Tree extraction from satellite imagery using segment-geospatial v0.5 and... the Segment Anything Model (SAM) - by Lucas Prado Osco LinkedIn post: Notebook: #geospatial #segmentanythingshow more

segment-geospatial v0.3.0 is out - segmenting satellite imagery with... the Segment Anything Model (SAM). GitHub: Docs: Notebook: #segmentanything #deeplearning #geopython #geospatialshow more

Introducing segment-geospatial, A Python package for segmenting geospatial data... with the Segment Anything Model (SAM) GitHub: Docs: Notebook: #segmentanything #deeplearning #geopythonshow more

A sneak peak of segment-geospatial v0.4.0 - Automatically generating... object masks for satellite imagery GitHub: Notebook: #geospatial #deeplearning #segmentanythingshow more

Segment-geospatial v0.4.0 is out. Segmenting satellite imagery and saving... results as GeoTIFF and vector formats 👇 GitHub: Notebook: Video: #geospatial #segmentanything #leafmapshow more

Create Stunning Time-Series Satellite Images in Seconds! The GEE... Data Catalogs Plugin v0.5 for QGIS is now available and it's a powerful upgrade. You can now create time-series satellite imagery with just a few clicks using a simple interface. The new version also supports direct downloads to your computer, making the workflow faster and more efficient. Key Features: - Access over 80 petabytes of satellite and geospatial datasets from Google Earth Engine - Generate animated time-series imagery effortlessly - Export results directly from QGIS to your local machine Useful Links: QGIS Plugin Page: GitHub Repository: Video Tutorial: #QGIS #geospatial #EarthEngine #Python #datascience #satelliteshow more

Check out this 📹 step-by-step tutorial on how to... visualize and download 🛰️ satellite images of the #Morocco earthquake using the Maxar Open Data on #AWS. Video: Web App: GitHub: Notebook: #moroccoearthquake #geospatial #dataviz #pythonshow more

🚀 The #GeoAI Python package now supports feature segmentation... from high-resolution satellite and aerial imagery using text prompts, such as trees, buildings, etc. It efficiently processes large datasets with automatic tiling and can save results as a single image. Stay tuned for more features coming soon! 📓 Access the notebook: 🛠️ Explore the GitHub repository: 📚 Dive into the documentation: 📺 Check out the entire YouTube playlist: #GeoAI #geospatial #AI #Python #DeepLearningshow more

The GeoAI Python package now supports object detection using... pre-trained models from the GeoDeep libarary ( The supported object types include cars, trees, birds, planes, aerovision, utilities, buildings, and roads. Try it out: GitHub: Notebook example: #geospatial #geoai #opensource #pythonshow more

Cloud and Cloud Shadow Detection From Satellite Imagery with... GeoAI and OmniCloudMask In this tutorial, you’ll detect clouds and cloud shadows, compute cloud statistics, clean segmentation outputs, convert raster masks to vectors, smooth boundaries, and generate a cloud-free mask for downstream remote sensing analysis. This workflow works with imagery that includes Red, Green, and NIR bands (e.g., Landsat, Sentinel-2, NAIP, and other commercial data). Notebook: Video tutorial: #geospatial #remotesensing #geoaishow more

Did you know we're working with environmental survey teams... to improve flood detection? Our Segment Anything Model (SAM) is being used to identify minute changes in water conditions from satellite images—we hope this faster analysis can contribute to better rapid response and keep communities safer.show more

Today we're releasing the Segment Anything Model (SAM) —... a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️show more

🚀 A sneak peek of a new feature in... the #GeoAI Python package! Now you can train an image segmentation model for extracting features (e.g., buildings) from satellite or aerial imagery—all with just a few lines of code. 🛠️ Check out the GitHub repository: 📚 Dive into the documentation: 📺 Check out the entire YouTube playlist: #GeoAI #geospatial #AI #Python #DeepLearningshow more

