TY - JOUR
T1 - Microcomputer-based artificial vision support system for real-time image processing for camera-driven visual prostheses
AU - Fink, Wolfgang
AU - You, Cindy X.
AU - Tarbell, Mark A.
N1 - Funding Information:
The work described in this publication was carried out at the California Institute of Technology under support of the National Science Foundation grant EEC-0310723. Fink and Tarbell may have proprietary interest in the technology presented here as a provisional patent has been filed on behalf of Caltech. You has no proprietary interest.
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
KW - Image processing
KW - Microprocessor
KW - Portable artificial vision system
KW - Real-time image processing
KW - Smartphone
KW - Visual prosthesis
UR - http://www.scopus.com/inward/record.url?scp=77953156869&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953156869&partnerID=8YFLogxK
U2 - 10.1117/1.3292012
DO - 10.1117/1.3292012
M3 - Article
C2 - 20210459
AN - SCOPUS:77953156869
SN - 1083-3668
VL - 15
JO - Journal of Biomedical Optics
JF - Journal of Biomedical Optics
IS - 1
M1 - 016013
ER -