Object-Guided Day-Night Visual Localization in Urban Scenes

TL;DR

This paper presents Object-Guided Localization (OGuL), a method that improves urban visual localization across day and night by combining object detection with local feature matching, outperforming traditional methods.

Contribution

The paper introduces a novel object-guided localization approach that enhances feature matching robustness under lighting changes, using object correspondences to guide local feature matching.

Findings

OGuL significantly improves localization accuracy.

Performance competes with CNN-based methods.

Effective with simple local features like SIFT.

Abstract

We introduce Object-Guided Localization (OGuL) based on a novel method of local-feature matching. Direct matching of local features is sensitive to significant changes in illumination. In contrast, object detection often survives severe changes in lighting conditions. The proposed method first detects semantic objects and establishes correspondences of those objects between images. Object correspondences provide local coarse alignment of the images in the form of a planar homography. These homographies are consequently used to guide the matching of local features. Experiments on standard urban localization datasets (Aachen, Extended-CMU-Season, RobotCar-Season) show that OGuL significantly improves localization results with as simple local features as SIFT, and its performance competes with the state-of-the-art CNN-based methods trained for day-to-night localization.