Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I received a message in my direct messages asking how difficult it would be to use computer vision to track cell movement. > SAM zero shot for the immune cell > YOLO finetuned on a small dataset for bacteria Realization time: ~2 hours

Marco Franzon

15,213 subscribers

188,212 views • 2 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

> I meet every requirement for 𝕏 monetisation, yet I’ve never bought a blue tick,the last one was gifted > I use 𝕏 purely for love of the game and to cook hijda IT cell

> I meet every requirement for 𝕏 monetisation, yet I’ve never bought a blue tick,the last one was gifted > I use 𝕏 purely for love of the game and to cook hijda IT cell

ghatak

18,089 views • 10 days ago

AN $8 ESP32 IS RUNNING LOCAL AI WITH ZERO LATENCY A creator deployed a computer vision model on an ESP32 microcontroller to track human movement locally in real time, showing what’s possible without a GPU.

AN $8 ESP32 IS RUNNING LOCAL AI WITH ZERO LATENCY A creator deployed a computer vision model on an ESP32 microcontroller to track human movement locally in real time, showing what’s possible without a GPU.

0xMarioNawfal

58,032 views • 20 days ago

i trained this computer vision model just by asking for "tennis players", using roboflow rapid and SAM3 the model picks out Alcaraz and Sinner, while correctly avoiding the ball boys and fans then I exported the model to python and wrote a script to filter the data, track movement history, and annotate the final video this was a quick experiment but I could expand the project to track player speeds, distance covered, shot count, etc. could use this for a sports analytics app that tracks live matches and calculates custom metrics

i trained this computer vision model just by asking for "tennis players", using roboflow rapid and SAM3 the model picks out Alcaraz and Sinner, while correctly avoiding the ball boys and fans then I exported the model to python and wrote a script to filter the data, track movement history, and annotate the final video this was a quick experiment but I could expand the project to track player speeds, distance covered, shot count, etc. could use this for a sports analytics app that tracks live matches and calculates custom metrics

AA

293,837 views • 8 months ago

this creator just built a zero-delay auto-aim system on an $8 microcontroller he deployed a custom local AI algorithm on a cheap ESP-32 to track human movement with absolute 0-pixel accuracy. the system completely eliminates standard computation delay. it processes the bounding box and moves the sniper reticle instantly, locking onto the target in real time. the next step is hooking it up to a physical robotic arm. it proves you don't need a massive GPU rig to run complex computer vision. 1. runs locally on a microcontroller 2. local AI inference for zero latency 3. 100% targeting precision when an eight-dollar chip can track movement with zero latency, AI becomes dangerous local infrastructure. this article breaks down exactly how the ESP-32 is powering this physical hardware shift.

this creator just built a zero-delay auto-aim system on an $8 microcontroller he deployed a custom local AI algorithm on a cheap ESP-32 to track human movement with absolute 0-pixel accuracy. the system completely eliminates standard computation delay. it processes the bounding box and moves the sniper reticle instantly, locking onto the target in real time. the next step is hooking it up to a physical robotic arm. it proves you don't need a massive GPU rig to run complex computer vision. 1. runs locally on a microcontroller 2. local AI inference for zero latency 3. 100% targeting precision when an eight-dollar chip can track movement with zero latency, AI becomes dangerous local infrastructure. this article breaks down exactly how the ESP-32 is powering this physical hardware shift.

ard

1,181,640 views • 21 days ago

I fear it might be time for me to graduate my shorts from a size small to a size medium 😔

I fear it might be time for me to graduate my shorts from a size small to a size medium 😔

lil guy

648,601 views • 11 months ago

1. Fat shaming is mean, even when directed at fictional intergalactic gangsters. 2. My DMs are open, my email follows the Globe's pattern. Message me for my cell, then use that number to find me on Signal and WhatsApp. Let's chat!

1. Fat shaming is mean, even when directed at fictional intergalactic gangsters. 2. My DMs are open, my email follows the Globe's pattern. Message me for my cell, then use that number to find me on Signal and WhatsApp. Let's chat!

Carrie Tait

31,639 views • 4 months ago

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

Peter Gostev

105,642 views • 3 months ago

Six years ago, the martyred leader, in response to a message from Trump, said: “I have no direct message for Trump, because I do not even consider him worthy of exchanging messages.”