Google just wired DeepMind and Earth Engine directly into... the biggest geospatial dataset on the planet. For two decades, millions of people used Google Earth to scale the Himalayas or zoom in on their childhood neighbourhoods. In 2026, Google is basically trying to shift the entire platform toward professional execution. They turned a massive digital twin of the world into an agentic AI engine for global infrastructure. The technical foundation is (obviously) all about data. Google integrated 20-metre and 40-metre elevation contours globally. Engineers and urban planners now have instant access to the exact topographic context required for site planning anywhere on Earth. The data catalogue updates continuously to maintain the freshest imagery possible. Collaboration used to kill geospatial projects. Teams would lose momentum through stale materials or bad handoffs. Google fixed this by building frictionless data import systems. You can now drop KML, KMZ, and GeoJSON files directly onto the global map. Entire departments can align on a single source of truth, moving from a raw question to a definitive answer instantly. The biggest upgrade is the introduction of agentic geospatial intelligence. Users can open 'Ask Google Earth' and search massive satellite and Street View databases using natural language. You type a command, and the AI handles the manual data wrangling. It identifies new site locations and analyses infrastructure before you even open a spreadsheet.show more

🚀 Free High Quality Satellite Imagery With Playback Today,... we're introducing beautiful high quality satellite imagery from the GOES weather satellites. Free for all users: • Access to all 16 bands (L1b products) • Coverage across CONUS, both Mesoscale sectors and Full Disk • Playback with up to 15 frames • Real-time updates • Inspect the data directly on the map Plus subscribers unlock more: • Imagery displayed on a 3D globe (Globe Projection) • Split View to compare bands side-by-side • Playback with up to 50 frames • Smoothing options: see the raw data or a polished look • RenderStream for faster loading when in low cell service areas Tropical season is now here - stay one step ahead Available on: iOS: Android: Browser: And to Plus subscribers using our Windows/Mac Appshow more

Hey Hana Nation!🤍 Valentine’s Week isn’t just about romantic... love… Sometimes it’s about celebrating someone who brings comfort, happiness, & smiles into your life. So, let’s dedicate this entire week to Farrhana Bhatt one love-filled segment every day. From Rose Day to Valentine’s Day, we’ll celebrate her through wishes, edits, memories, messages, and all the love she truly deserves. Join in and make this week special for her by using the hashtag #ValentinesWithHana🫶 #FarrhanaBhatt #FarrhanaRebellionsshow more

Google is doing some great AI work in India... that is actually helping farmers on the ground and honestly, almost nobody is talking about it. It’s surprising how much we focus on every new model drop, while some of the most meaningful AI work is happening quietly in the real world. Google DeepMind’s AnthroKrishi team built two AI models using satellite imagery: - Agricultural Landscape Understanding (ALU) maps farm boundaries, trees and water bodies, with historical data going back 15 years. - Agricultural Monitoring & Event Detection (AMED) uses multispectral data to monitor crops, sowing and harvesting, identifying 11 major crops. And this is already being used at scale: - 5M+ farmers in Telangana through its agricultural DPI - 140M+ hectares covered by Terrastack - 2.6M hectares of irrigated land in Karnataka - CarbonFarm is using it across 12 countries - FAO is integrating the models into its global agricultural data platform with $2.5M from Google These models are now providing agricultural insights across 6 African countries, and the Agricultural Landscape Understanding layer is one of the most popular layers on Google Earth globally.show more

🚀 The Segment Anything Model (SAM) has been upgraded... to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearchshow more

this faceless AI channel made over >1.5M views in... post -> repeat 🔁 thumbnails with Gemini and basic music from the Yt library (no copyright guaranteed💶) comment “china niche” and i’ll send you a full tutorial (must be following for DM)show more

