Skip to content

Commit d9f38bc

Browse files
author
Manuel Stoiber
committed
feat(ICG+): update readme
1 parent 9208f06 commit d9f38bc

1 file changed

Lines changed: 2 additions & 6 deletions

File tree

ICG+/readme.md

Lines changed: 2 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -21,18 +21,14 @@ In many applications of advanced robotic manipulation, six degrees of freedom (6
2121
The *ICG+* tracker was fully integrated into the multi-body, multi-modality, and multi-camera tracking library *M3T*. In contrast to *ICG+*, *M3T* provides additional functionality, such as the tracking of kinematic structures. Note that it was ensured that the evaluation results for *ICG+* and *M3T* are exactly the same. If you would like to reproduce results from our publication or use the tracker in your own application, please use the code from *M3T* from the following [directory](https://github.com/DLR-RM/3DObjectTracking/tree/master/M3T).
2222

2323
## Evaluation
24-
The [code](https://github.com/DLR-RM/3DObjectTracking/tree/master/M3T/examples) in `examples/evaluate_ycb_dataset.cpp`, `examples/evaluate_opt_dataset.cpp`, `examples/parameters_study_ycb.cpp`, and `examples/parameters_study_opt.cpp` was used for the evaluation on the [YCB-Video](https://rse-lab.cs.washington.edu/projects/posecnn/) and [OPT](http://media.ee.ntu.edu.tw/research/OPT/) datasets.
25-
To reproduce results, please download the datasets and adjust the parameters `dataset_directory` in the source code.
26-
Note that files for sparse viewpoint models (e.g. 002_master_chef_can_depth_model.bin, 002_master_chef_can_region_model.bin, ...) will be created automatically and are stored in specified `external_directory` folders.
27-
For the evaluation of the *YCB-Video* dataset, please unzip `data/ycb-video_poses.zip` and store its content in the corresponding `external_directory`.
28-
Also, for the evaluation of multi-region tracking, the content of the `data/ycb-video_multi-region_<X>.zip` files, which contain required .obj files, has to be copied into the `external_directory`.
24+
The [code](https://github.com/DLR-RM/3DObjectTracking/tree/master/M3T/examples) in `examples/evaluate_ycb_dataset.cpp`, `examples/evaluate_opt_dataset.cpp`, `examples/parameters_study_ycb.cpp`, and `examples/parameters_study_opt.cpp` was used for the evaluation on the [YCB-Video](https://rse-lab.cs.washington.edu/projects/posecnn/) and [OPT](http://media.ee.ntu.edu.tw/research/OPT/) datasets. To reproduce results, please download the datasets and adjust the parameters `dataset_directory` in the source code. Note that files for sparse viewpoint models (e.g. 002_master_chef_can_depth_model.bin, 002_master_chef_can_region_model.bin, ...) will be created automatically and are stored in specified `external_directory` folders. For the evaluation of the *YCB-Video* dataset, please unzip `data/ycb-video_poses.zip` and store its content in the corresponding `external_directory`. Also, for the evaluation of multi-region tracking, the content of the `data/ycb-video_multi-region_<X>.zip` files, which contain required .obj files, has to be copied into the `external_directory`. The .zip files can be found in the following [folder](https://github.com/DLR-RM/3DObjectTracking/tree/master/M3T/data).
2925

3026
## Citation
3127
If you find our work useful, please cite us with:
3228

3329
```
3430
@InProceedings{Stoiber_2023_IROS,
35-
author = {Stoiber, Manuel and Elsayed, Mariam and Rechert, Anne E. and Steidle, Florian and Lee, Dongheui and Triebel, Rudolph},
31+
author = {Stoiber, Manuel and Elsayed, Mariam and Rechert, Anne E. and Steidle, Florian and Lee, Dongheui and Triebel, Rudolph},
3632
title = {Fusing Visual Appearance and Geometry for Multi-Modality 6DoF Object Tracking},
3733
year = {2023},
3834
}

0 commit comments

Comments
 (0)