https://github.com/ivalab/grasp_multiObject

Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data. This dataset is annotated using the same protocal as Cornell Dataset, and can be used as multi-object extension of Cornell Dataset.
https://github.com/ivalab/grasp_multiObject

cornell-dataset dataset grasp grasping iros2018 ra-l robotics

Last synced: 6 days ago
JSON representation

Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data. This dataset is annotated using the same protocal as Cornell Dataset, and can be used as multi-object extension of Cornell Dataset.

• Host: GitHub
• URL: https://github.com/ivalab/grasp_multiObject
• Owner: ivalab
• Created: 2018-02-24T17:55:51.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2020-07-28T20:48:34.000Z (over 4 years ago)
• Last Synced: 2024-08-04T02:07:59.570Z (4 months ago)
• Topics: cornell-dataset, dataset, grasp, grasping, iros2018, ra-l, robotics
• Language: MATLAB
• Size: 102 KB
• Stars: 101
• Watchers: 5
• Forks: 21
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# grasp_multiObject

Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data.   

This dataset is annotated using the same protocal as [Cornell Dataset](http://pr.cs.cornell.edu/grasping/rect_data/data.php), and can be used as multi-object extension of Cornell Dataset.  







------------------------------

## Usage

Download [RGB-D data](https://www.dropbox.com/s/hrox34p9ymw8jv7/rgbd.tar.gz?dl=0) and put into `grasp_multiObject/rgbd/`  

Each testing data has one RGB image (rgb_xxxx) and one depth image (depth_xxxx).   

The corresponding grasp annotation (rgb_xxxx_annotations) can be found in `grasp_multiObject/annotation/` 

## Generate RG-D data?

```

mkdir rgd

run rgbd2rgd

```

you will have RG-D data in `grasp_multiObject/rgd/`

## Crop images?

```

mkdir rgd_cropped320

mkdir rgb_cropped320

run image2txt

```

you will have cropped RGB and RGD images in `grasp_multiObject/rgd_cropped320/` and `grasp_multiObject/rgb_cropped320/`, respectively.

also, you will have corresponding annotation files, as well as a full list of image path.

## Visualize grasp?

```

run visualizationGripper

```

this file shows a simple example to visualize ground truth grasps

## Annotate your own data?

```

git clone https://github.com/ivalab/grasp_annotation_tool

```

you can annotate grasps on your own data with this simple tool!  

Both dataset and annotation tool can also be found [here](https://www.dropbox.com/s/cwko0qubmqoxehb/multiObj_multiGrasp.tar.gz?dl=0)

## Citation

If you find it helpful for your research, please consider citing:

    @inproceedings{chu2018deep,

      title = {Real-World Multiobject, Multigrasp Detection},

      author = {F. Chu and R. Xu and P. A. Vela},

      journal = {IEEE Robotics and Automation Letters},

      year = {2018},

      volume = {3},

      number = {4},

      pages = {3355-3362},

      DOI = {10.1109/LRA.2018.2852777},

      ISSN = {2377-3766},

      month = {Oct}

    }

If you encounter any questions, please contact me at fujenchu[at]gatech[dot]edu