Camera pose estimation method and system based on semantics

Abstract

The invention relates to a camera pose estimation method and system based on semantics. The method comprises the following steps: S1, constructing an image database, a semantic feature database and a global feature database by using an RGB image sequence; s2, extracting a global feature vector of the RGB image of the pose to be estimated, and performing RGB retrieval to obtain an RGB retrieval result set R1; s3, extracting semantic feature vectors of the static semantic graph of the to-be-estimated pose RGB image for semantic retrieval to obtain a retrieval result set R2; s4, optimizing R1 and R2 by using an interval selection algorithm to obtain a set R; and S5, forming an image pair by each image in the R and a to-be-estimated pose RGB image, obtaining a 2D-3D matching pair through image feature matching and three-dimensional information of an image database, and inputting the 2D-3D matching pair into a pose estimation algorithm to calculate and obtain pose estimation of the camera. According to the method provided by the invention, the robustness of the pose estimation algorithm is enhanced by using the image semantic information, so that a more accurate pose estimation result can be obtained under the conditions of environment illumination change and dynamic object shielding.

Description

technical field [0001] The invention relates to the fields of autonomous navigation and robots, and in particular to a semantic-based camera pose estimation method and system. Background technique [0002] For many applications such as augmented reality, autonomous navigation, and intelligent robotics, accurate pose estimation has a critical impact on the experience and performance of the application. Only by accurately estimating the current pose information of the device can the current position be accurately calibrated in automatic navigation, and virtual objects can be accurately fused in various augmented reality scenes. The traditional civilian GPS positioning method, the horizontal error is often within 10m, and the error may reach 20-30m when there is signal fluctuation, which cannot meet the needs of some precise positioning; the lidar positioning method requires special lidar equipment, which is expensive and expensive. The portability is poor; the radio frequency...

AI Technical Summary

Problems solved by technology

The above semantic-based methods all use reprojection to process semantic information, and use image semantic information to perform accurate pose estimation, but the effect of pose estimation depends on the accuracy of semantic segmentation. no advantage

Images