Towards soccer pass feasibility maps: the role of players' orientation.

- Once player tracking has been established as one of the main data sources in soccer, many challenges have emerged for data scientists, who attempt to recognize patterns from 2D trajectories in order to build tools that might help coaches to improve the performance of their teams. For instance, pass models predict where the ball should go next during pass events. However, existing models are mainly fed with players' location and prior data, hence omitting critical pieces of information such as players' body orientation. This paper presents a computational model to obtain pass feasibility maps, where player orientation is exploited and analysed. As a matter of fact, orientation proves to be crucial when modelling field-of-view and correct positioning of players, since it limits the potential receiving area of all candidates. Different proposals are given to evaluate the proposed pass feasibility map, reaching 0.46 and 0.79 in Top1 and Top3 accuracy, respectively, with a + 0.2 boost obtained after merging positional data with orientation.

Affine Non-Local Means Image Denoising.

This paper presents an extension of the Non-Local Means denoising method, that effectively exploits the affine invariant self-similarities present in the images of real scenes. Our method provides a better image denoising result by grounding on the fact that in many occasions similar patches exist in the image but have undergone a transformation. The proposal uses an affine invariant patch similarity measure that performs an appropriate patch comparison by automatically and intrinsically adapting the size and shape of the patches. As a result, more similar patches are found and appropriately used. We show that this image denoising method achieves top-tier performance in terms of PSNR, outperforming consistently the results of the regular Non-Local Means, and that it provides state-of-the-art qualitative results.

An inpainting-based deinterlacing method.

Video is usually acquired in interlaced format, where each image frame is composed of two image fields, each field holding same parity lines. However, many display devices require progressive video as input; also, many video processing tasks perform better on progressive material than on interlaced video. In the literature, there exist a great number of algorithms for interlaced to progressive video conversion, with a great tradeoff between the speed and quality of the results. The best algorithms in terms of image quality require motion compensation; hence, they are computationally very intensive. In this paper, we propose a novel deinterlacing algorithm based on ideas from the image inpainting arena. We view the lines to interpolate as gaps that we need to inpaint. Numerically, this is implemented using a dynamic programming procedure, which ensures a complexity of O(S), where S is the number of pixels in the image. The results obtained with our algorithm compare favorably, in terms of image quality, with state-of-the-art methods, but at a lower computational cost, since we do not need to perform motion field estimation.