PLISS: Detecting and Labeling Places Using Online

摘要

We present PLISS (Place Labeling through Image Sequence Segmentation), a novel technique for place recognition and categorization from visual cues. PLISS operates on video or image streams and works by segmenting it into pieces corresponding to distinct places in the environment. An online Bayesian change-point detection framework that detects changes to model parameters is used to segment the image stream. Unlike current place recognition methods, in addition to using previously learned place models for labeling, PLISS can also detect and learn a previously unknown place or place category in an online manner. Moreover, since both the inferred boundaries of places (change-points) and the place labels are fully probabilistic, they can indicate when the inference is uncertain. New places and categories are detected using a systematic statistical hypothesis testing framework. We present extensive experiments on a large and difficult image dataset. We validate our claims by comparing results obtained using different types of features and by comparing results from PLISS against the state of the art.