Controlling a game using mediapipe hand tracking

These scripts use the Google mediapipe hand tracking solution in combination with a webcam in order to send game instructions to a racing game. It features 2 control schemes, one with a steering wheel which controls both acceleration/decceleration and steering, and an alternate one that decouples both and assigns a functionality to each hand. The alternate control scheme allows for better control, because you don't have to worry about keeping your hands the same distance.

In order to run this, either start up the 'Virtual_steering_mediapipe' for the steering wheel option, or 'virtual_steering_mediapipe_alternate_control_scheme' for the alternate version. The inputs are send to the game using GamePad, so as long as the game you have open is compatible with xbox 360 controllers, it should work.

For an added bonus content, try using this to control a first person shooter, you will quickly go mad.

CONTROL SCHEME 1 : steering wheel

CONTROL SCHEME 2 : alternate

Good luck and happy coding.

Controlling a game using mediapipe hand tracking

Related tags

Overview

Controlling a game using mediapipe hand tracking

Owner

Repo for code associated with Modeling the Mitral Valve.

torchlm is aims to build a high level pipeline for face landmarks detection, it supports training, evaluating, exporting, inference(Python/C++) and 100+ data augmentations

[NeurIPS-2021] Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

T-LOAM: Truncated Least Squares Lidar-only Odometry and Mapping in Real-Time

Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors, CVPR 2021

Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment"

Easily Process a Batch of Cox Models

A curated list of automated deep learning (including neural architecture search and hyper-parameter optimization) resources.

Repository for the Bias Benchmark for QA dataset.

RITA is a family of autoregressive protein models, developed by LightOn in collaboration with the OATML group at Oxford and the Debora Marks Lab at Harvard.

Federated Learning Based on Dynamic Regularization

Code base for reproducing results of I.Schubert, D.Driess, O.Oguz, and M.Toussaint: Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics. NeurIPS (2021)

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

Unadversarial Examples: Designing Objects for Robust Vision

An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"

[WACV21] Code for our paper: Samuel, Atzmon and Chechik, "From Generalized zero-shot learning to long-tail with class descriptors"

PyTorch Implementation for "ForkGAN with SIngle Rainy NIght Images: Leveraging the RumiGAN to See into the Rainy Night"

基于PaddleClas实现垃圾分类，并转换为inference格式用PaddleHub服务端部署

This implements the learning and inference/proposal algorithm described in "Learning to Propose Objects, Krähenbühl and Koltun"

StarGAN-ZSVC: Unofficial PyTorch Implementation