Chief Delphi - New Vision sample program

Chief Delphi (http://www.chiefdelphi.com/forums/index.php)

- Java (http://www.chiefdelphi.com/forums/forumdisplay.php?f=184)

- - New Vision sample program (http://www.chiefdelphi.com/forums/showthread.php?t=100792)

New Vision sample program

There is a new vision sample program included with the latest update of WPILibJ (just posted on the update site). Also, in the WPILib project, Documents section, there is a paper describing how it works. In addition, also in the Documents section, there are some sample images to play with and a Vision Assistant script that was used to create the sample code.

Please provide some feedback on this sample and the paper.

Brad

Re: New Vision sample program

This has already helped us a lot. Our team had been struggling for quite a while trying to figure out how to track but the paper and the sample code simplified it drastically! Thanks a bunch!

Re: New Vision sample program

Can you please provide a link to the update site you are referring to?

Thanks

Re: New Vision sample program

There was a thread about this but here http://firstforge.wpi.edu/sf/frs/do/...e ans_modules

Re: New Vision sample program

I've found the sample code but I can't find the document. Could someone provide the link?

Edit: Never mind, found it at http://firstforge.wpi.edu/sf/go/doc1304?nav=1

Re: New Vision sample program

Will the Eclipse plugin be updated, too?

Re: New Vision sample program

Thanks, Brad - this is very helpful. We are still in the process of figuring out whether we want to do onboard or offboard image processing, but at least with this update, doing it onboard is a viable option!

Re: New Vision sample program

If we use a red led ring, the sample code should work, correct? There is nothing we have to change for it to run correctly? We are having some trouble getting it to work.....

Re: New Vision sample program

Quote:

Originally Posted by rockytheworm (Post 1111168)

If we use a red led ring, the sample code should work, correct? There is nothing we have to change for it to run correctly? We are having some trouble getting it to work.....

I shot the images with a red ring light. Did you get it to work with the image downloaded into the cRIO and not using the camera?

Also, what problem are you having?

Brad

Re: New Vision sample program

In regards to the earlier Eclipse question, the plug-ins will soon be updated to include this sample

Re: New Vision sample program

Would anyone be able to suggest a light ring to use? This could be extremely useful but my team does not currently have a light ring.

Re: New Vision sample program

Quote:

Originally Posted by eddie12390 (Post 1111751)

Would anyone be able to suggest a light ring to use? This could be extremely useful but my team does not currently have a light ring.

We got ours from AndyMark for 8 credits each.

Re: New Vision sample program

I don't seem to be able to download the "Detecting Vision Targets in C++ and Java" PDF from FirstForge.

Reasons?

Doc

Re: New Vision sample program

Quote:

Originally Posted by nickpeq (Post 1111827)

We got ours from AndyMark for 8 credits each.

You can also get them here: http://www.superbrightleds.com/cgi-b...ni_tubes. htm

Use the angel eye lights. For extra brightness you can get two sizes and nest them.

Brad

Re: New Vision sample program

Quote:

Originally Posted by docdavies (Post 1112024)

I don't seem to be able to download the "Detecting Vision Targets in C++ and Java" PDF from FirstForge.

Reasons?

Doc

Did you look here: http://firstforge.wpi.edu/sf/go/doc1304?nav=1

Brad

Re: New Vision sample program

I have a question regarding the sample program, given that we have an image, what's to do with it? How can I begin to translate the image into motor movement?

Re: New Vision sample program

are there javadocs for the new code?

Re: New Vision sample program

Quote:

Originally Posted by xmendude217 (Post 1112351)

I have a question regarding the sample program, given that we have an image, what's to do with it? How can I begin to translate the image into motor movement?

We base our movement off of center_mass_x_normalized.

Quote:

Originally Posted by dxk3355 (Post 1113280)

are there javadocs for the new code?

Some of the methods involved seem to not be setup for javadocs.

Re: New Vision sample program

Is there a Netbeans plugin update? So far it looks like the CriteriaCollection, which is used in the Java sample code, doesn't exist.

Re: New Vision sample program

Quote:

Originally Posted by kamehameHA (Post 1113512)

Is there a Netbeans plugin update? So far it looks like the CriteriaCollection, which is used in the Java sample code, doesn't exist.

The plugin update came at the same time as the new sample.
If your Netbeans isn't set to update every startup/day, go into the Plugins and Reload the updates page.

Re: New Vision sample program

We're doing something very similar to the sample code (thresholding, convex hull, particle analysis), and finding it takes about a second to process each image on the cRio--far too slow for automated targeting.

Has anyone else been able to get the code to work onboard, with acceptable performance?

Thanks,

Steve (software mentor for team 649)

Re: New Vision sample program

Hi,
We copied the sample code into our project and are using the sample images provided. When we run it we get zero particles found. I added some extra code to print a particle report after every image operation and find that there are particles before the final filter is run(see below).

