opencv, to ai
@opencv@mastodon.social avatar

New on the OpenCV blog, an OpenCV 5 development progress update from the core team. Recent work includes new samples, ONNX improvements, documentation improvements, HAL and G-API work, and a lot more.

Read the post for the whole story https://opencv.org/blog/opencv-5-progress-update-may-9-2024/

villares, to python
@villares@ciberlandia.pt avatar
opencv, to hiring
@opencv@mastodon.social avatar

Anyone hiring OpenCV developers here on the Fediverse? Any OpenCV devs looking for work? Reply in this thread, let's fill some open positions today.

dragfyre, to fediBots
@dragfyre@mastodon.sandwich.net avatar

OK, so I got this close 🤏🏾 to getting @videodreams posting again. It downloads images properly and assembles them into a webm video file. But it seems like Mastodon's updated something because now I'm getting the attached HTTP 422 error when trying to post the file.

Nice to know that the code still works, though! I'll have to come back and figure out how to play nice with Mastodon.

dragfyre,
@dragfyre@mastodon.sandwich.net avatar

After that, the last of the late great dragfyre bots to bring back from the dead would be @laughingman, which tbh is one of my favourites. The problem is, it uses to detect faces, and I can't run the newest versions of openCV on my potato compy. So that one's going to be considerably more difficult to resurrect. Maybe I'll wait 'til Easter.

opalmirror, to space
@opalmirror@hachyderm.io avatar

Ingenuity Mars Helicopter winged, grounded forever. We are all temporarily able bodied! Such a successful mission though. I'm proud to have contributed to the OpenCV computer vision library open source project that it uses. https://www.jpl.nasa.gov/news/after-three-years-on-mars-nasas-ingenuity-helicopter-mission-ends

mwfc, to KindActions
@mwfc@chaos.social avatar

So many begging posts fly past me in the last couple of days, so here your quick reminder that is running a fundraiser to move to version 5 and get a significant amount of work done.

There is a ton of reasons to to any of those projects. But many projects are starving for money and opencv is quite an important library. So consider donating once, a small amount, and show that you care :)

Thanks!
https://www.indiegogo.com/projects/opencv-5-support-non-profit-open-source-cv-ai/x/3534730#/
How important is it?
https://scholar.google.com/scholar?q=opencv
Just Academia.

opencv, to ai
@opencv@mastodon.social avatar

DEADLINE EXTENDED-- we're pushing our campaign to keep OpenCV free to all into overtime with a 15-day extension to the original campaign.

Back us now: http://igg.me/at/opencv5

It's a very important time to show your support for open source computer vision and AI, so we can keep the future free for everyone and not locked up in private vaults at big companies.

rolle, to opensource
@rolle@mementomori.social avatar

I’m so tired of the capitalist argument that an open source project cannot be successful because it’s based on nonprofit or donations instead of vc funding and corporates.

Some people seem to actually believe in this narrative that Linux, Mozilla products and the Internet itself are all alive solely because of for-profit industries while forgetting that the actual people, inventors, universities and organisations do exist in this world. Also the contributing factors by companies do not nullify the brilliance of the original project. FFS, it is not all because of the money.

mwfc,
@mwfc@chaos.social avatar

@rolle
I am not sure I would include Linux in it, given that kernel work is really a lot of corporate work.

I consider a better example. A lot of academia goes into it and helps to foster a full ecosystem that is dependend on it. Yes, there are plenty of sponsors like Intel, but in its core it has been driven by academics for a long time.
And there are plenty of other ubiquous libraries. Maybe even products like
sadly is too, being neglected by funding for too long.

mwfc, to random
@mwfc@chaos.social avatar

extended their crowdfunder deadline

For me this is an important library. In a summerschool a prof told me: "you have to love every pixel" and exactly this is what I used it for. Many might argue, but isn't AI the CV way to go.
Yes and no. I worked on small FLIR images and am trying to do some small scale projects with mcus right now. We do not have endless compute. And we have certain time constraints. So preparing images can speed up as well.

Consider donating
https://www.indiegogo.com/projects/opencv-5-support-non-profit-open-source-cv-ai

mwfc, to random
@mwfc@chaos.social avatar

Looking at the 5 crowdfunder I am a bit sad.

I seriously do get that many cannot afford chipping in for important libraries. I do get that not everyone has 100 USD+ to spare and we are not big tech usually

Having seen demands of clear milestones and deliverables in the comments, I am a bit flabbergasted.
OpenCV did deliver. They delivered for a long time. They expanded into OpenCV University et al to acquire more funds

So consider donating to our infrastructure
https://www.indiegogo.com/projects/opencv-5-support-non-profit-open-source-cv-ai

mwfc, to community
@mwfc@chaos.social avatar

Do you know of a be it local or global, English, German or any other language? Kids doing great projects or adults dabbling into it for their weekend projects?

We would love to hear from you :)

There is an attempt to build a directory and help those communities gain visibility. After all the community is where the library is used and who needs what is great about OpenCV and where OpenCV lacks.

