Multi-Camera Analysis of Soccer Sequences

Abstract

The automatic detection of meaningful phases in a soccer game depends on the accurate localization of players and the ball at each moment. However, the automatic analysis of soccer sequences is a challenging task due to the presence of fast moving multiple objects. For this purpose, we present a multi-camera analysis system that yields the position of the ball and players on a common ground plane. The detection in each camera is based on a code-book algorithm and different features are used to classify the detected blobs. The detection results of each camera are transformed using homography to a virtual top-view of the playing field. Within this virtual top-view we merge trajectory information of the different cameras allowing to refine the found positions. In this paper, we evaluate the system on a public SOCCER dataset and end with a discussion of possible improvements of the dataset.

Multi-Commodity Network Flow for Tracking Multiple People

“…Hence, the appearance is based on shirt colors only. Similarly to [54], we use 5 identity groups that we denote as referees, team 1, team 2, goal keeper 1 and goal keeper 2. A sample of the dataset is presented in Fig.…”

Amateur football analytics using computer vision

“…Multiple detections relating to the same object may occur in which case, nonmaximum suppression method is applied [16]. For ball detection, circular Hough transform has been used for ball detection [11], [38]. Especially for the cases of partial or total occlusion of the ball, motion history images, along with Freeman chaincode have been employed [21].…”

FootAndBall: Integrated Player and Ball Detector

“…These criteria include blob size, colour and shape (circularity, eccentricity). Variants of Circle Hough Transform, modified to detect elliptical rather than circular objects, are used to verify if a blob contains the ball (D'Orazio et al, 2002;Poppe et al, 2010;Halbinger and Metzler, 2015). To achieve real-time performance and high detection accuracy, a two-stage approach may be employed (D'Orazio et al, 2002).…”