Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Self-adaptive pedestrian street-crossing signal calculating method based on video

An adaptive computing and pedestrian crossing technology, applied in computing, computer components, instruments, etc., can solve the problems of increased motor vehicle delays, pedestrian safety hazards, and fixed time for pedestrians to cross the street.

Inactive Publication Date: 2017-01-18
JILIN UNIV
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to overcome the problems in the prior art that the time of the green light for pedestrian crossing is fixed, which causes the delay of motor vehicles to increase, and at the same time brings hidden dangers to the safety of pedestrians, and provides a video-based pedestrian crossing signal self-adaptive calculation method

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
  • Self-adaptive pedestrian street-crossing signal calculating method based on video
  • Self-adaptive pedestrian street-crossing signal calculating method based on video
  • Self-adaptive pedestrian street-crossing signal calculating method based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0471] In this embodiment, a pedestrian crossing video at the East Gate of the Nanling Campus of Jilin University is selected, and a section of traffic video of an urban road in Changchun is selected, combined with figure 1 The described method process, using the method described in the present invention, includes installation of hardware equipment, background initialization, background update, shadow removal, feature selection and extraction, pedestrian number detection in the pedestrian waiting area, pedestrian crossing time detection, and pedestrian crossing time calculation. In the experiment, the detection accuracy of the number of pedestrians in the pedestrian waiting area was compared for example Figure 16 Shown. The detection rate of pedestrian waiting area reaches 90%, which can provide a reliable basis for the calculation of pedestrian crossing time.

[0472] 1. Install hardware equipment

[0473] Refer to figure 2 , At the east gate of the Nanling campus of Jilin Univ...

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 self-adaptive pedestrian street-crossing signal calculating method based on a video, and overcomes the problems that constant green light time, in which pedestrians cross the street, at present increases delay of motor vehicles and causes hidden troubles in pedestrian safety. The method comprises the steps that 1) hardware equipment is installed; 2) the background is initialized; 3) the background is updated by background difference, threshold calculation and background image update; 4) shadows are rejected by estimating the luminance difference, estimating the chroma difference and estimating a local position; 5) features are selected and extracted by counting the amount of foreground pixel points, determining a feature selecting threshold, selecting features and extracting features; 6) the amount of pedestrians in a pedestrian waiting area is detected by constructing a feature sample library, self-crossing verification of the sample library, establishing a pedestrian quantity detection model, and detecting the pedestrian amount via a video sequence; 7) street-crossing time of the pedestrians is detected; and 8) the street-crossing time of the pedestrians is calculated by constructing a self-learning sample library, establishing a street-crossing time model and calculating the street-crossing time.

Description

Technical field [0001] The present invention relates to a control method for urban traffic management. More specifically, the present invention relates to a video-based adaptive calculation method for pedestrian crossing signals. Background technique [0002] At present, the domestic pedestrian crossing signal setting is mainly based on the tolerable waiting time of pedestrian crossing on the unsignaled road section, and the pedestrian crossing signal control is carried out in a fixed period. Inductive control is mainly used abroad. Inductive control uses detection of the gap between motor vehicles to set pedestrian crossing time. These existing methods are all based on the premise of reducing motor vehicle delays. When the number of pedestrians is too large or too few, the time for pedestrians to cross the green light is insufficient or wasted, which brings hidden dangers to pedestrian safety. The manual button-type crossing signal control sets the pedestrian crossing time acco...

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): G06K9/00G06K9/62G08G1/01
CPCG08G1/01G06V20/53G06F18/214
Inventor 李志慧曲昭伟宋现敏陈永恒陶鹏飞魏巍李燕飞关可汗马佳磊胡永利夏英集
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products