Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

AI FOOTBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. You upload a regular match video. No sensors, no GPS trackers, just camera footage. The neural network finds every player, referee, and ball on its own. Every frame, in real time. KMeans clustering breaks down... jersey colors pixel by pixel. The system splits players into teams automatically. Without a single manual hint. Optical Flow tracks camera movement. Separates it from player movement. Perspective Transformation converts pixels into real meters. Speed of every player. Distance covered. Ball possession percentage. All calculated automatically. Four hours of tutorial from zero to a working system. The model is trained on real Bundesliga matches. Runs on a regular GPU. Python code - take it and run. Sports analytics is no longer behind closed doors. AI leveled the playing field.show more

zostaff

15,999 subscribers

1,076,435 Aufrufe • vor 4 Monaten •via X (Twitter)

Wissenschaft & Technologie Sport

Anya Rossi• Live Now

Private livecam show

36 Kommentare

Profilbild von YabsssAI

YabsssAIvor 4 Monaten

finding every player, referee, and ball in every frame of a match video with computer vision is a tall order, how do you handle occlusion or situations where the ball is partially out of frame with your yolo and opencv setup

Profilbild von Zakaria

Zakariavor 4 Monaten

That’s just an outdated video from codeinajiffy on youtube, stop taking credit for something you didn’t do.

Profilbild von zostaff

zostaffvor 4 Monaten

Answer me one question - where does it say that I did this?

Profilbild von Zakaria

Zakariavor 4 Monaten

You display the content as yours, without crediting the one who posted it. That’s plagiarism

Profilbild von Vincent Tervooren 🇨🇭 🇫🇷

Vincent Tervooren 🇨🇭 🇫🇷vor 4 Monaten

Can it replace Arteta? Asking for an Arsenal fan

Profilbild von zostaff

zostaffvor 4 Monaten

trading here: my tg channel:

Profilbild von shmidt

shmidtvor 4 Monaten

the fact that you can now build this with just python and a gpu changes everything for smaller clubs

Profilbild von Luke The Dev

Luke The Devvor 4 Monaten

Just like this one 😂

Profilbild von QuiqueTAMAYO🌳

QuiqueTAMAYO🌳vor 4 Monaten

What's truly incredible is that you haven't reached your usage limits.

Profilbild von @andresio

@andresiovor 4 Monaten

That is pretty cool! I will check it. I am building a commentators system for video games but with the passion of soccer commentators

Profilbild von TheSaid

TheSaidvor 4 Monaten

can it be used to detect offsides in realtime?

Profilbild von Neural Times

Neural Timesvor 4 Monaten

guess that's why they call it real-time, because the python script just magically knows how many meters a player ran without sensors who knew optical flow could turn pixels into actual speed metrics for free

Profilbild von Leto

Letovor 4 Monaten

0 edge bro wrong sport. pick something that hasnt been done yet.

Profilbild von palmer // not for everyone

palmer // not for everyonevor 4 Monaten

@huge_flood

Profilbild von slash1s

slash1svor 4 Monaten

this so smart to use AI to analyse football 🙌

Profilbild von cristal💎

cristal💎vor 4 Monaten

the fact that this runs without sensors or gps is a literal game changer for sunday leagues

Profilbild von Parletto

Parlettovor 4 Monaten

seems this setup is very possible to build for everyone

Profilbild von Philip vN

Philip vNvor 4 Monaten

When will it convert to a volumetric video (3DGS) that One can explore navigate in immersive VR?

Profilbild von Faiz

Faizvor 4 Monaten

This is seriously impressive — turning raw match footage into structured data like this is insane. Also built something along similar lines — an agentic football social network ⚽ Focused more on simulating the conversation layer around the game.

Profilbild von vvtentt

vvtenttvor 4 Monaten

This already looks like something impossible

Profilbild von ProTech💀

ProTech💀vor 4 Monaten

lmao who is falling for this 🤣

Profilbild von Neural Drop

Neural Dropvor 4 Monaten

kmeans on jersey colors sounds like a disaster waiting for any player to wear the same kit as the ref, and optical flow is notoriously bad at separating camera shake from actual movement without heavy calibration

Profilbild von Sella 📈

Sella 📈vor 4 Monaten

@tropianhs when are you cooking 🤣 polymarket and betting sites spreads are real edges today

Profilbild von Pedro Speranza

Pedro Speranzavor 4 Monaten

@yanpntes fique rico meu amigo

Profilbild von AI Automation Mastery

AI Automation Masteryvor 4 Monaten

Four hours of tutorial for something like this is wild value. Bookmarking this immediately.

