Python-based GUI tool to extract frames from video files produced with Azure Kinect cameras. Visit the project site at https://pypi.org/project/ak-frame-extractor/ and check the source code at https://github.com/GRAP-UdL-AT/ak_frame_extractor/
- Pre-requisites.
- Functionalities.
- Install and run.
- Files and folder description.
- Development tools, environment, build executables.
- SDK Azure Kinect installed.
- pyk4a library installed. If the operating system is Windows, follow this steps. You can find test basic examples with pyk4a here.
- In Ubuntu 20.04, we provide a script to install the camera drivers following the instructions in azure_kinect_notes.
- Videos recorded with the Azure Kinect camera, optional video samples are available at AK_FRAEX - Azure Kinect Frame Extractor demo videos
The functionalities of the software are briefly described. Supplementary material can be found in USER's Manual.
-
[Dataset creation] This option creates a hierarchy of metadata. This hierarchy contains sub-folders that will be used to store the extracted data.
-
[Data Extraction] The user can configure the parameters for extracting data frames from videos, such as: output folder, number of frames to extract. The extraction can be done from one video or by processing a whole folder in batch mode.
-
[Data Migration] In this tab, we offer a tool for data migration in object labelling tasks. It is used to convert files from .CSV format (generated with Pychet Labeller) to PASCALVOC format.
-
Data extracted and 3D cloud points can be retrieved from *"your dataset metadata folder"**.
Create your Python virtual environment.
** For Linux systems **
python3 -m venv ./ak_frame_extractor_venv
source ./ak_frame_extractor_venv/bin/activate
pip install --upgrade pip
pip install python -m ak-frame-extractor
** execute package **
python -m ak_frame_extractor
** For Windows 10 systems **
python -m venv ./ak_frame_extractor_venv
.\ak_frame_extractor_venv\Scripts\activate.bat
python.exe -m pip install --upgrade pip
pip install ak-frame-extractor
** execute package **
python -m ak_frame_extractor
- [Linux] Enter to the folder "ak_frame_extractor/"
Create virtual environment(only first time)
./creating_env_ak_frame_extractor.sh
Run script.
./ak_frame_extractor_start.sh
- [Windows] Enter to the folder "ak_frame_extractor/"
Create virtual environment(only first time)
TODO_HERE
Run script from CMD.
./ak_frame_extractor_start.bat
Folder description:
Folders | Description |
---|---|
docs/ | Documentation |
src/ | Source code |
win_exe_conf/ | Specifications for building .exe files with Pyinstaller.. |
tools/ | Examples of code to use data migrated. We offer scripts in MATLAB, Python, R. |
data/ | Examples of output produced by AK_FRAEX, data extracted from recorded video. |
. | . |
Python environment files:
Files | Description | OS |
---|---|---|
activate_env.bat | Activate environments in Windows | WIN |
clean_files.bat | Clean files under CMD. | WIN |
creating_env_ak_frame_extractor.sh | Automatically creates Python environments | Linux |
ak_sm_recorder_main.bat | Executing main script | WIN |
ak_frame_extractor_start.sh | Executing main script | Linux |
/ak_frame_extractor_main.py | Python main function | Supported by Python |
Pyinstaller files:
Files | Description | OS |
---|---|---|
build_win.bat | Build .EXE for distribution | WIN |
/src/ak_frame_extractor/main.py | Main function used in package compilation | Supported by Python |
/ak_frame_extractor_main.py | Python main function | Supported by Python |
Pypi.org PIP packages files:
Files | Description | OS |
---|---|---|
build_pip.bat | Build PIP package to distribution | WIN |
/src/ak_frame_extractor/main.py | Main function used in package compilation | Supported by Python |
setup.cfg | Package configuration PIP | Supported by Python |
pyproject.toml | Package description PIP | Supported by Python |
Some development tools are needed with this package, listed below:
- Pyinstaller.
- Opencv.
- Curses for Python
pip install windows-curses
. - 7zip.
