Degree Submission

BA (Hons) Interaction Design

Captured Transitions // 2021

Captured Transitions is a work which discovers the movement and morphing of the physical body interpreted by a machine. PoseNet is a machine learning model which recognises the human skeleton and key points of the body. In P5.js, a JavaScript library for creative coding, PoseNet is used to train the machine to recognise certain yoga poses and to draw the skeleton and key points of the body on a canvas in the web browser. The PoseNet model is very good at recognising people however with more complex yoga poses it would sometimes miss limbs in turn creating abstract outcomes and drawings.

The white lines represent the pose which the machine was trained to recognise while the black lines show the transition through to the second pose not taught to the machine. The abstract drawings vary between more delicate and subtle to bolder more obvious outcomes where a human body is more easily identified. The work is presented as large prints of human scale computer drawings.

PoseNet // P5.js // Photoshop // Webcam