Commit 57ce880f authored by Jong, Stefan1 de's avatar Jong, Stefan1 de
Browse files

Update README.md

parent 9382d020
......@@ -6,13 +6,14 @@ This is the code to our research 'Stepping towards real-time detection and track
![](visualizations/test_8_wearable_sensor.gif)
A video of the results of TrackR-CNN on our test set can be found on [Youtube][Youtube_link]
Link to 1-minute video of results on validation sets:
TODO: ADD VIDEO OR GIF of results
## Dataset
We created our own dataset called **APPLE_MOTS** related to the [KITTI_MOTS dataset][Kitti_MOTS] of [TrackR-CNN][TrackR-CNN_MOTS] (persons and cars).
Images and annotations of APPLE_MOTS can be downloaded [here][data].
Images and annotations of APPLE_MOTS can be downloaded [here][data]. Some example pictures of the 9 datasets:
![](visualizations/dataset_1.png) ![](visualizations/dataset_2.png) ![](visualizations/dataset_3.png)
![](visualizations/dataset_4.png) ![](visualizations/dataset_5.png) ![](visualizations/dataset_6.png)
......@@ -184,10 +185,10 @@ For future research it can be of interest to use the Tensorflow Object Detection
## Contact
For questions related to the code please contact stefan.dejong@wur.nl or create an issue.
<!-- Identifiers, in alphabetical order -->
[TrackR-CNN_MOTS]: https://www.vision.rwth-aachen.de/media/papers/mots-multi-object-tracking-and-segmentation/MOTS.pdf
[TrackR-CNN_repo]: https://github.com/VisualComputingInstitute/TrackR-CNN
[Kitti_MOTS]: https://www.vision.rwth-aachen.de/page/mots
[Youtube_link]: https://youtu.be/6pNhdK-T_e4
[data]: TODO
[pretrained]: TODO
[Tensorflow]: TODO
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment