文摘
This paper presents an alternative approach to the problem of outdoor, persistent visual localisation against a known map. Instead of blindly applying a feature detector/descriptor combination over all images of all places, we leverage prior experiences of a place to learn place-dependent feature detectors (i.e., features that are unique to each place in our map and used for localisation). Furthermore, as these features do not represent low-level structure, like edges or corners, but are in fact mid-level patches representing distinctive visual elements (e.g., windows, buildings, or silhouettes), we are able to localise across extreme appearance changes. Note that there is no requirement that the features posses semantic meaning, only that they are optimal for the task of localisation. This work is an extension on previous work (McManus et al. in Proceedings of robotics science and systems, 2014b) in the following ways: (i) we have included a landmark refinement and outlier rejection step during the learning phase, (ii) we have implemented an asynchronous pipeline design, (iii) we have tested on data collected in an urban environment, and (iv) we have implemented a purely monocular system. Using over 100 km worth of data for training, we present localisation results from Begbroke Science Park and central Oxford. Keywords Feature learning Appearance changes Cross seasonal Visual localisation Long-term autonomy Outdoor localisation