Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Ball Tracking and Virtual Replays for Innovative Tennis Broadcasts
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 4
An Introduction to the Kalman Filter
An Introduction to the Kalman Filter
MMDB '03 Proceedings of the 1st ACM international workshop on Multimedia databases
Pitching a baseball: tracking high-speed motion with multi-exposure images
ACM SIGGRAPH 2004 Papers
Multimedia Tools and Applications
Journal of Visual Communication and Image Representation
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
A software architecture for distributed visual tracking in a global vision localization system
ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
HMM-based ball hitting event exploration system for broadcast baseball video
Journal of Visual Communication and Image Representation
Multimedia Tools and Applications
Sports Information Retrieval for Video Annotation
International Journal of Digital Library Systems
International Journal of Multimedia Data Engineering & Management
Hi-index | 4.10 |
During the 2001 major league baseball season, the strike zone received special attention when officials decided to enforce the game's original definition, which made tracking pitches especially important. Tracking the flight of a pitch during a live broadcast presents two major challenges, however: speed and image-processing reliability.Meeting these challenges required developing a complex system that fuses high-end computer graphics with a sophisticated algorithm for calculating flight trajectories.ESPN's K Zone pitch-tracking system uses computer-generated graphics to create a shaded, translucent box that outlines the strike zone boundaries for viewers. Behind the flashy graphics, K Zone provides a sophisticated computing subsystem that monitors each pitch's trajectory. Its development model may well prove effective in future computer vision projects, regardless of the application domain.