Skip to content

Latest commit

 

History

History
92 lines (57 loc) · 3.48 KB

README.md

File metadata and controls

92 lines (57 loc) · 3.48 KB

Project GaitSystem

Project GaitSystem is an Gait recognition system based Windows Visual Studio 2017. The algorithm based the paper Gait optical flow image decomposition for human recognition.

As a behavioral biometric, gait recognition has gained an increased interest in recent years because it can operates without subject cooperation and from a distance. This paper present a novel gait feature extracting approach based on gait optical flow image(GOFI)decomposition.

I use this method implment the Project based C++, Qt and some 3rdparty to recognition the GaitDatasetB-silh. It's just use the silhouettes image and the angle fixed the 90 degree.

Table of Content

Prerequisites

  • Qt
  • armadillo-8.200.2DOWNLOAD LINK
    • you can download this library through above link or use my project 3rdparty dependences.
  • opencv3.1 DOWNLOAD LINK
  • Also you need the vs 2017
  • The testing Dataset(GaitDatasetB)

Getting the code

You can use the git tool to clone this project. through:

git clone [email protected]:Milittle/GaitSystem.git

Getting the Datasets

  1. Using this link to download the silhouettes GaitDatasetB
  2. Using the unzip software unzip the Dataset.

Running this Project with you

  1. Needing config the Qt library.
  2. Opening the project .sln file, you will look the Project structure. Fllowing:

Project Structure

  1. You can use Crtl + F5 run the project.
  2. you will see the following Figure:

UI

Load Model---: Load the gait silhouettes sequence from the Dataset B.

Add To DataBase---: Using this button add the gait feature to the Database(Feature database).

Recognition---: Using this button recognition the people already loaded.

Delete DataBase---: The button feature is not implement.(i will add it).

DataBase Count---: This will show the Database people's count.

RecognitionOBJ---: This will show the Recognitioned People's if you click the Recognition button after.

Gif Demo

DemoGif

Concat Getting Help

Email: [email protected]

Author: Milittle

最后:这是我写的比较水的一个步态识别的小Demo,以后再有机会做一些其他方面的工作。

毕竟这是第一个步态识别小Demo,留作纪念而已。(好多东西都需要优化!!!)

Ref:

About Armadillo Library:

Conrad Sanderson and Ryan Curtin. Armadillo: a template-based C++ library for linear algebra. Journal of Open Source Software, Vol. 1, pp. 26, 2016.

Conrad Sanderson and Ryan Curtin. A User-Friendly Hybrid Sparse Matrix Class in C++. Lecture Notes in Computer Science (LNCS), Vol. 10931, pp. 422-430, 2018.