Scribd
Upload
303 views8 pages

Flutter Body Pose Detection App Using Google ML-Kit Report

This document discusses developing a Flutter app using Google ML Kit to detect body pose from images or video. The app would allow users to upload or capture photos and receive posture details. It describes the system requirements, modules, advantages of real-time detection and image analysis, and limitations if the face is not visible.

Uploaded by

Prajyot06
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
303 views8 pages

Flutter Body Pose Detection App Using Google ML-Kit Report

This document discusses developing a Flutter app using Google ML Kit to detect body pose from images or video. The app would allow users to upload or capture photos and receive posture details. It describes the system requirements, modules, advantages of real-time detection and image analysis, and limitations if the face is not visible.

Uploaded by

Prajyot06
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 8

Flutter Body Pose Detection App using Google ML-

Kit

1) Background/ Problem Statement

Human posture is an important body part that indicates the


fundamental structure of the human body. ML Kit Pose Detection
doesn't require specialized equipment or ML expertise in order to
achieve great results. With this technology, we can create one-of-a-kind
experiences for the users.
ML Kit Pose Detection produces a full-body 33-point skeletal match that
includes facial landmarks (ears, eyes, mouth, and nose) and points on
the hands and feet. The user's face must be present in order to detect a
pose. Pose detection works best when the subject’s entire body is
visible in the frame, but it also detects a partial body pose.
The aim of our flutter-based Body Pose Detection System using Google
ML-Kit is to develop an application that can analyze the human body
posture by capturing an image of the body and providing the details of
it.
This project is written in Dart and the database used is SQLite, and it is
based on the flutter framework. Dart is a programming language that
Google developed and keeps up with. A cross-platform framework for
building high-performance mobile apps is called Flutter.
Human posture is an important body part that
indicates the fundamental structure of the
human body. Hence,
the aim of this project is to develop an
android application that
can analyze on the human body posture by
capturing an image
of the body and provide guide to improve it.
Human posture is an important body part that
indicates the fundamental structure of the
human body. Hence,
the aim of this project is to develop an
android application that
can analyze on the human body posture by
capturing an image
of the body and provide guide to improve it.

2) Working of the Project

In this system, the user can upload an image from their phone’s gallery
or capture a photo. From the static image, the system will detect the
body posture with the details. Here, there is also another option
available, a real-time camera. The user can open their phone’s camera
to see the body posture in real-time.
The system will display the posture details to the user. The ML Kit Pose
Detection API is a lightweight versatile solution to detect the pose of a
subject's body in real-time from a continuous video or static image.
A pose describes the body's position at one moment in time with a set
of skeletal landmark points. The landmarks correspond to different
body parts such as the shoulders and hips. The relative positions of
landmarks can be used to distinguish one pose from another.

3) Advantages

- It is easy to maintain.
- It is user-friendly.
- The user can easily detect body posture details from an
image.
- Also, real-time body pose detection is also available.
4) System Description
The system comprises 1 major module with their sub-modules as
follows:
 USER:
 Image
- The user can choose an image from the gallery or capture a
photo.
- The system will detect body pose with details.
 Realtime
- Also, the real-time camera option is also available.
- The user can open their camera and the body position will
be shown by the system with the details.

5) Project Life Cycle

The waterfall model is a classical model used in the system


development life cycle to create a system with a linear and sequential
approach. It is termed a waterfall because the model develops
systematically from one phase to another in a downward fashion. The
waterfall approach does not define the process to go back to the
previous phase to handle changes in requirements. The waterfall
approach is the earliest approach that was used for software
development.

6) System Requirements

I. Hardware Requirement

i. Laptop or PC
 macOS Sierra and above (If Mac setup is required)
 Windows 7 or higher
 I3 processor system or higher
 8 GB RAM or higher
 100 GB ROM or higher

ii. Android Phone (6.0 and above)


iii. iPhone (iOS 9 and above) (If the iOS version needs to be
checked)

II. Software Requirement

iv. Laptop or PC
 Android Studio with Flutter Plugin
 XCode (Latest version) (If the iOS version needs to
be checked on Mac)

7) Limitation/Disadvantages
- If the user’s face is not present in an image or in real-time, it
won’t be able to detect body pose.
- To detect body posture, the entire body must be visible in
the frame.
8) Application – This application helps to detect body posture using
Google ML-Kit.

9) Reference
- https://www.researchgate.net/publication/
354673294_Android_Application_for_Posture_Analysis_using_Tensor
flow_and_Computer_Vision
- https://www.researchgate.net/publication/
304410274_Human_posture_recognition_using_android_smartphon
e_and_artificial_neural_network
- https://link.springer.com/article/10.1007/s13042-020-01138-y

You might also like