Profilbild von NightWing 🇲🇽

NightWing 🇲🇽vor 4 Monaten

There’s already an open source library for this

Profilbild von Toonish

Toonishvor 4 Monaten

Really want to use this on Sunday league

Profilbild von Terhile

Terhilevor 4 Monaten

Wow

Profilbild von Fr3iJ@ck

Fr3iJ@ckvor 4 Monaten

@apoka @VelhoVamp1 olhem isso!

Profilbild von Noé

Noévor 4 Monaten

@Blxncx_4

Profilbild von Walter P. Chen

Walter P. Chenvor 4 Monaten

I need to do this for baseball!

Profilbild von AI Mastery Guide

AI Mastery Guidevor 4 Monaten

The optical flow + perspective transformation combo is clever. How well does it hold up with handheld or broadcast cameras that pan a lot? Curious about the accuracy drop.

Profilbild von Rafael Pimenta ®️

Rafael Pimenta ®️vor 4 Monaten

E o consumo de token disso?

Profilbild von Snowball Money

Snowball Moneyvor 4 Monaten

complex systems can be simple to use when the tech is invisible and the interface is clean

Profilbild von Hrundel75 🐷

Hrundel75 🐷vor 4 Monaten

Crazy what AI can do nowadays

Profilbild von Kyle Holmberg

Kyle Holmbergvor 4 Monaten

this is a really, really good thing. go on and kill OptaJoe. make data accessible again!

Ähnliche Videos

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

zostaff

230,988 Aufrufe • vor 4 Monaten

AI TENNIS ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, PYTORCH, AND KEYPOINT EXTRACTION. Take any tennis match broadcast, any camera angle, any resolution. Feed it into the pipeline. YOLO detects both players and the tennis ball frame by frame. No manual labeling, no pre-annotated dataset. A fine-tuned YOLOv5 model trained on a Roboflow tennis ball dataset handles the ball - the hardest object to track in any sport. Tiny, fast, constantly occluded. The model finds it anyway. Trackers maintain identity across frames so Player 1 stays Player 1 from the first serve to match point. But detection is just the start. A ResNet50 CNN trained in PyTorch predicts court keypoints from every frame - the corners, service lines, baselines, net posts. Fourteen points that define the entire playing surface geometry. From those keypoints the system builds a homography matrix and warps the broadcast perspective into a top-down mini court with real coordinates. Now every player has a position in real space, not pixel space. Every frame becomes a measurement. Every rally becomes a dataset. Player movement speed - calculated from position deltas between frames, converted to meters per second through the homography. Ball shot speed - measured from the ball trajectory across consecutive detections. Number of shots per rally - counted automatically through ball direction changes. All of this rendered live on the video as an overlay. A mini court in the corner showing both players as dots moving in real time. Stats updating after every point. OpenCV handles the rendering. Pandas handles the math. PyTorch handles the intelligence. YOLO handles the eyes. No Hawkeye subscription, no court-embedded sensors, no tracking chips in the ball. A Python script, a trained model, and a GPU. The full code is on GitHub. The tutorial walks through every module - from ball detector training to court keypoint extraction to the final statistical overlay. Professional teams used to need broadcast deals and proprietary hardware for this kind of analysis. Now you build it in an afternoon with open-source tools. Trading here: Computer vision didn't just enter tennis. It made the expensive stuff free.

AI TENNIS ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, PYTORCH, AND KEYPOINT EXTRACTION. Take any tennis match broadcast, any camera angle, any resolution. Feed it into the pipeline. YOLO detects both players and the tennis ball frame by frame. No manual labeling, no pre-annotated dataset. A fine-tuned YOLOv5 model trained on a Roboflow tennis ball dataset handles the ball - the hardest object to track in any sport. Tiny, fast, constantly occluded. The model finds it anyway. Trackers maintain identity across frames so Player 1 stays Player 1 from the first serve to match point. But detection is just the start. A ResNet50 CNN trained in PyTorch predicts court keypoints from every frame - the corners, service lines, baselines, net posts. Fourteen points that define the entire playing surface geometry. From those keypoints the system builds a homography matrix and warps the broadcast perspective into a top-down mini court with real coordinates. Now every player has a position in real space, not pixel space. Every frame becomes a measurement. Every rally becomes a dataset. Player movement speed - calculated from position deltas between frames, converted to meters per second through the homography. Ball shot speed - measured from the ball trajectory across consecutive detections. Number of shots per rally - counted automatically through ball direction changes. All of this rendered live on the video as an overlay. A mini court in the corner showing both players as dots moving in real time. Stats updating after every point. OpenCV handles the rendering. Pandas handles the math. PyTorch handles the intelligence. YOLO handles the eyes. No Hawkeye subscription, no court-embedded sensors, no tracking chips in the ball. A Python script, a trained model, and a GPU. The full code is on GitHub. The tutorial walks through every module - from ball detector training to court keypoint extraction to the final statistical overlay. Professional teams used to need broadcast deals and proprietary hardware for this kind of analysis. Now you build it in an afternoon with open-source tools. Trading here: Computer vision didn't just enter tennis. It made the expensive stuff free.

zostaff

120,370 Aufrufe • vor 4 Monaten

9 repos that mass replace a $150,000/year NBA analytics department. all free. all open source. -> replaces Second Spectrum and SportVU YOLO tracks every player and ball from any broadcast. assigns teams by jersey color. court keypoint detection builds a tactical top-down map. speed, distance, passes - all from a TV feed. no sensors. -> replaces paid NBA prediction services ($100/mo) XGBoost + Neural Net. moneyline and totals. Kelly Criterion sizing. 69% accuracy. pulls odds from FanDuel/DraftKings automatically. the most starred NBA betting repo on GitHub. -> replaces an entire quant sports desk 5-model ensemble: XGBoost + PyTorch MLP + Ridge + Lasso + baseline. Optuna-tuned hyperparameters. SQLite database with box scores, play-by-play, betting lines, injury reports. production-grade. -> replaces manual daily prediction workflows XGBoost/LightGBM with GitHub Actions automation. scrapes new data, retrains models, outputs daily win probabilities. set it and forget it. -> replaces ELO subscription services custom ELO + Ridge + XGBoost + Neural Networks ensemble. full data scraping pipeline. comprehensive visualizations. FiveThirtyEight-style ratings from scratch. -> replaces Four Factors analytics dashboards ELO rating system + Four Factors + PCA dimensionality reduction. detailed comparison of 10+ models. honest 65.3% accuracy - because that's what real NBA prediction looks like. -> replaces computer vision analytics platforms ($500/mo) YOLO player/ball tracking. automatic team assignment. court keypoints. pass and interception detection. speed and distance. full tactical view. modular architecture. -> replaces shot tracking hardware YOLOv8 detects ball and hoop in real-time. linear regression predicts trajectory. registers makes and misses automatically. works on any video feed. -> replaces paid sports data subscriptions ($300/mo) official Python client for NBA. com API. box scores, play-by-play, shot charts, player tracking. 40+ years of data. zero cost. the foundation every NBA ML project is built on. like + bookmark you'll need this when you build your first NBA prediction bot

9 repos that mass replace a $150,000/year NBA analytics department. all free. all open source. -> replaces Second Spectrum and SportVU YOLO tracks every player and ball from any broadcast. assigns teams by jersey color. court keypoint detection builds a tactical top-down map. speed, distance, passes - all from a TV feed. no sensors. -> replaces paid NBA prediction services ($100/mo) XGBoost + Neural Net. moneyline and totals. Kelly Criterion sizing. 69% accuracy. pulls odds from FanDuel/DraftKings automatically. the most starred NBA betting repo on GitHub. -> replaces an entire quant sports desk 5-model ensemble: XGBoost + PyTorch MLP + Ridge + Lasso + baseline. Optuna-tuned hyperparameters. SQLite database with box scores, play-by-play, betting lines, injury reports. production-grade. -> replaces manual daily prediction workflows XGBoost/LightGBM with GitHub Actions automation. scrapes new data, retrains models, outputs daily win probabilities. set it and forget it. -> replaces ELO subscription services custom ELO + Ridge + XGBoost + Neural Networks ensemble. full data scraping pipeline. comprehensive visualizations. FiveThirtyEight-style ratings from scratch. -> replaces Four Factors analytics dashboards ELO rating system + Four Factors + PCA dimensionality reduction. detailed comparison of 10+ models. honest 65.3% accuracy - because that's what real NBA prediction looks like. -> replaces computer vision analytics platforms ($500/mo) YOLO player/ball tracking. automatic team assignment. court keypoints. pass and interception detection. speed and distance. full tactical view. modular architecture. -> replaces shot tracking hardware YOLOv8 detects ball and hoop in real-time. linear regression predicts trajectory. registers makes and misses automatically. works on any video feed. -> replaces paid sports data subscriptions ($300/mo) official Python client for NBA. com API. box scores, play-by-play, shot charts, player tracking. 40+ years of data. zero cost. the foundation every NBA ML project is built on. like + bookmark you'll need this when you build your first NBA prediction bot

zostaff

103,649 Aufrufe • vor 4 Monaten

THIS GUY JUST BUILT A DRONE THAT TRACKS TARGETS WITH A LASER USING CLAUDE > No robotics team > No engineering degree > No budget He used Claude Code to write the entire system in Python - a drone that locks onto a target, follows it with a laser and corrects its own aim automatically after every attempt. The AI gets more accurate the longer it runs because it learns from every single shot. He's still improving it and this is only the beginning. You have the same tool he used. The article below is about how to actually use it to its full potential.

THIS GUY JUST BUILT A DRONE THAT TRACKS TARGETS WITH A LASER USING CLAUDE > No robotics team > No engineering degree > No budget He used Claude Code to write the entire system in Python - a drone that locks onto a target, follows it with a laser and corrects its own aim automatically after every attempt. The AI gets more accurate the longer it runs because it learns from every single shot. He's still improving it and this is only the beginning. You have the same tool he used. The article below is about how to actually use it to its full potential.

Anatoli Kopadze

276,199 Aufrufe • vor 4 Monaten

21 years old. Alone. In just 6 weeks, he built what NBA clubs pay $120,000 a year for. No team. No lab. Right from his apartment. He took what used to require an entire room of analysts and handed it over to a neural network. The camera watches the court and the machine does the rest: → Recognizes all 10 players simultaneously in real time, tagging names and numbers on the fly without losing track of them in motion. → Boosted jersey number accuracy from 56% to 93% after fine-tuning. → Calculates the exact distance to the nearest defender at the release point (4 feet, 16, 30) and instantly gauges how open the player is. → Logs shot type, court position, and outcome (make or miss) completely automatically. → Identifies a player even when they are fully occluded. Tracks the ball even when it's in the referee's hand. → Zero manual labeling. Zero human verification. 5 models in the stack, trained on 2,400 playoff clips. Something professional clubs pay a full specialist's annual salary for. I put this out for free. The bottleneck in sports analytics is no longer data or speed. It’s the human. And he removed it. Save this.

21 years old. Alone. In just 6 weeks, he built what NBA clubs pay $120,000 a year for. No team. No lab. Right from his apartment. He took what used to require an entire room of analysts and handed it over to a neural network. The camera watches the court and the machine does the rest: → Recognizes all 10 players simultaneously in real time, tagging names and numbers on the fly without losing track of them in motion. → Boosted jersey number accuracy from 56% to 93% after fine-tuning. → Calculates the exact distance to the nearest defender at the release point (4 feet, 16, 30) and instantly gauges how open the player is. → Logs shot type, court position, and outcome (make or miss) completely automatically. → Identifies a player even when they are fully occluded. Tracks the ball even when it's in the referee's hand. → Zero manual labeling. Zero human verification. 5 models in the stack, trained on 2,400 playoff clips. Something professional clubs pay a full specialist's annual salary for. I put this out for free. The bottleneck in sports analytics is no longer data or speed. It’s the human. And he removed it. Save this.

Ridark

16,251 Aufrufe • vor 2 Monaten

How a 24-year-old programmer from Portugal made $18,200 in a month on football betting He created an AI analyst that finds flaws in bookmakers' live lines in real time and delivers predictions with an 84% win rate. Costs: $0 (Used free APIs and Windsurf IDE) He launched a Python script that maps out match videos in real time: Top layer: A Computer Vision algorithm recognizes the positions of players from both teams (blue and pink dots) and the ball, instantly transferring them onto a 2D pitch layout. This allows the AI to track team formations and open spaces in high detail, things regular bettors completely miss. Bottom layer: Python code (written alongside the Windsurf AI assistant), where the SoccerPitchConfiguration class defines the field, penalty box, and center circle dimensions down to the centimeter for perfect player-distance calculations. The AI constantly correlates the real-time movement of players on the pitch with live bookmaker odds. The moment the algorithm detects that a team has pinned their opponent into a specific zone or exposed their flanks, while the bookmaker hasn't adjusted the odds yet, the script automatically fires a betting signal. First week: >Live bets placed: 142 > Won bets: 119 > Net profit: +$4,350 using a flat $50 stake The AI completely automated the entire cycle: Windsurf and Claude wrote the tracking code, and the algorithm autonomously parses live odds, calculates the mathematical expectation of value bets, generates player heatmaps, and spots hidden tactical anomalies. It runs 100% autonomously. Bookmark it and check out the article below 👇

How a 24-year-old programmer from Portugal made $18,200 in a month on football betting He created an AI analyst that finds flaws in bookmakers' live lines in real time and delivers predictions with an 84% win rate. Costs: $0 (Used free APIs and Windsurf IDE) He launched a Python script that maps out match videos in real time: Top layer: A Computer Vision algorithm recognizes the positions of players from both teams (blue and pink dots) and the ball, instantly transferring them onto a 2D pitch layout. This allows the AI to track team formations and open spaces in high detail, things regular bettors completely miss. Bottom layer: Python code (written alongside the Windsurf AI assistant), where the SoccerPitchConfiguration class defines the field, penalty box, and center circle dimensions down to the centimeter for perfect player-distance calculations. The AI constantly correlates the real-time movement of players on the pitch with live bookmaker odds. The moment the algorithm detects that a team has pinned their opponent into a specific zone or exposed their flanks, while the bookmaker hasn't adjusted the odds yet, the script automatically fires a betting signal. First week: >Live bets placed: 142 > Won bets: 119 > Net profit: +$4,350 using a flat $50 stake The AI completely automated the entire cycle: Windsurf and Claude wrote the tracking code, and the algorithm autonomously parses live odds, calculates the mathematical expectation of value bets, generates player heatmaps, and spots hidden tactical anomalies. It runs 100% autonomously. Bookmark it and check out the article below 👇

Ridark

373,695 Aufrufe • vor 2 Monaten

7 repos that mass replace a $50,000/year sports analytics department. all free. all open source. -> replaces Hawkeye-level court analysis YOLO tracks players and ball from any broadcast. ResNet50 extracts court keypoints. homography converts pixels to real meters. speed, position, aggression - all from a TV feed. -> replaces paid sports data subscriptions ($500/mo) every ATP match since 1968. rankings, results, stats. 1.5K stars. the holy grail dataset that every tennis ML project is built on. -> replaces point-level data feeds ($200/mo) point-by-point data for every Grand Slam since 2011. the kind of granularity you need for live Bayesian models. -> replaces shot-by-shot scouting reports 5,000+ matches charted shot by shot. direction, depth, error type. crowdsourced and free. -> replaces pre-match and in-match prediction services ELO + serve/return stats → win probability. updates during the match. exactly what a live Bayesian engine needs. -> replaces ball trajectory prediction tools CV analysis + CatBoost bounce prediction + separate court detector neural net. most advanced open-source tennis CV pipeline. -> replaces traditional bookmaker APIs Polymarket CLOB API. real-time share prices, orderbook depth, bid/ask spreads. no margin, no bookmaker - just the crowd. trade positions mid-match, not just pre-match. total before: $50K/year sports analytics stack total now: $0 like + bookmark you'll need this when you build your first tennis bot

7 repos that mass replace a $50,000/year sports analytics department. all free. all open source. -> replaces Hawkeye-level court analysis YOLO tracks players and ball from any broadcast. ResNet50 extracts court keypoints. homography converts pixels to real meters. speed, position, aggression - all from a TV feed. -> replaces paid sports data subscriptions ($500/mo) every ATP match since 1968. rankings, results, stats. 1.5K stars. the holy grail dataset that every tennis ML project is built on. -> replaces point-level data feeds ($200/mo) point-by-point data for every Grand Slam since 2011. the kind of granularity you need for live Bayesian models. -> replaces shot-by-shot scouting reports 5,000+ matches charted shot by shot. direction, depth, error type. crowdsourced and free. -> replaces pre-match and in-match prediction services ELO + serve/return stats → win probability. updates during the match. exactly what a live Bayesian engine needs. -> replaces ball trajectory prediction tools CV analysis + CatBoost bounce prediction + separate court detector neural net. most advanced open-source tennis CV pipeline. -> replaces traditional bookmaker APIs Polymarket CLOB API. real-time share prices, orderbook depth, bid/ask spreads. no margin, no bookmaker - just the crowd. trade positions mid-match, not just pre-match. total before: $50K/year sports analytics stack total now: $0 like + bookmark you'll need this when you build your first tennis bot

zostaff

35,722 Aufrufe • vor 4 Monaten

A drone just mapped an entire cemetery and found 9,940 individual grave headstones on its own in 21 minutes A 335 megapixel scan gets fused with 134 million lidar points, building a full 3D model of the terrain down to 5cm resolution An AI model called SAM3 scans the imagery and outlines every single headstone automatically, no human tracing anything by hand The system converts every detected object straight into CAD vectors, ready to export as a working drawing Surveyors used to spend weeks manually outlining thousands of objects on a map like this one This pipeline exported a finished CAD file in 21 minutes

A drone just mapped an entire cemetery and found 9,940 individual grave headstones on its own in 21 minutes A 335 megapixel scan gets fused with 134 million lidar points, building a full 3D model of the terrain down to 5cm resolution An AI model called SAM3 scans the imagery and outlines every single headstone automatically, no human tracing anything by hand The system converts every detected object straight into CAD vectors, ready to export as a working drawing Surveyors used to spend weeks manually outlining thousands of objects on a map like this one This pipeline exported a finished CAD file in 21 minutes

pulmencr

38,778 Aufrufe • vor 1 Monat

The brand tax is costing your team more than you think. Every team that makes video at scale is paying it. The hours spent fixing fonts, swapping colors, changing typography. Every video. One element at a time. That ends today. Introducing Brand Systems. Paste your company URL and HeyGen automatically extracts your logo, fonts, and colors. No uploads. No manual setup. Just a URL. From there, it works across everything you already use in HeyGen: → Templates: apply your brand in one click. Colors swap, logo drops in, fonts update. → AI Studio: every element you insert defaults to your brand automatically. → Video Agent: generate fully on-brand videos from a single prompt. Set it once. Stay on-brand across every video. No more brand tax. Try Brand Systems today on HeyGen.

