Laser bidirectional pedestrian counting method based on Gaussian process regression

A Gaussian process regression and pedestrian counting technology, which is applied to measuring devices, instruments, indicating/recording actions, etc., can solve and rank pedestrian counting problems, and achieve the effect of accurate pedestrian counting and direction judgment

Active Publication Date: 2015-11-11
SUN YAT SEN UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the problem that the existing laser-based pedestrian counting method cannot effectively count parallel pedestrians and judge the direction of pedestrians entering and exiting, the present invention provides a laser-based two-way pedestrian counting method based on Gaussian process regression

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
  • Laser bidirectional pedestrian counting method based on Gaussian process regression
  • Laser bidirectional pedestrian counting method based on Gaussian process regression
  • Laser bidirectional pedestrian counting method based on Gaussian process regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0020] A laser two-way pedestrian counting method based on Gaussian process regression, comprising the following steps:

[0021] The laser rangefinder detects and returns the distance information. After triangulation, the distance data is converted into height data; through the operation with the background model, the foreground height of the detection point is obtained; after a period of accumulation, the foreground height of each detection point is used Generate Timing Height picture ; at timing height in the picture Carry out detection point clustering to extract pedestrian height clusters; select the geometric and shape features of the height clusters, and select the Gaussian process regression method to calculate the number of pedestrians in the pedestrian height clusters;

[0022] Use a dynamically sized sliding window to act on the projection of the pedestrian height cluster along the time axis; the size of the sliding window is determined by the width of the pedestr...

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 laser bidirectional pedestrian counting method based on Gaussian process regression. The method comprises the following steps of detecting return distance information by a laser range finder and converting the distance data into height data; acquiring the prospect height of a detecting point through an operation with a background model; generating a sequential height map; extracting a pedestrian height agglomerate in the sequential height map; selecting the geometric and shape characteristics of the height agglomerate, adopting a Gaussian process regression method and calculating the number of pedestrians in the pedestrian height agglomerate; using a sliding window with a dynamic size to act on the projection of the pedestrian height agglomerate along a time axis; positioning the pedestrian head area by calculating the maximum point of a mean value curve; after the pedestrian head is positioned, judging the pedestrian entering exiting directions by using a ballot method. By means of the top laser range finder for obliquely illuminating and scanning, the laser bidirectional pedestrian counting method based on Gaussian process regression can achieve rapid and accurate indoor and outdoor pedestrian counting and direction judging with no contact with pedestrians.

Description

technical field [0001] The invention relates to a laser two-way pedestrian counting method based on Gaussian process regression. Background technique [0002] With the development of social economy, the number of urban commercial real estate is increasing day by day, and the scale is gradually expanding. Pedestrian counting can provide important decision-making basis for operators of commercial real estate and urban public safety managers. It is a work with both commercial value and safety significance. At present, there are methods of counting pedestrians using contact gates in public places, and there are also methods of counting pedestrians with non-contact infrared binary laser or video. These counting methods have their own advantages in specific scenarios, but they all have shortcomings, and it is difficult to achieve the counting effect expected by users. [0003] In a specific scene, the pedestrian counting method based on a common monocular camera can achieve a be...

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): G06M15/00G01P13/04
Inventor 刘宁牛群
Owner SUN YAT SEN 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