CoMIC: Good features for detection and matching at object boundaries

TL;DR

This paper introduces CoMIC, a feature detection method based on stable iso-intensity curves that improves boundary feature matching in dynamic scenes, outperforming existing detectors at object edges.

Contribution

The paper presents a novel boundary feature detector, CoMIC, leveraging stable iso-curves to enhance matching accuracy at object boundaries.

Findings

CoMIC outperforms state-of-the-art detectors at object boundaries.

CoMIC achieves comparable performance to existing methods in interior regions.

Experimental results demonstrate improved boundary matching in stereo and motion tracking.

Abstract

Feature or interest points typically use information aggregation in 2D patches which does not remain stable at object boundaries when there is object motion against a significantly varying background. Level or iso-intensity curves are much more stable under such conditions, especially the longer ones. In this paper, we identify stable portions on long iso-curves and detect corners on them. Further, the iso-curve associated with a corner is used to discard portions from the background and improve matching. Such CoMIC (Corners on Maximally-stable Iso-intensity Curves) points yield superior results at the object boundary regions compared to state-of-the-art detectors while performing comparably at the interior regions as well. This is illustrated in exhaustive matching experiments for both boundary and non-boundary regions in applications such as stereo and point tracking for structure from motion in video sequences.