A conditional random field model for place and object classification

Place categorization and object recognition are competencies needed by robots to perform a variety of service tasks in the home, such as fetch-and-carry, retrieval, cleaning, meal preparation, and companionship. Context is a powerful cue for place categorization and object recognition; rooms are laid out in a specific fashion to enable comfortable and efficient living, and objects are used within rooms for tasks specific to that room. This paper will present a technique which leverages contextual cues for joint reasoning about object and room classification via a conditional random field model.