Approximate optimization and learning of higher-order energy

2014 Fiscal Year Final Research Report

• Project/Area Number: 24300075
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Waseda University
• Principal Investigator: ISHIKAWA Hiroshi 早稲田大学, 理工学術院, 教授 (60381901)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 最適化 / コンピュータビジョン

Outline of Final Research Achievements

We realized an algorithm that approximately minimize non-submodular multi-label energies. We also made it possible to minimize binary higher-order energies faster and with less memory by enabling to reduce them into first-order energies without adding additional variables in certain cases. As applications of higher-order energies, we used them for segmentation of pulmonary artery-vein segmentation, where we represented the shapes of pulmonary blood vessels by higher-order potentials. We also improved algorithms to segment coronary lumen and plaques from CT angiography, also using higher-order shape priors.

Free Research Field

コンピュータビジョン