A Passenger Flow Statistics Method Based on Head Detection

A statistical method and head detection technology, applied in the field of passenger flow statistics, can solve problems such as cost constraints and development, and achieve the effect of fast detection and improved detection rate.

Active Publication Date: 2021-04-06
湖州宇泛智能科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The technology is more accurate, but the high cost limits the development of this method

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
  • A Passenger Flow Statistics Method Based on Head Detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with accompanying drawing.

[0035] Such as figure 1 As shown, the passenger flow counting method based on head detection of the present invention comprises the following steps:

[0036] 1. Based on the One-Stage target detection algorithm, combined with the Tiny-yolo network structure and the SSH context module in SSH (SingleStage Headless Face Detector) to detect the input initial frame picture, and obtain one or more human head frame coordinates; Create a path for each head frame to save the position information of the center point of the head frame in subsequent frames, and assign an id number to each path;

[0037] 2. Input the current frame picture for head detection to get the head frame coordinates of the current frame;

[0038] 3. Take the oks distance as the measurement method and the Euclidean distance as the supplementary measurement method, and use the coordinates of the center point of ...

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 discloses a passenger flow statistics method based on header detection, comprising: step 1. A target detection algorithm based on One-Stage, combining the network structure of Tiny-yolo and the SSH context module in SSH to input initial frame pictures Perform detection to obtain one or more head frame coordinates; create a path for each head frame to save the position information of the center point of the head frame in subsequent frames, and assign an id number to each path; step 2. Enter the current Perform head detection on the frame picture to obtain the coordinates of the head frame of the current frame; Step 3. Use the oks distance as a metric, use the Euclidean distance as a supplementary metric, and use the coordinates of the center point of the head frame to calculate all currently surviving paths and the current frame detected The oks distance matrix and Euclidean distance matrix of all head frames; Step 4. Associate all paths that survive with the head frame detected by the current frame; Step 5. Statistics of inbound and outbound passenger flow.

Description

technical field [0001] The invention belongs to the field of passenger flow statistics, in particular to a passenger flow statistics method based on head detection. Background technique [0002] At present, domestic and foreign passenger flow statistics techniques mainly include the following four types: [0003] Infrared passenger flow statistics: According to the passage of the human body to block the infrared rays to count the passenger flow, it is easy to use, the data transmission is small, the cost is low, the installation is convenient, and the light requirements are not high. However, this method is prone to missing statistics when many people pass by at the same time for a relatively wide doorway. [0004] Video customer flow statistics: mainly based on head counting, which has high accuracy. It can also track consumers' movement trajectories in the store based on image analysis. At the same time, it can be combined with the face recognition system for CRM manageme...

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): G06K9/00G06K9/62G06T7/246
CPCG06T7/246G06T2207/10016G06T2207/30196G06T2207/30241G06T2207/30242G06V20/53G06V2201/07G06F18/22
Inventor 赵拯李翠赵五岳
Owner 湖州宇泛智能科技有限公司
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