Tools tagged with "Deep Learning"

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.

The Spatial Data Science Conference (SDSC) brings together professionals from Geospatial, Analytics, and Data Science fields. It focuses on the latest advances in spatial analytics, relevant use cases, and new types of location data. SDSC provides a unique opportunity for networking, upskilling, and understanding industry evolution across private and public sectors.

Loop is an open-source platform for 3D probabilistic geological and geophysical modelling. Initiated by Geoscience Australia and OneGeology, it is funded by various Australian geological surveys, the Australian Research Council, and the MinEx CRC, supporting advanced subsurface analysis.

Ai2, founded by Paul Allen, conducts high-impact research and engineering to tackle key problems in artificial intelligence. This institute focuses on developing and providing open models, applications for science and the environment, and advancing AI research.

OmniCloudMask is a Python library designed for state-of-the-art cloud and cloud shadow segmentation in high to moderate resolution satellite imagery. It offers higher accuracy and supports a wide range of resolutions, sensors, and processing levels, validated on data from Sentinel-2, PlanetScope, Landsat, and Maxar.

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.

The KITTI Vision Benchmark Suite offers challenging real-world datasets for computer vision tasks in autonomous driving. Data is collected using a research vehicle equipped with high-resolution cameras, a Velodyne laser scanner, and a GPS system in various environments around Karlsruhe, Germany. It provides benchmarks for tasks like stereo, optical flow, visual odometry, 3D object detection, and 3D tracking.

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.

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.

FlexRoad is a framework that transforms noisy 3D road reconstructions into smooth, accurate, and realistic road meshes. It addresses limitations of existing methods by fitting Non-Uniform Rational B-Splines (NURBS) surfaces to 3D road points. The framework is crucial for autonomous driving, urban planning, and virtual simulations, ensuring high-quality road models by reducing artifacts and inconsistencies found in typical planar representations.

This GitHub repository hosts a robust library designed for time series forecasting leveraging the PyTorch framework. It provides tools and models to develop and contribute to state-of-the-art forecasting solutions using deep learning techniques.

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.

openMVG (open Multiple View Geometry) is a C++ library that offers a complete solution for 3D computer vision tasks, particularly focusing on Structure from Motion (SfM). It provides robust algorithms and tools for reconstructing 3D scenes from multiple images, making it a fundamental resource for photogrammetry and related applications.

COLMAP is a sophisticated open-source photogrammetry software solution designed for 3D reconstruction from collections of images. It implements a robust and modular Structure-from-Motion (SfM) and Multi-View Stereo (MVS) pipeline. This tool is widely used for generating dense point clouds and 3D models from unordered image sets, making it valuable for various computer vision and geospatial applications.

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 repository offers a global dataset of building density and height, generated quarterly by applying machine learning models to PlanetScope basemaps. It provides a global public layer and detailed data for five high-growth locations, distributed as Cloud-Optimized GeoTIFFs (COGs). The resource supports both data exploration and model training for users interested in urban development analysis.

The TACO dataset addresses the critical need for annotated images to train deep learning models for trash detection. It aims to advance AI applications in environmental monitoring, such as drone-based trash surveying and robotic litter collection, by providing a comprehensive and continually updated collection of segmented trash images.

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.

SegmentAnyTree is an open-source GitHub repository dedicated to tree segmentation. It provides code and resources for identifying and delineating individual trees, likely utilizing advanced machine learning techniques on various types of geospatial imagery. This project supports detailed forest analysis and environmental monitoring efforts.

This GitHub repository serves as an "awesome list" for photogrammetry, collecting a wide range of projects, libraries, and tools related to the field. It provides a community-driven compilation for developers, researchers, and enthusiasts looking for relevant resources. The list aims to categorize and highlight significant contributions in photogrammetry.