SUGAMAN: Describing Floor Plans for Visually Impaired by Annotation Learning and Proximity based Grammar

Abstract: In this paper, we propose SUGAMAN (Supervised and Unified framework using Grammar and Annotation Model for Access and Navigation). SUGAMAN is a Hindi word meaning "easy passage from one place to another". SUGAMAN synthesizes textual description from a given floor plan image for the visually impaired. A visually impaired person can navigate in an indoor environment using the textual description generated by SUGAMAN. With the help of a text reader software, the target user can understand the rooms within the building and arrangement of furniture to navigate. SUGAMAN is the first framework for describing a floor plan and giving direction for obstacle-free movement within a building. We learn $5$ classes of room categories from $1355$ room image samples under a supervised learning paradigm. These learned annotations are fed into a description synthesis framework to yield a holistic description of a floor plan image. We demonstrate the performance of various supervised classifiers on room learning. We also provide a comparative analysis of system generated and human written descriptions. SUGAMAN gives state of the art performance on challenging, real-world floor plan images. This work can be applied to areas like understanding floor plans of historical monuments, stability analysis of buildings, and retrieval.