1.人体姿态估计综述（Human Pose Estimation Overview
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields,可以做到实时，每帧只需要5毫秒，即200FPS。
2.论文阅读：《Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields》CVPR 2017
源码--Pose Estimation using Part Affinity Fields
3.OpenPose
4.SwiftOpenPose不能实时
Performance comparison
BenchMark Hardware: iPad 2017
OpenPose Caffe-Model
processing time .. range 2-4 Sec.
tf-openpose Mobilenet Model
processing time .. Less than 1 sec
Keras-OpenFace,Pre-trained CoreML version of OpenFace in model/openface.coreml which you can easily integrate OpenFace into your iOS application.
5.PoseNet-CoreML
size 257 0.068 seconds.

a.Real-time Human Pose Estimation in the Browser with TensorFlow.js

b.论文---- PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

c.基于TensorFlow.js框架的浏览器实时姿态估计

6.Human Pose Matching on mobile — a fun application using Human Pose Estimation
7.iOS-OpenPose（最稳定的方案）
size 368 coreml elapsed for 0.09 seconds
model来自于tf-pose-estimation
Keras Mobilenet-Model openpose