Microcomputer-based artificial vision support system for real-time image processing for camera-driven visual prostheses.

TL;DR: In this paper, the authors employ a commercial off-the-shelf battery-powered general purpose Linux microprocessor platform to create the µAVS^2 for real-time image processing.

Abstract: It is difficult to predict exactly what blind subjects with camera-driven visual prostheses (e.g., retinal implants) can perceive. Thus, it is prudent to offer them a wide variety of image processing filters and the capability to engage these filters repeatedly in any userdefined order to enhance their visual perception. To attain true portability, we employ a commercial off-the-shelf battery-powered general purpose Linux microprocessor platform to create the microcomputer-based artificial vision support system (µAVS^2) for real-time image processing. Truly standalone, µAVS^2 is smaller than a deck of playing cards, lightweight, fast, and equipped with USB, RS- 232 and Ethernet interfaces. Image processing filters on µAVS^2 operate in a user-defined linear sequential-loop fashion, resulting in vastly reduced memory and CPU requirements during execution. µAVS^2 imports raw video frames from a USB or IP camera, performs image processing, and issues the processed data over an outbound Internet TCP/IP or RS-232 connection to the visual prosthesis system. Hence, µAVS^2 affords users of current and future visual prostheses independent mobility and the capability to customize the visual perception generated. Additionally, µAVS^2 can easily be reconfigured for other prosthetic systems. Testing of µAVS^2 with actual retinal implant carriers is envisioned in the near future.