Robust three-dimensional point cloud feature matching method based on progressive consistency voting

• Main Authors: NAN KECHEN, YE KAIXIAO, KWON SA MUN, YIN KUNPENG
• Format: Patent
• Language: Chinese; English
• Published: 27.12.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention provides a robust three-dimensional point cloud feature matching method based on progressive consistency voting. The robust three-dimensional point cloud feature matching method comprises the following steps: acquiring three-dimensional point cloud data containing a source point cloud and a target point cloud; performing feature extraction and feature matching on the three-dimensional point cloud data to obtain an initial matching set; for each matched corresponding relation in the initial matching set, compatibility evaluation and voting are carried out on the corresponding relation and candidate corresponding relations in the current voting set, a confidence score is distributed to each corresponding relation through PCV (Progressive Consistency Voting), one voting set and the corresponding confidence score are optimized step by step through iteration, and the voting set and the confidence score corresponding to the voting set are optimized; then, selecting corresponding relations from the cor