HeyGen

220,460 Aufrufe • vor 5 Monaten

A guy just turned standard home Wi-Fi into a radar that sees through walls. Over 62,000 stars on GitHub for a system that tracks humans without using a single camera lens. It doesn’t just know you’re there. Watch what happens when a person lies down on a bed in another room. The AI instantly maps their exact posture, tracks their breathing, and calculates their heartbeat in real-time. No optical surveillance, no privacy leaks - it just analyzes how your body disrupts ordinary radio waves. The whole thing runs on a tiny $5 microchip. Traditional security requires a direct line of sight and invades your personal space. Now, your Wi-Fi router is a camera that sees through solid brick.

A guy just turned standard home Wi-Fi into a radar that sees through walls. Over 62,000 stars on GitHub for a system that tracks humans without using a single camera lens. It doesn’t just know you’re there. Watch what happens when a person lies down on a bed in another room. The AI instantly maps their exact posture, tracks their breathing, and calculates their heartbeat in real-time. No optical surveillance, no privacy leaks - it just analyzes how your body disrupts ordinary radio waves. The whole thing runs on a tiny $5 microchip. Traditional security requires a direct line of sight and invades your personal space. Now, your Wi-Fi router is a camera that sees through solid brick.

pulmencr

1,839,563 Aufrufe • vor 1 Monat

The vision behind $HABE is no longer a theory. It’s real. It’s active. And now, you can see it for yourself. The HABEVERSE is more than a platform. It’s a system built to move ideas into the real world, and it runs on four powerhouse zones: The HABE Innovation Zone: where raw ideas are shaped into structured proposals using HABEAI and a proven process that goes from seed to launch. The HABE Voting Zone: Where your vote helps decide what gets built, and every action earns $HABE. The HABE Marketplace: A new way to invest. Back real products, grow with innovation, and build a portfolio that reflects what you believe in. The HABE Profile Zone: Your personal dashboard. Everything you do is tracked and managed in one place. This prototype is just the first glimpse of what’s coming, and what’s already working. 👉 Check out the prototype on Figma: Start where it still counts: Final hour before the price shifts.

HABE

14,864 Aufrufe • vor 1 Jahr

CHINESE DEVELOPER JUST DROPPED A FULL 8-MINUTE SETUP GUIDE FOR THE NVIDIA DGX SPARK - AND SHOWED EXACTLY HOW TO RUN AI AGENTS AND ROBOTICS SIMULATIONS ON IT he unboxed the DGX Spark on camera - plugged in power, keyboard and ethernet and was inside the system within minutes then showed how to install iSECSIM 5.1 for virtual simulations, cloned the repo from GitHub, configured GCC 11 and built the entire stack from scratch 128GB of available memory, ARM processor, full Python library support and a complete AI development environment - all on a box the size of a paperback book at the end he launched a robotics environment and showed the DGX Spark handling full physics simulations in real time from unboxing to running agents in under 8 minutes - full guide on camera

CHINESE DEVELOPER JUST DROPPED A FULL 8-MINUTE SETUP GUIDE FOR THE NVIDIA DGX SPARK - AND SHOWED EXACTLY HOW TO RUN AI AGENTS AND ROBOTICS SIMULATIONS ON IT he unboxed the DGX Spark on camera - plugged in power, keyboard and ethernet and was inside the system within minutes then showed how to install iSECSIM 5.1 for virtual simulations, cloned the repo from GitHub, configured GCC 11 and built the entire stack from scratch 128GB of available memory, ARM processor, full Python library support and a complete AI development environment - all on a box the size of a paperback book at the end he launched a robotics environment and showed the DGX Spark handling full physics simulations in real time from unboxing to running agents in under 8 minutes - full guide on camera

Sprytix

57,512 Aufrufe • vor 3 Monaten

Sharing our computer vision system design for TRON: Ares. We approached these shots from the perspective of the machine. The frame becomes a field of observation. Every pixel is potential information waiting to be interpreted. The process begins by squarepacking the live action plates, dividing the image into a computational lattice. Once the grid exists, the system begins to read. Targets emerge. Motion vectors form. Signals ripple through layers of analysis. Inside these overlays lives the source code of the system itself. Streams of logic, fragments of instruction, the internal language of the machine. At times the imagery dissolves directly into that code, as if the world itself is being rewritten from within. Visual information collapses into structure, then reconstructs again as data. Scanning pulses move across the frame. Timers react. Coordinates lock. Each layer is part of a larger ecosystem of perception, constantly processing, evaluating, and iterating. The goal was maximum detail and living systems. Interfaces that breathe, think, and evolve in real time.

