Visual SLAM method and system based on image edge features

Abstract

The invention discloses a visual SLAM method based on image edge features. The visual SLAM method comprises the following steps: acquiring an image through a visual sensor; extracting edge features ofthe acquired image to perform pose estimation; carrying out nonlinear optimization according to a pose estimation result; performing closed-loop detection according to a nonlinear optimization result; carrying out global optimization according to a closed-loop detection result; and constructing a global map. Compared with the prior art, the method has the advantages that firstly, the image edge is an important component in the whole image and can always represent the whole image, so that the method has higher overall precision and signal-to-noise ratio and is more robust; secondly, the edge features can also operate in a robust mode under sparse textures, and the anti-interference capacity to illumination changes is high; and finally, the image edge features are the simplest expressions of the real scene, and the established map can well restore the real scene.

Description

technical field [0001] The present invention relates to the technical field of SLAM, in particular to a visual SLAM method, and more specifically to a visual SLAM method and system based on image edge features. Background technique [0002] SLAM (Simultaneous Localization and Mapping), that is, simultaneous positioning and composition, is a crucial technology in the field of robotics. It is mainly about the method for the robot to estimate its own position based on the surrounding environment map in an unknown environment, and at the same time incrementally build a global consistency map on the basis of its own positioning. SLAM is widely used in the fields of robot autonomous navigation and positioning, and has very important research value. Therefore, SLAM has become a research hotspot in academia and industry. [0003] Visual SLAM is based on visual sensors (such as monocular cameras, binocular cameras, RGB-D cameras, etc.), which can realize the construction of three-di...

AI Technical Summary

Problems solved by technology

[0013] However, the above two visual SLAM methods also have their own shortcomings.

[0014] For the SLAM method based on feature points, its disadvantage is that the feature points are very sparse, usually only occupy a small part of the entire image, and cannot represent the overall image well, so the anti-noise ability and overall accuracy are relatively low; in addition, the method The established sparse feature point map cannot represent the real scene very well, and it is prone to failure in scenes with sparse textures (such as corridors, walls, etc.)

[0015] For the SLAM method based on the direct method, its disadvantage is that it cannot run stably under the condition of brightness changes (such as indoor lights, outdoor shadows)

In addition, if the vision sensor moves too fast, it will fail in the case of motion blur in the image

Images