Overview / Usage

Millions of people spend 7-8 hours a day sitting in front of their computers. One common trait is apparent among people with improper computer usage: a head-forward posture. Since people usually sit while using a computer, people also tend to slouch and bend their spine into a curve as well [1].

Neck pain caused by improper computer usage can be prevented through mindfulness training without the need for uncomfortable equipment.

This head forward posture has been shown to exert considerable pressure on the human neck. A normal human head weighs around 10 to 12 pounds (4.54 kg). An assessment of stresses found that a 15 degrees head forward posture increased the effective weight on the neck portion of the spine to 27 pounds (12.25 kg). According to one study, work-related neck pain is twice as likely for those sitting with 20 degree neck flexion.

I built this app to help remind me when my head is too close to the computer and to improve the overall quality of my coding lifestyle. The current stage consists of an open source Python application which provides desktop notifications and tracks data in a file which can be analyzed.

Methodology / Approach

Detect posture using TensorFlow model of Cao et al's real-time pose estimator (https://github.com/JustinShenk/tf-pose-estimation) described on the author's post on software.intel.com [1] and optimized with OpenVino for Intel hardware.

The previously published model uses OpenCV and a Haar cascade for face detection. The addition here is real-time posture detection with a deep neural network which is more precise and robust than the Haar cascade alone.

Run OpenVino-optimized model in the background while providing notifications for the user when they sit too close, and tracking the data for later analytics.

1 - https://software.intel.com/en-us/blogs/2018/06/11/how-can-a-spacecraft-use-ai

Technologies Used

Intel laptop
OpenVino
Intel-optimized TensorFlow
Movidius neural com

Repository

https://github.com/justinshenk/sensei