Background:
In machine vision, the 3D reconstruction is widely used in medical system, autonomous navigation, aviation and remote sensing measurement, industrial automation and other fields, and the demand for reconstruction precision is significantly highlighted. Therefore, the 3D reconstruction is of great research value and will be an important research direction in the future.
Objective:
By reviewing the latest development and patent of 3D reconstruction, this paper provides references to researchers in related fields.
Methods:
Machine vision-based 3D reconstruction patents and literatures were analyzed from the aspects of the algorithm, innovation and application. Among them, there are more than 30 patents and nearly 30 literatures in the past ten years.
Results:
Researches on machine vision-based 3D reconstruction in recent 10 years are reviewed, and the typical characteristics were concluded. The main problems in its development were analyzed, the development trend was foreseen, and the current and future research on the productions and patents related to machine vision-based 3D reconstruction is discussed.
Conclusion:
The reconstruction result of binocular vision and multi-vision is better than monocular vision in most cases. Current researches of 3D reconstruction focus on robot vision navigation, intelligent vehicle environment sensing system and virtual reality. The aspects that need to be improved in the future include: improving robustness, reducing computational complexity, and reducing operating equipment requirements, and so on. Furthermore, more patents on machine vision-based 3D reconstruction also should be invented.
CNN Training Using 3D Virtual Models for Assisted Assembly with Mixed Reality and Collaborative Robots
