Home

Awesome

DUT-VTUAV

We release a large-scale benchmark for Visble-thermal UAV Tracking.

News

Main Feature

Download from google Drive (python and gdown are required)

import gdown
url = "https://drive.google.com/drive/folders/1GwYNPcrkUM-gVDAObxNqERi_2Db7okjP?usp=sharing"
gdown.download_folder(url, quiet=False, use_cookies=False)

Results for RGB trackers on short-term subset

alt text

Results for RGB trackers on long-term subset

alt text

Results for RGB-T trackers on short-term subset

MSRMPR
DAFNet45.862.0
ADRNet46.662.2
FSRPN54.465.3
mfDiMP55.467.3
HMFT62.775.8

Results for RGB-T trackers on long-term subset

MSRMPR
ADRNet17.523.5
DAFNet18.825.3
FSRPN27.231.5
mfDiMP31.436.6
HMFT35.541.4
HMFT_LT46.153.6

Evaluation toolkit & attribute annotation

The sequence-level attribute annotation can be found in BaiduDisk(code:h24u) and GoogleDrive.
The evaluation toolkit can be found in BaiduDisk(code:99j9) and GoogleDrive.

How to evaluate

Note: The dataset should be extracted into the same folder.

RGB-T tracker evaluation

RGB tracker evaluation

Reference

If you find this benchmark useful, please cite

@InProceedings{Zhang_CVPR22_VTUAV,
author = {Zhang Pengyu and Jie Zhao and Dong Wang and Huchuan Lu and Xiang Ruan},
title = {Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline},
booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
year = {2022}
}

Contact

If you have any questions, feel free to contact me.