chang-chih-yao / shoes-try-on-in-ar

Explore new custom sneakers experience in AR.

Shoes-Try-On-in-AR

• 開發時間：2019/08/01 ~ 2019/12/31
• 開發平台：Win 10, GTX 2070, i7-8700k
• 開發工具：Python 3.7, Unity 2019.2.1, CMake 3.16.0
• 開發環境：CUDA 10.0, cuDNN 7.5.0

---

本系統採用Server跟Client的方式互相傳遞訊息。
Server端(Python)運行OpenPose不斷的把骨架資訊以及影像傳遞給Client端(Unity)，Client端接收到骨架資訊以及影像後，把影像顯示在一個平面上，並且把鞋子的3D模型套到腳掌上，讓使用者站在鏡頭前面就可以自由試鞋，還能一鍵換成其他雙鞋子試穿。

---

Demo

DEMO VIDEO-1

DEMO VIDEO-2

---

Quick Start

1. Install OpenPose Python API. Check here
2. Connect the webcam to your computer through USB.
3. Run the Server. Navigate to openpose(clone root)/build(build name)/examples/tutorial_api_python folder, run python webcam.py.
4. Run the Untiy project.

shoes-try-on-in-ar's Issues

Unity doesn't work

1、Missing script. The following problem occurs. How to set the script？
The referenced script on this Behaviour (Game Object 'EventSystem') is missing!
The referenced script (Unknown) on this Behaviour is missing! etc
2、The following errors have been refreshed：
NullReferenceException: Object reference not set to an instance of an object
TCP.Start () (at Assets/Script/TCP.cs:202)
NullReferenceException: Object reference not set to an instance of an object
TCP.Update () (at Assets/Script/TCP.cs:226)
How to solve this problem, thank you

Where is the shoe model?

Hi, I do not see the shoe 3D model that is to render onto the feet. Am I missing something?

Low FPS

What can be the possible issue for frame lag in Unity and Python Frame??

How to add pybind11?

I have set up everything but it gives an error of pybind11

`Starting OpenPose Python Wrapper...
Auto-detecting all available GPUs... Detected 1 GPU(s), using 1 of them starting at GPU 0.
(540, 960, 3)
Wait for connection...
Client Info: <socket.socket fd=2272, family=AddressFamily.AF_INET, type=SocketKind.SOCK_STREAM, proto=0, laddr=('127.0.0.1', 9000), raddr=('127.0.0.1', 61761)> ('127.0.0.1', 61761)
emplaceAndPop(): incompatible function arguments. The following argument types are supported:
1. (self: pyopenpose.WrapperPython, arg0: std::vector<std::shared_ptrop::Datum,std::allocator<std::shared_ptrop::Datum > >) -> bool

Invoked with: <pyopenpose.WrapperPython object at 0x000001F2386CCA30>, [<pyopenpose.Datum object at 0x000001F2364714B0>]

Did you forget to #include <pybind11/stl.h>? Or <pybind11/complex.h>,
<pybind11/functional.h>, <pybind11/chrono.h>, etc. Some automatic
conversions are optional and require extra headers to be included
when compiling your pybind11 module.`

How to resolve this in windows?

webcam.py (Server) is not working

When I open it, it gives me error

Starting OpenPose Python Wrapper...
Auto-detecting all available GPUs... Detected 1 GPU(s), using 1 of them starting at GPU 0.
(480, 864, 3)
Wrong frame width or height! (need 960 for width and 540 for height)
480
[ WARN:0] global C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-oduouqig\opencv\modules\videoio\src\cap_msmf.cpp (434) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback

How can I solve it?

請問，如何使用 深度相機 和 openpose 獲得3維資訊呢?

請問，您是如何使用 深度相機 和 openpose 獲得3維資訊呢?

how to implement this model into android.

is there any way to detect feet and add 3d shoes model in android application.