A visual slam method based on line features
A line feature and line feature technology, applied in the field of visual SLAM based on line features, can solve problems such as mismatching, difficulty in feature point extraction, and easy to be affected by light, and achieve the effects of good system stability, improved accuracy, and high precision
Active Publication Date: 2022-06-03
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention aims at the difficulty of extracting feature points in visual SLAM based on feature points, being easily affected by illumination, mis-matching and other problems, and introduces straight line features
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0033] As shown in Figure 2, in each frame of image, the LSD straight line detection method is used to extract straight line features. Due to linear detection
[0039] As shown in Figure 5, the LBD descriptor schematic diagram is composed of several parallel strips to form a line segment support field LSR,
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides a visual SLAM method based on straight line features, comprising the following steps: S1, constructing new type point features at the intersection of feature lines; S2, extracting point features from line features, and introducing a straight line feature description method; S3, in the backend according to A new line feature description method, matching the line feature bag of words, to determine the unique line in the space. The invention can greatly improve the precision of feature extraction, and the straight line features are not affected by factors such as illumination, and the system has good stability and high precision.
Description
A Visual SLAM Method Based on Line Features technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a visual SLAM method based on linear features. technical background [0002] At present, the commonly used feature matching methods for images are point matching, line matching and surface matching. When the images are matched, by In different types of images, feature points are easy to extract, so point features are usually the most commonly used matching methods. but, Compared with feature lines, feature points have three disadvantages: first, feature points are easily affected by environmental noise, and the stability of The characteristic line has strong anti-interference ability to environmental noise and high stability. In addition, compared to the extraction of feature points Compared with positioning, the positioning of feature lines is more accurate and can reach the sub-pixel level. Second, the c...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/73G06V10/44
CPCG06T7/73
Inventor 蒋朝阳王慷郑晓妮
Owner BEIJING INSTITUTE OF TECHNOLOGYGY