Sharing our computer vision system design for TRON: Ares. We approached these shots from the perspective of the machine. The frame becomes a field of observation. Every pixel is potential information waiting to be interpreted. The process begins by squarepacking the live action plates, dividing the image into a computational lattice. Once the grid exists, the system begins to read. Targets emerge. Motion vectors form. Signals ripple through layers of analysis. Inside these overlays lives the source code of the system itself. Streams of logic, fragments of instruction, the internal language of the machine. At times the imagery dissolves directly into that code, as if the world itself is being rewritten from within. Visual information collapses into structure, then reconstructs again as data. Scanning pulses move across the frame. Timers react. Coordinates lock. Each layer is part of a larger ecosystem of perception, constantly processing, evaluating, and iterating. The goal was maximum detail and living systems. Interfaces that breathe, think, and evolve in real time.

GMUNK

37,698 Aufrufe • vor 6 Monaten

I told you I was the Kanye West of vibecoding. Or, as I call it: system sculpting. Today, with wabi, I recreated a fully working prototype of the stem player in less than 48 hours. A generative hardware interface that creates small samples and lets you mix them directly on the device. But here’s the wild part: there is no 3D model. No GLTF files, no external assets, no polygons. The entire device every curve, speaker hole, and glowing LED is pure math. Built with SDFs (Signed Distance Fields) and raymarched inside a single fragment shader on a 2D surface. Generative audio. Generative geometry. All native. All system sculpted. Have fun.

I told you I was the Kanye West of vibecoding. Or, as I call it: system sculpting. Today, with wabi, I recreated a fully working prototype of the stem player in less than 48 hours. A generative hardware interface that creates small samples and lets you mix them directly on the device. But here’s the wild part: there is no 3D model. No GLTF files, no external assets, no polygons. The entire device every curve, speaker hole, and glowing LED is pure math. Built with SDFs (Signed Distance Fields) and raymarched inside a single fragment shader on a 2D surface. Generative audio. Generative geometry. All native. All system sculpted. Have fun.

Tykra

111,274 Aufrufe • vor 5 Monaten

End-to-end neural networks racing drones in Abu Dhabi! 🚁 Check out the drone racing team from Delft University of Technology! A completely end-to-end neural network solution, from pixels to direct motor commands. No Kalman filters. No computer vision feature detectors. Just neurons flying the drone. The challenge is extreme. These drones fly at high speeds and need split-second decisions with minimal onboard resources: a single rolling-shutter camera and an IMU. Their approach is called SkyDreamer, based on the Dreamer-v3 reinforcement learning algorithm. First, a world model is trained in simulation. Then, the neural network learns how to fly in its dreams through reinforcement learning. The network's internal state can be read out to see where it thinks it is on the track or how fast it's going. Even better, the drone estimates some of its own body characteristics during flight, like the camera angle relative to the body, eliminating time-consuming manual calibration. The system uses only a single camera and the gyros from the IMU, ignoring the accelerometers, just like human FPV pilots do. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

End-to-end neural networks racing drones in Abu Dhabi! 🚁 Check out the drone racing team from Delft University of Technology! A completely end-to-end neural network solution, from pixels to direct motor commands. No Kalman filters. No computer vision feature detectors. Just neurons flying the drone. The challenge is extreme. These drones fly at high speeds and need split-second decisions with minimal onboard resources: a single rolling-shutter camera and an IMU. Their approach is called SkyDreamer, based on the Dreamer-v3 reinforcement learning algorithm. First, a world model is trained in simulation. Then, the neural network learns how to fly in its dreams through reinforcement learning. The network's internal state can be read out to see where it thinks it is on the track or how fast it's going. Even better, the drone estimates some of its own body characteristics during flight, like the camera angle relative to the body, eliminating time-consuming manual calibration. The system uses only a single camera and the gyros from the IMU, ignoring the accelerometers, just like human FPV pilots do. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

207,500 Aufrufe • vor 7 Monaten

NEW: Lumistar just launched an AI basketball machine that passes, rebounds, and coaches your shot. Lumistar Carry is built for solo training, using cameras to follow your movement, pass the ball back, and analyze your shooting form in real time. -Quad-camera system tracks both player and ball -190° court tracking lets you move around the floor -Gesture command calls for a pass hands-free -Adaptive passing adjusts speed, spin, timing, and release height -Tracks form, shot trajectory, backspin, location, and results -AI Coach turns your data into personalized drills -Supports up to 5 players with live scores and leaderboards Starts at $2,399.

