Setting tool offset using USB microscope
-
@Danal said in Setting tool offset using USB microscope:
While this looks like the other pic, this is machine vision "finding" the end of the nozzle. This also produces a coordinate (in pixels), and you can see that averaging these over a bunch of reads can get it nailed down:
316.0 240.0
316.0 240.0
315.88 239.88
316.0 239.75
316.0 240.0
316.0 240.0
316.0 240.0I moved the nozzle 0.1mm, and the readings (in pixels) changed to:
312.0 238.0
312.0 238.0appears to be about -4 x -2 pixels, so about 4.472 on the diagonal. Part of the work that needs to be done is figuring out how to "calibrate" movement in Pixels to movement in MM, when this is installed on a bunch of peoples printers, with different focus, and maybe even different cameras.
Danal,
Just out of curiosity and for my own understanding.I'm not sure if the nozzle is being moved by the Duet drivers or not? But if it is moved by the Duet drivers then after you lock in on the location of the nozzle can't you just get the XY location from the Duet, do the location (offset) calculations and then send it back into the Duet with the G10 command to set the proper offset?
Then the pixels to mm conversion would be irrelevant. Even different camera focus lengths wouldn't really matter. You can poll the Duet for it's XY location after the alignment is locked.
-
In the final alignment, yes, getting the position from the duet will work fine. No pixel/mm mapping required.
At the same time, lets assume the video image is 720 by 480. We find a circle with center, say 100 200. What is a good movement to get the nozzle closer to the circle being 720/2 480/2 (i.e. centered)? 1MM? 10mm? .1?
Perhaps the best way is to avoid camera to mm mapping at all, and just make a reasonable guess for the first move (1mm) and loop through successive approximations.
Perhaps the initial move could be 1mm, and establish a rough mm to pixel mapping, and the next move could be really close, and the final centering could be successive approximation.
These are all valid design ideas. Some involve the mapping, some don't. I'll need to play around with it and see what really works.
A separate, but related, challenge comes with the "out of the box" OpenCV "find a circle" function. It has several oddities.
First, it is REALLY good at finding circles. Glare on the nozzle will often result in several circles returned. We need it to find just the nozzle. One of the best ways to do that is to limit a min and max radius of found circles in pixels. I've hand tuned my examples, but I need to find a way to make this work for (almost) everyone.
Second, it is SLOW. The more constraints you add (like min/max from point 1 above) the slower it gets. A frame rate of about 2 a second is really good when searching with constraints. It gets even slower if it does not find circles (I assume it keeps looking). I am seriously considering modify the library to return a null if a certain amount of time passes and no circles have been found.
Combine these two things and getting it to find the actual nozzle, once and only once, is a challenge that I'm still researching.
One thought that I have not looked at at all: Are there other circle search functions built on OpenCV, beyond the one that comes with OCV?
The real key to all of this is time. At this moment, I'm rebuilding the printer with which I was doing most of these experiments. Maybe in a few days I can try some of this again.
Delta / Kossel printer fanatic
-
@Danal said in Setting tool offset using USB microscope:
@tekstyle said in Setting tool offset using USB microscope:
i got installopencv.sh installed on my raspberry pi. i have a Geany under programming. what do I do wiht the.py files? i have a duet2wifi
Did you run that script? It takes upwards of an hour. Command to run it:
cd to the directory where it is.
./installopencv.sh
Yes I did. It took a while to run. Then it would it was done, my monitor just turned off and I couldn't wake it up. Not sure if that's normal. Pulled the power and reboot. Went to the folder containing the toolalignimage.py file and that's what I got. I'll try to reformat, reinstall raspbian, and reinstall installopencv.sh again.
-
If at all possible, start with the image provided by Duet, the "full" not the "lite".
The install script does not turn off the monitor, it probably just "power saved" out. You may wish to search on "how to keep my screen on" or "how to keep my Pi from powering off".
-
@Danal said in Setting tool offset using USB microscope:
If at all possible, start with the image provided by Duet, the "full" not the "lite".
The install script does not turn off the monitor, it probably just "power saved" out. You may wish to search on "how to keep my screen on" or "how to keep my Pi from powering off".
The duetpi full and lite doesn't work with duet2. It's designed for the duet3 unfortunately.
-
@tekstyle said in Setting tool offset using USB microscope:
@Danal said in Setting tool offset using USB microscope:
If at all possible, start with the image provided by Duet, the "full" not the "lite".
The install script does not turn off the monitor, it probably just "power saved" out. You may wish to search on "how to keep my screen on" or "how to keep my Pi from powering off".
The duetpi full and lite doesn't work with duet2. It's designed for the duet3 unfortunately.
True... but... you can still run them. Just turn off the DSF, and you have a regular Pi.
