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.

The new SAM3 model from Meta is blowing my mind Shown here: detecting putting greens, pools, and cars in Scottsdale from simple text prompts via Mapbox imagery R, Shiny, mapgl for the UI; Python backend via Qiusheng Wu's segment-geospatial package (thanks Qiusheng!)

Kyle Walker

19,131 subscribers

43,790 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Mapping swimming pools 🏊‍♀️ interactively with text prompts and the Segment Anything Model 🤩 Notebook: GitHub: #geospatial #segmentanything #deeplearning

Mapping swimming pools 🏊‍♀️ interactively with text prompts and the Segment Anything Model 🤩 Notebook: GitHub: #geospatial #segmentanything #deeplearning

Qiusheng Wu

30,498 views • 3 years ago

🚀 A brand-new feature is coming to the SAMGeo Python package: interactive remote-sensing image segmentation with text prompts powered by SAM3. This update makes geospatial segmentation even more intuitive: just describe what you want to detect, and let GeoAI do the rest. ✨ GitHub PR: #GeoAI #SAM3 #OpenSource #Python

Qiusheng Wu

32,888 views • 7 months ago

Nearly 800 swimming pools identified from Mapbox satellite imagery with Meta's SAM3 in a section of Beverly Hills. In the soon-to-be-released {geosam} R package: review results by confidence level, filter, then export. This is shaping into a tool for serious applied work.

Nearly 800 swimming pools identified from Mapbox satellite imagery with Meta's SAM3 in a section of Beverly Hills. In the soon-to-be-released {geosam} R package: review results by confidence level, filter, then export. This is shaping into a tool for serious applied work.

Kyle Walker

285,468 views • 6 months ago

Detecting airplanes at DFW Airport from a single text prompt. Meta's Segment Anything Model 3 and the geosam R package make powerful image detection tools accessible.

Detecting airplanes at DFW Airport from a single text prompt. Meta's Segment Anything Model 3 and the geosam R package make powerful image detection tools accessible.

Kyle Walker

31,475 views • 5 months ago

🚀 SamGeo v0.14.0 is here! This release brings interactive segmentation for remote sensing imagery powered by Meta’s SAM3. 🟦 Draw a bounding box to automatically detect all similar objects across the image. 📝 Or just type a text prompt to segment objects instantly. No complex setup. No manual labeling. Just intuitive, AI-driven geospatial analysis. 🔗 GitHub: 🧪 Notebook: #SAM3 #GeoAI #Geospatial #OpenSource #Python #DataScience

🚀 SamGeo v0.14.0 is here! This release brings interactive segmentation for remote sensing imagery powered by Meta’s SAM3. 🟦 Draw a bounding box to automatically detect all similar objects across the image. 📝 Or just type a text prompt to segment objects instantly. No complex setup. No manual labeling. Just intuitive, AI-driven geospatial analysis. 🔗 GitHub: 🧪 Notebook: #SAM3 #GeoAI #Geospatial #OpenSource #Python #DataScience

Qiusheng Wu

33,526 views • 6 months ago

Interactive well pad identification in the Permian Basin using Meta's Segment Anything Model 3. Draw a box around one well pad using Mapbox imagery; SAM3 finds similar objects in the view. So many use-cases for AI in oil & gas, and I'm not just talking about ChatGPT.

Interactive well pad identification in the Permian Basin using Meta's Segment Anything Model 3. Draw a box around one well pad using Mapbox imagery; SAM3 finds similar objects in the view. So many use-cases for AI in oil & gas, and I'm not just talking about ChatGPT.

Kyle Walker

12,147 views • 4 months ago

For years, I've wanted to create an #rstats package bringing the power of Mapbox to R users. After a few failed attempts, I finally got {mapgl} over the finish line in 2024 (with some help from #GenAI). Get started with an interactive globe in one line of R code, and build from there!

For years, I've wanted to create an #rstats package bringing the power of Mapbox to R users. After a few failed attempts, I finally got {mapgl} over the finish line in 2024 (with some help from #GenAI). Get started with an interactive globe in one line of R code, and build from there!

Kyle Walker

13,748 views • 1 year ago

Introducing a new #Python package called mapwidget - creating interactive 3D maps in a Jupyter environment using popular JavaScript libraries, such as #CesiumJS, #Mapbox, #MapLibre, #Leaflet, and #OpenLayers GitHub: #geospatial #gischat #anywidget

Introducing a new #Python package called mapwidget - creating interactive 3D maps in a Jupyter environment using popular JavaScript libraries, such as #CesiumJS, #Mapbox, #MapLibre, #Leaflet, and #OpenLayers GitHub: #geospatial #gischat #anywidget

Qiusheng Wu

154,861 views • 3 years ago

1,890 swimming pools found across a 5 square mile suburban neighborhood with zero-shot image segmentation. Lower the confidence threshold to find even more! Use the interactive explorer in the {geosam} R package to try out Meta's SAM3 for satellite imagery analysis yourselves.

1,890 swimming pools found across a 5 square mile suburban neighborhood with zero-shot image segmentation. Lower the confidence threshold to find even more! Use the interactive explorer in the {geosam} R package to try out Meta's SAM3 for satellite imagery analysis yourselves.

Kyle Walker

50,458 views • 2 months ago

Distributed energy is harder to map than centralized infrastructure, but cutting-edge AI tools can help. Shown: identifying rooftop solar panels in a suburban neighborhood with Mapbox imagery, Meta's SAM3. Useful for utilities, grid planners, and solar prospecting.

