State-of-the-art in visual geo-localization

Large-scale visual geo-localization has recently gained a lot of attention in computer vision research and new methods are proposed steadily. However, surveys of visual geo-localization methods are rare and they focus mainly on city-scale localization methods. We present a comprehensive and balanced study of existing visual geo-localization domains, including city-scale, global approaches and methods for natural environments. We describe the methods to show their pros and cons, application domains, datasets, as well as evaluation techniques. We categorize the reviewed methods by two criteria. The first is the type of data the method uses for geo-location estimation. The second criterion is the target environment for which the method has been proposed and validated. Based on this categorization, we analyze important conditions that must be considered while solving geo-localization problems. Each category is in a different state of research-while city-scale image-based methods received a lot of attention, other categories such as natural environments using cross-domain data sources are still challenging problems under active research. Future research of large-scale visual geo-localization is discussed, primarily the challenging and new research category-geo-localization in natural environments.