All Projects → wfnian → posture_recognition

wfnian / posture_recognition

Licence: other
Posture recognition based on common camera

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to posture recognition

FastPose
pytorch realtime multi person keypoint estimation
Stars: ✭ 36 (-60.44%)
Mutual labels:  human-pose-estimation, pose-estimation, openpose
Openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Stars: ✭ 22,892 (+25056.04%)
Mutual labels:  human-pose-estimation, pose-estimation, openpose
Alphapose
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Stars: ✭ 5,697 (+6160.44%)
Mutual labels:  human-pose-estimation, pose-estimation
Openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Stars: ✭ 662 (+627.47%)
Mutual labels:  human-pose-estimation, pose-estimation
Poseestimationformobile
💃 Real-time single person pose estimation for Android and iOS.
Stars: ✭ 783 (+760.44%)
Mutual labels:  human-pose-estimation, pose-estimation
Openpose-based-GUI-for-Realtime-Pose-Estimate-and-Action-Recognition
GUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.
Stars: ✭ 69 (-24.18%)
Mutual labels:  pose-estimation, openpose
Tf Pose Estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+4137.36%)
Mutual labels:  human-pose-estimation, pose-estimation
Convolutional Pose Machines Tensorflow
Stars: ✭ 758 (+732.97%)
Mutual labels:  human-pose-estimation, pose-estimation
openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Stars: ✭ 900 (+889.01%)
Mutual labels:  human-pose-estimation, pose-estimation
Gccpm Look Into Person Cvpr19.pytorch
Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.
Stars: ✭ 137 (+50.55%)
Mutual labels:  human-pose-estimation, pose-estimation
Tensorflow realtime multi Person pose estimation
Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3
Stars: ✭ 129 (+41.76%)
Mutual labels:  human-pose-estimation, pose-estimation
Awesome Human Pose Estimation
A collection of awesome resources in Human Pose estimation.
Stars: ✭ 2,022 (+2121.98%)
Mutual labels:  human-pose-estimation, pose-estimation
Pytorch Human Pose Estimation
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
Stars: ✭ 346 (+280.22%)
Mutual labels:  human-pose-estimation, pose-estimation
Pose Residual Network Pytorch
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067
Stars: ✭ 277 (+204.4%)
Mutual labels:  human-pose-estimation, pose-estimation
rmpe dataset server
Realtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.
Stars: ✭ 14 (-84.62%)
Mutual labels:  human-pose-estimation, pose-estimation
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 728 (+700%)
Mutual labels:  human-pose-estimation, pose-estimation
Monoloco
[ICCV 2019] Official implementation of "MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation" in PyTorch + Social Distancing
Stars: ✭ 242 (+165.93%)
Mutual labels:  human-pose-estimation, pose-estimation
Keypoint Communities
[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".
Stars: ✭ 255 (+180.22%)
Mutual labels:  human-pose-estimation, pose-estimation
ICON
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (+604.4%)
Mutual labels:  human-pose-estimation, pose-estimation
Pytorch Pose
A PyTorch toolkit for 2D Human Pose Estimation.
Stars: ✭ 932 (+924.18%)
Mutual labels:  human-pose-estimation, pose-estimation

最新提示(2022-01-05):openpose的最新接口可能有所改动,需要对用地方改改。

0. 创新点


:octocat: 两个手工定制的特征,实现快速识别
:octocat: 第一个是距离,两个关键点的距离会随着动作不同而不同。
:octocat: 第二个是角度,考虑到距离会随着摄像头位置发生变化,而三个点的夹角不同,不论远近,夹角固定,同时夹角会随着动作不同而不同。

1. Overview pic

  • pic
  • 基于普通摄像头的太极姿势识别(分类),通过openpose采集的骨骼点数据做分类。
    • 第一就是通过openpose采集的骨骼数据做一个自定义特征的全连接网络的训练分类。(已完成)
    • 第二就是通过openpose采集的骨骼图片做卷积神经网络(CNN)分类(已完成)
  • 相关:基于Kinect的姿态识别(分类)

1.1. 安装与使用

首先根据OpenPose WindowsAPI安装说明安装,调用方式为Python调用。
OpenPose GitHub地址
OpenPose安装说明 最近迁移至Ubuntu,Windows的更新后cuda与caffee不兼容。部分程序有改动。总体不变。

  • 若有需要和问题可提issues.我在Windows,Ubuntu,Mac上均安装过OpenPose。

1.1.1. 程序开发目录说明

git clone 下来后cmake进行编译,其中要勾选BUILD_PYTHON进行编译才能被python调用。

workspace 程序开发目录详细说明

  • 📂workspace
    • 📁data_collection(数据采集)
      • data_collection_window.py
      • data_collection_window.ui
      • data_collection.py
    • 📁dataset (数据集)
      • 📁taichi
        • 📁marked_pic
          • 🎴 p_2_0.jpg(最后一个下划线后面是类别,此处0是类别,前一个数字2代表大概数量)
          • 🎴 ...
        • 📄bone_dataSet.data(骨骼特征数据)
        • 📄marked_pictrain.txt(图片路径)
    • 📁main_program
      • main.py 主程序入口
      • mainWindow.py
      • mainWindow.ui
    • 📁model_pth (模型保存位置)
      • 23classification_eigenvalue.pth
      • 23classification_pic.pth
    • 📁neural_network
      • 📁runs (tensorboard 可视化,如果有必要)
      • 📃classification23_taichi_eigenvalue.py
      • 📃classification23_taichi_pic.py
      • 📃data_process.py
      • 📃predict_eigenvalue.py
      • 📃predict_pic.py
    • 📁openpose_python_demos (包含一些python使用openpose的例子)
      • 📃flags.hpp(调用openpose的参数设置)
      • 📃use_camera_by_opencv.py
      • 📃use_camera.py
    • 📁sundry (包含一些界面设计的图片等杂项)
      • ...

1.2. 训练效果

(注意此处没有测试集,研一的时候我又利用此数据集,并且划分训练集测试集,利用四层卷积+池化能达到97%以上的效果)
全连接 卷积网络
pic pic

1.3. 展示效果

数据采集系统 识别系统
pic pic

说明:由于在Ubuntu下选择了桌面是unity所以不能录屏,展示为GIF图片。
由于电脑的摄像头在下方,使用iPad来作为输入。效果依旧是实时效果,但是数据量较小。
马赛克保护隐私。。。。。。

1.4. 关于更更更更具体的思路

论文地址:腾讯文档 (权限设置,需要申请才能开放查看)

1.5. 答辩结果

校级答辩 优秀 哈哈哈哈哈,承蒙老师指导,承蒙答辩老师欣赏,承蒙被抽到校级答辩。

写在最后

这个属于特别简单的一个本科生的毕业设计,思路可以模仿而内容不可照搬。

禁止商用

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].