Distributed energy is harder to map than centralized infrastructure, but cutting-edge AI tools can help. Shown: identifying rooftop solar panels in a suburban neighborhood with Mapbox imagery, Meta's SAM3. Useful for utilities, grid planners, and solar prospecting.

Kyle Walker

26,326 views • 4 months ago

🚀 The GeoAI QGIS Plugin is here 🔥 You can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: GitHub: Short demo: Full video tutorial: #QGIS #GeoAI #SAM3 #Geospatial #DeepLearning #ComputerVision #OpenSource #Python

🚀 The GeoAI QGIS Plugin is here 🔥 You can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: GitHub: Short demo: Full video tutorial: #QGIS #GeoAI #SAM3 #Geospatial #DeepLearning #ComputerVision #OpenSource #Python

Qiusheng Wu

11,682 views • 6 months ago

Segment-geospatial v0.9.0 is out📢It now supports segmenting remote sensing imagery with box prompts. You can create box prompts interactively or use existing vector data as box prompts 🌐 GitHub: Notebook: Video tutorial: #geospatial #segmentanything #deeplearning

Segment-geospatial v0.9.0 is out📢It now supports segmenting remote sensing imagery with box prompts. You can create box prompts interactively or use existing vector data as box prompts 🌐 GitHub: Notebook: Video tutorial: #geospatial #segmentanything #deeplearning

Qiusheng Wu

24,193 views • 2 years ago

The anymap-ts Python package now supports creating choropleth maps from vector data with a few simple clicks! Give it a try: Web demo: Jupyter demo: GitHub: Documentation: #geospatial #opensource

The anymap-ts Python package now supports creating choropleth maps from vector data with a few simple clicks! Give it a try: Web demo: Jupyter demo: GitHub: Documentation: #geospatial #opensource

Qiusheng Wu

12,496 views • 4 months ago

Generate photorealistic textures from text prompts with the new Text to Texture feature, now available in #Substance3DSampler (beta). Improve your workflow by spending less time hunting for reference imagery, and more time bringing your creative vision to life.

Generate photorealistic textures from text prompts with the new Text to Texture feature, now available in #Substance3DSampler (beta). Improve your workflow by spending less time hunting for reference imagery, and more time bringing your creative vision to life.

Adobe Substance 3D

484,254 views • 2 years ago

📢 Exciting news! Leafmap now supports creating 3D 🌎 maps with Mapbox! This demo showcases how to visualize the ESA global land cover from #EarthEngine on a 3D globe. Explore the 100 PB+ Earth Engine Data Catalog and display any geospatial datasets in 3D 🚀 Notebook: #leafmap #geospatial #opensource #python

📢 Exciting news! Leafmap now supports creating 3D 🌎 maps with Mapbox! This demo showcases how to visualize the ESA global land cover from #EarthEngine on a 3D globe. Explore the 100 PB+ Earth Engine Data Catalog and display any geospatial datasets in 3D 🚀 Notebook: #leafmap #geospatial #opensource #python

Qiusheng Wu

18,700 views • 1 year ago

The Russian “Talisman” EW device for detecting and jamming drone video frequencies is shown here successfully drowning out the video signal from a Ukrainian FPV.

The Russian “Talisman” EW device for detecting and jamming drone video frequencies is shown here successfully drowning out the video signal from a Ukrainian FPV.

Roy🇨🇦

24,154 views • 1 year ago

…and here is the The Federalist piece I cited in the same segment (via Mark Hemingway):

…and here is the The Federalist piece I cited in the same segment (via Mark Hemingway):

Guy Benson

15,082 views • 11 months ago

🚀 GeoAI Tutorial 19: Train a Semantic Segmentation Model for Objection Detection from Remote Sensing Imagery 🌍 Leverage any PyTorch segmentation model from — with hundreds of image encoders & pretrained weights available. 🎥 Watch the full tutorial here: 📓 Explore the notebook: 🛠️ Check out the GitHub repository: 📚 Dive into the documentation: 📺 Check out the entire YouTube playlist: #GeoAI #geospatial #AI #Python #DeepLearning

🚀 GeoAI Tutorial 19: Train a Semantic Segmentation Model for Objection Detection from Remote Sensing Imagery 🌍 Leverage any PyTorch segmentation model from — with hundreds of image encoders & pretrained weights available. 🎥 Watch the full tutorial here: 📓 Explore the notebook: 🛠️ Check out the GitHub repository: 📚 Dive into the documentation: 📺 Check out the entire YouTube playlist: #GeoAI #geospatial #AI #Python #DeepLearning

Qiusheng Wu

20,082 views • 1 year ago

✨Introducing Civitai models support. You can now Install ANY models from Civitai. Open and run comfy UI in the cloud. Run via simple API. This is Comfy Deploy. Join discord for the latest updates!

✨Introducing Civitai models support. You can now Install ANY models from Civitai. Open and run comfy UI in the cloud. Run via simple API. This is Comfy Deploy. Join discord for the latest updates!

BennyKok

24,443 views • 2 years ago

🧵 Two Images, Ten Unique Videos: All with Text Prompts Two starting images. Ten distinct stories. All by tweaking prompts. I've been loving the new Grok Imagine video model, and its ability to follow instructions is mind-blowing. Check out these 10 examples ... 👇

🧵 Two Images, Ten Unique Videos: All with Text Prompts Two starting images. Ten distinct stories. All by tweaking prompts. I've been loving the new Grok Imagine video model, and its ability to follow instructions is mind-blowing. Check out these 10 examples ... 👇

Marco

28,073 views • 8 months ago