About this document
Kalman Filter for Ball Tracking System by vixee is a document available to read on EtoBox.
This paper introduces a computer vision system for tracking and predicting flying balls in 3D using stereo cameras, employing a Multiple-Hypotheses Tracker (MHT) with an Unscented Kalman Filter (UKF) for robust detection and tracking. The system features a novel circle detection algorithm that operates without hard thresholds, enhancing robustness and reducing setup time through auto-calibration of physical parameters. Key contributions include a robust circle detection method, a multi-hypothesis tracking s
- Author
- vixee
- Language
- EN