Developed using darktable 3.2.1
Authors: Andreas Schmid, Raphael Wimmer, Stefan Lippl

Published in: ACM SIGGRAPH 2022 Posters (publication page)

Date: 2022-08-07

We trained a deep neural network to determine the orientation of a tracking pattern in sensor images with extremely low resolution. (Tweet this with link)

Inside-out optical 2D tracking of tangible objects on a surface oftentimes uses a high-resolution pattern printed on the surface. While De-Bruijn-torus patterns offer maximum information density, their orientation must be known to decode them. Determining the orientation is challenging for patterns with very fine details; traditional algorithms, such as Hough Lines, do not work reliably. We show that a convolutional neural network can reliably determine the orientation of quasi-random bitmaps with 6 × 6 pixels per block within 36 × 36 pixel images taken by a mouse sensor. Mean error rate is below 2°. Furthermore, our model outperformed Hough Lines in a test with arbitrarily rotated low-resolution rectangles. This implies that CNN-based rotation-detection might also be applicable for more general use cases.