I decided to write a second version of the requirements for the ethervideo, mostly so I could understand better what we are doing. Please let me know what you think, what I should change, which parts are hopelessly biased, etc -- it is on the web at www.cs.dartmouth.edu/~nasa/reqs-2.html.
I didn't add in all that stuff about low latency, responsiveness, documentation, etc -- all that will go in v2.1 once I get feedback ;-) I also somewhat forgot about this project, but remembered again... this is some of the work I have been doing in the last two months that is important. I think we should work on some C versions of the various parts of H.264 pipeline. This will give us a sense of what we can do with the chip, and any parts that we decide to implement in the DSP we will already have coded. I have drawn a simple version of what I understand the H.264 pipeline is, so people can work on different parts (the RED runs on the FPGA, but that is just preliminary and should be ignored). It is up at www.cs.dartmouth.edu/~nasa/DecodeFlow.png. Finally, I tried to find out as much as I could about licensing costs for various technologies we would be using, and those are up at www.cs.dartmouth.edu/~nasa/LicenseCosts.txt. For some of these, the costs change after about 100,000 units -- I assume we probably won't sell more than that to begin with? Cheers, nick _______________________________________________ Open-hardware-ethervideo mailing list [email protected] http://lists.duskglow.com/mailman/listinfo/open-hardware-ethervideo
