| Name | spseg-tool JSON |
| Version |
2023.5a0
JSON |
| download |
| home_page | |
| Summary | SP-SEG: Proof of concept tool for manual segmentation by spheripixel projection |
| upload_time | 2023-05-16 09:23:06 |
| maintainer | |
| docs_url | None |
| author | |
| requires_python | >=3.10 |
| license | MIT License |
| keywords |
point cloud
segmentation
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# SP-SEG: Proof of concept tool for manual segmentation by spheripixel projection
In this repository, you can find a proof of concept of the tool for manual point cloud labeling by spherical point-pixel projection.
## ❗ Limitations
The current version is just the proof of concept version.
## 🔧 Environment and installation
```python
python >= 3.10
```
Required packages:
```python
"PyQt5",
"Pillow",
"numpy",
"pydantic",
"scikit-learn",
"scipy",
"colormath",
"tqdm",
"toml"
```
To install the software:
1. Clone the repository and run inside:
```bash
pip install .
```
1. Or use:
```bash
pip install sp-seg
```
> If you're experiencing issues with installing the package, install firstly the dependencies:
> ```bash
> pip install PyQt5 Pillow numpy pydantic scikit-learn scipy colormath tqdm toml
> ```
Then, you can run the software with the command:
```bash
D:\>spseg
```
## 📖 Instruction
The main view of the software looks like the following:
1. [Starting the application](#starting-the-application)
1. [Opening point cloud](#opening-a-point-cloud)
1. [Loading labels definition](#loading-labels-definition)
1. [Zooming in and out](#zooming-in-and-out)
1. [Depth preview](#depth-preview)
1. [Depth scale](#depth-scale)
1. [Vertical roll](#vertical-roll)
1. [Horizontal roll](#horizontal-roll)
1. [Object segentation](#object-segmentation)
1. [Deselecting region](#deselecting-region)
1. [Changing mask opacity](#changing-mask-opacity)
1. [Accepting an object](#accepting-an-object)
1. [Saving segmentation result](#saving-segmentation-result)
### Starting the application
Having installed the application, just run the following command in the command line:
```bash
D:\>spseg
```
### Opening a point cloud
To open a point cloud, click `Open` icon in the toolbar and choose a proper file.
> ❗ At the moment only PTS files are supported
> ❗ If you need to change the columns meaning of PTS opener, modify the `opener.column` key of the config file. Currently interpretable letters are `X`, `Y`, `Z`, `R`, `G`, and `B`
### Loading labels definition
To open labels click the proper icon in the toolbar and choose the JSON file with labels definitions.
Example labels definition may look like below:
```json
[
{
"label": "ceiling",
"code": 0,
"color": [4, 255, 0]
},
{
"label": "floor",
"code": 1,
"color": [255, 128, 0]
}
]
```
### Zooming in and out
For easier detail selection you can zoom in and zoom out. To do so keep `Ctrl` pressed and use mouse wheel.
### Depth preview
Sometimes, it may be useful to get insight into depth distribution. To see the depth map, just press `Alt` button.
### Depth scale
To change $\gamma$ of the depth map, use `+` or `-` buttons while `Alt` is pressed.
### Vertical roll
To roll the scene vertically, press `Q` button.
### Horizontal roll
To roll the scene horizontally, press `W` button.
### Object segmentation
To segment an object, choose the proper category in the menu of the left and start selecting the polygon.
To add a vertex to the polygon, use left mouse button. If you want to close a polygon, click right mouse button.
> ❗ Closing polygon creates an edge between the first and the last added vertex!
> ❗ You don't need to select the entire object using a single polygon. You can draw as many polygons for an object as you wish, until the object segmentation will be accepted by pressing `F1` button.
### Deselecting region
You can deselect fragments of scene selected by mistake. To do so, check the mode to `Deselect` (radio button in the tollbar) or use `Caps Lock` button.
For deselecting you also draws a polygon.
> ❗ Remember to change the mode to `Select` when you already deselected the desired points.
### Changing mask opacity
To change the opacity of the mask of currently segmented object, use the slider just below the toolbar.
### Accepting an object
When you finish the object segmentation you need to accept the instance of the category by clicking `F1` button.
### Saving segmentation result
To save the PTS result, choose the proper icon in the toolbar menu.