NEW: Lumistar just launched an AI basketball machine that passes, rebounds, and coaches your shot. Lumistar Carry is built for solo training, using cameras to follow your movement, pass the ball back, and analyze your shooting form in real time. -Quad-camera system tracks both player and ball -190° court tracking lets you move around the floor -Gesture command calls for a pass hands-free -Adaptive passing adjusts speed, spin, timing, and release height -Tracks form, shot trajectory, backspin, location, and results -AI Coach turns your data into personalized drills -Supports up to 5 players with live scores and leaderboards Starts at $2,399.

Ritwik Pavan

393,112 Aufrufe • vor 1 Monat

This 30 minute Roboflow interview will teach you more about shipping real-world Computer Vision products than most ML engineers learn in 3 years at big tech. Bookmark and watch, no matter what. It'll be the most productive thing you do this week. Marc Zoghby, co-founder of PlayVision, walks through exactly how they turn raw basketball footage into full scouting reports. They track every player, the ball, and complex events like "good vs bad passes" - with actual business logic behind the labels. No hand-waving, no hype. He shows the demo, then opens the hood: > how they picked the right OCR and pose estimation models instead of defaulting to the biggest one > their data curation and active learning loop (the part nobody posts about on LinkedIn) > how they deal with gym lighting, motion blur, and all the ugly real-world CV problems > his jump from MedTech to sports AI and what actually transfers > concrete advice for anyone building real-world AI products, not demos Trading here: If you're working on CV, sports tech, or any vertical AI product - this is 30 minutes of compressed operator knowledge you won't find in papers or Twitter threads.

This 30 minute Roboflow interview will teach you more about shipping real-world Computer Vision products than most ML engineers learn in 3 years at big tech. Bookmark and watch, no matter what. It'll be the most productive thing you do this week. Marc Zoghby, co-founder of PlayVision, walks through exactly how they turn raw basketball footage into full scouting reports. They track every player, the ball, and complex events like "good vs bad passes" - with actual business logic behind the labels. No hand-waving, no hype. He shows the demo, then opens the hood: > how they picked the right OCR and pose estimation models instead of defaulting to the biggest one > their data curation and active learning loop (the part nobody posts about on LinkedIn) > how they deal with gym lighting, motion blur, and all the ugly real-world CV problems > his jump from MedTech to sports AI and what actually transfers > concrete advice for anyone building real-world AI products, not demos Trading here: If you're working on CV, sports tech, or any vertical AI product - this is 30 minutes of compressed operator knowledge you won't find in papers or Twitter threads.

zostaff

101,196 Aufrufe • vor 4 Monaten

Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and kyutai, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.

Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and kyutai, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.

General Intuition

503,453 Aufrufe • vor 2 Monaten

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

Sprytix

66,333 Aufrufe • vor 1 Monat

A 21-year-old solo developer stopped chasing AI trends and locked in a $35,000/month B2B niche using a single Python script He built a production-ready traffic monitoring Micro-SaaS that smart cities and businesses pay big money for He didn't build complex AI agent teams He just paired an open-source model with a high-ticket commercial concept Every single day, his system follows a military-like routine: tracks the bounding boxes, calculates telemetry, and locks in the data For 4 to 6 steps straight, the pipeline is completely optimized. Zero frame drops, zero lag. Just pure automated tracking under the hood He doesn't even use raw screen pixels for calculation to keep his speed metrics clean from perspective distortion Out of 6 core features he launched, 3 handle the baseline detection and tracking using YOLOv8, Supervision, and ByteTrack But one single feature (Perspective Transform via OpenCV) converts pixels to real meters and generates high-value Excel traffic reports for clients His main secret? He utilizes a custom Polygon Zone to filter out noise and ships a ready-to-sell B2B product immediately instead of overcomplicating the setup

A 21-year-old solo developer stopped chasing AI trends and locked in a $35,000/month B2B niche using a single Python script He built a production-ready traffic monitoring Micro-SaaS that smart cities and businesses pay big money for He didn't build complex AI agent teams He just paired an open-source model with a high-ticket commercial concept Every single day, his system follows a military-like routine: tracks the bounding boxes, calculates telemetry, and locks in the data For 4 to 6 steps straight, the pipeline is completely optimized. Zero frame drops, zero lag. Just pure automated tracking under the hood He doesn't even use raw screen pixels for calculation to keep his speed metrics clean from perspective distortion Out of 6 core features he launched, 3 handle the baseline detection and tracking using YOLOv8, Supervision, and ByteTrack But one single feature (Perspective Transform via OpenCV) converts pixels to real meters and generates high-value Excel traffic reports for clients His main secret? He utilizes a custom Polygon Zone to filter out noise and ships a ready-to-sell B2B product immediately instead of overcomplicating the setup

Ridark

29,326 Aufrufe • vor 2 Monaten