Moving Object Detection from Optical Flow without Empirical Thresholds

スポンサーリンク

概要

• 論文の詳細を見る

• We show that moving objects can be detected from optical flow without using any knowledge about the magnitude of the noise in the flow or any thresholds to be adjusted empirically. The underlying principle is viewing a particular interpretation about the flow as a geometric model and comparing the relative"goodness"of candidate models measured by the geometric AIC.

• 社団法人電子情報通信学会の論文
• 1998-02-25

著者

• KANATANI Kenichi

  the Department of Computer Science, Gunma University

• Kanatani Kenichi

  The Department Of Computer Science Gunma University

• Ohta Naoya

  The Department Of Computer Science Gunma University

• KIMURA Kazuhiro

  CSK, Co.,

関連論文

• Optimal Homography Computation with a Reliability Measure(Special Issue on Machine Vision Applications)
• Moving Object Detection from Optical Flow without Empirical Thresholds
• Automatic Recognition of Regular Figures by Geometric AIC

スポンサーリンク