What about putting a computer vision processor on the camera or sensor platform itself?

Dream big and be open minded

Marius Slavescu
2 min readApr 9, 2017

Thanks to John Kost for starting and leading the OSSDC Smart Camera MVP (see OSSDC Slack channel #3-mvp-smart-camera), which should bring low cost cameras with very advanced features, in our Open Source SDC platform, similar with MobilEye ADAS vision sensors.

Here is a paragraph from a very nice and interesting article Automotive Ethernet for vision-based ADAS: Loss, cost, and latency, an interview with Marco Jacobs, which emphasizes exactly this idea:

JACOBS: Doing computer vision close to the sensor makes a lot of sense. Indeed, you could do computer vision after you do the Ethernet transportation in a more central location in a vehicle, but you could also do it at the edge, inside the camera module. This has a lot of advantages. One advantage is that you get rid of this lossy compression issue because you would do the computer vision before you do the compression on the raw image. But there’s another advantage that’s more about modularity.

You can read the whole article here.

The image above is from Xilinx The Total Solution for Next-Generation Automotive Applications article, Xilinx are the inventors of commercially viable FPGAs, in 1985.

Here are more details about Open Source Self Driving Car Initiative:

What is next in OSSDC.org

We are currently hiring in these possitions, our team is continuously growing:

  • Computer vision (standard and deep learning based), stereo vision and structure from motion experience is nice to have
  • Robotics and auto specialists, ROS and CAN bus experience is nice to have
  • Embedded specialists, FPGA experience is nice to have
  • Machine learning, Tensorflow experience is nice to have
  • Mobile developers, Android and IOS
  • Web developers, GitHub pages experience is nice to have
  • Human-computer interaction specialists
  • Specialists in road laws and regulation (from all countries)
  • Anyone else, who wants to Learn, Teach, Invent, Make!

You can work from anywhere in the world, and only when you have time and feel like to give something for free, that others can benefit from also.

The pay is good, but it comes only after you actively stay with the organization for 2 years :-)

So the earlier you join, the faster you’ll reap the benefits.

Join us here:

http://ossdc.org

For more updates on OSSDC, Robotics and Artificial Intelligence, follow me also on Twitter at @gtarobotics

--

--

Marius Slavescu

STEMCA Inventor co-author, robotics/STEM education and DIY/maker platform, and Founder of GTA Robotics and OSSDC communities. Follow me at @gtarobotics