DeepSense 6G

A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset for
6G Deep Learning Research

0 +

 Downloads Since Release in March 2022

News

3 November 2024

The DeepSense6G Workshop recording is now live!

We are pleased to announce that 1st DeepSense 6G Workshop has now a recording available. Let us know if you have any questions and if you find the ML notebooks useful!

 

Click here for the Notebooks!

Reproducing the Research Results

What is DeepSense 6G?

DeepSense 6G is a real-world multi-modal dataset that comprises coexisting multi-modal sensing and communication data, such as mmWave wireless communication, Camera, GPS data, LiDAR, and Radar, collected in realistic wireless environments 

  • World’s first large-scale real-world sensing-communication dataset 
  • 1Million+ multi-modal sensing-communication data samples 
  • Modalities include mmWave comm., GPS, Image, LiDAR and Radar
  • 30+ scenarios targeting various applications 
  • Several indoor/outdoor locations with high diversity 
  • Data collected at different times of day and weather conditions
  • Tens of thousands of manually and auto labeled data 

DeepSense Scenarios

The DeepSense 6G dataset is offered in different scenarios. The different scenarios cover a diverse vehicular, drone, indoor/outdoor scenarios. Each scenario consists of co-existing multi-modal sensing and communication data

Key Highlights:
  • 30+ scenarios collected over several locations
  • Both indoor and outdoor scenarios
  • Locations range from parking lots to busy downtown streets
  • Scenarios comprise  data collected at different times of the day
  • Scenarios for drones, vehicles, RIS, human, robots, and more … 
  • Scenarios are designed to enable different novel applications

For more details, please click on the link below. 

Applications and ML Tasks

DeepSense 6G enables a wide range of applications in communication, sensing, and localization. 

To encourage the development of machine learning solutions for these applications and motivate benchmarking and comparisons, we define specific machine learning task. 

For each DeepSense 6G-based task, we provide (i) Task definition and formulation, (ii) diverse real-world task-specific development dataset, and (iii) benchmarking scripts. For more details, please click on the link below

License

In order to use the DeepSense dataset/scripts or any (modified) part of them, please cite:

A. Alkhateeb, G. Charan, T. Osman, A. Hredzak, J. Morais, U. Demirhan, and N. Srinivas, “DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Datasets,” IEEE Communications Magazine, 2023.

@Article{DeepSense,
author={Alkhateeb, Ahmed and Charan, Gouranga and Osman, Tawfik and Hredzak, Andrew and Morais, Joao and Demirhan, Umut and Srinivas, Nikhil},
title={DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset},
journal={IEEE Communications Magazine},
year={2023},
publisher={IEEE}}

Join the DeepSense mailing list to get the recent updates