Re: How fast was your vision processing?
 

All the hurdles to implementing machine vision kept us out of machine vision. We are like a lot of small teams in that we do not have time to chase machine vision when the drive motors are not running. All the chatter on Chief Delphi about using Net Tables, ancillary processors or loading opencv libraries reinforced our reluctance. In addition, 2 years of issues the hd3000 usb camera did not help.

This was particularly painful for me, since a big part of my engineering and programming career was machine vision.

This year we implemented a quick n dirty tower tracker for our regional event. It worked amazingly well, but a little too late to get us to St Louis.

I will post some screen shots and some code when we finish getting unpacked. Here are the highlights

• C++ code
  runs in roboRio using minimum set of nivision.h functions.
  runs at frame rate (appeared to be about 15 fps)
  annotated image shows detection and tracking.
  Cpu load went up less than 10% when tracking.
  Logitech 9xxx? USB camera

Summary. We were already using IMAQxxxx functions (nivision.h) to select between a front viewing and rear viewing camera. When tracking, we copied each scan frame into a 2 dimensional array (something I am comfortable with) using imagImageToArray. Then used some fairly simple techniques to detect bright vertical and horizontal lines. Finally a little magic to home in on the bottom horizontal reflective tape. Then we copied our annotated image data back to the normal scan frame using imaqArrayToImage.

Once we could track the tower, we struggled with trying to make minimal angle correction with the a skid-steering robot. Finally ran out of time.

We did manage one 20 point autonomous, so we think we are cool.

Re: How fast was your vision processing?
 

Jared and I will be giving a presentation at the FIRST Championship Conferences about how to build fast vision processing systems and integrate them into your FRC robot's control system. We will post a thread on CD soon with more details, but for now you can see some details here.

Re: How fast was your vision processing?
 

It's killing me that I will not be attending CMP this year. So, I am truly looking forward to seeing what you will be releasing when that time comes.

I am amazed at what 254 came up with this year! I know 254 has not been a huge advocate of using vision unless it was truly necessary in the past. Jump forward to 2016, and we have one of the coolest and fastest vision tracking systems in FRC (that I am aware of).
Classic 254!!

Re: How fast was your vision processing?
 

Rod,
Would you, or anyone for that matter, be interested in a fairly low cost, say under $100, easy to tune, easy to modify, >30 fps (as high as 50 fps), no network table requirements, vision tracking system? All parts are easily available and all software is free. Even the vision code will be provided.

Keep your eyes open on CD. 2073 is refining it's code and approach to vision tracking and will be sharing it in time for the fall off season. We are not 254, but I think what you will see may change your mind about what a small team can do with vision in the middle of a build season crunch!

Re: How fast was your vision processing?
 

Aww man. Which presentation do we attend - Transformers, or Decepticons? Decisions, decisions...

Re: How fast was your vision processing?
 

I hope you guys are recording this! I'm really interested in this topic!

Re: How fast was your vision processing?
 

Obviously Decepticons. They're WAY cooler.

Also, @Tom is that presentation going to be recorded/posted online? I'd love to see it. The motion profiling one was terrific.

Re: How fast was your vision processing?
 

Build the wrong robot that aims well or build the right robot that can't aim.... decisions, decisions....

Re: How fast was your vision processing?
 

Like other people have said - is it going to be posted online? This is exactly the kind of thing our team needs!

Re: How fast was your vision processing?
 

Our team used a raspberry pi running OpenCV and stored the data on the pi, accessing it through a TCP port. This enabled the vision tracking to update its info at its maximum speed, which was practically real-time , and allowed the rio to only access the data when necessary, making the only cap on our tracking speed our algorithm in the rio to adjust the aim of the robot, which was never fully developed so it was very slow.