

• MSER
• StarDetector，又名 StarFeatureDetector
• FastFeatureDetector
• GFTTDetector，又名 GoodFeaturesToTrackDetector
• SimpleBlobDetector
• DenseFeatureDetector

FeatureDetector 还提供一系列特殊的适配器子类，用于增强或加速之前的 FeatureDetector 类

• GridAdaptedFeatureDetector
• PyramidAdaptedFeatureDetector
• AdjusterAdapter
• DynamicAdaptedFeatureDetector
• FastAdjuster
• StarAdjuster
• SurfAdjuster

Feature2D 的子类既是 FeatureDetector，又是 DescriptorExtractor，包含

• BRISK
• ORB
• SIFT
• SURF