Method for constructing and storing three-dimensional semantic map for road scene

A semantic map and three-dimensional technology, which is applied in the construction and storage of three-dimensional semantic maps for road scenes, can solve the problems of large loads and massive calculations in vehicle systems, reduce occupation, meet the needs of rapid construction and storage, and optimize map updates way effect

Active Publication Date: 2019-01-01
SOUTHEAST UNIV
View PDF4 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in terms of road 3D map construction, how to use cameras for map construction is still relatively small, and beca

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for constructing and storing three-dimensional semantic map for road scene
  • Method for constructing and storing three-dimensional semantic map for road scene
  • Method for constructing and storing three-dimensional semantic map for road scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings and specific examples.

[0023] figure 1 It is a schematic diagram of the implementation process of the present invention, and the specific steps are shown by reference numerals 101-106.

[0024] Use the on-board camera to directly shoot the road scene video during driving, and use the visual synchronization positioning and composition technology, that is, VSLAM, to complete the camera pose estimation and key frame capture, and perform image pixel depth estimation on the key frame, such as figure 2 As shown; 3D map reconstruction can be realized by using the obtained key frames and image depth estimation. For the key frame acquired at a certain time t, using the trained two-dimensional semantic segmentation model based on deep convolutional neural network, the original color image of the current key frame is used as input to infer its image semantic information, that is...

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

No PUM Login to view more

Abstract

The invention discloses a method for constructing and storing a three-dimensional semantic map facing a road scene. The method comprises the following steps: a sensor collects road condition video data in a moving process, obtains key frames by using a synchronous positioning and mapping technology, calculates a pose and an inverse depth map, and constructs a semi-dense point cloud map; the semantic markers are extracted from the obtained key frames by using the semantic segmentation model. The semantic tagging data of continuous key frames are fused to modify the three-dimensional point cloudsemantic tagging by using two-dimensional to three-dimensional spatial semantic tagging transformation. According to the obtained 3D semantic point cloud map, the 3D semantic point cloud data is represented as a 3D map based on occupancy probability and semantic information. The invention utilizes a camera to carry out three-dimensional semantic composition, comprising a plurality of road targetscene distributions; the road 3D semantic information is constructed quickly by vehicle-mounted system to meet the requirement of real-time storage. Using map compression technology, compared with theoriginal large volume of three-dimensional map storage requirements, only occupy a small amount of storage space.

Description

technical field [0001] The invention relates to the application of road information collection and three-dimensional modeling methods in the technical field of vehicles, in particular to a fast three-dimensional semantic composition method and an efficient storage method for road scenes. Background technique [0002] With the development of information sensing and computer vision technology, it has become an increasingly important research and development requirement to collect road scene data for map construction and use it for assisted driving and driverless applications. [0003] Because the cost of the camera is relatively low and the installation is convenient, the vehicle-mounted system with the camera as the core sensor has a wide range of applications. However, in terms of road three-dimensional map construction, how to use cameras for map construction is still relatively small, and because building three-dimensional maps often requires a lot of computing and storage...

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
no application Login to view more
IPC IPC(8): G06K9/00G06T7/55
CPCG06T7/55G06T2207/10024G06T2207/10016G06T2207/10028G06T2207/20016G06T2207/20081G06T2207/20084G06T2207/30252G06V20/10
Inventor 李煊鹏敖焕轩李宇杰薛启凡
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap