Invited Talk by Julian Stoettinger

Julian Stoettinger CV Lab, TU Vienna, Austria Date: Friday, 04 February 2011 Time: 11:30 Location: 03.13.010

Detection and Evaluation Methods for Local Image and Video Features

Abstract:

In computer vision, local image descriptors computed in areas around salient interest points are the state-of-the-art in visual matching. This work aims at finding more stable and more informative interest points in the domain of images and videos. The research interest is the development of relevant evaluation methods for visual matching approaches. The contribution of this work lies on one hand in the introduction of new features to the computer vision community. On the other hand, there is a strong demand for valid evaluation methods and approaches gaining new insights for general recognition tasks. This talk presents research in the detection of local features both in the spatial (``2D'' or image) domain as well for spatio-temporal (``3D'' or video) features. For state-of-the-art classification the extraction of discriminative interest points has an impact on the final classification performance. It is crucial to find which interest points are of use in a specific task. The proposed sparse color interest point detector gives a stable number of features and thus a better comparable image representation. By taking the saliency of color information and color invariances into account, improved retrieval of color images, being more stable to lighting and shadowing effects than using illumination correlated color information, is obtained. In the last decade, a great interest in evaluation of local visual features in the domain of images is observed. Most of the state-of-the-art features have been extended to the temporal domain to allow for video retrieval and categorization using similar techniques as used for images. However, there is no comprehensive evaluation of these. This work provides the first comparative evaluation based on isolated and well defined alterations of video data. The aim is to provide researchers with guidance when selecting the best approaches for new applications and data-sets.