- Number
- 20180157974
- Published
- 2018-06-07
- Filed
- 2017-12-04
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Carr; George Peter Kenneth; Le; Hoang M.; Yue; Yisong
- CPC
- A63B24/0006; G06N3/0442; G06N3/09; G06N3/092; G06V10/454; G06V10/70; G06V10/82; G06V20/41; G06V40/23
- Verdict
- Medium Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Deep imitation learning motion priors (ghosting).
Abstract
One embodiment provides a method, comprising: training, using deep imitation learning, a neural network associated with a predetermined ghosting model to predict player movements for at least one player during at least one sequence in a game; receiving, at an information handling device, tracking data associated with a player movement path for at least one player during the at least one sequence; analyzing, using a processor, the tracking data to determine at least one feature associated with the at least one player at a plurality of predetermined time points during the at least one sequence; and determining, using the predetermined ghosting model and the at least one feature, a ghosted movement path for the at least one player beginning from one of the plurality of predetermined time points. Other aspects are described and claimed.
Background
BACKGROUND
Current state-of-the-art sports statistics compare players and teams to league average performance. For example, metrics such as “Wins-above-Replacement” (WAR) in baseball, “Expected Point Value” (EPV) in basketball and “Expected Goal Value” (EGV) in soccer and hockey are now commonplace in performance analysis. Such measures provide analysts with a variety of useful statistical information such as, for example, how a player or team compares to other players or teams in their respective league or how a player's or team's current performance compares to their expected performance.BRIEF SUMMARY
In summary, one aspect provides a method, comprising: training, using deep imitation learning, a neural network associated with a predetermined ghosting model to predict player movements for at least one player during at least one sequence in a game; receiving, at an information handling device, tracking data associated with a player movement path for at least one player during the at least one sequence; analyzing, using a processor, the tracking data to determine at least one feature associated with the at least one player at a plurality of predetermined time points during the at least one sequence; and determining, using the predetermined ghosting model and the at least one feature, a ghosted movement path for the at least one player beginning from one of the plurality of predetermined time points.
Another aspect provides an information handling device, com
Claims
1. A method, comprising: training, using deep imitation learning, a neural network associated with a predetermined ghosting model to predict player movements for at least one player during at least one sequence in a game; receiving, at an information handling device, tracking data associated with a player movement path for at least one player during the at least one sequence; analyzing, using a processor, the tracking data to determine at least one feature associated with the at least one player at a plurality of predetermined time points during the at least one sequence; and determining, using the predetermined ghosting model and the at least one feature, a ghosted movement path for the at least one player beginning from one of the plurality of predetermined time points.
11. An information handling device, comprising: a processor; a memory device that stores instructions executable by the processor to: train, using deep imitation learning, a neural network associated with a predetermined ghosting model to predict player movements for at least one player during at least one sequence in a game; receive tracking data associated with a player movement path for at least one player during the at least one sequence; analyze the tracking data to determine at least one feature associated with the at least one player at a plurality of predetermined time points during the at least one sequence; and determine, using the predetermined ghosting model and the at least one feature, a ghosted movement path for the at least one player beginning from one of the plurality of predetermined time points.
20. A product, comprising: a storage device that stores code, the code being executable by a processor and comprising: code that trains a neural network associated with a predetermined ghosting model to predict player movements for at least one player during at least one sequence in a game; code that receives tracking data associated with a player movement path for at least one player during the at least one sequence; code that analyzes the tracking data to determine at least one feature associated with the at least one player at a plurality of predetermined time points during the at least one sequence; and code that determines, using the predetermined ghosting model and the at least one feature, a ghosted movement path for the at least one player beginning from one of the plurality of predetermined time points.
21. An information handling device, comprising: a processor; a memory device that stores instructions executable by the processor to: receive, on a display screen of the information handling device, user sketch input corresponding to offensive player positions and offensive player movement paths; receive activation input to animate the user sketch input, wherein the animation of the user sketch input comprises movement of the offensive players along the offensive player movement paths; determine, using a predetermined ghosting model, ghosted movement paths for defensive players based on the offensive player positions and the offensive player movement paths; and provide, based on the determining, a visualization of the defense players executing the ghosted movement paths responsive to the offensive player movement paths.