A Fragmented Map Stitching Method Based on Road Traffic Markings
A road traffic and fragmentation technology, which is applied to the details of image stitching, image data processing, and graphics and image conversion, and can solve problems such as poor stitching effects
Active Publication Date: 2022-05-17
WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the technical problems existing in the prior art, the present invention provides a splicing method of fragmented maps based on road traffic markings, which solves the problem of poor splicing effect in the prior art
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 1
[0060] Embodiment 1 provided by the present invention is an embodiment of a fragmented map splicing method based on road traffic markings provided by the present invention, such as figure 2 Shown is a flow chart of an embodiment of a fragmented map splicing method based on road traffic markings provided by the present invention. figure 2 As can be seen, this embodiment includes:
[0061] Step 1: Carry out road traffic marking detection based on computer vision perception technology, and store each road traffic marking in a sequence format according to the detection order.
[0062] Computer perception technology uses neural network technology to detect and locate road traffic markings in the sequence images continuously collected by the camera during vehicle driving.
[0063] preferred, such as image 3 Shown is a schematic diagram of an embodiment of road traffic markings, represented by image 3 It can be seen that the types of road traffic markings include arrows, stop ...
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 relates to a splicing method for fragmented maps based on road traffic markings, comprising: detecting road traffic markings based on computer vision perception technology, storing each road traffic markings in a sequence format according to the detection sequence; The sequence of road traffic markings of the two fragmented maps is slidingly matched; the relative pose relationship between the two fragmented maps is calculated according to the position coordinate information of the road traffic markings in the matching success sequence, and the relative pose relationship is calculated according to the relative pose relationship Carry out splicing of fragmented maps; do not need to rely on artificially designed sparse key point extraction and matching methods, based on robust road traffic marking matching methods, can effectively improve the probability of successful splicing of fragmented maps; and can cope with the existence of dynamic objects, Environments with large lighting changes can improve the effectiveness and robustness of multiple fragmented map stitching schemes in the same scene, and improve the composition accuracy of low-cost composition schemes.
Description
technical field [0001] The invention relates to the field of automatic production of high-precision maps, in particular to a splicing method for fragmented maps based on road traffic markings. Background technique [0002] High-precision maps play an important role in the automatic driving system and are an indispensable part of the automatic driving system. Traditional high-precision map production methods rely on professional collection equipment and professional collection personnel. Collection equipment usually uses high-frequency Mapping lidar and high-precision POS system for positioning and attitude determination. The POS system includes GNSS (Global Navigation Satellite System, Global Navigation Satellite Positioning System) and high-precision IMU (Inertial Measurement Uni, Inertial Measurement Unit), which makes the cost of collecting data high. . At the same time, the more complex collection process and operation methods take a long time, which will cause the high...
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): G06T3/40G06K9/62G06V20/56G06V10/74G06V20/58
CPCG06T3/4038G06T2200/32G06V20/588G06F18/22Y02T10/40
Inventor 刘江吴凯王晨宇付垚刘奋
Owner WUHAN ZHONGHAITING DATA TECH CO LTD