Ball tracking with velocity based on Monte-Carlo localization

Jun Inoue, Akira Ishino, Ayumi Shinohara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This work presents methods for tracking a ball from noisy data taken by robots. In robotic soccer, getting a good estimation of a ball's position is a critical. In addition, accurate ball tracking enables robots to play well, for example, efficiently passing to other robots, fine saves by the goalie, good team play, and so on. In this paper, we present new ball tracking technique based on Monte-Carlo localization. The key idea of our technique is to consider two kinds of samples, one for position and the other for velocity. As a result of this technique, it enables us to estimate trajectory of the ball even when it goes out of view.

Original languageEnglish
Title of host publicationIntelligent Autonomous Systems 9, IAS 2006
Pages686-693
Number of pages8
Publication statusPublished - 2006 Dec 1
Event9th International Conference on Intelligent Autonomous Systems, IAS 2006 - Tokyo, Japan
Duration: 2006 Mar 72006 Mar 9

Publication series

NameIntelligent Autonomous Systems 9, IAS 2006

Other

Other9th International Conference on Intelligent Autonomous Systems, IAS 2006
CountryJapan
CityTokyo
Period06/3/706/3/9

Keywords

  • Monte-Carlo Localization
  • Object Recognition
  • Object Tracking
  • RoboCup

ASJC Scopus subject areas

  • Computer Science(all)
  • Computational Mechanics
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Ball tracking with velocity based on Monte-Carlo localization'. Together they form a unique fingerprint.

Cite this