gesture-recognition

Linux multi-touch gesture recognizer

Multitouch gestures with libinput driver on Linux

Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

A toolbox for skeleton-based action recognition.

Gesture recognition via CNN. Implemented in Keras + Tensorflow/Theano + OpenCV

ICCV 2023 Papers: Discover cutting-edge research from ICCV 2023, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

gesture recognition toolkit

HAnd Gesture Recognition Image Dataset

Enhance your application with the ability to see and interact with humans using any RGB camera.

Real-time Hand Gesture Recognition with PyTorch on EgoGesture, NvGesture, Jester, Kinetics and UCF101

MediaPipe(Python版)を用いて手の姿勢推定を行い、検出したキーポイントを用いて、簡易なMLPでハンドサインとフィンガージェスチャーを認識するサンプルプログラムです。（Estimate hand pose using MediaPipe(Python version). This is a sample program that recognizes hand signs and finger gestures with a simple MLP using the detected key points.）

Lazyeat 吃饭时看剧/刷网页不想沾油手？ 对着摄像头比划手势就能暂停视频/全屏/切换视频！Lazyeat is a touch-free controller for use while eating! Don't want greasy hands while watching shows or browsing the web during meals? You can pause videos/full screen/switch videos just by gesturing to the camera!

Virtually controlling computer using hand-gestures and voice commands. Using MediaPipe, OpenCV Python.

Asset that improves touch input support (includes new gestures) in the Godot game engine. It also translates mouse input to touch input.

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included. ⭐ support visual intelligence development!

A simple Fingers Detection (or Gesture Recognition) using OpenCV and Python with background substraction 简单手势识别

Simple project to recognize hands in realtime. 👋 Serves as an Example for building your own object recognizer.

Recognizing Hand Gestures using OpenCV and Python

Unified learning approach for egocentric hand gesture recognition and fingertip detection.