I told you to claim your free 16GB NVIDIA... GPU for learning Local LLMs. Now I’m going to show you how to double its inference speed without touching the hardware. Google Colab gives you an enterprise grade NVIDIA Tesla T4 GPU for free, roughly 4 hours every single day. It is the absolute perfect sandbox for learning AI engineering, testing inference flags, and pushing massive context windows. The local AI timeline is moving way too fast. If you aren't using Multi Token Prediction (MTP) yet, you are leaving massive performance on the table. I just pushed DeepMind’s Gemma 4 26B to 64.9 t/s on this exact free tier. Let's look at the raw benchmark data running on an Ubuntu Linux environment with the latest compiled llama.cpp binaries and quantized GGUFs from Unsloth via HuggingFace: # Qwen 3.5 9B (Dense): Base: [ Prompt: 626.7 t/s | Generation: 21.0 t/s ] With MTP: [ Prompt: 539.1 t/s | Generation: 24.8 t/s ] # Gemma 4 26B QAT (MoE): Base: [ Prompt: 634.2 t/s | Generation: 48.3 t/s ] With MTP: [ Prompt: 572.1 t/s | Generation: 64.9 t/s ] If you are paying attention, this single Colab notebook reveals 3 massive observations about the current state of local LLMs: # 1. The MTP Speedup (Software Overclocking) Standard autoregressive decoding guesses one token at a time. MTP acts like a highly optimized, built in speculative decoder. It predicts multiple future tokens at once and the main model verifies them in parallel. The result? Zero accuracy loss and a massive throughput increase. Gemma jumped from 48 to 65 t/s just by flipping a flag. # 2. The MoE Paradox (Bigger is Faster) How does a 26B parameter model absolutely destroy a 9B model in raw speed on the exact same hardware? Architecture. Qwen 3.5 9B is a dense model. it activates all 9 billion parameters for every single token. Gemma 4 26B is a Mixture of Experts (MoE) model. It routes data efficiently, activating only 4B parameters per token. You get the reasoning capabilities of a 26B model with the compute cost of a 4B model. 3. Thinking Efficiency When I ran the exact same complex prompt on both models, the larger MoE spent significantly fewer "thinking" tokens to arrive at the correct answer. A smarter model doesn't just give better answers; it gets to the point faster, saving you compute cycles and preserving your context window. # Want to run this yourself? Here are the exact llama.cpp CLI commands. For Qwen (MTP is baked into the main model): ./llama-cli -m Qwen3.5-9B-UD-Q4_K_XL.gguf -p "Explain quantum computing." -n 2000 -c 8000 -ngl 99 -fa on --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 For Gemma (Using a separate lightweight draft model): ./llama-cli -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --model-draft mtp-gemma-4-26B-A4B-it.gguf -p "Explain quantum computing." -n 2000 -c 8000 -ngl 99 -fa on --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 Stop waiting for a $3,000 rig. Boot up Colab, pull these models, and start building your stack. I’ve put together a completely free, cell by cell Google Colab notebook that automates this entire workflow so you can test it yourself in 5 minutes and learn. Link to the notebook is in the comments below. Experiemt with different MTP parameters, context windows and post your results in the comments.show more

Something big is happening in robotics - and it’s... hiding in plain sight. This post is not about dancing robots but in the data that powers them. Open robotics datasets have exploded this year, turning the field into a more scalable and collaborative ecosystem. In just two years, Hugging Face datasets grew from 11k to over 600k - and robotics is by far the fastest-growing segment. We went from 1k robotics datasets in 2024 to 27k in 2025! For comparison, text generation, the second-largest category, has only around 5k datasets in 2025. That gap is massive. Open datasets are important because robotics lives and dies by real-world robot data - video, actions, sensors, failures. By making this data easy to upload, reuse, and benchmark, researchers, startups, and large players are now releasing real-robot datasets that would have stayed locked inside labs just a few years ago. Major contributors include NVIDIA, LeRobot initiative, and a rapidly growing maker community. This surge is also enabled by cheaper video storage, better tooling, and an open-source AI culture now spilling into the physical world. And it really matters: open robotics data dramatically lowers entry barriers, accelerates learning-by-doing, and speeds up progress toward generalist and humanoid robots. Robotics won’t scale through hardware alone - but to a large extent through shared data. Viz below from AI World - link to the story and more viz/filters in comment.show more