Commodity shelf vacancy identification early warning method and system based on visual algorithm

A commodity and shelf technology, which is applied in the field of commodity shelf vacancy recognition and early warning based on visual algorithms, can solve the problems of untimely counting by shop assistants and low efficiency, and achieve the effect of intelligent patrol inspection

Pending Publication Date: 2022-08-05
上海悠络客电子科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Usually, shopping places hire clerks to check the shelves frequently, arrange and report them, and replenish goods. This may cause problems that the clerks do not count in time, which leads to inefficiency, and requires frequent inspections by employees next to the shelves.

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
  • Commodity shelf vacancy identification early warning method and system based on visual algorithm
  • Commodity shelf vacancy identification early warning method and system based on visual algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make it easy to understand the technical means, creative features, achieved goals and effects of the present invention, the present invention is described in detail below with reference to the embodiments and the accompanying drawings.

[0031]

[0032] refer to figure 1 , the visual algorithm-based early warning method for identifying the vacancy of commodity shelves provided by this embodiment is used to identify and warn the vacant areas of commodity shelves; A commodity label, and the commodity label box of each commodity label has commodity identification characters of the corresponding commodity. In this embodiment, the commodity identification characters are commodity names. The visual algorithm-based early warning method for vacancy recognition of commodity shelves specifically includes the following steps S1 to S8.

[0033] Step S1, extracting multiple single-frame images from at least one piece of surveillance video under the collected target sc...

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 provides a commodity shelf vacancy identification early warning method and system based on a visual algorithm. The identification early warning method comprises the following steps: extracting and selecting a plurality of training images; performing manual labeling on each training image to obtain corresponding labeling vacant area data, labeling commodity label frame data and labeling commodity identification character data; a vacant area detection model, a commodity label box detection model and a label character recognition model are constructed and trained; obtaining current commodity label box data, current commodity identification characters and current vacant area data corresponding to the current image through the trained commodity label box detection model, label character identification model and vacant area detection model, and calculating to obtain a current vacant area proportion in an area in which the corresponding commodity is stored; judging whether the current vacant area proportion is greater than a preset vacant area proportion or not; and when the judgment result is yes, sending early warning information containing the proportion of the current vacant area and the corresponding commodity identification characters.

Description

technical field [0001] The invention belongs to the technical field of intelligent commodity management, and in particular relates to a visual algorithm-based method and system for early warning of commodity shelf vacancy identification. Background technique [0002] In daily life, some shopping places such as stores and supermarkets, due to the large number of shoppers and the scattered shopping, can accurately and timely find the vacant goods and remind the staff to replenish the goods in time, which can not only better meet the needs of customers, but also It can boost the profit of the supermarket. [0003] Usually, shopping places employ store clerks to frequently count the shelves, organize and report them, and then replenish the goods. This may cause problems such as inefficiency caused by the delay of the clerk in the inventory, and frequent inspections by employees beside the shelves. SUMMARY OF THE INVENTION [0004] The present invention is made to solve the ab...

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): G06V20/52G06V20/62G06V30/19G06V20/40G06V10/82G06N3/04G06N3/08
CPCG06V20/52G06V20/40G06V20/62G06V30/19G06N3/08G06V10/82G06N3/045
Inventor 张祥祥沈修平
Owner 上海悠络客电子科技股份有限公司
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