Pedestrian flow monitoring method and device, storage medium and equipment

A monitoring device and a technology for people flow, applied in the information field, can solve the problem of inaccurate counting of people flow, and achieve the effect of good robustness, accurate and rapid statistics

Active Publication Date: 2019-04-30
CHONGQING ZHONGKE YUNCONG TECH CO LTD
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a method, device, storage medium and equipment for monitoring the flow of people, which is used to solve the problem of crowd detection and density analysis of the flow of people in the prior art in complex backgrounds. The problem of inaccurate counting of people flow for dense crowds under light and shadow

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
  • Pedestrian flow monitoring method and device, storage medium and equipment
  • Pedestrian flow monitoring method and device, storage medium and equipment
  • Pedestrian flow monitoring method and device, storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] see figure 1 , showing a flow chart of a method for monitoring human flow provided by the present invention, detailed as follows:

[0039] Step S101, acquiring the target image of the pedestrian to be monitored in the video image;

[0040] Wherein, the source of the acquired video images may be cameras installed in various places, such as image information of corresponding areas collected by cameras installed in shopping malls, stations and other public places, or some video images.

[0041] Step S102, using a deep residual network to extract the features of the target image;

[0042] Wherein, based on each residual block sequentially connected in the deep residual network, the feature extraction is performed on the target image, and the head and shoulders of a single person, the box of the crowd area, the confidence level and the density map information of the target image are obtained according to the network structure; Any residual block includes an identity map an...

Embodiment 2

[0054] see figure 2 , which is a flow chart of training a crowd detection model for a crowd monitoring method provided by the present invention, and is described in detail as follows:

[0055] Step S201, mark the crowd area of ​​multiple sample images, mark the head and shoulders of the person when the sample image is a single person image, and mark the group frame when the sample image is a crowd image, and according to each of the sample images Build a crowd detection model in the marked area;

[0056] Step S202, train the crowd detection model through a plurality of training samples, and generate the crowd detection model capable of classifying and locating regions in the target image according to crowd characteristics.

[0057] Specifically, when training the model, it is necessary to prepare the data labels to be detected, that is, sample data (including sample images of various densities), for example, labeling the input sample images according to the clear human head ...

Embodiment 3

[0068] see image 3 , which is a structural block diagram of a human flow monitoring device provided by the present invention, and is described in detail as follows:

[0069] Image acquisition module 31, for acquiring the target image of the pedestrian to be monitored in the video image;

[0070] The feature extraction module 32 utilizes the depth residual network to extract the features in the target image;

[0071] Wherein, based on each residual block sequentially connected in the deep residual network, the feature extraction of the target image is performed, any residual block includes an identity map and at least two convolutional layers, and any residual The identity map of the block is directed from the input end of any residual block to the output end of any residual block.

[0072] The crowd detection module 33 uses the crowd detection model to classify and locate the unmanned area, single person area and crowd area in the target image;

[0073] Wherein, labeling t...

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 provides a visitor flow monitoring method and device, a storage medium and equipment, and is applicable to the technical field of image processing. The method comprises the steps of obtaining a target image of a to-be-monitored pedestrian in a video image; extracting graphic features by using a model trained based on a deep residual network; classifying and positioning an unmanned area, a single person area and a crowd area in the target image by utilizing a crowd detection model; adopting a density regression model to obtain a head distribution density map of the crowd detectionclassification as a crowd area, and calculating the number of people in the crowd area according to the head distribution density map; and counting the number of people in the single person area andthe number of people in the crowd area in the crowd detection classification, and calculating the total number of people in the target image. When people flow is monitored, the number of people in thevideo image is counted based on the deep residual network in combination with crowd detection and density analysis, the number of people in the image can be counted accurately and rapidly, and the method has good robustness.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a method, device, storage medium and equipment for monitoring people flow. Background technique [0002] In recent years, crowd counting technology has been a research hotspot that has attracted much attention in the industry. It has also been gradually applied to major shopping malls, chain stores, supermarkets, hotels, airports, subways, scenic spots, etc. The people flow data generated in these scenarios can provide information for many fields. Very valuable information. For major shopping mall chain stores and supermarkets, facing the current hot online e-commerce systems, such as Jingdong, Taobao, Tmall, Amazon, etc., the offline sales market has been crowded, and scientific management is obviously to improve their own effective means of competitiveness. The flow of people data in different time periods and regions in the shopping mall plays an important role ...

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): G06K9/00G06K9/62
CPCG06V20/53G06F18/214G06F18/241
Inventor 周曦姚志强周翔李夏凤李继伟张庭
Owner CHONGQING ZHONGKE YUNCONG TECH CO LTD
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