Human Pose Estimation with Implicit Shape Models

• Tác giả: Jürgen Brauer
• Ngôn ngữ: eng
• ISBN-13: 978-3731501848
• Thông tin xuất bản: Karlsruhe : KIT Scientific Publishing, 2014
• Mô tả vật lý: 1 electronic resource (XVIII, 264 p. p.)
• Bộ sưu tập: Tài liệu truy cập mở
• ID: 203407

Tóm tắt

This work presents a new approach for estimating 3D human poses based on monocular camera information only. For this, the Implicit Shape Model is augmented by new voting strategies that allow to localize 2D anatomical landmarks in the image. The actual 3D pose estimation is then formulated as a Particle Swarm Optimization (PSO) where projected 3D pose hypotheses are compared with the generated landmark vote distributions.