Image Patch-Matching with Graph-Based Learning in Street Scenes

TL;DR

This paper introduces a graph-based learning approach for patch matching in street scenes, incorporating spatial neighborhood information to improve accuracy in autonomous driving perception tasks.

Contribution

It proposes a joint feature and metric learning model using spatial graphs, providing a theoretical basis and achieving state-of-the-art results.

Findings

Achieves state-of-the-art matching accuracy on street-scene datasets

Incorporates spatial neighborhood information into patch matching

Provides theoretical analysis of the graph-based loss function

Abstract

Matching landmark patches from a real-time image captured by an on-vehicle camera with landmark patches in an image database plays an important role in various computer perception tasks for autonomous driving. Current methods focus on local matching for regions of interest and do not take into account spatial neighborhood relationships among the image patches, which typically correspond to objects in the environment. In this paper, we construct a spatial graph with the graph vertices corresponding to patches and edges capturing the spatial neighborhood information. We propose a joint feature and metric learning model with graph-based learning. We provide a theoretical basis for the graph-based loss by showing that the information distance between the distributions conditioned on matched and unmatched pairs is maximized under our framework. We evaluate our model using several street-scene datasets and demonstrate that our approach achieves state-of-the-art matching results.