Non-planar Object Detection and Identification by Features Matching and Triangulation Growth

TL;DR

This paper introduces a feature-matching and triangulation growth method for detecting and identifying non-planar or distorted objects in images, outperforming traditional homography-based approaches in highly distorted scenarios.

Contribution

A novel incremental grouping approach using Delaunay triangulation for object detection that works effectively with non-planar and distorted objects, bypassing the need for geometric models like homography.

Findings

Performs as well or better than homography-based RANSAC in undistorted cases.

Outperforms in scenarios with significant object distortion.

Effective for non-planar object detection without geometric models.

Abstract

Object detection and identification is surely a fundamental topic in the computer vision field; it plays a crucial role in many applications such as object tracking, industrial robots control, image retrieval, etc. We propose a feature-based approach for detecting and identifying distorted occurrences of a given template in a scene image by incremental grouping of feature matches between the image and the template. For this purpose, we consider the Delaunay triangulation of template features as an useful tool through which to be guided in this iterative approach. The triangulation is treated as a graph and, starting from a single triangle, neighboring nodes are considered and the corresponding features are identified; then matches related to them are evaluated to determine if they are worthy to be grouped. This evaluation is based on local consistency criteria derived from geometric and photometric properties of local features. Our solution allows the identification of the object in situations where geometric models (e.g. homography) does not hold, thus enable the detection of objects such that the template is non planar or when it is planar but appears distorted in the image. We show that our approach performs just as well or better than application of homography-based RANSAC in scenarios in which distortion is nearly absent, while when the deformation becomes relevant our method shows better description performance.