Re: Vision Targeting for Aerial Assist 2014
 

Thanks for providing this information that is very cool and perhaps you can show a demo of it in action sometime.

You may know this already, but in case you do not... and for anyone else considering to use UDP. There is still a remaining VxWorks bug which is also the same bug in Winsock (i.e. not Winsock2)... if the client receiver sends UDP packets to the robot without the robot being able to receive them (i.e. recvfrom())... the buffer will overflow and start to corrupt the TCP/IP packets. All of a sudden the driver station will disconnect and reconnect and blink between these when that happens. Team 118 experienced this in 2012 as well as our team... I worked around this problem by spawning a new task to receive the packets as soon as the robot starts up, but I still feel a bit uneasy about this solution as we haven't had enough test time with the FMS environment, as it can become a race condition. For this season we'll use the Network Tables code, which uses TCP/IP. We are doing vision processing over the network through the driver station.

Re: Vision Targeting for Aerial Assist 2014
 

Does anyone have a preference as to where I should outsource the vision tape code? Our team's website people have other more important tasks to do, such as build the robot, so that media platform won't work.

As for the udp, I have no idea how they are received on the labview side, but i do know we have not had cotrouble withmmunications via udp for the past 2 years and past 5 competitions. This is the first I've heard of this issue. Interesting.

Re: Vision Targeting for Aerial Assist 2014
 

You should try SourceForge or FirstForge this it what I have used... for example:
http://firstforge.wpi.edu/sf/projects/smartcppdashboard
This is a great setup for releasing source, binaries, and it has a place for documentation and discussion.

As for the UDP... Greg McKaskle is the one who told me of this problem, so I believe NI has already made this problem go away for labview... 118 was the only other team I know who used c++ and vision. I do not know how Java teams send messages back to the robot, but I suspect they were probably already using Network Tables behind the scenes since it was available on the Java platform.

Re: Vision Targeting for Aerial Assist 2014
 

Alright, I'm going to have to go in an rename some variables and add comments to make things for readable to the thirdparty viewer. I just realized that. I'll try to have it up before the sun sets on the midwest.

Ah, Greg McKaskle. I always learn something when I read a post of his. We go c++ to labview, so that could explain why we haven't experienced it before.

update 1: project is being submitted for approval. more updates to come.

update 2: project was approved, trying to figure out how to add .cpp files.

Re: Vision Targeting for Aerial Assist 2014
 

if any of you is willing to send the code it would help my team, we have never used the camera really.

Re: Vision Targeting for Aerial Assist 2014
 

I'm trying, and failing. If someone could third party it for me, that'd be great. i have the project created, just can't figure out how to add files to it....

http://firstforge.wpi.edu/sf/project...on_source_code

Just message me and I'll email you a bunch of it with descriptions and you could post it on the project.

Re: Vision Targeting for Aerial Assist 2014
 

Another student put this up online for me: https://cmastudios.me/owncloud/publi...74f 6a3486745

it is an hsv code with trackbars. It grabs an image, converts it to hsv, thresholds it, I think it dilates, find the contours, and colours the contour according to how many sides it has. Enjoy!

Re: Vision Targeting for Aerial Assist 2014
 

The UDP problem as it is being called, is fundamental to how VxWorks did its networking in the version of the networking libraries and OS on the cRIO. It will affect all languages, but shouldn't affect LV as readily because it is a more threaded environment. Team 118 and others who saw this were doing many things in a single thread and were therefore congesting traffic. If you let traffic buffer in LV because you fail to read from a port, you will see symptoms where other network ports fail to operate correctly.

Greg McKaskle

Re: Vision Targeting for Aerial Assist 2014
 

How about Bangalore?

Re: Vision Targeting for Aerial Assist 2014
 

I would also recommend using github for your code repositories. Github has been donating free repository slots (5 - 10) for FRC teams this year with no limit for user accounts. You'll just have to send them an email requesting a team account.

Go to http://github.com and search for "FRC team" and you'll see several great examples of FRC team's code for previous years.

Re: Vision Targeting for Aerial Assist 2014
 

I posted a bunch of stuff here:

https://cmastudios.me/owncloud/publi...928edef612274f 6a3486745

It has....2 of some tutorial like programs I wrote. One does a bunch of stuff, so it isn't efficient, but it will be good to learn from. The other has to do with camera calibration and doesn't require a camera. There are also some programming textbooks and the opencv textbook, as well as a 2 research papers, one that wrote the solvepnp algorithm, and the other is my attempt at an academic paper I had to write for a class about the 2012 program.

Re: Vision Targeting for Aerial Assist 2014
 

When clicking that link I get the following message:
(See attachment)
Then clicking to continue I get the second attachment message saying the link is gone.

Maybe GitHub is the way to go... I don't like git at all, but at least it works, and it sounds like you can have your own repository for free, which is great.

With First Forge you can request for a subversion account and once it is granted you can upload there. subversion is great in that there is one repository and easy to use for people to be able to "glv" (get latest version). Git on the other hand has many repositories (each client is a repository) and you can't glv you fetch and merge. I'm sure those you use git everyday have gotten a good workflow going but it is not intuitive. So far all the git experts I have ran into are the console unix type people who prefer not to use UI. Me on the otherhand I'll use tortoise for all of them!<Ok James is now off his soapbox about git>.

Re: Vision Targeting for Aerial Assist 2014
 

All,
Our team is just starting out with vision and object tracking this year. I created a site to document "How to" do something. It is pretty basic so far but we will keep updating it. We have been posting code there also.

https://sites.google.com/site/sieberschool/

Re: Vision Targeting for Aerial Assist 2014
 

Oh boy. Time to figure out how to use git.

Re: Vision Targeting for Aerial Assist 2014
 

Github has some good tutorials on getting started that you can use to learn the syntax.