Live Video Segmentation in Dynamic Backgrounds Using Thermal Vision

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper we describe a new technique for live video segmentation of human regions from dynamic backgrounds. Correct segmentations are produced in real-time even in severe background changes caused by camera movement and illumination changes. There are three key contributions. The first contribution is the employing of the thermal cue which proves to be very effective when fused with color. Second, we propose a new speed-up GraphCut algorithm by combining with the Bayesian estimation. The third contribution is a novel online learning method using cumulative histograms. The segmentation accuracy and speed are quite capable of the live video segmentation purpose.

• Information and Media Technologies 編集運営会議の論文

著者

• TAKAHASHI Keita

  IRT Research Initiative, The University of Tokyo

• NAEMURA Takeshi

  Graduate School of Information Science & Technology, The University of Tokyo

• Takahashi Keita

  Irt Research Initiative The University Of Tokyo

• Pham Viet-Quoc

  Graduate School of Information Science and Technology, The University of Tokyo

関連論文

• 流体レンズアレイを用いた光学焦点と合成焦点の制御
• Design and Implementation of a Real-Time Video-Based Rendering System Using a Network Camera Array
• Optical and Synthetic Focusing Using Liquid Lens Array
• THERMOSAIC : AUTOMATIC OBSCURE EFFECTS USING THERMAL INFORMATION(International Workshop on Advanced Image Technology 2006)
• Theoretical Analysis of Multi-View Camera Arrangement and Light-Field Super-Resolution
• Live Video Segmentation in Dynamic Backgrounds Using Thermal Vision

スポンサーリンク