The challenge

The environment represented using vision processing algorithms

The challenge is to develop novel vision processing methods that aim to extract and process salient information from a scene and represent that information using only the limited amount of phosophenes (points of light) from the retinal implant (i.e. bionic eye). The aim is to represent the environment using vision processing algorithms that enable individuals implanted with the bionic eye to experience improved functional vision.

Our response

A Software library

A software library was developed incorporating our corporate vision approach. This library was used to drive the first-generation retinal implant in patients (2012-2014). Clinical trials showed promising results and has also resulted in numerous conference and journal papers. Based on these results, we have further developed the library and approach for use in the 2nd generation clinical trial (2018-). Early results are supporting improved functional vision with this cohort.

The results

Vision processing in the bionic eye

With vision processing in the bionic eye, we have restored a sense of vision to seven blind individuals.  Randomised clinical trials have shown that our novel vision processing methods are effective for improving functional vision with recipients being able to navigate without an aid and avoid overhanging objects and trip hazards.

The research and technology will enable new vision processing methods to be developed and implemented in the next generation bionic eye, which is currently under development for commercialisation.  The main success has been CSIRO's Data61 vision library to drive the bionic eye, as well as publications in top-tier journals and at leading international conferences.

Person wearing bionic eye technology showing all the parts that make up the implant and how it works, including:

  1. Camera captures images in real time - pair of glasses worn on the face
  2. Image sent to processing device and sent to interface - arrows show the data going from the 'camera' down a cord to the 'processing device' worn near the shoulder.
  3. Data sent to implant, then to brain for user navigation -arrows show data moving from '2. processing device' back along the cord to the 'implant' that is fixed to the skull slightly up and behind the ear.

Inset image also shows a scan of the actual implant from both the top and side view.

  • top view reveals part of the inside of the eye with the a section of the implant visible
  • side view shows the implant position in relation to the structure of the eye; scan labelled left to right - choroid, retina, silicone, electrode to retina distance, platinum electrode.

Bionic Vision Technologies announced recently the interim results of a pilot study involving four patients with late-stage Retinitis Pigmentosa (RP) implanted with a visual prosthesis designed to improve awareness of external objects and patient surroundings.  Results presented during the 38th annual JP Morgan Conference in San Francisco demonstrated and improved combined performance of all six functional vision tests at 44 weeks of active use of the device.

Read more at Bionic Vision Technologies Announces Interim Pilot Study Results of the BVT Bionic Eye System Designed to Help the Blind Achieve Greater Mobility and Independence .

Research and implementation of new vision processing algorithms to improve the results for people using visual prosthesis will continue.

BVT  logo

Do business with us to help your organisation thrive

We partner with small and large companies, government and industry in Australia and around the world.

Contact us now to start doing business

Contact Data61

How can we help you create your data-driven future? Use the form below to send us a message.
Your contact details
0 / 100
0 / 1900
You shouldn't be able to see this field. Please try again and leave the field blank.

For security reasons attachments are not accepted.