Vision Based Dynamic Offside Line Marker for Soccer Games

Link to detailed description: Vision Based Dynamic Offside Line Marker for Soccer Games

Offside detection in soccer has emerged as one of the most important decision with an average of 50 offside decisions every game. False detections and rash calls adversely affect game conditions and in many cases drastically change the outcome of the game. The human eye has finite precision and can only discern a limited amount of detail in a given instance. Current offside decisions are made manually by sideline referees and tend to remain controversial in many games. This calls for automated offside detection techniques in order to assist accurate refereeing.

In this work, we have explicitly used computer vision and image processing techniques like Hough transform, color similarity (quantization), graph connected components, and vanishing point ideas to identify the probable offside regions.

Due to the unavailability of specific datasets, we have implemented and evaluated our algorithms on FIFA 16 game videos with a standard camera setting.

Result

Algorithmic Workflow

Identifying the Field of Play using Hough Transform and Colour Similarity

Input Video	Cropped Field of Play

Localizing Players within the Field of Play

Input Video	Identifying Attacking Team	Localizing player locations

Tracking the Last Defender using the KLT tracker

Figure shows the efficient team-wise player classification & tracking of the last defender to determine the offside marker

Marking the Offside Line - Vanishing Points

Initial Calibration of the Field	Offside Marker - Last Defender

Implemetation

Run Offside Line Marker.m to implement out work with corresponding input video directory. For accurate results, calibrate the first frame accurately. The program will generate an output video, with frame level details of the offside line.