Virtual hand gesture mouse using a webcam

Overview

NonMouse

GitHub GitHub release (latest by date) zenn

日本語のREADMEはこちら

This is an application that allows you to use your hand itself as a mouse.
The program uses a web camera to recognize your hand and control the mouse cursor.

The video is available on Youtube

スクリーンショット 2021-09-13 午後5 33 21

スクリーンショット 2021-09-13 午後5 33 21

Feature

  • Entirely new mouse: a mouse with a software approach. It recognizes your hand and works as a mouse.
  • NonMouse can be invoked by the global hotkey even when this application is inactive.
  • Works well with typing
  • You can make it look like a touch display, by pointing the web camera at the display.
  • You can use the mouse wherever you want.
  • Just download from the latest release (windows, mac only)

Installation

📁 Run as executable file

Download the zip file that matches your environment from the latest release.

OR

🐍 Run as python

Run the following script.

$ git clone https://github.com/takeyamayuki/NonMouse
$ cd NonMouse
$ pip install -r requirements.txt

If you have trouble installing mediapipe, please visit the official website.

† For mac, you need to add the location where you want to run it, such as Terminal or VScode, to the Security and Privacy Accessibility and Cammera section in System Preferences.

Usage

1. Install a camera

The following three ways of placing the device are assumed.

  • Normal: Place a webcam normally and point it at yourself (or use your laptop's built-in camera)

    Examples of installation methods Point the palm of your hand at the camera
    スクリーンショット 2021-09-13 午後5 33 21
    スクリーンショット 2021-09-13 午後5 33 21 スクリーンショット 2021-09-23 044041
  • Above: Place it above your hand and point it towards your hand.

    An example of installation methods Point the back of your hand at the camera.
    スクリーンショット 2021-09-13 午後5 33 21 スクリーンショット 2021-09-23 044243
  • Behind: Place it behind you and point it at the display.

    An example of installation methods Point the back of your hand at the camera.
    スクリーンショット 2021-09-13 午後5 33 21 スクリーンショット 2021-09-23 044403

2. Run

  • Run the executable as described in the GitHub wiki.

    OR

  • Run the following script from the continuation of the installation.

    For windows, linux(global hotkey function does not work in linux.)

    $ python3 app.py

    For MacOS, you need execute permission.

    $ sudo python3 app.py

3. Settings

When you run the program, You will see a screen similar to the following. On this screen, you can set the camera and sensitivity.

スクリーンショット 2021-12-02 154251

  • Camera
    Select a camera device. If multiple cameras are connected, try them in order, starting with the smallest number.

  • How to place
    Select the location where you placed the camera. Place the camera in one of the following positions: Normal, Above, Behind in [ 📷 Install a Camera].

  • Sensitivity
    Set the sensitivity. If set too high, the mouse cursor will shake slightly.

When you are done with the settings, click continue. The camera image will then be displayed, and you can use NonMouse with the settings you selected.

4. Hand Movements

stop cursor left click right click scroll
aaa aaa aaa aaa

The following hand movements are enabled only when you hold down Alt(Windows), Command(MacOS). You can define your own global hotkeys by rewriting here. You can use this function even if the window is not active.This feature is only available on windows and mac.

  • cursor
    • Mouse cursor: tip of index finger → A blue circle will appear at the tip of your index finger.
    • Stop mouse cursor: Attach the tip of your index finger to the tip of your middle finger. → The blue circle disappears.
  • left click
    • Left click: Attach the fingertips of your thumb to the second joint of your index finger → A yellow circle will appear on the tip of your index finger.
    • Left click release: Release the thumb fingertip and the second joint of the index finger. → The yellow circle disappears.
    • Double click: Left click twice within 0.5 seconds.
  • other
    • Right click: Hold the click state for 1.5 second without moving the cursor. → A red circle will appear at the tip of your index finger.
    • Scroll: Scroll with the index finger with the index finger folded → a black circle will appear.

† Use it with a bright light at hand.
† Keep your hand as straight as possible to the camera.

5. Quit

Press Ctrl+C, when a terminal window is active.
Press close button(Valid only on windows, linux) or Esc key, when an application window is active.

Build

† The built binary files can be downloaded from latest realease.

In app-mac.spec and app-win.spec, change pathex to fit your environment.
Run the following scripts for each OS.

