TOLDI: An effective and robust approach for 3D local shape description

详细信息    查看全文

• 作者：Jiaqi Yang ^{jqyang@hust.edu.cn}Author Vitae ; Qian Zhang ^{hangfanzq@163.com}Author Vitae ; Yang Xiao ^{Yang_Xiao@hust.edu.cn}Author Vitae ; Zhiguo Cao ; ^{zgcao@hust.edu.cn}Author Vitae
• 关键词：Local reference frame ; Local feature descriptor ; Shape retrieval ; Object recognition ; 3D registration
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：65
• 期：Complete
• 页码：175-187
• 全文大小：1731 K
• 卷排序：65

文摘

A novel local reference frame (LRF) is proposed for local shape descriptors. A new feature representation called the triple orthogonal local depth images (TOLDI) is presented. Extensive experiments on the shape retrieval, object recognition and 3D matching datasets are carried out. Our proposal achieves the best overall performance against several existing methods.