Human-Body-Measurements-using-Computer-Vision
Human-Body-Measurements-using-Computer-Vision copied to clipboard
Anthropometric measurement extraction using single image
Human body measurement using computer vision/ 3D modeling
Anthropometric measurement extraction

Getting human body measurements from image is a very hard problem. This repository provides a starting solution for any one who is working in this domain. It maps single input image onto 3-dimientional model using 3D human reconstruction and then extracts body measurements such as waist, chest etc. All meausrements are in centimeters. 3D reconstruction is done using HMR. Tested on tensorflow==1.13.1.

Download pre-trained model
Type the following command on terminal to download pretrained model
wget https://people.eecs.berkeley.edu/~kanazawa/cachedir/hmr/models.tar.gz && tar -xf models.tar.gz
and save it in 'models' folder.
CustomBodyPoints
Download CustomBodyPoints text file and place it in data folder.
Install Packages
pip install -r requirements.txt
or
pip3 install -r requirements.txt
Inference
python3 inference.py -i <path to Image1> -ht <height in cm>