Tools tagged with "Classification"

Alaska DNR Open Data provides a public platform for exploring and downloading geospatial land and resource data. It offers access to applications, maps, and publications produced and maintained by the divisions and offices of the Department of Natural Resources. Users can discover and build apps, and engage to solve important local issues within the community.

GeeFlow is a Python library from Google DeepMind designed for generating and processing large-scale geospatial datasets using Google Earth Engine. It focuses on supporting geospatial AI research by creating datasets in TFDS format, ready for model training, and enabling the creation of inference maps up to global scale.

PyTorch Wildlife is an AI platform designed for the AI for Conservation community. It allows users to create, modify, and share powerful AI conservation models, directly loading various models like MegaDetector, DeepFaune, and HerdNet from its expanding model zoo for animal detection and classification. The framework aims to provide a unified and straightforward experience for building and deploying conservation AI.

point-cloud-utils is a Python library designed for efficient processing and manipulation of 3D point clouds and meshes. It offers a straightforward interface for common operations, making it accessible for developers and researchers working with 3D geospatial data. The library aims to simplify complex tasks related to 3D data handling.

sits is an open-source R/Python package designed for satellite image time series analysis. It enables users to apply machine learning techniques for classifying image time series obtained from Earth observation data cubes, providing a complete workflow.

The Computer Vision Group at TUM offers a variety of datasets for researchers in computer vision, image processing, and pattern recognition. These datasets are shared to foster academic collaboration, with a request to cite the relevant publications when utilized.

This platform provides access to Land Cover and conditions data from the European Space Agency's Climate Change Initiative (ESA CCI) project. Users can explore and download various geospatial products, including land cover maps, plant functional type maps, and surface reflectance composites. The viewer supports data extraction at specific locations and offers yearly classifications spanning decades.

This repository provides an ensemble of AI models, known as SpeciesNet, developed by Google to classify wildlife in camera trap images. It combines an object detector (MegaDetector) to find objects of interest and an image classifier to identify species, significantly accelerating wildlife monitoring efforts. These models are utilized within the Wildlife Insights platform.

This Python package is designed for segmenting geospatial data, integrating the Segment Anything Model (SAM) to bring advanced AI-driven computer vision to the geospatial domain. It enables efficient identification and delineation of objects or regions within various raster datasets, including satellite imagery and aerial photos.

S1FloodFinder is a user-friendly open-source solution designed for flood mapping using Synthetic Aperture Radar (SAR) imagery from Sentinel-1. This package addresses the limitations of optical satellite imagery during floods, which often struggle with cloud cover, by leveraging SAR's ability to penetrate clouds. It provides specialized techniques and tools for accurate floodwater extent measurements, crucial for emergency response and minimizing disaster impact.

OpenCV is a comprehensive, real-time optimized computer vision library that also supports machine learning and artificial intelligence model execution. It offers tools and hardware, enabling a wide range of applications from image processing to object detection and deep learning. The platform provides resources for learning, consulting, and an active community store.

GeoAI Essentials is a learning plan from Esri that focuses on integrating artificial intelligence (AI), machine learning (ML), and deep learning (DL) with GIS. It teaches how to apply GeoAI workflows to produce knowledge and solve geographic challenges.

Flash Point Classifier is a powerful and user-friendly software tool designed for rapid classification of airborne lidar point clouds. It transforms raw lidar data into actionable insights, offering custom classification options and the ability to manage data locally without cloud uploads. The software is cross-platform, available for Windows and macOS, and enhances productivity through streamlined workflows and parallel processing.

The Global Land Cover by National Mapping Organizations (GLCNMO) provides geospatial land cover information in raster format, classifying the entire globe into 20 categories based on FAO's LCCS. Developed through international collaboration, it offers three versions (2003, 2008, 2013) using MODIS data, allowing for comparisons and integration with other LCCS-based products.

This GitHub repository provides tools and methods for performing road corrections and measurements using Airborne Laser Scanning (ALS) data. It focuses on extracting valuable information about road infrastructure from high-resolution LiDAR scans. The project aims to facilitate accurate analysis and management of road networks.

WorldCereal is a research project funded by the European Space Agency, dedicated to providing a free, cloud-based processing system. This system generates high-resolution custom crop location and type products at both local and global scales. It aims to enhance food security through advanced geospatial data and analysis.

SensatUrban is a large-scale photogrammetric point cloud dataset designed for urban semantic segmentation research. It features nearly three billion richly annotated points, covering approximately 6 km² across two UK cities. This dataset provides essential benchmarks and challenges for advancing 3D point cloud analysis and deep learning applications.

This resource provides access to version 1.2 of the Global Forest Change dataset, offering detailed information on forest extent and loss from 2000 through 2014. The data is derived from time-series analysis of Landsat imagery, with updates incorporating Landsat 8 OLI for more recent years. Users can download the dataset and are encouraged to register for updates.

