layumi/University1652-Baseline

ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization :helicopter: annotates 1652 buildings in 72 universities around the world.

What it solves

This project provides a benchmark and baseline for drone-based geo-localization. It addresses the challenge of matching images from different perspectives—specifically drone-view, satellite-view, and street-view—to identify the location of a target building.

How it works

The system uses deep learning models (such as ResNet or VGG-16) to extract features from images. It supports two primary tasks:

  1. Drone-view target localization: Matching a drone-view image or video to the most similar satellite-view image to locate a building.
  2. Drone navigation: Using a satellite-view image to find relevant drone-view images from a flight history to navigate back to a target location.

Who it’s for

This is primarily for researchers and developers working on spatial intelligence, UAV (Unmanned Aerial Vehicle) navigation, and cross-view image retrieval.

Highlights

  • Multi-source Dataset: Includes images of 1,652 buildings from 72 universities worldwide across drone, satellite, and street views.
  • Training Features: Supports native PyTorch Float16 and BFloat16, linear warm-up, and random erasing.
  • Evaluation Tools: Includes capabilities for re-ranking, multiple query evaluation, and visualization of ranking results.
  • Extensibility: Provides a baseline for triplet loss and integrates with other datasets like CVUSA and CVACT.

Related

  • Project
    facebookresearch/OrienterNet

    A deep neural network for visual localization that determines an image's position and orientation by matching it to 2D public maps like OpenStreetMap.

  • Project
    azavea/raster-vision

    A Python library and low-code framework for building computer vision models on satellite, aerial, and drone imagery using PyTorch.

  • Project
    tudelft-iv/view-of-delft-dataset

    A multi-sensor automotive dataset containing synchronized LiDAR, camera, and 3+1D radar data with 3D bounding box annotations for road user detection in urban traffic.

  • Project
    Climate-Vision/ClimateVision

    An open-source machine learning platform that uses deep learning and satellite imagery to automatically detect deforestation, arctic ice melting, and flooding.

  • Project
    dfl-rlab/dddmr_navigation

    A 3D mobile robot navigation stack that enables mapping, localization, and autonomous navigation in complex multi-level environments, overcoming the limitations of 2D navigation frameworks.