A Fast and Accurate Feature-Matching Algorithm for Minimally-Invasive Endoscopic Images

Abstract

The ability to find image similarities between two distinct endoscopic views is known as feature matching, and is essential in many robotic-assisted minimally-invasive surgery (MIS) applications. Differently from feature-tracking methods, feature matching does not make any restrictive assumption about the chronological order between the two images or about the organ motion, but first obtains a set of appearance-based image matches, and subsequently removes possible outliers based on geometric constraints. As a consequence, feature-matching algorithms can be used to recover the position of any image feature after unexpected camera events, such as complete occlusions, sudden endoscopic-camera retraction, or strong illumination changes. We introduce the hierarchical multi-affine (HMA) algorithm, which improves over existing feature-matching methods because of the larger number of image correspondences, the increased speed, and the higher accuracy and robustness. We tested HMA over a large (and annotated) dataset with more than 100 MIS image pairs obtained from real interventions, and containing many of the aforementioned sudden events. In all of these cases, HMA outperforms the existing state-of-the-art methods in terms of speed, accuracy, and robustness. In addition, HMA and the image database are made freely available on the internet.

Content-based processing and analysis of endoscopic images and videos: A survey

“…A comparative evaluation of state-of-the-art feature-matching algorithms for endoscopic images has been carried out in [186]. [155,187,188,205,231,268], deforming tissue tracking is a very hard research challenge that still requires a lot of further work. Endoscopic videos feature many domain-induced problems like scarcity of distinctive landmarks because of homogenous surfaces and indistinctive texture that makes it hard to find good points to track.…”

A comparative study on 3-D stereo reconstruction from endoscopic images

“…Some feature matching methods already include outlier removal such as the Hierarchical Multi-Affine (HMA) algorithm. However those methods only capture a limited number of matches (approximately in the order of 10 2 in an image with approximately 10 6 pixels) [22].…”

Efficient Vessel Feature Detection for Endoscopic Image Analysis

“…Puerto-Souza and Mariottini proposed the novel hierarchical multi-affine (HMA) [21], [22] and adaptive multiaffine (AMA) [23] algorithms to improve the feature matching performance for endoscopic images. They also developed a dense feature matching method to recover the locations of image features on tissue surfaces [24]. Tissue surface tracking and reconstruction for MIS have also been widely studied and different methods have been introduced to overcome the difficulties of tissue deformations and low texture [3], [4], [6], [25].…”