## 🏎️ Further development
- [ ] code optimization
- [ ] code cleaning
- [ ] add handling other point cloud formats
- [ ] handle non-single-setup point clouds
- [ ] enable saving draft segmentation result
## 📝 Citation
```bibtex
@ONLINE{sp-seg,
author = {Walczak, J., Osuch, A., Wojciechowski, A.},
title = {{SP-SEG}: Proof of concept tool for manual segmentation by spheripixel projection},
year = 2023,
url = {https://github.com/jamesWalczak/sp-seg-tool},
urldate = {<access date here>}
}
```
## ⚖️ 3rd party attribution
<b>Icons attribution:</b> <a href='https://www.flaticon.com/free-icons/save' title='save icons'>Save icons created by Freepik - Flaticon</a>
<br/>
<b>Animation attribution:</b> Animation generated from <a href='https://icons8.com'>Icons8</a>
## 🎁 Ackowledgement
This software was developed as a part of the research project "Semantic analysis of 3D point clouds", co-funded by the Polish National Center for Research and Development under the LIDER XI program [grant number 0092/L-11/2019].
Raw data
{
"_id": null,
"home_page": "",
"name": "spseg-tool",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": "",
"keywords": "point cloud,segmentation",
"author": "",
"author_email": "\"Jakub Walczak, Adam Osuch, Adam Wojciechowski\" <jakub.walczak@p.lodz.pl>",
"download_url": "https://files.pythonhosted.org/packages/37/d7/ae992c349fb47a913718466f0a70f6536c5017b1ec218bcacb24612939f4/spseg-tool-2023.5a0.tar.gz",
"platform": null,
"description": "# SP-SEG: Proof of concept tool for manual segmentation by spheripixel projection\nIn this repository, you can find a proof of concept of the tool for manual point cloud labeling by spherical point-pixel projection.\n\n## \u2757 Limitations\nThe current version is just the proof of concept version.\n\n## \ud83d\udd27 Environment and installation\n```python\npython >= 3.10\n```\nRequired packages:\n```python\n\"PyQt5\",\n\"Pillow\",\n\"numpy\",\n\"pydantic\",\n\"scikit-learn\",\n\"scipy\",\n\"colormath\",\n\"tqdm\",\n\"toml\"\n```\n\nTo install the software:\n1. Clone the repository and run inside:\n```bash\npip install .\n```\n1. Or use:\n```bash\npip install sp-seg\n```\n\n> If you're experiencing issues with installing the package, install firstly the dependencies:\n> ```bash\n> pip install PyQt5 Pillow numpy pydantic scikit-learn scipy colormath tqdm toml\n> ```\n\nThen, you can run the software with the command:\n```bash\nD:\\>spseg\n```\n\n\n## \ud83d\udcd6 Instruction\nThe main view of the software looks like the following:\n\n1. [Starting the application](#starting-the-application)\n1. [Opening point cloud](#opening-a-point-cloud)\n1. [Loading labels definition](#loading-labels-definition)\n1. [Zooming in and out](#zooming-in-and-out)\n1. [Depth preview](#depth-preview)\n1. [Depth scale](#depth-scale)\n1. [Vertical roll](#vertical-roll)\n1. [Horizontal roll](#horizontal-roll)\n1. [Object segentation](#object-segmentation)\n1. [Deselecting region](#deselecting-region)\n1. [Changing mask opacity](#changing-mask-opacity)\n1. [Accepting an object](#accepting-an-object)\n1. [Saving segmentation result](#saving-segmentation-result)\n\n\n### Starting the application\nHaving installed the application, just run the following command in the command line:\n```bash\nD:\\>spseg\n```\n### Opening a point cloud\nTo open a point cloud, click `Open` icon in the toolbar and choose a proper file.\n> \u2757 At the moment only PTS files are supported \n\n> \u2757 If you need to change the columns meaning of PTS opener, modify the `opener.column` key of the config file. Currently interpretable letters are `X`, `Y`, `Z`, `R`, `G`, and `B`\n\n\n\n\n### Loading labels definition\nTo open labels click the proper icon in the toolbar and choose the JSON file with labels definitions.\nExample labels definition may look like below:\n\n```json\n[\n {\n \"label\": \"ceiling\",\n \"code\": 0,\n \"color\": [4, 255, 0]\n },\n {\n \"label\": \"floor\",\n \"code\": 1,\n \"color\": [255, 128, 0]\n }\n]\n```\n\n\n\n\n### Zooming in and out\nFor easier detail selection you can zoom in and zoom out. To do so keep `Ctrl` pressed and use mouse wheel.\n\n\n\n### Depth preview\nSometimes, it may be useful to get insight into depth distribution. To see the depth map, just press `Alt` button.