  • windows

    Copy and paste the location obtained by pip show mediapipe into datas, referring to what is written originally.
    Run the following script.

    $ pip show mediapipe
    ...
    Location: c:\users\namik\appdata\local\programs\python\python37\lib\site_packages
    ...
    #Copy and paste into the datas in app-win.spec
    $ pyinstaller app-win.spec
    ... ````
  • mac

    Create a venv environment and perform pip install, because the directory specified in datas is for an assumed venv environment.

    $ python3 -m venv venv
    $ . venv/bin/activate
    (venv)$ pip install -r requirements.txt
    (venv)$ pyinstaller app-mac.spec
Comments
  • error: PyObjC requires macOS to build

    error: PyObjC requires macOS to build

    Hello. When installing requirements on Linux I get this error:

    Collecting pyobjc-core==7.3
      Downloading pyobjc-core-7.3.tar.gz (684 kB)
         ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 684.2/684.2 KB 5.4 MB/s eta 0:00:00
      Preparing metadata (setup.py) ... error
      error: subprocess-exited-with-error
      
      × python setup.py egg_info did not run successfully.
      │ exit code: 1
      ╰─> [2 lines of output]
          running egg_info
          error: PyObjC requires macOS to build
          [end of output]
      
      note: This error originates from a subprocess, and is likely not a problem with pip.
    error: metadata-generation-failed
    
    × Encountered error while generating package metadata.
    ╰─> See above for output.
    
    opened by jbrepogmailcom 2
  • ZeroDivisionErrorでクラッシュする

    ZeroDivisionErrorでクラッシュする

    cfps = int(cap.get(cv2.CAP_PROP_FPS)) でcfpsが1になって if cfps < 30: cap.set(cv2.CAP_PROP_FRAME_WIDTH, cap_width) cap.set(cv2.CAP_PROP_FRAME_HEIGHT, cap_height) cfps = int(cap.get(cv2.CAP_PROP_FPS)) を通してもcfpsが1になり、 ran = int(cfps/10) でranが0になってしまい、ZeroDivisionErrorでクラッシュします。

    環境は以下の通りです PC: MacBook Pro 2020 Intel OS: macOS Monterey カメラ: Mac内蔵Webカメラ Pythonバージョン: 3.9.7

    opened by takpika 2
  • MacOS MontereyでカメラFPSが5Hz程度になる

    MacOS MontereyでカメラFPSが5Hz程度になる

    https://github.com/takeyamayuki/NonMouse/blob/1e7f7bc5e9f52a29196ae631b4cb7e83a910aa27/app.py#L117-L121

    cfps = int(cap.get(cv2.CAP_PROP_FPS))で取得するカメラのFPSが5Hzになってしまい、カーソルが小刻みに揺れてしまう。 これは恐らく、cv2の問題だと思われる。

    opened by takeyamayuki 0
  • How to set screen size?

    How to set screen size?

    Hello the mouse only works on left two thirds of the screen. I gues it has something to do with screen size, my lapto has 1920x1080. Can I reconfigure it somewhere?

    opened by jbrepogmailcom 1
  • カメラや手が傾くと、自分の指先移動量に対するマウス移動量が異なってしまう

    カメラや手が傾くと、自分の指先移動量に対するマウス移動量が異なってしまう

    たとえば、カメラを斜めに取り付けると、カメラに映る指は縦方向に圧縮されたものになり、当然移動量もその分小さくなる。 現在の自分の環境だと手に向けてまっすぐ取り付けられているので問題はないが、初めて使う人にとってはこのアプリケーションを使う上での大きな壁となる。

    「解決策」 まず、基準となる指の関節座標を用意しておく。 その基準となる座標群と現在の座標群を比較して手の傾き具合を求める。 それによって、dx,dy変える

    opened by takeyamayuki 0
Releases(2.6.0)
This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra

Ju He 307 Jan 03, 2023
Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

A Self-Supervised Descriptor for Image Copy Detection (SSCD) This is the open-source codebase for "A Self-Supervised Descriptor for Image Copy Detecti

Meta Research 68 Jan 04, 2023
Multi-Output Gaussian Process Toolkit

Multi-Output Gaussian Process Toolkit Paper - API Documentation - Tutorials & Examples The Multi-Output Gaussian Process Toolkit is a Python toolkit f

GAMES 113 Nov 25, 2022
Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

SinGAN Project | Arxiv | CVF | Supplementary materials | Talk (ICCV`19) Official pytorch implementation of the paper: "SinGAN: Learning a Generative M

Tamar Rott Shaham 3.2k Dec 25, 2022
High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.

