home.social

#machine-vision — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #machine-vision, aggregated by home.social.

fetched live
  1. Hey #MachineLearning / #MachineVision / #ComputerVision people.
    I want to setup a pet identification system with a surveillance camera that first detects a moving object, classifies it (optionally), and uses some heuristic to specify whether the bounding box of the movement detection is one of several pets.
    I don't want to pretrain a ML-model, I want to train the model guided - i.e. each time the object movement triggers, and a snapshot is created I want to assign a tag later.

  2. Hey #MachineLearning / #MachineVision / #ComputerVision people.
    I want to setup a pet identification system with a surveillance camera that first detects a moving object, classifies it (optionally), and uses some heuristic to specify whether the bounding box of the movement detection is one of several pets.
    I don't want to pretrain a ML-model, I want to train the model guided - i.e. each time the object movement triggers, and a snapshot is created I want to assign a tag later.

  3. Hey #MachineLearning / #MachineVision / #ComputerVision people.
    I want to setup a pet identification system with a surveillance camera that first detects a moving object, classifies it (optionally), and uses some heuristic to specify whether the bounding box of the movement detection is one of several pets.
    I don't want to pretrain a ML-model, I want to train the model guided - i.e. each time the object movement triggers, and a snapshot is created I want to assign a tag later.

  4. University of British Columbia: How camera-equipped homing pigeons could improve robotic vision in flight. “The system weighs just 27 grams and includes a miniature computer, about half the size of a credit card; a tiny modified commercial camera, a motion and orientation measurement unit and cables and electronics tape to reduce static during flight.”

    https://rbfirehose.com/2026/07/30/university-of-british-columbia-how-camera-equipped-homing-pigeons-could-improve-robotic-vision-in-flight/
  5. University of British Columbia: How camera-equipped homing pigeons could improve robotic vision in flight. “The system weighs just 27 grams and includes a miniature computer, about half the size of a credit card; a tiny modified commercial camera, a motion and orientation measurement unit and cables and electronics tape to reduce static during flight.”

    https://rbfirehose.com/2026/07/30/university-of-british-columbia-how-camera-equipped-homing-pigeons-could-improve-robotic-vision-in-flight/
  6. University of British Columbia: How camera-equipped homing pigeons could improve robotic vision in flight. “The system weighs just 27 grams and includes a miniature computer, about half the size of a credit card; a tiny modified commercial camera, a motion and orientation measurement unit and cables and electronics tape to reduce static during flight.”

    https://rbfirehose.com/2026/07/30/university-of-british-columbia-how-camera-equipped-homing-pigeons-could-improve-robotic-vision-in-flight/
  7. University of British Columbia: How camera-equipped homing pigeons could improve robotic vision in flight. “The system weighs just 27 grams and includes a miniature computer, about half the size of a credit card; a tiny modified commercial camera, a motion and orientation measurement unit and cables and electronics tape to reduce static during flight.”

    https://rbfirehose.com/2026/07/30/university-of-british-columbia-how-camera-equipped-homing-pigeons-could-improve-robotic-vision-in-flight/
  8. University of British Columbia: How camera-equipped homing pigeons could improve robotic vision in flight. “The system weighs just 27 grams and includes a miniature computer, about half the size of a credit card; a tiny modified commercial camera, a motion and orientation measurement unit and cables and electronics tape to reduce static during flight.”

    https://rbfirehose.com/2026/07/30/university-of-british-columbia-how-camera-equipped-homing-pigeons-could-improve-robotic-vision-in-flight/
  9. After facing down the (much feared) challenges of the day, I was even able to do something interesting by the afternoon, exploring the mysteries of camera lens calibration.

    (Posting this here chiefly as it was roundly ignored everywhere else online - I mean, I think it's cool!?)

    #machineVision #raspberryPi #creativeCoding

  10. After facing down the (much feared) challenges of the day, I was even able to do something interesting by the afternoon, exploring the mysteries of camera lens calibration.

    (Posting this here chiefly as it was roundly ignored everywhere else online - I mean, I think it's cool!?)

    #machineVision #raspberryPi #creativeCoding

  11. After facing down the (much feared) challenges of the day, I was even able to do something interesting by the afternoon, exploring the mysteries of camera lens calibration.

    (Posting this here chiefly as it was roundly ignored everywhere else online - I mean, I think it's cool!?)

    #machineVision #raspberryPi #creativeCoding

  12. After facing down the (much feared) challenges of the day, I was even able to do something interesting by the afternoon, exploring the mysteries of camera lens calibration.

    (Posting this here chiefly as it was roundly ignored everywhere else online - I mean, I think it's cool!?)

    #machineVision #raspberryPi #creativeCoding

  13. After facing down the (much feared) challenges of the day, I was even able to do something interesting by the afternoon, exploring the mysteries of camera lens calibration.

    (Posting this here chiefly as it was roundly ignored everywhere else online - I mean, I think it's cool!?)

