A binocular vision SLAM method combining point and line characteristics

Abstract

The invention discloses a point-line feature combined binocular vision SLAM method. The method comprises the following steps: S1, calibrating internal parameters of a binocular camera; S2, using the calibrated camera to collect an environment image, and using a gradient density filter to filter a feature dense region to obtain an effective image detection region; S3, extracting feature points andfeature lines; S4, performing broken line combination on the extracted line features; S5, performing tracking matching by utilizing the feature point line, and selecting a key frame; S6, constructinga cost function by using the re-projection error of the feature point line; S7, performing local map optimization; And S8, judging a closed loop by using the point-line combined word bag model, and optimizing the global track. The invention provides an image filtering mechanism, a line segment merging method and an accelerated back-end optimization calculation method, solves the problems that a large number of invalid features are extracted from an image feature dense region, a line feature extraction method is broken, a traditional back-end optimization method is long in time consumption andthe like, and improves the robustness, the precision and the speed of a system.

Description

technical field [0001] The invention belongs to the technical field of photogrammetry and computer vision, and in particular relates to a binocular vision SLAM method combining point and line features. Background technique [0002] The SLAM algorithm based on point features can perform feature tracking, composition, and closed-loop detection in real time, and complete simultaneous positioning and map construction. It is currently one of the most mainstream algorithms in the visual field. However, point features are easily disturbed by light and noise, and the constructed 3D point map is relatively sparse, which cannot express the real scene structure. Especially in some low-texture scenes, there are often insufficient features and the performance of the algorithm decreases. Compared with point features, line features carry more structural information. The point-line fusion algorithm that introduces line features can better restore the scene structure, and still performs wel...

AI Technical Summary

Problems solved by technology

However, the traditional LSD-based line feature extraction method is easy to cause problems such as over-segmentation of line segments, which reduces the accuracy of the algorithm.

And in large-scale 3D reconstruction, the traditional calculation method is inefficient and not suitable for real-time calculation

Images