Unlock instant, AI-driven research and patent intelligence for your innovation.

Crowd counting method and system based on bimodal network

A crowd counting and dual-modal technology, applied in the field of computer vision, can solve problems such as deviation and difficult detection of crowds, and achieve the effects of reduced calculation, high resolution, and improved calculation efficiency

Pending Publication Date: 2021-07-30
SHANDONG NORMAL UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method has excellent performance in bright scenes with sufficient light, but most of them only use limited RGB image information, especially in low-light scenes, it is difficult to directly detect crowds from RGB images, resulting in estimation The results have a large deviation from the real situation

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
  • Crowd counting method and system based on bimodal network
  • Crowd counting method and system based on bimodal network
  • Crowd counting method and system based on bimodal network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] like figure 1 As shown, this embodiment provides a method for crowd counting based on a dual-modal network. This embodiment uses this method as an example to illustrate the application of the server. It can be understood that this method can also be applied to terminals, and can also be applied to It includes terminals, servers and systems, and is realized through the interaction between terminals and servers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or it can provide cloud services, cloud database, cloud computing, cloud function, cloud storage, network server, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security service CDN, and big data and artificial intelligence platforms. The terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart ...

Embodiment 2

[0057] This embodiment provides a crowd counting system based on a bimodal network.

[0058] A bimodal network-based crowd counting system comprising:

[0059] An image acquisition unit configured to: acquire an image data set of the crowd to be tested, and perform preprocessing;

[0060] A crowd counting unit configured to: input the preprocessed crowd image data set into a pre-trained crowd counting network, generate a density map and count the number of people;

[0061] Wherein, the crowd counting network includes three parallel branches in the vertical direction and three stages in the horizontal direction, and the three parallel branches include: two specific modality branches and a shared modality branch; the three stages include : front-end network, middle-end network and back-end network; the front-end network extracts the specific modal features extracted by two specific modal branches, and obtains the basic features of the two modalities, the basic features of the t...

Embodiment 3

[0064] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps in the method for crowd counting based on a dual-mode network as described in the first embodiment above are implemented.

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 belongs to the field of computer vision, and provides a crowd counting method and system based on a bimodal network. The method comprises the steps: acquiring and preprocessing a to-be-detected crowd image data set; inputting the preprocessed crowd image data set into a pre-trained crowd counting network, generating a density map and calculating the number of people, wherein the crowd counting network comprises three parallel branches in the vertical direction and three stages in the horizontal direction, and the three parallel branches comprise two specific modal branches and a shared modal branch, the three stages comprise a front-end network, a middle-end network and a rear-end network, the front-end network extracts specific modal features extracted by two specific modal branches to obtain basic features of two modals, the basic features of the two modals and features input by the shared modal hierarchically aggregate specific modal feature information in the middle-end network, and the rear-end network receives information output by the middle-end network to generate a density map.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a crowd counting method and system based on a dual-mode network. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Crowd counting plays an important role in the field of public security. Stampede incidents have occurred frequently in recent years. If the image data in the video can be used to accurately estimate the number and density distribution of the current scene, relevant departments will take corresponding measures and flow control , then the occurrence of similar incidents can be greatly reduced. [0004] Most of the early crowd counting methods are based on detection and regression methods. The detection-based method can accurately estimate the number of people in a sparse crowd scene, but the effect is not good in a dense cr...

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): G06T7/00G06K9/00G06K9/62G06N3/04
CPCG06T7/0002G06N3/04G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/30242G06V20/53G06F18/214
Inventor 吕蕾韩润庞辰吕晨
Owner SHANDONG NORMAL UNIV