    #machineVision #raspberryPi #creativeCoding

  14. University of Stuttgart: Innovative Algorithms for species conservation. “Patterns reveal the individual: The AI algorithm RAPID identifies wild animals by their unique patterns in real time. It works quickly and precisely, enabling significant progress in the monitoring and protection of

    https://rbfirehose.com/2026/06/29/university-of-stuttgart-innovative-algorithms-for-species-conservation/
  15. University of Stuttgart: Innovative Algorithms for species conservation. “Patterns reveal the individual: The AI algorithm RAPID identifies wild animals by their unique patterns in real time. It works quickly and precisely, enabling significant progress in the monitoring and protection of

    https://rbfirehose.com/2026/06/29/university-of-stuttgart-innovative-algorithms-for-species-conservation/
  16. University of Stuttgart: Innovative Algorithms for species conservation. “Patterns reveal the individual: The AI algorithm RAPID identifies wild animals by their unique patterns in real time. It works quickly and precisely, enabling significant progress in the monitoring and protection of

    https://rbfirehose.com/2026/06/29/university-of-stuttgart-innovative-algorithms-for-species-conservation/
  17. University of Stuttgart: Innovative Algorithms for species conservation. “Patterns reveal the individual: The AI algorithm RAPID identifies wild animals by their unique patterns in real time. It works quickly and precisely, enabling significant progress in the monitoring and protection of

    https://rbfirehose.com/2026/06/29/university-of-stuttgart-innovative-algorithms-for-species-conservation/
  18. University of Stuttgart: Innovative Algorithms for species conservation. “Patterns reveal the individual: The AI algorithm RAPID identifies wild animals by their unique patterns in real time. It works quickly and precisely, enabling significant progress in the monitoring and protection of

    https://rbfirehose.com/2026/06/29/university-of-stuttgart-innovative-algorithms-for-species-conservation/
  19. Naver Labs Unveils ‘DUNE’ to Run AI Robots on Less Memory

    The robot developed by Naver and the Divine logo. Photo courtesy of Naver Naver Labs Europe on Monday…
    #EuropeSays #Korea #KR #Naver #AIrobots #DUNE #machinevision #multi-teacherdistillation #NaverLabs #physicalai #robotmemoryefficiency #universalencoder
    europesays.com/korea/61385/

  20. MIT News: MIT researchers teach AI models to interpret charts. “…researchers from MIT and the MIT-IBM Computing Research Lab developed a multifaceted resource for AI users that is specifically designed to teach vision-language models (VLMs) how to effectively interpret charts. They used a novel data generation method to build a state-of-the-art dataset that includes more than a million varied […]

    https://rbfirehose.com/2026/06/05/mit-news-mit-researchers-teach-ai-models-to-interpret-charts/
  21. MIT News: MIT researchers teach AI models to interpret charts. “…researchers from MIT and the MIT-IBM Computing Research Lab developed a multifaceted resource for AI users that is specifically designed to teach vision-language models (VLMs) how to effectively interpret charts. They used a novel data generation method to build a state-of-the-art dataset that includes more than a million varied […]

    https://rbfirehose.com/2026/06/05/mit-news-mit-researchers-teach-ai-models-to-interpret-charts/
  22. MIT News: MIT researchers teach AI models to interpret charts. “…researchers from MIT and the MIT-IBM Computing Research Lab developed a multifaceted resource for AI users that is specifically designed to teach vision-language models (VLMs) how to effectively interpret charts. They used a novel data generation method to build a state-of-the-art dataset that includes more than a million varied […]

    https://rbfirehose.com/2026/06/05/mit-news-mit-researchers-teach-ai-models-to-interpret-charts/
  23. MIT News: MIT researchers teach AI models to interpret charts. “…researchers from MIT and the MIT-IBM Computing Research Lab developed a multifaceted resource for AI users that is specifically designed to teach vision-language models (VLMs) how to effectively interpret charts. They used a novel data generation method to build a state-of-the-art dataset that includes more than a million varied […]

    https://rbfirehose.com/2026/06/05/mit-news-mit-researchers-teach-ai-models-to-interpret-charts/
  24. MIT News: MIT researchers teach AI models to interpret charts. “…researchers from MIT and the MIT-IBM Computing Research Lab developed a multifaceted resource for AI users that is specifically designed to teach vision-language models (VLMs) how to effectively interpret charts. They used a novel data generation method to build a state-of-the-art dataset that includes more than a million varied […]

    https://rbfirehose.com/2026/06/05/mit-news-mit-researchers-teach-ai-models-to-interpret-charts/
  25. #Tinder Plans to Let #AI Scan Your #Camera Roll

    Tinder plans to let machine vision #algorithms loose on your camera roll. Instead of building a profile on their own, AI will scan users’ locally-stored photos—everything from gym #selfies to pictures of their family, sensitive documents and dick pics—to help construct profiles by determining what users’ interests and values are.
    #privacy #security #dating #romance #machinevision

