LampTop: touch detection for a projector-camera system based on shape classification

  • Authors:
  • Doney Alex;Pushkar Gorur;Bharadwaj Amrutur;Kalpathi Ramakrishnan

  • Affiliations:
  • Indian Institute of Science, Bangalore, India;Indian Institute of Science, Bangalore, India;Indian Institute of Science, Bangalore, India;Indian Institute of Science, Bangalore, India

  • Venue:
  • Proceedings of the 2013 ACM international conference on Interactive tabletops and surfaces
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The LampTop enables an effective low cost touch interface utilizing only a single camera and a pico projector. It embeds a small shape in the image generated by the user application (e.g. a touch screen menu with icons) and detects touch by measuring the geometrical distortion in the camera captured image. Fourier shape descriptors are extracted from the camera-captured image to obtain an estimate of the shape distortion. The touch event is detected using a Support Vector Machine. Quantitative results show that the proposed method can effectively detect touch.