Welcome to Synthiam!

Program robots using technologies created from industry experts. ARC is our free-to-use robot programming software that makes features like vision recognition, navigation and artificial intelligence easy.

Get Started
Asked — Edited
Resolved Resolved by ptp!

Darknet / Yolo Real-Time Object Detection

DJ and Team,

Have you seen the TensorFlow / Darknet / YOLO Real-time Object Detection videos? A friend of mine has implemented it on his PC and OMG, it is the fastest and most accurate object identification software that I have ever seen. It is light years beyond Open CV. And the best part is that like Open CV, it is also open source. It is a neural network program which it runs on Windows (and Linux).

TED Talk:
https://www.youtube.com/watch?v=Cgxsv1riJhI

Have you ever thought of adding this to EZ Builder?



Thomas Messerschmidt



User-inserted image


Object detection/recognition

AI Support Bot
Related Content
Synthiam
#9  
Well thank you for that detailed explanation. It is certainly an interesting mix of software. :D Someone should come up with a name for this. A simple, descriptive name would be a good thing. Tensorflow/Darknet/YOLO is a bit of a mouthful to say. Perhaps "TiDY" or "DitTY" :D

--Thomas
#10  
SUCCESS!

I finally have DTY (Darknet/Tensorflow/YOLO2) working with ARC. DTY classifies/identifies an object. I added code to then output what it sees to a text file. Then I read the text into ARC, and finally parse it and assigns each atribute to a variable. The attributes are

- OBJECT
- CONFIDENCE
- TOP
- BOTTOM
- LEFT
- RIGHT
- HCENTER
- VCENTER
- TIMESTAMP


Quote:

If at first you don't succeed, code, code again!


User-inserted image
PRO
USA
#11  
@thomas! Great job! I look forward to details and videos !
#12  
Congratulations @thomasfromla ! That is no small feat to accomplish! It sounds like you did it a very efficient way as well (write text file/read in - I love that method).

I hope you'll get to share more on how your did it, I'd like to follow in your foot steps and experiment. With TensorFlow I assume you used the 'CPU' install instead of the GPU install?

I was pricing a multi unit GPU system the other day...PHEEWWW! I was not prepared for those prices!
#13  
@thomasfromla Man this is great...really looking forward to see how you accomplished!:D
PRO
USA
#14  
@thomasfromla:
Good job.
Compiling Yolo is quick, regarding Tensorflow:
How long it took to compile ?
Did you enabled AVX2 extensions ?

(write text/read in) pointed by Justin follows the KISS principle !

I'm working on a different integration, not so simple .. so no results yet.
#15  
@ptp

Thanks.

I'm running it from Atom/Python with a few changes.

Best of luck on your implementation!
#16  
PS. I've gotten my robot to physically point at requested objects.

Me: do you see a dog?
Robot: yes. It's on my left. (Points to the dog.)
PRO
USA
#17  
This sounds great, is there any way to post up a vid of it operation? There is an immovable implementation over on the MRL site the video looks awesome.
#18  
@thomasfromla this is great progress! We could also use the information perceived to drive a fully IK rigged arm within Unity, which would be my next goal!

Do you think it is possible to send the Values from YOLO directly to the Http Server, this would eliminated to read and write a .txt file and speed up things significantly!:)
PRO
USA
#19  
Now this is getting interesting. I look forward to a video!
#20  
OK. I hear you. You want a video (or two)

Here is my to do list:

1. Put a demo video up this weekend showing the software working.
2. Put up a video showing the robot running via ARC.
3. Put up a Tensorflow / darkflow / YOLO instructional video with links to all the needed software.
4. Put up a Atom installation video
5. Put up a OpenCV installation video
6. Correct any errors
7. Answer all questions
8. Improve as needed

Depending on your internet connection, setting this up should take less than a half of an hour to install and get working. You will need a computer with good "horsepower" under the hood--a strong 4 core processor and at least 8 GB of RAM. And a GPU will get you up to 10-30 images processed per second. I don't have a GPU, so the best I get is about 1 image every 2 or 3 seconds.
#21  
Hi,

I put up a demo video with tensorflow/YOLO/Darknet/Darkflow on YouTube:

#22  
@thomasfromla this is a great demo! The end is hilarious!:D
Looking forward to see the setup and it would be great if you could share the ARC Project! Cant wait to try it myself!

Btw, I heard there are a few faster version of YOLO out there with a reduced amount of trained objects, can you confirm this?
#23  
There is a mini version, but I could never get it to work right. It is currently unsupported.
#24  
Next video: installation of the free Atom editor. You can run the software without Atom, but it is a whole lot harder. You see, Atom is more than just an editor. It allows you to compile and run code.
PRO
USA
#26  
Fantastic progress Thomas! Very Impressive.
#28  
Well, I started it two years ago, but ptp finished it this year! Thanks ptp for making it work for everyone!