    404media.co/tinder-plans-to-le

  26. #Tinder Plans to Let #AI Scan Your #Camera Roll

    Tinder plans to let machine vision #algorithms loose on your camera roll. Instead of building a profile on their own, AI will scan users’ locally-stored photos—everything from gym #selfies to pictures of their family, sensitive documents and dick pics—to help construct profiles by determining what users’ interests and values are.
    #privacy #security #dating #romance #machinevision

    404media.co/tinder-plans-to-le

  27. #Tinder Plans to Let #AI Scan Your #Camera Roll

    Tinder plans to let machine vision #algorithms loose on your camera roll. Instead of building a profile on their own, AI will scan users’ locally-stored photos—everything from gym #selfies to pictures of their family, sensitive documents and dick pics—to help construct profiles by determining what users’ interests and values are.
    #privacy #security #dating #romance #machinevision

    404media.co/tinder-plans-to-le

  28. Plans to Let Scan Your Roll

    Tinder plans to let machine vision loose on your camera roll. Instead of building a profile on their own, AI will scan users’ locally-stored photos—everything from gym to pictures of their family, sensitive documents and dick pics—to help construct profiles by determining what users’ interests and values are.

    404media.co/tinder-plans-to-le

  29. #Tinder Plans to Let #AI Scan Your #Camera Roll

    Tinder plans to let machine vision #algorithms loose on your camera roll. Instead of building a profile on their own, AI will scan users’ locally-stored photos—everything from gym #selfies to pictures of their family, sensitive documents and dick pics—to help construct profiles by determining what users’ interests and values are.
    #privacy #security #dating #romance #machinevision

    404media.co/tinder-plans-to-le

  30. University of Exeter: Wildlife imaging shows that AI models aren’t as smart as we think. “Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across ecosystems and settings, much in the same way as human observers. But in a new article, two University of Exeter researchers argue that this is based on a ‘flawed assumption’.”

    https://rbfirehose.com/2026/03/07/university-of-exeter-wildlife-imaging-shows-that-ai-models-arent-as-smart-as-we-think/
  31. University of Exeter: Wildlife imaging shows that AI models aren’t as smart as we think. “Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across ecosystems and settings, much in the same way as human observers. But in a new article, two University of Exeter researchers argue that this is based on a ‘flawed assumption’.”

    https://rbfirehose.com/2026/03/07/university-of-exeter-wildlife-imaging-shows-that-ai-models-arent-as-smart-as-we-think/
  32. University of Exeter: Wildlife imaging shows that AI models aren’t as smart as we think. “Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across ecosystems and settings, much in the same way as human observers. But in a new article, two University of Exeter researchers argue that this is based on a ‘flawed assumption’.”

    https://rbfirehose.com/2026/03/07/university-of-exeter-wildlife-imaging-shows-that-ai-models-arent-as-smart-as-we-think/
  33. University of Exeter: Wildlife imaging shows that AI models aren’t as smart as we think. “Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across ecosystems and settings, much in the same way as human observers. But in a new article, two University of Exeter researchers argue that this is based on a ‘flawed assumption’.”

    https://rbfirehose.com/2026/03/07/university-of-exeter-wildlife-imaging-shows-that-ai-models-arent-as-smart-as-we-think/
  34. Automation is moving from “perfectly placed parts” to real-world randomness — mixed bins, uneven shapes, variable orientation.
    know more: zurl.co/3Skrb
    #Smidmart #SmartGrippers #Cobots #Robotics #MachineVision #3DVision

  35. Automation is moving from “perfectly placed parts” to real-world randomness — mixed bins, uneven shapes, variable orientation.
    know more: zurl.co/3Skrb
    #Smidmart #SmartGrippers #Cobots #Robotics #MachineVision #3DVision

  36. Automation is moving from “perfectly placed parts” to real-world randomness — mixed bins, uneven shapes, variable orientation.
    know more: zurl.co/3Skrb
    #Smidmart #SmartGrippers #Cobots #Robotics #MachineVision #3DVision

  37. Q42 Research: Expanding visual search for online art collections. “Ever wanted to find artworks containing a specific object? Like a particular vase, animal, or architectural element across an art collection? I made this a reality by combining two machine learning models during my graduation research project for Q42 and University of Applied Sciences Windesheim.”

    https://rbfirehose.com/2026/01/27/q42-research-expanding-visual-search-for-online-art-collections/
  38. Q42 Research: Expanding visual search for online art collections. “Ever wanted to find artworks containing a specific object? Like a particular vase, animal, or architectural element across an art collection? I made this a reality by combining two machine learning models during my graduation research project for Q42 and University of Applied Sciences Windesheim.”

    https://rbfirehose.com/2026/01/27/q42-research-expanding-visual-search-for-online-art-collections/