The NOAA Office for Coastal Management provides C-CAP High-Resolution Land Cover data through its Digital Coast initiative. This resource offers detailed land cover information, including up to 25 classification categories, for most coastal areas nationwide. Data is available at 1 to 2.4-meter resolution, with 1-meter data recently released.

Pointly offers an innovative cloud-based platform for 3D point cloud classification and labeling. It leverages artificial intelligence to automate the analysis of large-scale point clouds, transforming raw data into structured, actionable information. The platform also provides tools for centralized point cloud management and custom classifier development.

Whitebox Geospatial is the home of WhiteboxTools, an open-source, fast, and innovative geospatial software. It offers a suite of tools and workflows for Python, along with extensions and a core library, enabling advanced geospatial analysis. The platform emphasizes open-source development and provides resources for learning and implementation.

This GitHub repository hosts an open-source project dedicated to the detection of mining activities. It provides tooling and code for analyzing geospatial data to identify and monitor mining operations, contributing to environmental awareness. The project likely leverages remote sensing and machine learning techniques for automated detection.

This resource provides access to the book "Cloud-Based Remote Sensing with Google Earth Engine: Fundamentals and Applications." Published by Springer, the book is available for free download as a PDF, offering in-depth material for learning and applying geospatial analysis. It covers essential concepts and practical applications within the Google Earth Engine platform.

This GitHub repository provides a curated list of ground-truth forest datasets for the machine learning and forestry community. It focuses on in-situ and validation data for various analyses, including biodiversity, carbon, and wildfire. The goal is to help researchers and practitioners easily find datasets for building machine learning models for forest analysis.

DeepForest is an open-source Python package designed for tree crown detection and analysis in airborne RGB imagery. It leverages deep learning techniques to process high-resolution aerial data, providing tools for ecological research and conservation. The package aims to streamline the extraction of individual tree information from diverse environmental datasets.

The Point Cloud Library (PCL) is a standalone, large-scale, open project for 2D/3D image and point cloud processing. It provides advanced algorithms and data structures for tasks like filtering, feature estimation, surface reconstruction, segmentation, and object recognition. PCL is designed for a wide range of applications in robotics, computer vision, and geospatial analysis.

The `landscapemetrics` R package provides a comprehensive collection of landscape metrics designed for analyzing categorical map patterns. It enables researchers and practitioners to quantify various aspects of landscape structure and composition within the R environment, facilitating advanced spatial ecological analysis. This tool is essential for studies in landscape ecology, conservation, and environmental management.

This resource provides global, remote-sensing supported environmental layers at 1-km resolution for assessing status and trends in biodiversity, ecosystems, and climate. It offers two versions of consensus land-cover datasets, integrating multiple satellite products.

RarePlanes is an open-source machine learning dataset from CosmiQ Works and AI.Reverie, designed to test the value of synthetic data in computer vision. It combines real Maxar WorldView-3 satellite imagery with synthetically generated data to enhance algorithms for automatic aircraft detection and attribute identification. This dataset is the largest openly available very high-resolution resource for synthetic data testing in an overhead perspective.

jakteristics is an open-source Python library designed for extracting geometric features from point cloud data. It provides tools for analyzing the local neighborhood of points and deriving various descriptive attributes, which are crucial for tasks like classification and segmentation of 3D data.

lidR is an R package designed for processing airborne LiDAR data. It provides powerful tools for point cloud manipulation, analysis, and visualization, with a strong focus on applications in forestry. The package enables users to perform tasks such as terrain modeling, individual tree segmentation, and forest structure analysis.

The FloodPlanet dataset provides manually labeled inundation data, meticulously collected for advancing flood detection research. It serves as a crucial resource for training and validating deep learning models, utilizing high-resolution imagery from PlanetScope, Sentinel-1, and Sentinel-2 satellites. This version 1.0 dataset, contributed by Zhijie(JJ) Zhang and collaborators, is a valuable asset for the geospatial community.

This GitHub repository provides a comprehensive collection of resources focused on the intersection of mineral exploration and machine learning. It features useful code examples, libraries, and tools to assist practitioners and researchers in applying advanced analytical methods to geological data. The repository serves as a valuable hub for discovering practical applications and learning materials in this specialized field.

This initiative by the Space Research Institute of the Russian Academy of Sciences focuses on satellite monitoring technologies. The project utilizes satellite imagery, such as that from Proba-V, to create detailed maps of forest cover. These maps are a key output of the Proba-V-TerraNorte project, contributing to environmental understanding.

Orfeo ToolBox (OTB) is a powerful C++ library designed for processing satellite images and other high-resolution geospatial data. It offers a wide array of image processing algorithms, including classification, segmentation, filtering, and geometric corrections, making it a robust solution for remote sensing applications.

The GlobCover Portal offers global land cover maps and composites, a result of an ESA initiative with partners like JRC, EEA, and FAO. It utilizes observations from the 300m MERIS sensor on board the ENVISAT satellite mission to deliver land cover products for specific periods, including 2004-2006 and 2009.