6DOF pose estimation of a 3D rigid object based on edge-enhanced point pair features

作     者：Chenyi Liu Fei Chen Lu Deng Renjiao Yi Lintao Zheng Chenyang Zhu Jia Wang Kai Xu 

作者机构：College of ComputingNational University of Defense TechnologyChangsha410073China Department of Spine Surgerythe Second Xiangya HospitalCentral South UniversityChangsha410011China Clinical Nursing Teaching and Research Sectionthe Second Xiangya HospitalChangsha410011China College of Meteorology and OceanographyNational University of Defense TechnologyChangsha410073China Beijing Institute of Tracking and Communication TechnologyBeijing100094China 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2024年第10卷第1期

页      面：61-77页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported in part by the National Key R&D Program of China(2018AAA0102200) National Natural Science Foundation of China(62132021,62102435,61902419,62002375,62002376) Natural Science Foundation of Hunan Province of China(2021JJ40696) Huxiang Youth Talent Support Program(2021RC3071) NUDT Research Grants(ZK19-30,ZK22-52) 

主　　题：point pair feature(PPF) pose estimation object recognition 3D point cloud 

摘      要：The point pair feature(PPF)is widely used for 6D pose *** this paper,we propose an efficient 6D pose estimation method based on the PPF *** introduce a well-targeted down-sampling strategy that focuses on edge areas for efficient feature extraction for complex geometry.A pose hypothesis validation approach is proposed to resolve ambiguity due to symmetry by calculating the edge matching *** perform evaluations on two challenging datasets and one real-world collected dataset,demonstrating the superiority of our method for pose estimation for geometrically complex,occluded,symmetrical *** further validate our method by applying it to simulated punctures.