Single Scene Video Anomaly Detection Metrics
Project description
Single-Scene Video Anomaly Detection Metrics
This project contains evaluation protocol (metrics) for benchmarking single-scene video anomaly detection.
Evaluation Protocol
This is an unofficial implementation of Sec. 2.2 of A Survey of Single-Scene Video Anomaly Detection.
Installation
This metrics is available via PyPI.
pip install py-ssvad-metrics
Usage
-
Prepare ground-truth JSON file and prediction JSON file. Examples are in the
tests
folder. -
For UCSD Pedestrian 1 and 2 datasets, CUHK Avenue dataset, and Street Scene dataset, we provided scripts for converting ground-truth annotation files from Street Scene dataset. Download link is provided in the paper [http://www.merl.com/demos/video-anomaly-detection].
-
Example usage for single groundtruth and prediction file pair:
import ssvad_metrics result = ssvad_metrics.metrics.evaluate( "tests/gt_examples/Test001_gt.json", "tests/pred_examples/Test001_pred.json")
-
Example usage for multiple groundtruth and prediction file pairs:
import ssvad_metrics result = ssvad_metrics.metrics.accumulated_evaluate( "tests/gt_examples", "tests/pred_examples", gt_name_suffix="_gt", pred_name_suffix="_pred")
References
- B. Ramachandra, M. Jones and R. R. Vatsavai, "A Survey of Single-Scene Video Anomaly Detection," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2020.3040591.
Copyright
Copyright PT Qlue Performa Indonesia 2021 All Rights Reserved
Contributing
Feel free to contribute for improvements.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for py_ssvad_metrics-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 07e7022b397d2ae0b6cb142878bdbf2031b772339132505118aec6ad6e5bc658 |
|
MD5 | caa57ca1eb3f1c8837a3b18ca774d716 |
|
BLAKE2b-256 | b091ace3b1b621f583f033c30bfc014f222bcfd1077c6e43edef02edc8bf0407 |