Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning

This paper addresses the problem of absolute visual ego-localization of an autonomous vehicle equipped with a monocular camera that has to navigate in an urban en-vironment. The proposed method is based on a combina-tion of: 1) a Hidden Markov Model (HMM) exploiting the spatio-temporal coherency of acquired images and 2) learnt metrics dedicated to robust visual localization in complex scenes, such as streets. The HMM merges odometric mea-surements and visual similarities computed from specific (local) metrics learnt for each image of the database. To achieve this goal, we define some constraints so that the distance between a database image and a query image rep-resenting the same scene is smaller than the distance be-tween this query image and other neighbor images of the database. Successful experiments, conducted using a freely available geo-referenced image database, reveal that the proposed method significantly improves results: the mean localization error is reduced from 12.9m to 3.9m over a 11km path. 1