Hybrid package detection and identification method, device and system based on cloud platform

A recognition method and a recognition device technology, which are applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of difficult to accurately identify the shape of the package, real-time positioning of the package, etc., and achieve the requirements of convenient control and storage, and reduce configuration , cost reduction effect

Inactive Publication Date: 2019-08-23
SF TECH
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, because the linear model algorithm is too simple, it is difficult to accurately iden

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
  • Hybrid package detection and identification method, device and system based on cloud platform
  • Hybrid package detection and identification method, device and system based on cloud platform
  • Hybrid package detection and identification method, device and system based on cloud platform

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0073] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for ease of description, only parts related to the invention are shown in the drawings.

[0074] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0075] As mentioned in the background art, when the volume of packages is large, the linear model used in the existing package detection and recognition cannot accurately detect the shape of the package and accurately locate the location of the package in real time. Based on this, the present appl...

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 hybrid package detection and identification method, device and system based on a cloud platform. The method comprises the steps of collecting an image or an image sequence; extracting feature information from the collected image or image sequence; judging whether to update the detection and identification model: if yes, sending a request to the cloud platform, downloadingan algorithm parameter packet of the detection and identification model, and updating the detection and identification model; and if not, inputting the feature information into a detection and recognition model for recognition, and obtaining a detection and recognition result and outputting the detection and recognition result. The dynamic updating of the package data set, the dynamic updating oftraining algorithm model parameters and the dynamic updating of the detection and identification model are realized. Deep learning training is carried out by utilizing the cloud platform, so that therequirement on the configuration of the camera/camera combination end processor is reduced, and the execution efficiency of the whole system is improved. In addition, the cloud platform can carry outdetection and recognition model training, multiple devices can share one detection and recognition algorithm model trained by the cloud platform, the cost is reduced, and the execution efficiency isimproved.

Description

technical field [0001] The invention relates to the field of logistics technology, in particular to a method, device and system for detecting and identifying mixed packages based on a cloud platform. Background technique [0002] In recent years, the upsurge of online shopping has become stronger and stronger, the transaction scale of China's e-commerce market has become larger and larger, and consumers have higher and higher requirements for logistics speed and logistics quality. In the field of logistics, the detection and identification of express parcels is a very important technical problem, which plays a pivotal role in express sorting. [0003] In current application scenarios, traditional linear model algorithms are generally used. Linear models use a simple formula to find the line of best fit through a set of data points, and with known variable equations, you can find the variable you want to predict. [0004] However, linear models have a tendency to overfit, i...

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): G06K9/62
CPCG06F18/24G06F18/214
Inventor 陈冬梅张东文
Owner SF TECH
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