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

Pedestrian motion identification method, device and equipment

A motion and pedestrian technology, applied in the field of pedestrian motion recognition, can solve the problems of slow response speed in the recognition and tracking process, low accuracy rate of pedestrian motion recognition, and high training cost, so as to save training cost, save computing power, and reduce computing power. volume effect

Pending Publication Date: 2021-02-02
上海迈外迪网络科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] From the above two examples, it can be seen that the accuracy of the algorithm for identifying pedestrian movement in the prior art is low
[0007] At the same time, there are many other defects in the algorithm for recognizing pedestrian movement through machine learning training, such as high training cost (the training process requires a lot of computing power), and slow response speed in the recognition and tracking process.

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
  • Pedestrian motion identification method, device and equipment
  • Pedestrian motion identification method, device and equipment
  • Pedestrian motion identification method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] As described below, an embodiment of the present invention provides a method for identifying pedestrian movement.

[0067] refer to figure 1 The flow chart of the method for identifying pedestrian movement is shown as follows:

[0068] S101. Obtain an algorithm for identifying pedestrian movement.

[0069] After the data is collected by the thermopile array sensor, it is necessary to process the algorithm to identify pedestrian movement from the collected data. In this embodiment, an algorithm for identifying pedestrian movement from the collected thermopile array data is established in advance.

[0070] The difference from the prior art is that this embodiment abandons the machine learning scheme in the prior art, saves the training cost of machine learning, and uses a series of technical means to speed up the operation speed of the algorithm and improve the performance of the algorithm. Accuracy, while having better noise resistance and plasticity (using modular de...

Embodiment 2

[0117] As described below, an embodiment of the present invention provides a device for identifying pedestrian movement.

[0118] Devices that recognize pedestrian movement include:

[0119] a processor adapted to load and execute instructions of a software program;

[0120] A memory adapted to store a software program comprising instructions for performing the following steps:

[0121] obtain an algorithm for recognizing pedestrian movement;

[0122] Using the algorithm to identify pedestrian movement from the collected thermopile array data;

[0123] Wherein, the algorithm identifies pedestrian movement from the collected thermopile array data in the following ways, including:

[0124] Eliminate or partially eliminate the noise in each frame data packet of the thermopile array data, and obtain the frame data packet after preliminary processing;

[0125] Determining hotspots of people from the preliminarily processed frame data packets;

[0126] Determine the moving traj...

Embodiment 3

[0130] As described below, an embodiment of the present invention provides a device for recognizing pedestrian movement.

[0131] The difference from the prior art is that the device for identifying pedestrian movement uses the method for identifying pedestrian movement provided in the embodiment of the present invention to identify pedestrian movement from the collected thermopile array data. Therefore, the equipment that recognizes the movement of pedestrians can save the training cost of machine learning, save the computing power of the training process, and at the same time, the response speed during operation is faster.

[0132] Those of ordinary skill in the art can understand that in the various methods of the above-mentioned embodiments, all or part of the steps can be completed by hardware related to program instructions, and the program can be stored in a computer-readable storage medium, and the storage medium can include : ROM, RAM, disk or CD, etc.

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 pedestrian motion identification method, device and equipment, and the method comprises the steps: enabling an algorithm to recognize the pedestrian motion from collected thermopile array data through the following modes: eliminating or partially eliminating noise points in all frame data packets of the thermopile array data, and obtaining frame data packets after preliminary processing; determining a figure hotspot from the preliminarily processed frame data packet; respectively determining a moving track of each figure hotspot in the thermopile array data and tracking the moving track; and when disappearance of a certain figure hotspot from a subsequent frame data packet is found by tracking the moving track, analyzing the moving track of the figure hotspot andclassifying the figure hotspot. According to the invention, the training cost of machine learning is saved, the computing power of the training process is saved, and the response speed during operation is faster.

Description

technical field [0001] The present invention relates to the technical field of target detection, in particular to a method, device and equipment for identifying pedestrian movement. Background technique [0002] Passenger flow analysis refers to the analysis of information such as the number and identity of passenger flow in a venue. With the rise of digital operations, the demand for passenger flow analysis in offline shopping malls, stores, public transportation and other places is increasing. Passenger flow analysis equipment provides operators with accurate and professional passenger flow data, helping operators to analyze passenger flow with scientific basis. Feed back the analysis conclusions into daily operations and management, making their decisions more evidence-based and quantifiable. [0003] Passenger flow analysis equipment collects data through sensors, and processes the collected data to identify the behavior of people entering / leaving the predetermined are...

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
IPC IPC(8): G06K9/00G06K9/40G06K9/46G06K9/62G06N20/00
CPCG06N20/00G06V40/20G06V20/52G06V10/30G06V10/40G06F18/22G06F18/214
Inventor 姚生意刘经济朱文鲁张程
Owner 上海迈外迪网络科技有限公司
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com