A three-dimensional wire frame structure method and system fusing a binocular camera and IMU positioning

Abstract

The invention relates to a three-dimensional wire frame structure method and system fusing a binocular camera and IMU positioning. On the basis of binocular vision, the invention initializes and fusesinertial measurement information by using a divide-and-conquer strategy, implements tracking, positioning and drawing, and can robustly run in indoor and outdoor environments and complex motion conditions. On the basis of accurate positioning, 3D wireframe reconstruction and iterative optimization are carried out based on the posture of the key frame. Linear segments are matched by local featuresand spatial geometric constraints and back-projected into three-dimensional space. Through the angle and distance constraints, the straight line segments are divided into different sets. Based on thegrouping results, the fitting region is determined and the straight line segments are merged. Finally, a 3-D wireframe structure is output. The invention fuses multi-source information to improve thestability and robustness of the system on the traditional vision-based positioning and mapping method. At the same time, line information is added to the key frame to sparsely express the structuralcharacteristics of the three-dimensional environment, which improves the computational efficiency.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a method and system for merging positioning of a binocular camera and an IMU and reconstructing a three-dimensional wireframe structure. Background technique [0002] Vision-based simultaneous localization and mapping is an important research topic in the field of computer vision. It means that the vehicle is equipped with a specific visual sensor, which can perceive and describe the surrounding environment and estimate its own motion without prior environmental information. The complete visual positioning and mapping system can be divided into five parts: acquisition of sensor data, front-end visual odometer, back-end nonlinear optimization, loop detection and mapping. Compared with other measurement methods, the visual measurement method has the advantages of high precision, high efficiency, low cost, and simple system structure, and is widely used in robot navigatio...

AI Technical Summary

Problems solved by technology

On the one hand, the construction of sparse maps based on feature points loses key structural information in the environment and cannot form an effective description of the environment

The construction of dense maps requires processing a huge amount of point cloud data, which is expensive to calculate

On the other hand, only relying on a single visual sensor cannot meet the robustness and stability requirements of the system in some complex scenes (such as illumination changes, occlusion, highlights, repeated textures, and independent moving objects, etc.)

At present, there is no system capable of reconstructing environmental structural information with high efficiency and high precision in complex environments.

Images