Luggage re-identification model training method and luggage re-identification method

A model training and re-recognition technology, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problems of high cost of baggage tracking and recognition, troublesome implementation, low security, etc., and achieve strong portability. , Overcome the effects of high cost and high recognition accuracy

Pending Publication Date: 2021-03-23
广州丰石科技有限公司
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a luggage weight recognition model training and a luggage weight recognition method in order to

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
  • Luggage re-identification model training method and luggage re-identification method
  • Luggage re-identification model training method and luggage re-identification method
  • Luggage re-identification model training method and luggage re-identification method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0040] Example 1

[0041] Such as figure 1 As shown, a baggage re-identification model training and luggage reissue method, including the following steps:

[0042] S1: Get video monitoring data, extract video monitoring data using the target detection model YOLOV3;

[0043] It should be noted that the present invention can be applied to a scenario such as airport, high-speed rail station, and the like, to acquire video monitoring data from the above application scenario, and then extract the baggage image using the target detection model, the acquired baggage image includes the same Pieces of luggage in different perspectives, such as figure 2 The baggage image shown is identified.

[0044] S2: The baggage image is labeled to get the baggage image data set;

[0045] It should be noted that the baggage image can be unified after the baggage image is acquired after step S1, and then the luggage image is labeled to obtain a baggage image data set. In a specific embodiment, the labe...

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 luggage re-identification model training and luggage re-identification method, and the method comprises the following steps: S1, obtaining video monitoring data, and extracting a luggage image of the video monitoring data through a target detection model; S2, labeling the luggage image to obtain a luggage image data set; S3, dividing the luggage image data set into a training set and a verification set; S4, training a luggage re-identification model by using the training set, evaluating the luggage re-identification model by using the verification set, and screening out the luggage re-identification model with the optimal prediction performance; S5, obtaining similarity distribution between the luggage images by using the luggage re-identification model obtained in the step S4, and determining a discrimination threshold according to the similarity distribution; and S6, inputting any two luggage images into the luggage re-identification model to predict whetherthe two luggage images are from the same luggage or not. According to the invention, the defects of high cost and low security of a traditional luggage identification tracking scheme are overcome, the portability is strong, and the identification accuracy is high.

Description

technical field [0001] The present invention relates to the technical field of object re-identification in computer vision, and more specifically, to a luggage re-identification model training and a luggage re-identification method. Background technique [0002] Existing luggage tracking scheme generally uses RFID (radio frequency identification) technology to track luggage, and the scheme includes the following steps: 1. The RFID (radio frequency identification) card reader in each area reads the RFID (radio frequency identification) ) tag and send it to the data summarization unit, and the RFID (radio frequency identification) tag is attached to the luggage; 2. The data summarization unit in each location sums up the luggage information in each area and sends it to the data collection unit. Processing system; 3. The data processing system generates whereabouts information according to all the luggage information received, and sends the whereabouts information to the inform...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/52G06N3/045G06F18/241
Inventor 陈曦蓝志坚钟国海
Owner 广州丰石科技有限公司
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

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