Processing

Please wait...

Settings

Settings

Goto Application

1. WO2019056845 - ROAD MAP GENERATING METHOD AND APPARATUS, ELECTRONIC DEVICE, AND COMPUTER STORAGE MEDIUM

Publication Number WO/2019/056845
Publication Date 28.03.2019
International Application No. PCT/CN2018/096332
International Filing Date 19.07.2018
IPC
G06T 11/20 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D image generation
20Drawing from basic elements, e.g. lines or circles
G01C 21/32 2006.01
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/-G01C19/104
26specially adapted for navigation in a road network
28with correlation of data from several navigational instruments
30Map- or contour-matching
32Structuring or formatting of map data
G06F 17/30 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
30Information retrieval; Database structures therefor
G06N 3/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
CPC
G01C 21/32
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in preceding groups G01C1/00-G01C19/00
26specially adapted for navigation in a road network
28with correlation of data from several navigational instruments
30Map- or contour-matching
32Structuring or formatting of map data
G01C 21/3822
G01C 21/3852
G06F 16/29
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
29Geographical information databases
G06F 17/18
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
10Complex mathematical operations
18for evaluating statistical data ; , e.g. average values, frequency distributions, probability functions, regression analysis
G06K 9/00651
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
0063Recognising patterns in remote scenes, e.g. aerial images, vegetation versus urban areas
00651of network patterns, such as roads, rivers
Applicants
  • 北京市商汤科技开发有限公司 BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD. [CN]/[CN]
Inventors
  • 程光亮 CHENG, Guangliang
  • 石建萍 SHI, Jianping
Agents
  • 北京思源智汇知识产权代理有限公司 BEIJING SIYUANZHIHUI INTELLECTUAL PROPERTY AGENCY
Priority Data
201710848159.219.09.2017CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) ROAD MAP GENERATING METHOD AND APPARATUS, ELECTRONIC DEVICE, AND COMPUTER STORAGE MEDIUM
(FR) PROCÉDÉ ET APPAREIL DE GÉNÉRATION DE CARTE ROUTIÈRE, DISPOSITIF ÉLECTRONIQUE ET SUPPORT D'INFORMATIONS D'ORDINATEUR
(ZH) 道路图生成方法、装置、电子设备和计算机存储介质
Abstract
(EN)
Disclosed in embodiments of the present application are a road map generating method and apparatus, an electronic device, and a computer storage medium. An optional implementation of the method comprises: inputting a remote sensing image into a first neural network, to extract first multichannel road feature information via the first neural network; inputting the first multichannel road feature information into a third neural network, to extract third multichannel road feature information via the third neural network, wherein the third neural network is a neural network trained by means of supervision on the basis of road direction information; fusing the first road feature information and the third road feature information; and generating a road map according to the fusion result. The embodiments of the present application improve the accuracy of extracting road direction features of the remote sensing image.
(FR)
Des modes de réalisation de la présente invention concernent un procédé et un appareil de génération de carte routière, un dispositif électronique et un support d'informations d'ordinateur. Une mise en œuvre facultative du procédé comprend : l'entrée d'une image de détection à distance dans un premier réseau neuronal, pour extraire des premières informations de caractéristiques de route à canaux multiples via le premier réseau neuronal; l'entrée des premières informations de caractéristiques de route à canaux multiples dans un troisième réseau neuronal, pour extraire des troisièmes informations de caractéristiques de route à canaux multiples via le troisième réseau neuronal, le troisième réseau neuronal étant un réseau neuronal formé par supervision sur la base des informations de direction de route; la fusion des premières informations de caractéristiques de route et des troisièmes informations de caractéristiques de route; et la génération d'une carte routière selon le résultat de la fusion. Les modes de réalisation de la présente invention améliorent la précision pour extraire des caractéristiques de direction de route de l'image de détection à distance.
(ZH)
本申请实施例公开了一种道路图生成方法、装置、电子设备和计算机存储介质。该方法的一可选实施方式包括:将遥感图像输入第一神经网络,以经所述第一神经网络提取多通道的第一道路特征信息;将所述多通道的第一道路特征信息输入第三神经网络,以经所述第三神经网络提取多通道的第三道路特征信息,其中,所述第三神经网络为以道路方向信息为监督训练完成的神经网络;融合所述第一道路特征信息和所述第三道路特征信息;根据融合结果生成道路图。本申请实施例提高了提取遥感图像对道路方向特征的准确性。
Latest bibliographic data on file with the International Bureau