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

Crowd crowding detection method, device and system

A detection method and technology of crowding degree, applied in the field of image recognition, which can solve the problems that the image cannot cover all areas, the hardware configuration is high, and the recognition speed of large areas is slow.

Active Publication Date: 2021-05-11
重庆交通开投科技发展有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For application scenarios with relatively large areas, the images collected by the camera cannot cover all areas, resulting in inaccurate detection results of crowd crowding, and the existing crowd crowding detection methods determine the number of heads by processing and analyzing video data , and then get the congestion degree of the current area, which leads to the slow recognition speed and low recognition accuracy of this method for the congestion degree of large areas, and the required hardware configuration is high

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 crowding detection method, device and system
  • Crowd crowding detection method, device and system
  • Crowd crowding detection method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] An embodiment of the present invention provides a crowd crowd detection method, which can be applied in various application scenarios. see figure 1 As shown, the method includes the following steps:

[0065] S101: Acquire a plurality of first images of a region to be detected; the plurality of first images include: a plurality of images captured by a plurality of photographing devices installed in the region to be detected.

[0066] In the embodiment of the present invention, the area to be detected may be an area under different application scenarios, wherein the application scenarios include but are not limited to: bus compartments, rail train compartments, ship cabins, various waiting rooms, bus stations, ticket windows, and A room or floor with obvious landmarks such as floor tile lines. Before performing congestion recognition, first obtain images in a certain application scene to be detected. Specifically, a plurality of shooting devices installed at different a...

Embodiment 2

[0114] An embodiment of the present invention provides a crowd crowd detection device, see Figure 7 As shown, the device includes: an image acquisition module 71 , an area division module 72 , an image processing module 73 , a feature extraction module 74 , a congestion degree recognition module 75 , and a congestion degree calculation module 76 .

[0115] Wherein, the image acquisition module 71 is used to obtain a plurality of first images of the region to be detected; the plurality of first images include: a plurality of images collected at the same time point by a plurality of cameras installed in the region to be detected; the region division module 72, for dividing the area to be detected into a plurality of target areas by taking the markers in the area to be detected as the dividing point; the image processing module 73 is used for performing overlapping parts in the plurality of first images according to the plurality of target areas Perform processing to obtain a pl...

Embodiment 3

[0118] An embodiment of the present invention provides a crowd crowd detection system, which can be applied in various application scenarios. For example: buses, places where crowds gather, such as tracks, trains, waiting stations, ticketing or shopping locations. see Figure 8 As shown, the system includes: a background server 81, a terminal device 82, and a crowd congestion detection device 83 as described in the second aspect.

[0119] Wherein, the background server 81, the terminal equipment 82 and the crowd congestion detection device 83 are connected in pairs; terminal device 82 .

[0120] The above-mentioned background server 81 can be a monitoring center in different application industries, and the above-mentioned terminal equipment 82 can be an information publishing platform, a display, and a hand-held terminal of relevant staff in various industries. Specifically, the above-mentioned crowd congestion detection device 83 is applied to Different related application...

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 crowd crowd detection method, device and system, which relate to the technical field of image recognition. The method includes: acquiring a plurality of first images of an area to be detected; The area covered by the first image is divided into multiple target areas; according to the multiple target areas, the overlapping parts in the multiple first images are processed to obtain multiple images to be recognized; the first image in each image to be recognized is extracted Crowd crowding features; each first crowd crowding feature is input into a pre-trained crowding degree detection classifier to obtain the crowding degree classification results of multiple images to be identified; according to the crowding degree classification results of multiple images to be identified , calculate the congestion degree of the area to be detected. The method can realize fast and accurate congestion degree detection, and solve the problems of slow recognition speed of congestion degree, low recognition accuracy rate and high required hardware configuration in the prior art.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a crowd crowd detection method, device and system. Background technique [0002] At present, the mainstream crowd crowding algorithm generally adopts the pattern recognition method of counting heads, first removes the background of the flow of people, and then distinguishes the number of heads in the remaining images according to the shape of the heads of the people, because the images in the video are dynamic. Continuous change, so a more accurate number of personnel can be obtained after a series of processing. This method has relatively high requirements on the accuracy of video equipment, and because it needs to use more complex algorithms to process video streams, the amount of background calculations required by the algorithms is relatively large, so special hardware is generally required to obtain more accurate head processing at a faster speed result. [0003]...

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): G06K9/00G06K9/34G06K9/62
CPCG06V40/10G06V20/53G06V10/267G06F18/241
Inventor 邓伟
Owner 重庆交通开投科技发展有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com