You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+43-47Lines changed: 43 additions & 47 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,10 @@
1
1
OpenPose
2
2
====================================
3
3
4
+
OpenPose is a **library for real-time multi-person keypoint detection and multi-threading written in C++** using OpenCV and Caffe*, authored by [Gines Hidalgo](http://gines-hidalgo.site123.me/), [Zhe Cao](http://www.andrew.cmu.edu/user/zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon/), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Hanbyul Joo](http://www.cs.cmu.edu/~hanbyulj/) and [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/).
5
+
6
+
\* It uses Caffe, but it could easily be ported to other frameworks (Tensorflow, Torch, etc.). If you implement any of those, feel free to make a pull request!
7
+
4
8
## Latest News
5
9
- Jul 2017: **Windows**, New [**portable demo**](doc/installation.md#installation---demo)**and**[**easier library installation**](doc/installation.md#installation---library)!
6
10
- Jul 2017: **Hands** released!
@@ -9,25 +13,58 @@ OpenPose
9
13
- Apr 2017: **Body** released!
10
14
- Check all the [release notes](doc/release_notes.md).
11
15
12
-
We are offering [internships at Carnegie Mellon University as OpenPose programmer](https://docs.google.com/document/d/14SygG39NjIRZfx08clewTdFMGwVdtRu2acyCi3TYcHs/edit?usp=sharing) (need to live in or be willing to move to Pittsburgh).
OpenPose is a **library for real-time multi-person keypoint detection and multi-threading written in C++** using OpenCV and Caffe*, authored by [Gines Hidalgo](http://gines-hidalgo.site123.me/), [Zhe Cao](http://www.andrew.cmu.edu/user/zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon/), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Hanbyul Joo](http://www.cs.cmu.edu/~hanbyulj/) and [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/).
37
+
## Contents
38
+
1.[Latest News](#latest-news)
39
+
2.[Results](#results)
40
+
3.[Introduction](#introduction)
41
+
4.[Functionality](#functionality)
42
+
5.[Operating Systems](#operating-systems)
43
+
6.[Installation, Reinstallation and Uninstallation](#installation-reinstallation-and-uninstallation)
44
+
7.[Custom Caffe](#custom-caffe)
45
+
8.[Quick Start](#quick-start)
46
+
1.[Demo](#demo)
47
+
2.[OpenPose Wrapper](#openpose-wrapper)
48
+
3.[OpenPose Library](#openpose-library)
49
+
9.[Output](#output)
50
+
10.[Speed Up Openpose And Benchmark](#speed-up-openpose-and-benchmark)
51
+
11.[Send Us Failure Cases!](#send-us-failure-cases)
52
+
12.[Send Us Your Feedback!](#send-us-your-feedback)
53
+
13.[Citation](#citation)
54
+
14.[Other Contributors](#other-contributors)
18
55
19
-
\* It uses Caffe, but the code is ready to be ported to other frameworks (Tensorflow, Torch, etc.). If you implement any of those, feel free to make a pull request!
20
56
57
+
## Introduction
21
58
OpenPose represents the **first real-time system to jointly detect human body, hand and facial keypoints (in total 130 keypoints) on single images**. In addition, the system computational performance on body keypoint estimation is invariant to the number of detected people in the image.
22
59
23
60
OpenPose is freely available for free non-commercial use, and may be redistributed under these conditions. Please, see the [license](LICENSE) for further details. [Interested in a commercial license? Check this link](https://flintbox.com/public/project/47343/). For commercial queries, contact [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/).
24
61
25
62
In addition, OpenPose would not be possible without the [CMU Panoptic Studio](http://domedb.perception.cs.cmu.edu/).
26
63
64
+
The pose estimation work is based on the C++ code from [the ECCV 2016 demo](https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose), "Realtime Multiperson Pose Estimation", [Zhe Cao](http://www.andrew.cmu.edu/user/zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon/), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/). The [original repo](https://github.com/ZheC/Multi-Person-Pose-Estimation) includes Matlab and Python version, as well as the training code.
27
65
28
66
29
-
Library main functionality:
30
-
67
+
## Functionality
31
68
* Multi-person 15 or **18-keypoint body pose** estimation and rendering. **Running time invariant to number of people** on the image.
32
69
33
70
* Multi-person **2x21-keypoint hand** estimation and rendering. Note: In this initial version, **running time** linearly **depends** on the **number of people** on the image. **Coming soon (in around 1-5 days)!**
@@ -44,8 +81,6 @@ Library main functionality:
44
81
45
82
* All the functionality is wrapped into a **simple-to-use OpenPose Wrapper class**.
46
83
47
-
The pose estimation work is based on the C++ code from [the ECCV 2016 demo](https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose), "Realtime Multiperson Pose Estimation", [Zhe Cao](http://www.andrew.cmu.edu/user/zhecao), [Tomas Simon](http://www.cs.cmu.edu/~tsimon/), [Shih-En Wei](https://scholar.google.com/citations?user=sFQD3k4AAAAJ&hl=en), [Yaser Sheikh](http://www.cs.cmu.edu/~yaser/). The [full project repo](https://github.com/ZheC/Multi-Person-Pose-Estimation) includes Matlab and Python version, as well as training code.
48
-
49
84
50
85
51
86
## Operating Systems
@@ -55,45 +90,6 @@ The pose estimation work is based on the C++ code from [the ECCV 2016 demo](http
0 commit comments