Simultaneous positioning and dense three-dimensional reconstruction method

Abstract

The invention discloses a simultaneous positioning and dense three-dimensional reconstruction method, and the method can process quick motion and frequent closing of a loop in a robust manner, and can operate all the time in a larger-scale scene. The method not only can be used for scanning a high-quality three-dimensional model, but also can meet the demands of virtual reality and augmented reality. The method proposes a simultaneous positioning and map construction framework based on a key frame. At first, the method employs the depth and color information at the same time, and can operate on a CPU at a high speed based on the positioning of the key frame, and also can operate in a challenging scene in a robust manner. In order to reduce an accumulated error, the method introduces increment bundling adjustment, can greatly reduce the calculation amount, and enables the local and global bundling adjustment to be completed in a unified framework. Secondly, the invention proposes a fusion method based on the key frame, and the method can achieve the online generation of a model and updates the three-dimensional model in real time during the adjustment of the posture of the key frame.

Description

technical field [0001] The invention relates to a simultaneous positioning and dense three-dimensional reconstruction method applicable to the fields of augmented reality, virtual reality, robot navigation, etc., in particular to a simultaneous positioning and dense three-dimensional reconstruction method. Background technique [0002] Simultaneously Locating and Mapping (SLAM) is a fundamental problem in the field of robotics and computer vision. In the past few years, there have been many successful applications of real-time structure from motion (Structure from Motion) and visual SLAM. However, visual SLAM is difficult to deal with untextured scenes, and it is also difficult to restore dense 3D structures in real time and stably. Using a depth sensor can help with both issues. With the popularity of depth sensors (such as Microsoft Kinect and Intel RealSense 3D cameras), a large number of RGB-D based SLAM schemes have been proposed. [0003] Most dense SLAM methods use...

AI Technical Summary

Problems solved by technology

However, BundleFusion saves all input data, limiting its operation on long sequence data

At the same time, even with a strong GPU, using brute force matching on long sequence input is very time-consuming

Images