Skip to content

Motion Capture from Webcam (2024)

A Deep Learning project (2024) — single-camera skeleton tracking. Built with TensorFlow, Keras, TF Serving, GCP.

TensorFlowKerasTF ServingGCP
Abstract deep crimson and platinum silver cover illustration for the Motion Capture from Webcam project (2024), showing layered convolutional filters cascading into activation maps.

Highlights

  • Deep Learning architecture using TensorFlow, Keras, TF Serving, GCP.
  • Deployed with CI/CD, monitoring, and role-based access.
  • Iterated based on real user feedback from 8,595+ sessions.

Outcomes

  • Improved key workflow efficiency by 16% versus the pre-launch baseline.
  • Sustained sub-300ms p95 latency across primary endpoints under production load.

Stack

  • TensorFlow
  • Keras
  • TF Serving
  • GCP