I also had a question about the following lines:

Code:

        cc = new CriteriaCollection();

        cc.addCriteria(MeasurementType.IMAQ_MT_BOUNDING_RECT_WIDTH, 30, 400, false);

        cc.addCriteria(MeasurementType.IMAQ_MT_BOUNDING_RECT_HEIGHT, 40, 400, false);

I read through the vision concepts doc and found descriptions of these criteria. But I was not sure if it meant:
a) crop the entire image to the described rectangle and return particles in the cropped area.
b) only return particles that fit in the size of described rectangle, so search entire image for particles that fit.

Here's the code and output. I am using 10ft2.jpg in this example output. I also tried the other xxft2.jpg images and got the same result, the last filter found zero particles.

Code:

            BinaryImage bigObjectsImage = thresholdImage.removeSmallObjects(false, 2);

            printParticleReports("bigobj", bigObjectsImage);



            // fill in occluded rectangles

            BinaryImage convexHullImage = bigObjectsImage.convexHull(false);

            printParticleReports("convexhull", convexHullImage);



            // find filled in rectangles

            BinaryImage filteredImage = convexHullImage.particleFilter(cc);

            printParticleReports("filtered", filteredImage);

The output is jumbled, see this thread: http://www.chiefdelphi.com/forums/sh...d.php?t=101438

Quote:

[cRIO]
[cRIO] * bigobj******************************************** *
[cRIO] 031250000000000444 , 0.0 )
[cRIO] Area : 301746.0
[cRIO] percent : 98.224609375
[cRIO] Bounding Rect : ( 0 , 0 ) 640*480
[cRIO] Quality : 98.33023755987878
[cRIO]
[cRIO]
[cRIO] Particle(1/2)
[cRIO] Particle Report:
[cRIO] Image Height : 480
[cRIO] Image Width : 640
[cRIO] Center of mass : ( 319 , 240 )
[cRIO] normalized : ( -0.0Particle(2/2)
[cRIO] Particle Report:
[cRIO] Image Height : 480
[cRIO] Image Width : 640
[cRIO] Center of mass : ( 323 , 31 )
[cRIO] normalized : ( 0.009374999999999911 , -0.8708333333333333 )
[cRIO] Area : 272.0
[cRIO] percent : 0.08854166666666666
[cRIO] Bounding Rect : ( 294 , 29 ) 55*7
[cRIO] Quality : 95.77464788732394
[cRIO]
[cRIO]
[cRIO] 2 146.245212
[cRIO] **********************************************
[cRIO]
[cRIO] 652 )
[cRIO] Area : 307200.0
[cRIO] percent : 100.0
[cRIO] Bounding Rect : ( 0 , 0 ) 640*480
[cRIO] Quality : 100.0
[cRIO]
[cRIO]
[cRIO] Particle(1/1)
[cRIO] Particle Report:
[cRIO] Image Height : 480
[cRIO] Image Width : 640
[cRIO] Center of mass : ( 319 , 239 )
[cRIO] normalized : ( -0.0031250000000000444 , -0.004166666666666vexhull************************** *******************
[cRIO]
[cRIO] * con1 146.837495
[cRIO] **********************************************
[cRIO]
[cRIO]
[cRIO] * filtered****************************************** ***
[cRIO] 0 147.054589
[cRIO] **********************************************
[cRIO]

Re: New Vision sample program

Turns out someone had changed the low R param of the RGB filter (from 25 to 40) while switching between our green light filter and sample's red light filter. I changed it back to 25 and was able to run the sample code in our robot project and find targets. Once that worked we are guessing that the criteria lines add a filter that looks for particles that are in the size range 30,40 to 400,400.

Code:

cc.addCriteria(MeasurementType.IMAQ_MT_BOUNDING_RECT_WIDTH, 30, 400, false);

        cc.addCriteria(MeasurementType.IMAQ_MT_BOUNDING_RECT_HEIGHT, 40, 400, false);

These criteria do not crop an image. If that explanation of the bounding rect width/height is incorrect please let me know.

Re: New Vision sample program

We are a second year team that is trying at this late stage in the build cycle to do some image analysis. We have a high level question to help us visualize how to make this work. We are using Java.

Where is the best place to do the image analysis? It seems we have a couple of possibilities:
1. Send images from camera to cRio and then run the image analysis code on cRio.
2. Send images from camera to laptop and then run the image analysis code on laptop
3. Send images from camera to cRio and access the images using ftp to laptop and run image analysis on laptop

Are teams using all of these alternatives? Which one is most popular?
Recommendations?
Other alternatives we haven't thought of?
thanks
Dave Fischer - mentor
Jasper Indiana team 3559