Leveraging outdoor webcams for local descriptor learning

M. Pultar, D. Mishkin, J. Matas. Leveraging outdoor webcams for local descriptor learning. pages 51-60, DOI 10.3217/978-3-85125-652-9-06, 2, 2019.

Autoren
  • Milan Pultar
  • Dmytro Mishkin
  • Jiri Matas
BuchProceedings of the 24th Computer Vision Winter Workshop (CVWW 2019)
TypIn Konferenzband
VerlagVerlag TU Graz
DOI10.3217/978-3-85125-652-9-06
ISBN978-3-85125-652-9
Monat2
Jahr2019
Seiten51-60
Abstract

We present AMOS Patches, a large set of image cut-outs, intended primarily for the robustification of trainable local feature descriptors to illumination and appearance changes. Images contributing to AMOS Patches originate from the AMOS dataset of recordings from a large set of outdoor webcams.

The semiautomatic method used to generate AMOS Patches is described. It includes camera selection, viewpoint clustering and patch selection. For training, we provide both the registered full source images as well as the patches.

A new descriptor, trained on the AMOS Patches and 6Brown datasets, is introduced. It achieves stateof-the-art in matching under illumination changes on standard benchmarks.