Like all open source it is a long trip and not a short sprint. So join us!

mwfc, to brazil
@mwfc@chaos.social avatar

"Hello, everyone! We are working on creating content and bringing visibility to the OpenCV 5 crowdfunding campaign! This weekend, we will have a talk with Alessandro de Oliveira Faria, a Brazillian Computer Vision Engineer who has contributed to OpenCV. We want to bring his history and inspire the Brazilian community to join us in this campaign."
Thanks for organizing this Natalia et al!

https://www.youtube.com/watch?v=BzYkHiWK7hU

opencv, to random
@opencv@mastodon.social avatar

Who Uses OpenCV? Snapchat, from Snap Inc. Snap has had massive success with their app, innovating in awesome augmented reality experiences and using OpenCV in their Android app. So far, they haven't become OpenCV members. Let's see if we can get their attention.
https://opencv.org/blog/who-uses-opencv-part-1-snap-inc-meta/

mempko, to machinelearning
@mempko@fosstodon.org avatar
evan, (edited ) to random
@evan@cosocial.ca avatar

How many Raspberry Pis are in your home right now?

JamesDBartlett3,
@JamesDBartlett3@techhub.social avatar

@NormanDunbar
Interesting! I wrote my first program on a graphing calculator sometime in the 1990s, so I've never gotten anywhere near "the bare metal" like some of y'all were doing in the 1980s, but I've still ended up with three boards, one , and two kits, so I must have caught the hardware bug somewhere along the line.

@evan @themagpi

opencv, to ai
@opencv@mastodon.social avatar

This Wednesday, join us for a special 4-HOUR live stream as we launch the crowdfunding campaign for OpenCV 5. We'll have live music, special guests, and are taking questions from the audience. #OpenCV #ComputerVision #AI #OpenSource https://youtube.com/live/y_Zr7n_4Pog

opencv, to ai
@opencv@mastodon.social avatar

In this edition of the OpenCV Newsletter: , a fresh episode of OpenCV Live for Open Hardware Month, and the PX4 Developer Summit!
https://www.linkedin.com/pulse/physical-future-open-source-everybody-loves-opencv-opencv

Brett_E_Carlock, to random
@Brett_E_Carlock@mastodon.online avatar

Do I have anyone in my wider network with skills in programming CUDA, SYCL, and OpenCL?

We want to determine feasibility of migrating CUDA-only code to SYCL (via SYCLomatic?): OpenCV feature detection/extraction modules (SIFT, HAGOG, ORB, AKAZE).

The intent is to upstream all feasible work.

This, hopefully, should stand to benefit everyone instead of being limited to NVIDIA.

Currently in info gathering/people connecting phase, not yet funded & ready to go.

mwfc, to random
@mwfc@chaos.social avatar

7h ROS Workshop beats 2h Data Science Webinar.
Sadly.

weekly still fits in tho :P

mwfc, to random
@mwfc@chaos.social avatar

Any recommendations for camera setups?
TKD or Karate katas.
Most likely distance to runner 6-8m, I would love lidar/stereo in some cases.
I need high quality for some stuff and some estimations.

I am considering atm 2 angles and Luxonis https://shop.luxonis.com/collections/oak-cameras-1/products/oak-d-lite-1

Which ofc are not that great, but I have them handy.
I will need stable Tripods for competitions and need gear to store the data away.
I most likely will try to record complete class, and give the others their fottage.

opencv, to ai
@opencv@mastodon.social avatar

In this edition of OpenCV's newsletter: Our next live stream on choosing an AI vendor, new weekly insights from OpenCV.AI, a new post about using the "AI for audio and video" library MediaPipe with Python, and a big OpenCV AI Competition milestone. https://www.linkedin.com/pulse/webinar-how-choose-ai-vendor-your-business-weekly-insights-more

opencv, to ai
@opencv@mastodon.social avatar

The latest episode of OpenCV Live, our streaming show hosted by CEO Dr. Satya Mallick and Director of Content & Creative @phil features Anomalib: A Deep Learning Library for Anomaly Detection https://youtu.be/658VmfX2cBE

kandid, to random
@kandid@chaos.social avatar

blaubeurer ring, tuesday, january 30, 2018, 8:56 PM CET

used a contour finder on several frames. Combining the contours later.

with

mwfc, to random
@mwfc@chaos.social avatar

Are there many kits for cheap or is there only the Crazyflie?

My hope is to have some indoor fun and be able to do some on a small swarm.
https://www.bitcraze.io/products/crazyflie-2-1/

For testing purposes a full 450 sized drone would be too much. (I think)

bleeptrack, to generative
@bleeptrack@vis.social avatar

"Art and Ice Cream" is my summer mood ☀️🍨 #generative

video/mp4

kandid,
@kandid@chaos.social avatar

@bleeptrack Das Eis im Partikelsturm.

  1. Versuch:

Der Kantendetektor stammt aus einem Beispiel. Er verwendet als Basis . Die Kantenerkennung läuft mit 15 fps.

https://gitlab.com/metagrowing/ana/-/blob/master/visual_server/src/shape/ShapeContour.cpp

Die Bewegung der Partikel interagiert mit den gefundenen Kanten. Wirkt sehr verrauscht.

  • All
  • Subscribed
  • Moderated
  • Favorites
  • megavids
  • GTA5RPClips
  • thenastyranch
  • ethstaker
  • everett
  • Durango
  • rosin
  • InstantRegret
  • DreamBathrooms
  • magazineikmin
  • Youngstown
  • mdbf
  • slotface
  • tacticalgear
  • JUstTest
  • kavyap
  • modclub
  • cisconetworking
  • cubers
  • ngwrru68w68
  • khanakhh
  • tester
  • anitta
  • normalnudes
  • Leos
  • osvaldo12
  • provamag3
  • lostlight
  • All magazines