A computer vision based gesture detection system that automatically detects the number of fingers as a hand gesture and enables you to control simple button pressing games using you hand gestures.
A computer vision based gesture detection system that automatically detects the number of fingers as a hand gesture and enables you to control simple button pressing games using you hand gestures. Currently the system has been tested on the T-Rex Runner game.
Installation
Clone the repo using git clone https://github.com/soumik12345/Kinect-Vision
Use cd Kinect-Vision to get inside the folder
Create a new conda environment using conda create --name kinect_vision
Activate the environment using activate kinect_vision
Install the requirements using pip install -r requirements.txt
Run The Program
Run the program using python3 main.py or python main.py or ipython main.py
Select the Camera port (choose 0 if you are using a laptop)
Tune the upper and lower thresholds using the trackbars unless the gestures are being detected accurately enough. Ideally the lower threshold is around 130 and the upper threshold is 255.
Once the detection is working satisfactorily, switch on Game On and open the game window
If you want to change the control scheme, you can do so by editing the config.json file.
Demo
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].