Leveraging Outdoor Webcams for Local Descriptor Learning
This work addresses the challenge of reliable image matching in varying lighting for computer vision applications, representing an incremental improvement with a new dataset and descriptor.
The paper tackles the problem of robustifying local feature descriptors to illumination and appearance changes by introducing AMOS Patches, a dataset derived from outdoor webcam images, and a new descriptor trained on it that achieves state-of-the-art matching performance under such conditions.
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 state-of-the-art in matching under illumination changes on standard benchmarks.