Quasi-Dense Matching for Oblique Stereo Images through Semantic Segmentation and Local Feature Enhancement

Quasi-Dense Matching for Oblique Stereo Images through Semantic Segmentation and Local Feature Enhancement

This paper proposes a quasi-dense feature matching algorithm that combines image semantic segmentation and local feature enhancement networks to address the problem of the poor matching of image features because of complex distortions, considerable occlusions, and a lack of texture on large oblique...

Full description

Bibliographic Details
Main Authors: Guobiao Yao, Jin Zhang, Fengqi Zhu, Jianya Gong, Fengxiang Jin, Qingqing Fu, Xiaofang Ren
Format: Article
Language:English
Published: MDPI AG 2024-02-01
Series:Remote Sensing
Subjects:
oblique stereo images
deep learning
semantic segmentation
weak texture feature matching
quasi-dense matching
Online Access:https://www.mdpi.com/2072-4292/16/4/632

Internet

https://www.mdpi.com/2072-4292/16/4/632

Similar Items