Object-Guided Day-Night Visual Localization in Urban Scenes
This addresses a key challenge for autonomous systems and robotics that need reliable localization in urban environments across varying lighting conditions, representing an incremental advance over existing methods.
The paper tackles the problem of visual localization under severe illumination changes between day and night by introducing Object-Guided Localization (OGuL), which uses object correspondences to guide local-feature matching, resulting in significant improvements on standard datasets like Aachen and RobotCar-Season, with performance competitive to state-of-the-art CNN-based methods.
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.