Anakin2.0 Welcome to the Anakin GitHub. Anakin is a cross-platform, high-performance inference engine, which is originally developed by Baidu engineer

514 Dec 28, 2022
RIFE - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

RIFE - Real-Time Intermediate Flow Estimation for Video Frame Interpolation YouTube | BiliBili 16X interpolation results from two input images: Introd

旷视天元 MegEngine 28 Dec 09, 2022
A collection of pre-trained StyleGAN2 models trained on different datasets at different resolution.

Awesome Pretrained StyleGAN2 A collection of pre-trained StyleGAN2 models trained on different datasets at different resolution. Note the readme is a

Justin 1.1k Dec 24, 2022
[NeurIPS 2021] Garment4D: Garment Reconstruction from Point Cloud Sequences

Garment4D [PDF] | [OpenReview] | [Project Page] Overview This is the codebase for our NeurIPS 2021 paper Garment4D: Garment Reconstruction from Point

Fangzhou Hong 112 Dec 23, 2022
这是一个yolo3-tf2的源码,可以用于训练自己的模型。

YOLOV3:You Only Look Once目标检测模型在Tensorflow2当中的实现 目录 性能情况 Performance 所需环境 Environment 文件下载 Download 训练步骤 How2train 预测步骤 How2predict 评估步骤 How2eval 参考资料

Bubbliiiing 68 Dec 21, 2022
Object-aware Contrastive Learning for Debiased Scene Representation

Object-aware Contrastive Learning Official PyTorch implementation of "Object-aware Contrastive Learning for Debiased Scene Representation" by Sangwoo

43 Dec 14, 2022
DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene.

DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene. We achieve NeRF-comparable novel-view synthesis quality with super-fast convergence.

sunset 709 Dec 31, 2022
OCRA (Object-Centric Recurrent Attention) source code

OCRA (Object-Centric Recurrent Attention) source code Hossein Adeli and Seoyoung Ahn Please cite this article if you find this repository useful: For

Hossein Adeli 2 Jun 18, 2022
网络协议2天集训

网络协议2天集训 抓包工具安装 Wireshark wireshark下载地址 Tcpdump CentOS yum install tcpdump -y Ubuntu apt-get install tcpdump -y k8s抓包测试环境 查看虚拟网卡veth pair 查看

120 Dec 12, 2022
Malmo Collaborative AI Challenge - Team Pig Catcher

The Malmo Collaborative AI Challenge - Team Pig Catcher Approach The challenge involves 2 agents who can either cooperate or defect. The optimal polic

Kai Arulkumaran 66 Jun 29, 2022
CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View

Rethinking Semantic Segmentation: A Prototype View Rethinking Semantic Segmentation: A Prototype View, Tianfei Zhou, Wenguan Wang, Ender Konukoglu and

Tianfei Zhou 239 Dec 26, 2022
CLIPImageClassifier wraps clip image model from transformers

CLIPImageClassifier CLIPImageClassifier wraps clip image model from transformers. CLIPImageClassifier is initialized with the argument classes, these

Jina AI 6 Sep 12, 2022
A Real-World Benchmark for Reinforcement Learning based Recommender System

RL4RS: A Real-World Benchmark for Reinforcement Learning based Recommender System RL4RS is a real-world deep reinforcement learning recommender system

121 Dec 01, 2022
buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

buildseg buildseg is a building extraction plugin of QGIS based on PaddlePaddle. TODO Extract building on 512x512 remote sensing images. Extract build

Yizhou Chen 11 Sep 26, 2022
HDMapNet: A Local Semantic Map Learning and Evaluation Framework

HDMapNet_devkit Devkit for HDMapNet. HDMapNet: A Local Semantic Map Learning and Evaluation Framework Qi Li, Yue Wang, Yilun Wang, Hang Zhao [Paper] [

Tsinghua MARS Lab 421 Jan 04, 2023
Dataset and Code for ICCV 2021 paper "Real-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme"

Dataset and Code for RealVSR Real-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme Xi Yang, Wangmeng Xiang,

Xi Yang 92 Jan 04, 2023