Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
en.osm.town is one of the many independent Mastodon servers you can use to participate in the fediverse.
An independent, community of OpenStreetMap people on the Fediverse/Mastodon. Funding graciously provided by the OpenStreetMap Foundation.

Administered by:

Server stats:

267
active users

en.osm.town: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#computervision

1 post1 participant0 posts today
Public
RHET AI Center

✍ 📰 𝗨𝗻𝘀𝗲𝗿 𝗝𝗼𝘂𝗿𝗻𝗮𝗹𝗶𝘀𝘁-𝗶𝗻-𝗥𝗲𝘀𝗶𝗱𝗲𝗻𝗰𝗲-𝗣𝗿𝗼𝗴𝗿𝗮𝗺𝗺 𝗴𝗲𝗵𝘁 𝗶𝗻 𝗱𝗶𝗲 𝗻ä𝗰𝗵𝘀𝘁𝗲 𝗥𝘂𝗻𝗱𝗲

👩‍💻 Das Programm bietet Journalist:innen die Möglichkeit, in einem drei- bis sechsmonatigen, bezahlten Aufenthalt in Tübingen zu einem selbst gewählten Thema zu recherchieren.

🤖 Von uns gibt es Einführungen in Themen wie #MachineLearning, #ComputerVision und #Robotik

📧 Bitte bewerben Sie sich mit kurzem Ideenpapier, Anschreiben&Lebenslauf (DE o. ENG) 𝗯𝗶𝘀 𝟮𝟰.𝟬𝟰.𝟮𝟬𝟮𝟱
Bewerbungen bitte per E-Mail an janis.fischer@cyber-valley.de

Das Bild zeigt das Logo des Journalist-in-Residence Programms neben geometrischen Formen, die die Anfangsbuchstaben des Cyber Valleys bilden. Am unteren Bildrand sind die Logos des Cyber Valley, des RHET AI Center und der Volkswagen Stiftung abgebildet.
Public
Karsten Schmidt

To avoid a massive OpenCV dependency for a current project I'm involved in, I ended up porting my own homemade, naive optical flow code from 2008 and just released it as a new package. Originally this was written for a gestural UI system for Nokia retail stores (prior to the Microsoft takeover), the package readme contains another short video showing the flow field being utilized to rotate a 3D cube:

thi.ng/pixel-flow

I've also created a small new example project for testing with either webcam or videos:

demo.thi.ng/umbrella/optical-f

GIF
#ThingUmbrella#OpticalFlow#ImageAnalysis
Public
Albert Cardona

Anna Kreshuk always works on research questions that matter. Here, a method to quantitatively select the best existing neural network model for segmenting an image volume of a biological sample in the absence of any ground truth. Hats off!

"Ranking pre-trained segmentation models for zero-shot transferability", Talks & Kreshuk 2025
arxiv.org/html/2503.00450v1

"We focus on the unsupervised regime where no labels are available for the target dataset. Building on previous work linking model generalisation and consistency under perturbation, we propose the first unsupervised transferability estimator for semantic and instance segmentation tasks which doesn’t require access to source training data or target domain labels. "

arxiv.orgRanking pre-trained segmentation models for zero-shot transferability
#MachineLearning#ComputerVision
Public
deadprogram

Both of my talks from @fosdem last weekend are now available online.

"Return To Go Without Wires" about using Go/TinyGo to make your own AirTags without any Apple hardware:

cuddly.tube/w/p/2H3BJMkJZEJRUS

"Seeing Eye to Eye: Computer Vision using wasmVision" in the first ever WebAssembly dev room at FOSDEM:

video.fosdem.org/2025/k4601/fo

PeerTubeGo Devroom @ FOSDEM 2025By Go Devroom @ FOSDEM
#fosdem#fosdem2025#golang
Public *
JimmyChezPants

Hey #OpenCV #ComputerVision #Python

I would like to point a camera at an area of the house and have it announce when a dog has entered the camera frame.

I am quite handy with Python and can muddle my way through C-like stuff if I have good documentation or example code.

Is this easy or hard? Hard is not a dealbreaker, just trying to tune my expectations a bit.

edit: strictly speaking, it only needs to spot two dogs, that I have many photos of, but a generic dog detector would also be fine.

Public
Miguel Afonso Caetano

Beyond Fairness in Computer Vision: A Holistic Approach to
Mitigating Harms and Fostering Community-Rooted Computer
Vision Research

Timnit Gebru and Remi Denton

"ABSTRACT: The field of computer vision is now a multi-billion dollar enterprise, with its use in surveillance applications driving
this large market share. In the last six years, computer vision researchers have started to discuss the risks and harms of some of these systems, mostly using the lens of fairness introduced in the machine learning literature to perform this analysis. While this lens is useful to uncover and mitigate a narrow segment of the harms that can be enacted through computer vision systems, it is only one of the toolkits that researchers have available to uncover and mitigate the harms of the systems they build.

In this monograph, we discuss a wide range of risks and harms that can be enacted through the development and deployment of computer vision systems. We also discuss some existing technical approaches to mitigating these harms, as well as the shortcomings of these mitigation strategies.

Then, we introduce computer vision researchers to harm mitigation strategies proposed by journalists, human rights activists, individuals harmed by computer vision systems, and researchers in disciplines ranging from sociology to physics. We conclude the monograph by listing principles that researchers can follow to build what we call community rooted computer vision tools in the public interest, and give examples of such research directions. We hope that this monograph can serve as a starting point for researchers exploring the harms of current computer vision systems and attempting to steer the field into community-rooted work."

cdn.sanity.io/files/wc2kmxvk/r

#ComputerVision#STS#Surveillance
Public
Dr. Carlotta A. Berry, PhD

#AI #MachineLearning #BiasInAI #STEMSaturday #DeepLearning #ComputerVision #Robotics #ReinforcementLearning

Meet the editors of "Mitigating Bias in Machine Learning" Dr. Carlotta Berry and Dr. Brandeis Hill Marshall (Brandeis Marshall, PhD)
This practical guide shows, step by step, how to use machine learning to carry out actionable decisions that do not discriminate based on numerous human factors, including ethnicity and gender.
On Sale On Amazon a.co/d/dtMizVH

Public *
just a💧in my 🍺

Attention the #python PyPI package of the popular object detection model #YOLO in its implementation by #Ultralytics has been compromised.

There is an angoing investigation about the matter:

github.com/ultralytics/ultraly

For now it would be best do uninstall the package.

GitHubDiscrepancy between what's in GitHub and what's been published to PyPI for v8.3.41 · Issue #18027 · ultralytics/ultralyticsBy metrizable
#ComputerVision
Public
Dave

nianticlabs.com/news/largegeos

“Niantic is in a unique position to lead the way in making a Large Geospatial Model a reality, supported by more than a million user-contributed scans of real-world places we receive per week.” #Maps #ComputerVision

I’m curious whether this will go any further than LLMs have gone - or fall short. How valuable is a model like this without fully labeled, real-world objects & features?

nianticlabs.comBuilding a Large Geospatial Model to Achieve Spatial IntelligenceAt Niantic, we are pioneering the concept of a Large Geospatial Model that will use large-scale machine learning to understand a scene and connect it to millions of other scenes globally.
ExploreLive feeds
About