UBI
Event Detection

Abnormal Event Detection Dataset

UBI-Fights [Download] Concerning a specific anomaly detection and still providing a wide diversity in fighting scenarios, the UBI-Fights dataset is a unique new large-scale dataset of 80 hours of video fully annotated at the frame level. Consisting of 1000 videos, where 216 videos contain a fight event, and 784 are normal daily life situations. All unnecessary video segments (e.g., video introductions, news, etc.) that could disturb the learning process were removed. The videos' title contains flags concerning the type of the respective video, such as:

Fight: F_id_environment_camera_color.mp4
Normal: N_id_environment_camera_color.mp4

Environment: Indoor (0) / Outdoor (1);
Camera: Fixed (0) / Rotated (1) / Movable (2);
Color: RGB (0) / Grayscale (1);

Examples

Statistics

All videos are resized to the dimension 640x360 pixels, and the frame rate was set to 30 fps.

Authors

Bruno Degardin and Hugo Proença

bruno.degardin@ubi.pt | hugomcp@di.ubi.pt

If you find this useful, please cite our work as follows:

					
@inproceedings{degardin2020human,
	title={Human Activity Analysis: Iterative Weak/Self-Supervised Learning Frameworks for Detecting Abnormal Events},
	author={Degardin, Bruno and Proen{\c{c}}a, Hugo},
	booktitle={2020 IEEE International Joint Conference on Biometrics (IJCB)},
	pages={1--7},
	organization={IEEE}
}