Abstract
Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a feature-space, such as that produced by a convolutional neural network (CNN), that provides more tolerance to changes in appearance. In this article we investigate combining features from different layers of a CNN in order to obtain a feature-space that allows both precise and tolerant template matching. Furthermore we investigate if enhancing the encoding of shape information by the CNN can improve the performance of template matching. These investigations result in a new template matching method that produces state-of-the-art results on a standard benchmark. To confirm these results we also create a new benchmark and show that the proposed method also outperforms existing techniques on this new dataset. We further applied the proposed method to tracking and achieved more robust results.
Abstract (translated)
URL
https://arxiv.org/abs/2007.15817
