Grass band detection in soccer images for improved image registration

Description

This site contains some supplementary material associated to the detection strategy proposed in [1].

The work in [1] describes a strategy to detect the borders between the grass bands of the playing field in soccer stadiums, making it possible to locate many key points that will allow to carry out a subsequent registration of the images. First, a preprocessing is applied to obtain grayscale images in which the grass bands are easily distinguishable, and to obtain a binary mask of the entire playing field that determines the area of interest. Then, a local analysis is carried out to detect most of the borders between grass bands. Finally, a global analysis based on the intersections between lines is applied to group the detected borders and rule out false detections.

The strategy has been evaluated on two databases (the LaSoDa database and Homayounfar's database) composed of hundreds of annotated images from matches in several stadiums with different characteristics and light conditions. The results obtained have shown that most of the lines delimiting the grass bands are found successfully, while the number of false detections is very small.

Citation

[1] C. Cuevas, D. Berjón, N. García, “Grass band detection in soccer images for improved image registration”, Signal Processing: Image Communication, vol. xx, article 116837, pp. 1-xx, xxx 2022 (Journal Pre-proof, In Press).