Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Crowd counting method, system, computer readable storage medium and server

A crowd counting and crowd counting technology, applied in crowd counting methods, computer-readable storage media and servers, and system fields, can solve the problems of many network parameters, difficult training, high hardware costs, etc., to achieve improved computing performance, wide application range, imperceptible effect

Active Publication Date: 2021-12-17
WINNER TECH CO INC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are many complex network parameters, which not only have a certain difficulty in training, but also spend a lot of hardware cost in implementation, and it is often difficult to meet the application requirements in terms of real-time performance.
[0006] Therefore, how to provide a crowd counting method, system, computer-readable storage medium, and server to solve the problem that the existing technology cannot solve the problem of crowd counting in multiple scales and in multiple scenarios has become an urgent need for those skilled in the art to solve technical issues

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, system, computer readable storage medium and server
  • Crowd counting method, system, computer readable storage medium and server
  • Crowd counting method, system, computer readable storage medium and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] This embodiment provides a crowd counting method, including:

[0052] Perform training preprocessing on the original image set containing the crowd to form a preprocessed image set;

[0053] Combining multi-channel deformable convolution to build a convolutional neural network; the convolutional neural network is used to map the original image set containing the crowd into a heat map;

[0054] Train the built convolutional neural network to form another convolutional neural network;

[0055] Inputting the original image set into the another convolutional neural network to obtain a heat map corresponding to the original image set.

[0056] The crowd counting method provided by this embodiment will be described in detail below with reference to figures. The crowd counting method described in this embodiment is applied to such as figure 1 In the application scenario 1 shown. In this application scenario 1, RTSP video streams or frame screenshots are collected through v...

Embodiment 2

[0106] This embodiment provides a crowd counting system, including:

[0107] A preprocessing module, configured to perform training preprocessing on the original image set containing the crowd to form a preprocessing image set;

[0108] A building module is used to combine multi-channel deformable convolution to build a convolutional neural network; the convolutional neural network is used to map the original image set containing the crowd into a heat map;

[0109] The training module is used to train the built convolutional neural network to form another convolutional neural network;

[0110] A verification module, configured to input the original image set into the other convolutional neural network, so as to obtain a heat map corresponding to the original image set.

[0111] The crowd counting system provided by this embodiment will be described in detail below with reference to illustrations. It should be noted that it should be understood that the following division of ...

Embodiment 3

[0120] This embodiment provides a server, including: a processor, a memory, a transceiver, a communication interface or / and a system bus; the memory and the communication interface are connected to the processor and the transceiver through the system bus and complete mutual communication, and the memory is used for The computer program is stored, the communication interface is used to communicate with other devices, the processor and the transceiver are used to run the computer program, so that the server executes various steps of the crowd counting method described in the embodiment.

[0121] The system bus mentioned above may be a Peripheral Component Interconnect (PCI for short) bus or an Extended Industry Standard Architecture (EISA for short) bus or the like. The system bus can be divided into address bus, data bus, control bus and so on. The communication interface is used to realize the communication between the database access device and other devices (such as client, ...

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 present invention provides a crowd counting method, system, computer-readable storage medium, and server. The crowd counting method includes: training and preprocessing an original image set containing crowds to form a preprocessed image set; combining multi-channel deformable convolution , build a convolutional neural network; the convolutional neural network is used to map the original image set containing the crowd into a heat map; train the built convolutional neural network to form another convolutional neural network; The test atlas in the original image set is input into the another convolutional neural network to obtain a heat map corresponding to the original image set. The crowd counting method, system, computer-readable storage medium and server provided by the present invention can effectively solve crowd counting problems in various scales and in various scenarios.

Description

technical field [0001] The invention belongs to the field of intelligent monitoring and counting, and relates to a counting method and system, in particular to a crowd counting method, system, computer-readable storage medium and server. Background technique [0002] In various gatherings, traffic arteries and other public places, crowds often gather. At this time, the problem of crowd control is very important. In terms of safety, it is necessary to give early warning to the number of crowds for reasonable scheduling. In business In fact, crowd gathering places often mean the mining of commercial value points. However, crowds are fluid and diverse, so how to use surveillance images, videos, etc. to obtain the number of current crowds in these public places is very meaningful. [0003] At present, there are many intelligent monitoring solutions for calculating the current number of people, and their technical directions mainly include the following: [0004] 1) Target dete...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V20/53
Inventor 袁德胜游浩泉张欣欣王作辉姚磊杨进参王海涛
Owner WINNER TECH CO INC
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
Eureka Blog
Learn More
PatSnap group products