ADITI GUPTA

INFO  /  INDEX

2025 — installation, website
BLOBBY


Blobby is an installation and web work that uses webcam feed to transform user movement and position into organic blob-like silhouettes. Using MediaPipe’s BlazePose model, the work captures a user’s body contour as a set of points, which are then processed to create a polygonal outline. From there, the outline is gradually adjusted to appear less rigid in order to create the desired “blob-y” shape.

The installation invites participants to step in front of one of six webcams, where their transformed silhouettes are incorporated into an overhead projection. The projection uses a derivative of the Truchet tiling algorithm to turn each of the six blobs into their own “tiles,” which are generatively arranged to construct a larger overarching image. As participants move, their blob contours shift in real time, creating an ever-evolving composition that captures a fleeting collaboration among all the individuals involved.

The installation is hosted on a local host site which is currently in the process of being refactored to accomodate a single webcam for a personal web version. This version will use the same shaping model and tile grid display but instead of other webcams, delayed streams of feed from the user’s webcam will populate the other tiles. This way, the individual user would still be able to move about the webcam view to collaborate with their past self to create an overarching image. Check back soon to see the personal web version. In the meantime, you can read more about the making of the project here.

This is a graduate thesis by Aditi Gupta. 







Using: BlazePose, OpenCV, WebSocket, Python, JavaScript




DANCE 4 ME


[2024 — web]
‘Dance4Me' (Dance For Me) is a web project that uses Google’s Pose Landmark Detection deep learning framework to pinpoint the coordinates of one’s body to create a sound experience in which a “song reacts to you as you react to it.” By enabling the webcam and uploading a .wav file within the site, the coordinate data is used to create sound alterations that will interfere with the playback of the song as the user moves in front of the camera. Some examples of sound alteration include pitch shift, a phaser, feedback delay, distortion, and playback rate.