About
To promote the ISAC sduty, we build a
sensing channel dataset -- Sensiverse, which includes channel
data in different scenarios and
a large number of scenes and can bring the following benefits.
- Building a multi-scenario and multi-mode sensing channel dataset supports applications such as moving target detection, 3D environment imaging and reconstruction, and integrated sensing and communication solution evaluation.
- Avoiding the problem of evaluating results that do not converge to the real performance due to a limited number of evaluated channel samples.
- Mitigating the problem of high computational complexity. The dataset is generated offline and stored, which exchanges storage for computing power to reduce the computational resource consumption required by subsequent large-scale simulation evaluations.
- The dataset can be used for calibration and training of hybrid channel models and for training and testing in machine learning for sensing.
We will continue to update and enrich its contents in the future, and welcome feedbacks and suggestions from industry and academia to participate in expanding the dataset together.
Scenarios supported and examples
3D environment reconstruction




multi-static extended object tracking




License
This Sensiverse dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/.
Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/.
Citation
@misc{Luo2023Sensiverse, title={Sensiverse: A dataset for ISAC study}, author={Jiajin Luo, Baojian Zhou, Yang Yu, Ping Zhang, Xiaohui Peng, Jianglei Ma, Peiying Zhu, Jianmin Lu, Wen Tong}, year={2023}, eprint={2308.13789}, archivePrefix={arXiv}, primaryClass={eess.SP} }
If you have any comments or suggestions,
please feel free to contact us via email at luojiajin@huawei.com