Recent Reviews on Machine Vision-Based 3D Reconstruction

Background: In machine vision, 3D reconstruction is widely used in the medical system, autonomous navigation, aviation and remote sensing measurement, industrial automation, and other fields, and the demand for reconstruction precision is significantly highlighted. Therefore, 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 on 3D reconstruction, this paper provides references to researchers in related fields. Methods: Machine vision-based 3D reconstruction patents and articles were analyzed from the aspects of the algorithm, innovation, and application. Among them, there are over 30 patents and nearly 30 articles that have been published in the past ten years. Results: Researches on machine vision-based 3D reconstruction in the recent 10 years were 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 was 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, etc. Furthermore, more patents on machine vision-based 3D reconstruction should also be invented.