Six years ago, the martyred leader, in response to a message from Trump, said: “I have no direct message for Trump, because I do not even consider him worthy of exchanging messages.”

Iran Embassy Sarajevo

263,584 views • 2 months ago

This library turns “I know how the shot should feel, but I can’t describe it” into a visual reference and a ready-to-use camera movement prompt in seconds Pick the movement Copy the prompt Stop wasting generations trying to explain the camera It looks like a small tool But small tools like this often become the pages people save, share and quietly return to whenever the same problem appears again That is how useful content starts becoming an asset instead of another post lost in the feed I explored the wider system behind that idea in the article below Save this for your next shot

This library turns “I know how the shot should feel, but I can’t describe it” into a visual reference and a ready-to-use camera movement prompt in seconds Pick the movement Copy the prompt Stop wasting generations trying to explain the camera It looks like a small tool But small tools like this often become the pages people save, share and quietly return to whenever the same problem appears again That is how useful content starts becoming an asset instead of another post lost in the feed I explored the wider system behind that idea in the article below Save this for your next shot

Cip⚡️

12,661 views • 1 month ago

i built a telegram bot that turns your social media feed into an agent brain how it works: > send content to the bot > bot stores content on obsidian > use obsidian file path for your agents context the smarter the brain the smarter the agent

i built a telegram bot that turns your social media feed into an agent brain how it works: > send content to the bot > bot stores content on obsidian > use obsidian file path for your agents context the smarter the brain the smarter the agent

sophia

40,475 views • 4 months ago

I haven’t seen my mother for 13 years. The Islamic Republic interrogated her for 2 hours to stop her from sharing her love with me. In a rally in Italy, I saw a young girl holding my mom’s picture to show her support. You have to be an immigrant to understand this movement 💔

I haven’t seen my mother for 13 years. The Islamic Republic interrogated her for 2 hours to stop her from sharing her love with me. In a rally in Italy, I saw a young girl holding my mom’s picture to show her support. You have to be an immigrant to understand this movement 💔

Masih Alinejad

408,548 views • 3 years ago

It is difficult to describe the pure joy that would fill my heart if I saw this sign during a walk. I would be standing there for the duration. 😂🥰🐾

It is difficult to describe the pure joy that would fill my heart if I saw this sign during a walk. I would be standing there for the duration. 😂🥰🐾

SULLY

125,649 views • 7 months ago

"I would like to use the rest of my time to say how appalled I am that people are bringing up the Holocaust. Do not use other genocide to describe this one!" A Freudian slip took place during a special city council meeting in Burlington on Monday, which voted not to pass a formal pledge to call for a ceasefire in Gaza.

"I would like to use the rest of my time to say how appalled I am that people are bringing up the Holocaust. Do not use other genocide to describe this one!" A Freudian slip took place during a special city council meeting in Burlington on Monday, which voted not to pass a formal pledge to call for a ceasefire in Gaza.

Quds News Network

140,688 views • 2 years ago

i picked the best time ever to double down on content creation lmao if i dont like my outfit…i can just change it????? done in Premiere > Higgsfield Extension > Seedance 2

i picked the best time ever to double down on content creation lmao if i dont like my outfit…i can just change it????? done in Premiere > Higgsfield Extension > Seedance 2

techbimbo

79,537 views • 2 months ago

Codex + 5.5 + computer use built me an iPhone shortcut to make it easy to use GPT Image 2 on any photo in my camera roll. Then it edited this screen recording with ffmpeg to speed it up so I could share it. Great for making quick UI mocks on my phone. And for lulz.

Codex + 5.5 + computer use built me an iPhone shortcut to make it easy to use GPT Image 2 on any photo in my camera roll. Then it edited this screen recording with ffmpeg to speed it up so I could share it. Great for making quick UI mocks on my phone. And for lulz.

Ilya Abyzov

45,451 views • 3 months ago

MORE ARRESTS Arrests are now happening in Cambridge under the Terrorism Act. This rain-poncho-clad woman is arrested for holding a sign with the words “I oppose genocide - I support Palestine Action” on it. She is taken to a police van and is expected to be put in a cell.

MORE ARRESTS Arrests are now happening in Cambridge under the Terrorism Act. This rain-poncho-clad woman is arrested for holding a sign with the words “I oppose genocide - I support Palestine Action” on it. She is taken to a police van and is expected to be put in a cell.

Defend Our Juries

18,166 views • 8 months ago