Unlock instant, AI-driven research and patent intelligence for your innovation.

Commodity identification processing method, device, equipment, system and storage medium

A technology for a commodity and a camera device, applied in the field of image recognition, can solve problems such as low commodity detection efficiency, and achieve the effects of improving efficiency, avoiding misjudgment, and improving accuracy

Active Publication Date: 2020-10-09
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a processing method, device, equipment, system and storage medium for commodity identification to solve the defects of low commodity detection efficiency in the prior art

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 identification processing method, device, equipment, system and storage medium
  • Commodity identification processing method, device, equipment, system and storage medium
  • Commodity identification processing method, device, equipment, system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] This embodiment provides a method for processing commodity identification, which is used for commodity identification processing. The execution subject of this embodiment is a processing device for commodity identification (hereinafter referred to as the processing device), and the processing device may be set in a computer device, such as an AI chip.

[0040] Such as figure 1 As shown, it is a schematic flowchart of the processing method for product identification provided in this embodiment, the method includes:

[0041] Step 101, receiving the image information sent by the camera device and the distance signal sent by the distance sensor corresponding to the camera device.

[0042] Specifically, the camera device captures image information of commodities within its shooting range in real time and sends it to the processing device, either in real time or at regular intervals, and the image information may be image data information or video data information. The imag...

Embodiment 2

[0054] This embodiment provides a further supplementary description of the method provided in the first embodiment.

[0055] As an implementable manner, on the basis of the first embodiment above, optionally, step 102 specifically includes:

[0056] Identify the difference between the back frame and the front frame of the image information to judge whether there is a target object protruding in or out; and judge whether there is a target object protruding in or out according to the distance signal, wherein the back frame and the front frame are adjacent frames , or, the interval between the next frame and the previous frame is the preset number of frames.

[0057] If it is recognized according to the image information that the frame behind the target has a target object protruding from the frame before the target, then the frame before the target is determined to be the starting frame of the user's behavior of picking up the goods.

[0058] If it is determined according to th...

Embodiment 3

[0106] This embodiment provides a processing device for product identification, which is used to implement the method in the first embodiment above.

[0107] Such as Figure 4 As shown in , it is a schematic structural diagram of the processing device for commodity identification provided in this embodiment. The commodity identification processing device 30 includes a receiving module 31 , a determining module 32 and a processing module 33 .

[0108] Wherein, the receiving module 31 is used to receive the image information sent by the camera device and the distance signal sent by the distance sensor corresponding to the camera device; the determination module 32 is used to determine the start frame and end frame of the user's picking behavior according to the image information and the distance signal ; The processing module 33 is used to determine the product information taken by the user according to the start frame and end frame of the user's picking behavior.

[0109] Reg...

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 present application provides a processing method, device, equipment, system and storage medium for commodity identification, the method comprising: receiving image information sent by the camera device and a distance signal sent by a distance sensor corresponding to the camera device; according to the image information and the distance signal, Determine the start frame and end frame of the user's pick-up behavior; determine the product information picked up by the user according to the start frame and end frame of the user's pick-up behavior. By performing product identification on the start frame and end frame of the user's pick-up behavior, the product information picked up by the user is determined, and the efficiency of product identification is effectively improved. And combining the image information captured by the camera device and the distance signal detected by the distance sensor to jointly determine the start frame and end frame of the user's pick-up behavior can avoid misjudgment of the user's pick-up behavior and improve the accuracy of the user's pick-up behavior judgment.

Description

technical field [0001] The present application relates to the technical field of image recognition, and in particular to a processing method, device, equipment, system and storage medium for product recognition. Background technique [0002] With the rapid development of science and technology, the unmanned retail model has gradually entered people's lives. In the unmanned retail system, it is an important technical issue to correctly identify which products the user has taken from the shelf, and it plays an important role in the subsequent product management. [0003] In the prior art, images are usually collected by a camera, and a commodity recognition model is used to detect commodities in each frame of images in real time, and it is judged whether the commodities are taken away or put back through changes in the detection results. [0004] However, the existing commodity recognition method performs commodity detection on each frame, and the processing efficiency is low...

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): G06K9/00
CPCG06V40/20G06F2218/00G06N3/08G06V20/52G06N3/045G06N5/02G06F18/2111
Inventor 付鹏王奎澎胡跃祥周强范彦文寇浩锋何声一周仁义方阳华包英泽
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD