Survizor is a visual analysis tool for the mining and understanding of the key content of the surveillance video.
This website is Survizor's Django Web project.
If you want to test the existing video data in the project, please prepare the python environment (Installation) and the Django Web project (Get Started).
First, you need to create a virtual environment for Survizor, and then install related dependencies. Please refer to "requirements.txt" for more detailed tools and versions.conda create -n SurVizorEnv python=3.8
conda activate SurVizorEnv
pip install numpy
pip install pandas
...
If you want to run Survizor on your own video data, please get relevant features first, and the reference link is as follows:
Aesthetics and Quality Feature, Memory Feature, Anomaly Feature.
Survizor provides a pipeline, so the project includes but not limited to these four features.
You can expand the project according to your needs and modify the corresponding codes.
If you find this project useful in your research, please consider cite:
@article{sun2022survizor,
title={SurVizor: visualizing and understanding the key content of surveillance videos},
author={Sun, Guodao and Li, Tong and Liang, Ronghua},
journal={Journal of Visualization},
volume={25},
number={3},
pages={635--651},
year={2022},
publisher={Springer}
}