Urban main road speed prediction method based on big data and deep learning

A trunk road and speed prediction technology, applied in forecasting, data processing applications, traffic control systems of road vehicles, etc., can solve the problem of low accuracy of trunk road traffic speed, easy loss of correlation between different roads, and difficulty in extracting roads Speed ​​and other issues, to achieve high prediction accuracy and reliability, less vehicle data features, and low cost

Pending Publication Date: 2021-06-11
宁波中科信息技术应用研究院(宁波人工智能产业研究院) +1
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional time series model is based on linear fitting, it is difficult to extract the characteristics of road speed, and it is easy to lose the correlation between different roads, and the accuracy of predicting the main road speed is not high

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
  • Urban main road speed prediction method based on big data and deep learning
  • Urban main road speed prediction method based on big data and deep learning
  • Urban main road speed prediction method based on big data and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] A kind of urban arterial road speed prediction method based on big data and deep learning of the present invention comprises the following steps:

[0023] Step 1. Call the Amap API interface to collect the static data of the city's main road map and create a static road set A. Specifically include the following steps:

[0024] Step 1.1, collect the names of the main roads in the city and the names of the driving roads with a large daily traffic volume.

[0025] Step 1.2. Call the Gaode map API interface to obtain the vector map data of the above roads, including: road latitude and longitude, vehicle driving direction, etc.

[0026] Step 1.3, if figure 1 As shown, any vector road Road j , according to the different driving directions of the vehicle, it is split into two independent roads Road j_1 and Road j_2 .

[0027] Step 1.4, if figure 1 As shown, the vector road (Road j_1 or Road j_2 ), so that each road is composed of several line segments connected end to...

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 an urban main road speed prediction method based on big data and deep learning. The method comprises the following steps: calling an Amap API (Application Program Interface) to collect urban main road map data; collecting vehicle latitude and longitude coordinates and vehicle speed data in a vehicle-mounted GPS device (a new energy vehicle slave TBOX device), and performing road matching on each vehicle; calculating road average passing speed according to a road matching result, and establishing a road passing speed characteristic matrix by taking the road average passing speed as a characteristic; expanding a time dimension to create a road space-time passing speed characteristic matrix; utilizing a convolutional neural network model to extract road space-time passing speed features, and training the model to achieve main road passing speed prediction in a short time in the future. According to the road speed prediction method, few vehicle data features are needed, road matching is achieved through latitude and longitude coordinates, and vector operation is reduced; the road passing speed is calculated by using the vehicle speed, and the prediction model considers the relevance between time and space, so that the prediction accuracy and reliability are improved.

Description

technical field [0001] The invention belongs to the field of urban intelligent transportation, in particular to a method for predicting the speed of urban arterial roads based on big data and deep learning. Background technique [0002] With the acceleration of people's life rhythm, the demand for public transportation is increasing day by day, and the resulting traffic congestion and other problems are the real problems that the traffic management department is facing. By accurately estimating the average speed of urban arterial roads, it provides a basis for balancing traffic flow and optimizing traffic management, which is of great significance and social value for alleviating road congestion. [0003] For the urban arterial road speed prediction task, it is mainly divided into three steps: acquisition of arterial road speed data, vehicle road matching, road speed calculation and prediction: 1. In terms of data acquisition, install on different arterial road sections Fix...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/01G06N3/04G06Q10/04
CPCG08G1/0104G06Q10/04G06N3/045
Inventor 钟杰王磊黄晁
Owner 宁波中科信息技术应用研究院(宁波人工智能产业研究院)
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