Having said that, current base raspbian should be OK as well. We just might have to install something that the isntallopencv.sh script doesn't currently get, because I built and tested it on top of the Duet image. No big deal either way.
Let me know when you have it rebuilt, modified for no sleep, and opencv installed.
-
i followed this tutorial to set up duetpi on raspberry pi 3. took out the card and put it into the raspberry pi. powered it up (not connected to the duet2. not sure how i would do it). all i get is an endless list of EXT4-fs error lines after line. been doing this for the past 2 hours. not sure if I did something wrong?
-
@Danal said in Setting tool offset using USB microscope:
Second, it is SLOW.
Are you doing any post-capture/pre-recognition processing of the image? You can convert colour images to greyscale or black and white (with a threshold level), and even use the black and white version as a mask. This will reduce the amount of image recognition processing massively. I can't say I've tried this myself, just read about it.
Ian
-
@droftarts said in Setting tool offset using USB microscope:
@Danal said in Setting tool offset using USB microscope:
Second, it is SLOW.
Are you doing any post-capture/pre-recognition processing of the image? You can convert colour images to greyscale or black and white (with a threshold level), and even use the black and white version as a mask. This will reduce the amount of image recognition processing massively. I can't say I've tried this myself, just read about it.
Ian
Yeah, that's all very fundamental, always grayscaling, trying different kinds of blur and threshold and mask and... Some do perform better than others, but the best still have highly variable "search" times that are extremely sensitive to the tuning parameters vs. the image.
-
@tekstyle said in Setting tool offset using USB microscope:
(not connected to the duet2. not sure how i would do it).
You can't. Don't connect it. It is really a stand-alone PI, just happens to be built with the Duet image as a start.
i followed this tutorial to set up duetpi on raspberry pi 3. took out the card and put it into the raspberry pi. powered it up, all i get is an endless list of EXT4-fs error lines after line. been doing this for the past 2 hours. not sure if I did something wrong?
Followed the Duet "etch" tutorial? And edited wpasupplicant.conf? And did NOT format when windows complained about the card after etching?
That last bit is the most important. The card is partitioned, with a windows readable "boot" partition and a much larger Linux partition. Windows tries to assign a drive letter to that Linux partition, balks, and asks to format it. Which you must always decline,
EXT4-fs is the file system that windows doesn't like, and asks to format. That certainly seems to relate to those error messages.
-
@Danal said in Setting tool offset using USB microscope:
@tekstyle said in Setting tool offset using USB microscope:
(not connected to the duet2. not sure how i would do it).
You can't. Don't connect it. It is really a stand-alone PI, just happens to be built with the Duet image as a start.
i followed this tutorial to set up duetpi on raspberry pi 3. took out the card and put it into the raspberry pi. powered it up, all i get is an endless list of EXT4-fs error lines after line. been doing this for the past 2 hours. not sure if I did something wrong?
Followed the Duet "etch" tutorial? And edited wpasupplicant.conf? And did NOT format when windows complained about the card after etching?
That last bit is the most important. The card is partitioned, with a windows readable "boot" partition and a much larger Linux partition. Windows tries to assign a drive letter to that Linux partition, balks, and asks to format it. Which you must always decline,
EXT4-fs is the file system that windows doesn't like, and asks to format. That certainly seems to relate to those error messages.
Yup. I followed the tutorial on duet exactly. Only thing was inside the boot partition, it already contained a wpasupplicant.conf file. I Openned itnin notepad and editted it with my ssid and PW. Pulled the card out and popped it in to the rpi. Then powered it up. Will try again tonight
-
@tekstyle said in Setting tool offset using USB microscope:
@Danal said in Setting tool offset using USB microscope:
@tekstyle said in Setting tool offset using USB microscope:
(not connected to the duet2. not sure how i would do it).
You can't. Don't connect it. It is really a stand-alone PI, just happens to be built with the Duet image as a start.
i followed this tutorial to set up duetpi on raspberry pi 3. took out the card and put it into the raspberry pi. powered it up, all i get is an endless list of EXT4-fs error lines after line. been doing this for the past 2 hours. not sure if I did something wrong?
Followed the Duet "etch" tutorial? And edited wpasupplicant.conf? And did NOT format when windows complained about the card after etching?
That last bit is the most important. The card is partitioned, with a windows readable "boot" partition and a much larger Linux partition. Windows tries to assign a drive letter to that Linux partition, balks, and asks to format it. Which you must always decline,
EXT4-fs is the file system that windows doesn't like, and asks to format. That certainly seems to relate to those error messages.
