HawkEye is a system that leverages a cGAN architecture to recover high-frequency shapes from raw low-resolution mmWave heatmaps. It addresses challenges specific to the structure and nature of the radar signals involved. We also develop a data synthesizer to aid with large-scale dataset generation for training.
This repository contains the 3D Millimeter-wave radar heatmap dataset of cars used in HawkEye, as well as the Matlab implementation of the radar data synthesizer that is used to generated simulated training dataset for HawkEye.
Through Fog High Resolution Imaging Using Millimeter Wave Radar
Junfeng Guan, Sohrab Madani, Suraj Jog, Saurabh Gupta, Haitham Hassanieh
In CVPR 2020.
.
├── Dataset
├── camera # RGB camera images
├── documentation # Document for HawkEye Dataset
├── radar # 3D mmWave radar heatmaps
├── stereo camera # Stereo camera depth-maps
├── Synthesizer
├── CAD # CAD models of cars
├── documentation # Document for HawkEye Radar Data Synthesizer
├── scripts # Various setup scripts for mmwavestudio, etc
├── functions
├── model_point_reflector.m # model radar point reflectors in the scene
├── radar_dsp.m # radar signal processing, generating 3D radar heatmaps
├── remove_occlusion.m # remove occluded body of the car
├── simulate_radar_signal.m # simulate received radar signals in the receiver antenna array
├── main.m # main radar data simulation function
├── variable_library.m # library of various variables
├── variable_library_radar.m # radar configuration related variables
├── COPYRIGHT.txt
├── README.md
- Please submit issues to our GitHub if you found any bugs or have any suggestions
- For anything else, send an email at [email protected]
Please cite our paper in your publications if it helps your research. Here is an example BibTeX entry:
@InProceedings{Guan_2020_CVPR,
author = {Guan, Junfeng and Madani, Sohrab and Jog, Suraj and Gupta, Saurabh and Hassanieh, Haitham},
title = {Through Fog High-Resolution Imaging Using Millimeter Wave Radar},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}