\n\n\n### Depth scale\nTo change $\\gamma$ of the depth map, use `+` or `-` buttons while `Alt` is pressed.\n\n\n\n### Vertical roll\nTo roll the scene vertically, press `Q` button.\n\n\n\n### Horizontal roll\nTo roll the scene horizontally, press `W` button.\n\n\n### Object segmentation\nTo segment an object, choose the proper category in the menu of the left and start selecting the polygon.\nTo add a vertex to the polygon, use left mouse button. If you want to close a polygon, click right mouse button.\n\n> \u2757 Closing polygon creates an edge between the first and the last added vertex!\n\n> \u2757 You don't need to select the entire object using a single polygon. You can draw as many polygons for an object as you wish, until the object segmentation will be accepted by pressing `F1` button.\n\n\n\n### Deselecting region\nYou can deselect fragments of scene selected by mistake. To do so, check the mode to `Deselect` (radio button in the tollbar) or use `Caps Lock` button.\nFor deselecting you also draws a polygon.\n\n> \u2757 Remember to change the mode to `Select` when you already deselected the desired points.\n\n\n\n### Changing mask opacity\n\nTo change the opacity of the mask of currently segmented object, use the slider just below the toolbar.\n\n\n\n### Accepting an object\nWhen you finish the object segmentation you need to accept the instance of the category by clicking `F1` button.\n\n\n\n### Saving segmentation result\nTo save the PTS result, choose the proper icon in the toolbar menu.\n\n\n\n## \ud83c\udfce\ufe0f Further development\n- [ ] code optimization\n- [ ] code cleaning\n- [ ] add handling other point cloud formats\n- [ ] handle non-single-setup point clouds\n- [ ] enable saving draft segmentation result\n\n\n## \ud83d\udcdd Citation\n\n```bibtex\n@ONLINE{sp-seg,\n author = {Walczak, J., Osuch, A., Wojciechowski, A.},\n title = {{SP-SEG}: Proof of concept tool for manual segmentation by spheripixel projection},\n year = 2023,\n url = {https://github.com/jamesWalczak/sp-seg-tool},\n urldate = {<access date here>}\n}\n```\n\n## \u2696\ufe0f 3rd party attribution\n<b>Icons attribution:</b> <a href='https://www.flaticon.com/free-icons/save' title='save icons'>Save icons created by Freepik - Flaticon</a>\n<br/>\n<b>Animation attribution:</b> Animation generated from <a href='https://icons8.com'>Icons8</a>\n\n## \ud83c\udf81 Ackowledgement\nThis software was developed as a part of the research project \"Semantic analysis of 3D point clouds\", co-funded by the Polish National Center for Research and Development under the LIDER XI program [grant number 0092/L-11/2019]. \n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "SP-SEG: Proof of concept tool for manual segmentation by spheripixel projection",
"version": "2023.5a0",
"project_urls": null,
"split_keywords": [
"point cloud",
"segmentation"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "71dc20a709335ea2bb3bcf26193668a740685a4d7c8e6d7faea5ec61d24989a3",
"md5": "4a6a45749466c2e9846aceacc821f1e7",
"sha256": "bfaef8ca2bc0cbb3758ba8cdd9ba04c3c9ff97710f3e4982048de868fd910cba"
},
"downloads": -1,
"filename": "spseg_tool-2023.5a0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4a6a45749466c2e9846aceacc821f1e7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 134592,
"upload_time": "2023-05-16T09:23:03",
"upload_time_iso_8601": "2023-05-16T09:23:03.764226Z",
"url": "https://files.pythonhosted.org/packages/71/dc/20a709335ea2bb3bcf26193668a740685a4d7c8e6d7faea5ec61d24989a3/spseg_tool-2023.5a0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "37d7ae992c349fb47a913718466f0a70f6536c5017b1ec218bcacb24612939f4",
"md5": "95ac54524cf195c1e4e64948fde1a2de",
"sha256": "d6c88c6ff3fe39d6b8186813e1150247c41cb00301b7ea5c5a56291c74147ead"
},
"downloads": -1,
"filename": "spseg-tool-2023.5a0.tar.gz",
"has_sig": false,
"md5_digest": "95ac54524cf195c1e4e64948fde1a2de",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 133637,
"upload_time": "2023-05-16T09:23:06",
"upload_time_iso_8601": "2023-05-16T09:23:06.482691Z",
"url": "https://files.pythonhosted.org/packages/37/d7/ae992c349fb47a913718466f0a70f6536c5017b1ec218bcacb24612939f4/spseg-tool-2023.5a0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-16 09:23:06",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "spseg-tool"
}