Yup. I followed the tutorial on duet exactly. Only thing was inside the boot partition, it already contained a wpasupplicant.conf file. I Openned itnin notepad and editted it with my ssid and PW. Pulled the card out and popped it in to the rpi. Then powered it up. Will try again tonight
you won't believe this. I used my other laptop running windows 8, win32diskimager to load the duetpi image. and that worked. i have no idea why using balena etcher on win 10 doesn't work.
-
@wilriker said in Setting tool offset using USB microscope:
@dc42 Would a
G10 L10to set tool offsets relative to current position desirable (makingG10even more complex OTOH)?Not necessary, because you can already do that using the object model.
@tekstyle said in Setting tool offset using USB microscope:
Tool offset with limit switches would be great.
Already supported if you can configure the limit switch as a Z probe. See the G30 S-2 command.
Duet WiFi hardware designer and firmware engineer
Please do not ask me for Duet support via PM or email, use the forum
http://www.escher3d.com, https://miscsolutions.wordpress.com -
@wilriker said in Setting tool offset using USB microscope:
@dc42 Would aG10 L10to set tool offsets relative to current position desirable (makingG10even more complex OTOH)?Also, any scripting environment that is complex enough to do multi-tool alignment with "one button" is going to have basic math. And that's all that is needed to produce the final G10 commands. Subtract T0's coordinates from T1s, etc, etc. So, no, G10 does not need any changes.
P.S. That's why Python at the moment... a better place might be conditional G-Code, but that does not yet work from the Pi DSF... so having a single script have access to the camera, and the printer, requires something on the attached Pi at the moment. Python seems very suitable for the required image processing.
@tekstyle said in Setting tool offset using USB microscope:
Tool offset with limit switches would be great.The "Zonly.py" script in the https://github.com/DanalEstes/PythonDSF/ repository is touchplate based. It is still very much experimental 'under development'. Still maybe worth looking at for ideas.
-
@Danal said in Setting tool offset using USB microscope:
P.S. That's why Python at the moment... a better place might be conditional G-Code, but that does not yet work from the Pi DSF
Expressions within GCode commands do work from the Pi DSF in RRF 3.04. It's meta commands such as 'if' and 'while' that don't yet.
Duet WiFi hardware designer and firmware engineer
Please do not ask me for Duet support via PM or email, use the forum
http://www.escher3d.com, https://miscsolutions.wordpress.com -
@dc42 said in Setting tool offset using USB microscope:
@Danal said in Setting tool offset using USB microscope:
P.S. That's why Python at the moment... a better place might be conditional G-Code, but that does not yet work from the Pi DSF
Expressions within GCode commands do work from the Pi DSF in RRF 3.04. It's meta commands such as 'if' and 'while' that don't yet.
Good point. Lots of progress being made very quickly. Which is quite exciting!!
It is probably more clear to say that touchplate oriented stuff can/could/will be done in Cond G-Code at some point very soon now as that all progresses. On the other hand, Camera based stuff seems like it will be on the Pi for the foreseeable planning horizon.
-
@tekstyle said in Setting tool offset using USB microscope:
you won't believe this. I used my other laptop running windows 8, win32diskimager to load the duetpi image. and that worked. i have no idea why using balena etcher on win 10 doesn't work.
Good news is you are up and have a reproducable path.
Odd thing is I use W10 with Balena for all my SD cards for PIs, and I probably build two a week. Well, maybe one a week. Anyway, it has been trouble free.
Anyway, glad to see you have a working SD, feel free to ask other questions, I'm eager for testing of the camera based scripts in particular.
Sometime today I'm going to post an entirely new set of "machine vision" scripts... had some breakthroughs in the last 24 hours. Look for a new top-level post in a few hours.
-
Unopenned terminal typed CD ~/Desktop/Duet
My folder is on the Desktop and I renamed it to Duet. Didn't find the path. So I just right clicked the .sh file and selected open in terminal. I'll see how it goes after work.
-
pi@duet3:~/Desktop/Duet $ python3 toolAlignImage.py
Traceback (most recent call last):
File "toolAlignImage.py", line 11, in <module>
import cv2
ModuleNotFoundError: No module named 'cv2'this is what i am getting when i try to run toolAlignImage.py. i have the camera plugged in as well when I attempt to run the *.py file. it is not connected in any way to the duet2wifi for obvious reasons.
-
That means that OpenCV is not installed.
You can re-run the installOpenCV.sh any number of times. It is long enough that you may need to ensure your Pi does not go to sleep or otherwise time out. It does produce yellow warnings at various points; it should not produce any red failures.
Important If you re-run it, when it finishes, copy the last dozen or so lines of output and post them here.
Also, see this post: https://forum.duet3d.com/topic/15026/tool-alignment-machine-vision-some-progress
I'd highly, highly recommend switching to the code described in that thread. You will still need OpenCV...