You can use the main.py for execute as first time in src/ak_frame_extractor/_ _ main _ _.py Configure the path of
the project, if you use Pycharm, put your folder root like this:
python3 -m venv ./venv
source ./venv/bin/activate
pip install --upgrade pip
pip install -r requirements_linux.txt
%userprofile%"\AppData\Local\Programs\Python\Python38\python.exe" -m venv ./venv
venv\Scripts\activate.bat
pip install --upgrade pip
pip install -r requirements_windows.txt
** If there are some problems in Windows, follow this **
pip install pyk4a --no-use-pep517 --global-option=build_ext --global-option="-IC:\Program Files\Azure Kinect SDK v1.4.1\sdk\include" --global-option="-LC:\Program Files\Azure Kinect SDK v1.4.1\sdk\windows-desktop\amd64\release\lib"
We are working to offer Pypi support for this package. At this time this software can be built by scripts automatically.
py -m pip install --upgrade build
build_pip.bat
pip install package.whl
python -m ak_frame_extractor.py
build_win.bat
After the execution of the script, a new folder will be generated inside the project "/dist". You can copy ** ak_frame_extracted_f/** or a compressed file "ak_frame_Extractor_f.zip" to distribute.
Explain about packages distribution.
Package type | Package | Url | Description |
---|---|---|---|
Windows | .EXE | .EXE | Executables are stored under build/ |
Linux | .deb | .deb | NOT IMPLEMENTED YET |
PIP | .whl | .whl | PIP packages are stored in build/ |
This project is contributed by GRAP-UdL-AT. Please contact authors to report bugs juancarlos.miranda@udl.cat
If you find this code useful, please consider citing:
@article{MIRANDA2022101231,
title = {AKFruitData: A dual software application for Azure Kinect cameras to acquire and extract informative data in yield tests performed in fruit orchard environments},
journal = {SoftwareX},
volume = {20},
pages = {101231},
year = {2022},
issn = {2352-7110},
doi = {https://doi.org/10.1016/j.softx.2022.101231},
url = {https://www.sciencedirect.com/science/article/pii/S2352711022001492},
author = {Juan Carlos Miranda and Jordi Gené-Mola and Jaume Arnó and Eduard Gregorio},
keywords = {RGB-D camera, Data acquisition, Data extraction, Fruit yield trials, Precision fructiculture},
abstract = {The emergence of low-cost 3D sensors, and particularly RGB-D cameras, together with recent advances in artificial intelligence, is currently driving the development of in-field methods for fruit detection, size measurement and yield estimation. However, as the performance of these methods depends on the availability of quality fruit datasets, the development of ad-hoc software to use RGB-D cameras in agricultural environments is essential. The AKFruitData software introduced in this work aims to facilitate use of the Azure Kinect RGB-D camera for testing in field trials. This software presents a dual structure that addresses both the data acquisition and the data creation stages. The acquisition software (AK_ACQS) allows different sensors to be activated simultaneously in addition to the Azure Kinect. Then, the extraction software (AK_FRAEX) allows videos generated with the Azure Kinect camera to be processed to create the datasets, making available colour, depth, IR and point cloud metadata. AKFruitData has been used by the authors to acquire and extract data from apple fruit trees for subsequent fruit yield estimation. Moreover, this software can also be applied to many other areas in the framework of precision agriculture, thus making it a very useful tool for all researchers working in fruit growing.}
}
This work is a result of the RTI2018-094222-B-I00 project (PAgFRUIT) granted by MCIN/AEI and by the European Regional Development Fund (ERDF). This work was also supported by the Secretaria d’Universitats i Recerca del Departament d’Empresa i Coneixement de la Generalitat de Catalunya under Grant 2017-SGR-646. The Secretariat of Universities and Research of the Department of Business and Knowledge of the Generalitat de Catalunya and Fons Social Europeu (FSE) are also thanked for financing Juan Carlos Miranda’s pre-doctoral fellowship (2020 FI_B 00586). The work of Jordi Gené-Mola was supported by the Spanish Ministry of Universities through a Margarita Salas postdoctoral grant funded by the European Union - NextGenerationEU. The authors would also like to thank the Institut de Recerca i Tecnologia Agroalimentàries (IRTA) for allowing the use of their experimental fields, and in particular Dr. Luís Asín and Dr. Jaume Lordán who have contributed to the success of this work.