Integration of RFID and Computer Vision for Remote Object Perception for Individuals Who Are Blind

Over the last few years, Radio-Frequency Identification (RFID) technology has gained popularity for use in assistive technology for individuals who are blind. Recently, RFID-based wearable assistive devices have been developed for individuals who are blind to assist with navigation or remote object perception. However, RFID-based assistive technology suffers from two major drawbacks: (1) information overload in environments with many tagged objects, and (2) usability issues in untagged environments. In this paper, we propose a framework for integrating RFID and computer vision in assistive devices for remote object perception to overcome the aforementioned limitations. Computer vision enables content selection to help prevent information overload and provide users with only relevant information found through RFID. Moreover, computer vision can be used to learn a mapping between visual data and object features as acquired through tags, which will enable computer vision to replace RFID in untagged environments.