Robust Geo-Positioning Across Lighting Conditions: A Day–Night Image Localization Model With Visible and Infrared Fusion

Visual image-based localization is important to intelligent systems, greatly influencing Earth science uses. However, variability in lighting conditions can impair the performance of such systems, particularly for single-image localization tasks. This paper proposes an original all-day visual localization model that incorporates visible and infrared imagery, boosting its robustness to lighting changes. The proposed model takes on a large-scale architecture, exploiting the capabilities of both image modalities to achieve better localization accuracy across different lighting situations. The contributions of this study include: (i) A multimodal fusion approach correlates visual data with geographic coordinates, refining the precision of image localization. (ii) An adaptive fusion mechanism is implemented, adjusting the contribution of each image stream in response to environmental cues, thereby ensuring more reliable localization outcomes. (iii) a lightweight localization method that utilizes a single image for outdoor localization, eliminating the need for additional sensor data. We have conducted extensive testing, including shared datasets and random experiments, and the results show that our designed model not only improves localization accuracy in different dimensions compared to other models, but also enhances the coverage of the lighting environment. It can also achieve image localization in nighttime environments and simulate the ability of human eyes to perceive environmental location information.