In the Saddle: Chasing Fast and Repeatable Features
This work addresses the need for efficient and reliable feature detection in computer vision, offering a fast and repeatable method that is incremental in improving speed and matching accuracy.
The paper tackles the problem of feature detection in images by proposing a novel similarity-covariant detector that identifies saddle-like intensity profiles, resulting in features that are fast, general, evenly spread, and show superior matching performance compared to similarly fast detectors on challenging datasets.
A novel similarity-covariant feature detector that extracts points whose neighbourhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Experiments show that the Saddle features are general, evenly spread and appearing in high density in a range of images. The Saddle detector is among the fastest proposed. In comparison with detector with similar speed, the Saddle features show superior matching performance on number of challenging datasets.