Optimization for image stereo-matching using deep reinforcement learning in rule constraints and parallax estimation

Stereo-matching is a hot topic in the field of visual image research, to address the low image-matching accuracy of traditional algorithms. In this paper, an optimization for image stereo-matching algorithm using deep reinforcement learning (DRL) is proposed in rule constraints and parallax estimati...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2023-12, Vol.35 (35), p.24701-24711
Main Authors: Ren, Jie, Guan, Fuyu, Li, Xueyan, Cao, Jie, Li, Xiaofeng
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial Intelligence
Artificial neural networks
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Deep learning
Feature extraction
Geometric constraints
Image Processing and Computer Vision
Machine learning
Matching
Neural networks
Optimization
Parallax
Pixels
Probability and Statistics in Computer Science
S.I.: Applications and Techniques in Cyber Intelligence (ATCI2022)
Semantics
Special Issue on Applications and Techniques in Cyber Intelligence (ATCI2022)
Visual fields
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Stereo-matching is a hot topic in the field of visual image research, to address the low image-matching accuracy of traditional algorithms. In this paper, an optimization for image stereo-matching algorithm using deep reinforcement learning (DRL) is proposed in rule constraints and parallax estimation. First, the image edge pixel constraint rules are established, and the image sample blocks are adjusted. Second, the image parallax estimation is performed by computing geometric constraint and pixel parallax probability in rule constraints, and a DRL structure is designed. Finally, the DRL analysis is performed iteratively by the convolutional neural networks feature extraction, agent training decision, and reward value accumulation, and stereo-matching images are output. Experiments show that the image structural similarity of the proposed algorithm is high, and the correct matching rate is more than 95%. The images have good interpretability, and the stereo-matching effect is good.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-023-08227-3