QR-code Reconstruction from Event Data via Optimization in Code Subspace

Jun Nagata, Yusuke Sekikawa, Kosuke Hara, Teppei Suzuki, Yoshimitsu Aoki; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 2124-2132

Abstract

We propose an image reconstruction method from event data, assuming the target images belong to a prespecified class like QR codes. Instead of solving the reconstruction problem in the image space, we introduce a code space that covers all the noiseless target class images and solves the reconstruction problem on it. This restriction enormously reduces the number of optimizing parameters and makes the reconstruction problem well posed and robust to noise. We demonstrate fast and robust QR-code scanning in difficult, high-speed scenes with industrial high-speed cameras and other reconstruction methods.

Related Material

[pdf] [video]
[bibtex]
@InProceedings{Nagata_2020_WACV,
author = {Nagata, Jun and Sekikawa, Yusuke and Hara, Kosuke and Suzuki, Teppei and Aoki, Yoshimitsu},
title = {QR-code Reconstruction from Event Data via Optimization in Code Subspace},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}