Capture Body Anthropometrics Using a Smart Device

Engineering, IT, Mathematics and Statistics

PLEASE NOTE

  • This internship is able to cover project costs for domestic students only.
  • Applications for this opportunity are ongoing until Candidate successful.

Project Background

SmartFit Technologies has created a set of innovative systems to accurately measure multiple features of the human body with a Smart device. Our engineers have developed our core technology using machine prediction and computer vision algorithms to analyse images of the human body and return accurate anthropometrics to the user.

This start-up has a working prototype of the core technology and is now seeking a Researcher with a background in at least one of the following areas:

  • Multiple view geometry
  • 3D reconstruction from images & sensors
  • Mesh processing and other computer 3D vision related fields.

Research to be Conducted

  • Research latest academic literature on applications of deep learning / 3D vision to human anthropometric modelling.
  • Explore the available 3D models/mesh of human images data set and propose ways to leverage them to improve accuracy in the existing solution.
  • Research and design prototype to compute body measurements from 2D images.
  • Design landmark detection algorithm to detect key feature points (bust, waist, hip etc) in human images.

Skills Required

If you’re a PhD student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:

Experience in one of the following:

  • Multiple view geometry, 3D reconstruction from images & sensors, Mesh processing and other computer 3D vision related fields.
  • Experience in applying machine learning and deep learning techniques to computer vision.
  • Ability to prototype code from research papers.

Experience working in:

  • Photogrammetry
  • Python and C#

Expected Outcomes

  • Improve the accuracy of body measurement component to 95% i.e. 95% of the cross validated set images to have individual measurement error within 5mm.
  • Design landmark detection algorithm to replace the existing heuristics/hand crafted approach of feature point detection.

Additional Details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

LOCATION:
Sydney, NSW
DURATION:
5 months
CLOSING DATE:
08/07/2020
ELIGIBILITY:
Domestic students only
REF NO:
APR – 1270

INTERNSHIP CONTACT

CONNECT WITH APR.INTERN

Suggested Internships

FUSETEC (APR – 1478)

Location:
Adelaide, SA
Cutting Edge Medical Devices

DON ALAN (APR – 1479)

Location:
Adelaide, SA or can be completed remotely
Modelling Power Losses in Inductors and Transformers used in Switch Mode Transformers

ERATOS GROUP (APR – 1466)

Location:
Melbourne, VIC or can be completed remotely
Metadata Extraction on the Edge