Escalator passenger flow volume statistical method based on video monitoring

An escalator and video surveillance technology, applied in computing, computer parts, image data processing, etc., can solve problems such as interference, information waste, and unutilized rich-color information, and achieve the effect of improving the ability to resist light interference

Active Publication Date: 2020-07-03
SOUTH CHINA UNIV OF TECH +1
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, this is also its shortcoming. When the background is complex or the texture of the object is rich, the noise in the back projection image will be very large, which will directly interfere with the judgment of the object position by the mean shift algorithm.
The Kalman filter based on position information is used for tracking. There is a big problem, that is, only the passenger position information is used in the tracking process, and the color information of each passenger is very different, and the rich color information is not used in the tracking. , which is a waste of information

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
  • Escalator passenger flow volume statistical method based on video monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with specific examples.

[0039] like figure 1 As shown, the escalator passenger flow statistics method based on video surveillance provided by the present embodiment, its specific circumstances are as follows:

[0040] 1) Use the open source labeling tool labelImg to label the head images of passengers on the floor plate collected by the camera, and build a data set of passenger heads in the escalator. The label information is (x, y, w, h, c), which represent the heads of passengers in the image In the relative abscissa, relative ordinate, relative width, relative height and category, since there is only one category, c is uniformly marked as 0, and then according to the ratio of 7:3, the data set is divided into training set, verification set, training set The head images of the set are used for YOLOv3 training, while the verification set images are used to select the best trained YOLOv3 model.

[...

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 escalator passenger flow volume statistical method based on video monitoring. The escalator passenger flow volume statistical method comprises the steps that (1) YOLOv3 is used for conducting head detection on passengers who photograph the escalator at a high angle; 2) training a YOLOv3 network; 3) judging whether the current frame number is a key frame or not, if so, executing the steps 4)-9), otherwise, executing the step 10), and finally executing the steps 11) and 12); 4) detecting the head of the passenger by using YOLOv3; 5) if t is equal to 0, initializing a particle filtering result by using a detection result, otherwise, executing particle filtering; 6) solving a matrix D; 7) performing Hungary matching on the D pair; 8) removing the target leaving the monitoring range; 9) newly adding a target entering the monitoring range; according to the method, the illumination interference resistance is high, the performance is excellent in different illumination scenes, meanwhile, different detection periods can be set according to the conditions of actual equipment, and the accurate passenger flow statistics effect can be achieved on equipment with different properties.

Description

technical field [0001] The invention relates to the technical field of video surveillance and computer vision of an escalator, in particular to a video surveillance-based passenger flow statistics method for an escalator. Background technique [0002] Escalators are usually installed in important places with dense traffic in cities to bring convenience to citizens. Finally, the entrance and exit of the escalator is the "fortress" where the flow of people passes. The statistics of the flow of people at the entrance and exit of the escalator can be used to analyze the passenger flow, so that shopping malls, airports, etc. can make correct decisions in management and decision-making. Therefore, statistics Passenger flow of escalators can assist business analysis and thus bring commercial value. [0003] Traditional passenger flow statistics methods include: artificial statistics, infrared induction, gravity induction, etc. Manual statistical methods are prone to counting erro...

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 & AuthorityApplications(China)
IPC IPC(8): G06T7/277G06T7/246G06T7/223G06K9/00G06K9/62
CPCG06T7/277G06T7/223G06T7/248G06T2207/10016G06T2207/20081G06T2207/20076G06T2207/30196G06T2207/30242G06T2207/30232G06V20/53G06V10/758G06F18/22G06F18/214
Inventor杜启亮黄理广田联房
OwnerSOUTH CHINA UNIV OF TECH