dETRUSC: video dataset for detection and tracking
This dataset includes 24 videos captured with the on-board camera of the Jetson TX2 development kit.
The videos are classified in two directories:
| Name | Content description | Number of videos | Resolution | FPS |
|---|---|---|---|---|
| in | Indoor scenes | 07 | 320×240 | 10 |
| out | Outdoor scenes | 17 | 320×240 | 10 |
Application
The dataset was used to validate the peformance of a deep learning-based multiple object visual tracking algorithm on Jetson TX2 development kit.
This video example shows both video processing and live performance results in outdoor and indoor scenarios.
Live performance
Video examples of real time performance at 10 fps video capture.
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You can use this dataset on your publication as long as you include a citation to the reference on this page. When including a link to the dataset, please use this page instead of linking the files directly.
Info
-
- Researchers
- Daniel García Lesta
- Víctor Manuel Brea Sánchez
- Paula López Martínez
- Beatriz Blanco Filgueira
