Interest Point Detector and Feature Descriptor Survey

Abstract

What is a good keypoint for a given application? Which ones are most useful? Which ones should be ignored? Tuning the detectors is not simple. Each detector has different parameters to tune for best results on a given image, and each image presents different challenges regarding lighting, contrast, and image pre-processing. Additionally, each detector is designed to be useful for a different class of interest points, and must be tuned accordingly to filter the results down to a useful set of good candidates for a specific feature descriptor. Each feature detector will work best with certain descriptors, see appendix A. So, the keypoints are further filtered to be useful for the chosen feature descriptor. In some cases, a keypoint is not suitable for producing a useful feature descriptor, even if the keypoint has a high score and high response. If the feature descriptor computed at the keypoint produces a descriptor score that is too weak, for example, the keypoint and corresponding descriptor should both be rejected. OpenCV provides several novel methods for working with detectors, enabling the user to try different detectors and descriptors in a common framework, and automatically adjust the parameters for tuning and culling as follows: • DynamicAdaptedFeatureDetector. This class will tune supported detectors using an adjusterAdapter() to only keep a limited number of features, and iterate the detector parameters several times and redetect features in an attempt to find the best parameters, keeping only the requested number of best features. Several OpenCV detectors have an adjusterAdapter() provided, some do not; the API allows for adjusters to be created. • AdjusterAdapter. This class implements the criteria for culling and keeping interest points. Criteria may include KNN nearest neighbor matching, detector response or strength, radius distance to nearest other detected points, number of keypoints within a local region, and other measures that can be included for culling keypoints for which a good descriptor cannot be computed.