Track motion mode recognition method and device

A pattern recognition and trajectory motion technology, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve problems such as low accuracy and complex process, and achieve the effect of improving accuracy and good recognition.

Pending Publication Date: 2020-03-06
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a trajectory motion pattern recognition method and device to solve the problem that the current motion pattern recognition process needs to manually select representative features, resulting in complicated process and low accuracy

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
  • Track motion mode recognition method and device
  • Track motion mode recognition method and device
  • Track motion mode recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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

[0023] method embodiment

[0024] The present invention discretizes the track data space into a grid, and converts the track expression form from a coordinate sequence to a grid sequence containing multi-dimensional information, wherein the position of each grid represents the user's position, and the grid sequence reflects the geographic space of the user's track Features and geometric features, the pixels of each grid represent the average speed of the user in the grid, reflecting the mobility characteristics of the user's trajectory; the grid sequence obtained after preprocessing is input into the deep learning model, and the deep learning model The movement pattern recognition is carried out on the track data of the user to be recognized, and the deep learning model is obtained by training the historical track data with known movement pa...

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 relates to a track motion mode recognition method and device, and belongs to the technical field of artificial intelligence. The track motion mode recognition method includes the steps:through a deep learning mode, automatically extracting depth features of preprocessed to-be-identified track data, wherein the obtained depth features have a better identification degree, so that theaccuracy of mode identification can be significantly improved; and meanwhile, when carrying out pretreatment, converting the track data into the grid data containing the multi-dimensional information,wherein the positions of the grids represent the positions of the users, and the grid sequence reflects the geographic space characteristics and the geometrical characteristics of the user track, andthe pixels of the grid represent the average speed of the user in the grid and reflect the kinematicity characteristics of the user track, so as to guarantee that the converted track data can fully express the representative characteristics of the mobile user track, and the accuracy of pattern recognition is further improved.

Description

technical field [0001] The invention relates to a trajectory motion pattern recognition method and device, belonging to the technical field of artificial intelligence. Background technique [0002] Analyzing the movement patterns of mobile user trajectories is a key means to understand the spatio-temporal characteristics of user behavior, traffic conditions, and the user's environment. User travel usually includes specific motion patterns, such as individual users choose different destinations and routes, different means of transportation (taxi, bus, walking, bicycle, etc.), ship users perform different navigation activities (fishing, oil transportation, etc.) , transportation of goods, towing, sightseeing, etc.). Information about specific motion patterns is usually not actively reported by users, and such information has a wide range of application values ​​for practical applications, such as intelligent transportation systems, urban traffic management, early warning syst...

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): G06K9/00G06K9/62G06N3/04
CPCG06V10/95G06N3/045G06F18/214
Inventor 陈锐陈明剑
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
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