A Soccer Image Sequence Mosaicking and Analysis Method Using Line and Advertisement Board Detection

Abstract

This paper introduces a system for mosaicking sequences of soccer images in a panoramic view for soccer game analysis. The continuous mosaic images of the soccer ground field allow the user to view a wide picture of the players’ actions. The initial component of our algorithm automatically detects and traces the players and some lines. The next component of our algorithm finds the parameters of the captured image coordinates and transforms them into ground model coordinates for automatic soccer game analysis. The results of our experimentations indicate that the proposed system offers a promising method for segmenting, mosaicking, and analyzing soccer image sequences.

An overview of automatic event detection in soccer matches

“…A very similar approach is presented by Yoon et al in [23]. However, according to [12], the suitable threshold may be different from one image to another due to weather condition, lighting and so forth.…”

Automatic soccer players tracking in goal scenes by camera motion elimination

“…Utsumi et al [9] detected and tracked players based on their colour rarity and local edge properties. Seo et al [10] and Yoon et al [11] proposed systems for mosaicing a sequence of soccer images and tracking players based on Template-Matching algorithm. The players' positions at the next frame are predicted by Kalman Filter in [10] and by nearest neighbourhood in [11].…”

“…Seo et al [10] and Yoon et al [11] proposed systems for mosaicing a sequence of soccer images and tracking players based on Template-Matching algorithm. The players' positions at the next frame are predicted by Kalman Filter in [10] and by nearest neighbourhood in [11]. Also, the next players' positions are predicted by assuming that a player moves at a constant velocity during a short period of time and then tracked by extracting players' colourful uniforms in [12].…”

“…Some researches have used RGB (Red-Green-Blue) space [10,11]. Yoon et al [11] suggested the following rules to extract the field.…”

Video based soccer ball tracking

“…Analysis of soccer video sequences has been an interesting application in computer vision and image analysis [1][2][3][4]. Much research has been done on ball and player detection and tracking.…”