Shop people flow identification and analysis method and system

A store and people flow technology, applied in the field of store people flow identification and analysis, to achieve the effect of simple and feasible method and high accuracy

Pending Publication Date: 2019-06-11
上海宝尊电子商务有限公司
View PDF7 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, this patent document uses the image data in the monitoring system to count the flow of people, which is still a primary application. There is no deep processing of the store monitoring data based on computer vision and image recognition technology to identify and analyze the identity and posture of the flow of people to better A method and system for guiding store operations, supervising store staff and discovering abnormal behaviors of people and objects in the store in a timely manner

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
  • Shop people flow identification and analysis method and system
  • Shop people flow identification and analysis method and system
  • Shop people flow identification and analysis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Embodiment 1 The present invention relates to a method for identifying and analyzing shop flow of people

[0080] This embodiment provides a method for identifying and analyzing the flow of people in a shop, see figure 1 Shown is a flow chart of a method for identifying and analyzing people flow in a store according to the present invention. The method for identifying and analyzing people flow in a store includes the following steps:

[0081] S1. Install the camera at a fixed position with a wide view in the store, and then connect it to the server through a network cable.

[0082] S2. After the camera is powered on, the video frames extracted from the video stream are read on the server, and part or all of the frames are read in a preset manner. The minimum frame rate for extraction is one frame per second.

[0083] S3. Use each frame of the extracted picture as an input of the video image processing and identification module.

[0084] S4. The video image processing...

Embodiment 2

[0111] Embodiment 2 Another method for identification and analysis of store flow of people in the present invention

[0112] This embodiment provides a method for identifying and analyzing people flow in a store. The method for identifying and analyzing people flow in a store includes the following steps:

[0113] S1. Install the camera at a fixed position with a wide view in the store, and then connect it to the server through a network cable.

[0114] Further, the camera is a single-channel surveillance camera with a definition of 1080P 2 million pixels, a frame rate of 25FPS, a lens size of 8mm, a monitoring angle of 38°, and a monitoring distance of 20-30 meters.

[0115] S2. After the camera is powered on, the video frames extracted from the video stream are read on the server, and part or all of the frames are read in a preset manner. The minimum frame rate for extraction is one frame per second.

[0116] S3. Use each frame of the extracted picture as an input of the v...

Embodiment 3

[0143] Embodiment 3 The present invention is a system for identifying and analyzing people flow in a store

[0144] This embodiment provides a system for identifying and analyzing people flow in a shop, see figure 2 Shown is a structural block diagram of a system for identifying and analyzing people flow in a store according to the present invention, the system for identifying and analyzing people flow in a store includes:

[0145] 1. Information collection equipment in the store: including server 1, camera 2 and display screen 3. The camera 2 is connected to a local or remote server 1 through a communication carrier such as Wi-Fi, USB data cable or network cable, and transmits the collected data back to the server 1 for storage in real time, and the server 1 reads the video stream and extracts the video frame , to read part or all of the frames according to the preset method. The display screen 3 is used to intuitively call and view the video images collected by the camera...

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 relates to a shop people flow identification and analysis method and system. The method comprises the following steps of: enabling a server to read video streams, extracting video frames, enabling a video image processing identification module to identify a rectangular frame which tightly surrounds the contour of an identifiable object and the probability that the identifiable objectmay be a set target according to a deep neural network target identification model; recognizing key points corresponding to human skeleton points according to the deep neural network key point recognition model; calculating attributes of postures, tracks and motion status of the target person in the frame at the moment and on a certain time axis based on the relative positions of the key points and the interval time sequence relation between frames, and finally, counting and displaying the passenger flow groups capable of being identified within a certain time length to a user. The system includes components that implement the method. According to the invention, a comprehensive and three-dimensional video monitoring data and store operation management combined system is constructed, and objective, accurate and valuable in-store personnel and passenger flow monitoring analysis can be provided for owners.

Description

technical field [0001] The invention relates to the technical fields of computer vision and image recognition, and in particular to a method and system for identifying and analyzing people flow in a shop. Background technique [0002] Image recognition technology is the specific application of pattern recognition in the field of images. It is a technology that processes, analyzes and classifies images through computers to identify targets and objects in different patterns. Image recognition technology analyzes the observed images, distinguishes objects and judges categories, and realizes image recognition, that is, uses modern information processing and integration methods and computing programs to simulate and complete the process of human cognition and understanding. In a narrow sense, image recognition is a discipline based on the main features of images and using image processing technology to recognize images [1]. [0003] Image recognition technology has been widely u...

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): G06K9/00G06K9/62G06Q10/06G06Q10/10
Inventor 林博胡玉琛
Owner 上海宝尊电子商务有限公司
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