Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment

TL;DR

This paper introduces a multi-scale template matching method using a novel similarity measure called scalable diversity similarity (SDS), which is robust against scale, rotation, deformations, clutter, and occlusions in unconstrained environments.

Contribution

The paper presents SDS, a new similarity measure that jointly uses appearance and rank information for robust multi-scale template matching in challenging conditions.

Findings

SDS significantly outperforms state-of-the-art methods in experiments.

SDS is effective against size, rotation, and deformation changes.

The method is validated on synthetic and real-world data.

Abstract

We propose a novel multi-scale template matching method which is robust against both scaling and rotation in unconstrained environments. The key component behind is a similarity measure referred to as scalable diversity similarity (SDS). Specifically, SDS exploits bidirectional diversity of the nearest neighbor (NN) matches between two sets of points. To address the scale-robustness of the similarity measure, local appearance and rank information are jointly used for the NN search. Furthermore, by introducing penalty term on the scale change, and polar radius term into the similarity measure, SDS is shown to be a well-performing similarity measure against overall size and rotation changes, as well as non-rigid geometric deformations, background clutter, and occlusions. The properties of SDS are statistically justified, and experiments on both synthetic and real-world data show that SDS can significantly outperform state-of-the-art methods.