This code has been tested on Ubuntu 16.04, Python 3.6, Pytorch 0.4.1/1.2.0, CUDA 9.0. Please install related libraries before running this code:
pip install -r requirements.txt| Dataset | ADSiamRPN | BAENet | MFIHVT | MHT | DeepHKCF | BS-SiamRPN | SiamRPN++ | DaSiamRPN | |
| HOT2022 | Success | 57.5 | 61.6 | 60.1 | 58.4 | 38.5 | 53.3 | 52.9 | 55.8 |
| Precision | 86.1 | 87.6 | 89.1 | 87.6 | 73.7 | 84.5 | 83.4 | 83.1 | |
Download the pretrained model:
model code: bm1e
and put them into models directory.
Download the test result:
hot2022_result code: 4taf
The code is implemented based on pysot. We would like to express our sincere thanks to the contributors.
If you use ADSiamRPN in your work please cite our papers:
@article{wang2023ad,
title={AD-SiamRPN: Anti-Deformation Object Tracking via an Improved Siamese Region Proposal Network on Hyperspectral Videos},
author={Wang, Shiqing and Qian, Kun and Shen, Jianlu and Ma, Hongyu and Chen, Peng},
journal={Remote Sensing},
volume={15},
number={7},
pages={1731},
year={2023},
publisher={MDPI}
}
@inproceedings{wang2022bs,
title={BS-SiamRPN: Hyperspectral video tracking based on band selection and the Siamese region proposal network},
author={Wang, ShiQing and Qian, Kun and Chen, Peng},
booktitle={2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)},
pages={1--8},
year={2022},
organization={IEEE}
}