A Multi-Modal Edge Consistency Metric Based on Regression Robustness of Truncated SVD

作     者：Zhu, Mingzhu Yu, Junzhi Gao, Zhang He, Bingwei Liu, Jiantao 

作者机构：Fuzhou Univ Sch Mech Engn & Automat Fuzhou 350108 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen 518055 Peoples R China Peking Univ State Key Lab Turbulence & Complex Syst Dept Adv Mfg & Robot BIC ESATColl Engn Beijing 100871 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China 

出 版 物：《IEEE SIGNAL PROCESSING LETTERS》 (IEEE Signal Process Lett)

年 卷 期：2021年第28卷

页      面：1065-1069页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：National Key Research and Development Program of China [2020YFB1312800] Opening Project of Guangdong Provincial Key Lab of Robotics and Intelligent System 

主　　题：Image edge detection Measurement Robustness Linear regression Complexity theory Noise measurement Mutual information Regression robustness multi-modal corres-pondence edge consistency singular value decomposition 

摘      要：In this paper, we propose a novel edge consistency metric for multi-modal correspondence. It is based on a novel observation on image truncated SVD (singular value decomposition) termed regression robustness, which describes the fact that, a good approximation from image truncated SVD can be inherited even if the eigen-images change due to expansion and channel-dependent offsets. Compared to state-of-the-arts, multi-modal edge consistency metric can simultaneously handle multiple images with complex modality changes, including local variation, gradient reverse, intensity order change, and texture loss. Its complexity is almost linear to pixel number. Remarkable accuracies have been achieved in experiments.