Map construction method and device based on semantic point cloud
A map construction and semantic technology, applied in the field of map construction based on semantic point cloud, can solve the problems of high bandwidth occupation and transmission delay, occupation of large computing resources, high-precision map occupation of large hard disk space, etc., to reduce the amount of data, The effect of reducing the amount of calculation and occupying storage space
Active Publication Date: 2020-02-07
BEIJING HORIZON ROBOTICS TECH RES & DEV CO LTD
View PDF12 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If these 3D semantic point clouds are directly stored in the database, the generated high-precision map will occupy a large amount of hard disk space. If the map data is transmitted through the network during the positioning stage, it will bring extremely high bandwidth occupation and transmission delay. consumes a lot of computing resources
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
[0035] Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described here.
[0036] Application overview
[0037] When the vehicle is driving, it usually needs to open the map for navigation. The higher the accuracy of the map, the more detailed information it contains, which plays a very important role in the navigation, positioning and control of the vehicle. In order to obtain high-precision maps, one of the solutions commonly used at present is to obtain images through cameras and construct maps through SLAM. In the SLAM mapping scheme, a dense 3D semantic point cloud can be obtained through 3D reconstruction, which contains a ...
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 invention discloses a map construction method and a device based on semantic point cloud, and the method comprises the steps: carrying out the classification of semantic point cloud data accordingto a semantic type, so as to obtain at least one piece of sub-point cloud data; for each type of sub-point cloud data, constructing a corresponding Gaussian mixture map; and combining the Gaussian mixture maps corresponding to the sub-point cloud data of each type to obtain a semantic Gaussian mixture map. Point cloud data are classified according to semantic types; for each type of sub-point cloud data, a Gaussian function is adopted to fit the height of a data point of the sub-point cloud data, so that height distribution can be stored in a mode of storing parameters of the Gaussian function, the data volume of the semantic Gaussian mixture map is greatly reduced, and the storage space occupied by the map is reduced.
Description
technical field [0001] The present application relates to the technical field of electronic maps, and more specifically, to a method and device for constructing maps based on semantic point clouds. Background technique [0002] In related technologies, dense visual real-time localization and map construction (Simultaneous Localization and Mapping, SLAM for short) are used in many fields. In the SLAM mapping scheme, a dense 3D point cloud is obtained through 3D reconstruction, and a 3D semantic point cloud can be obtained through image semantic segmentation and image semantic type projection to the 3D point cloud. If these 3D semantic point clouds are directly stored in the database, the generated high-precision map will occupy a large amount of hard disk space. If the map data is transmitted through the network during the positioning stage, it will bring extremely high bandwidth occupation and transmission delay. It will take up a lot of computing resources. Contents of t...
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 Applications(China)
IPC IPC(8): G06T17/05G06T7/10G06K9/62
CPCG06T17/05G06T7/10G06T2207/10028G06T2207/10044G06F18/241
Inventor 徐斌峰
Owner BEIJING HORIZON ROBOTICS TECH RES & DEV CO LTD