Object positioning method and device and computer system

A positioning method and positioning device technology, applied in the field of image recognition, can solve the problems of invasion of customer privacy, high cost, inconvenient use, etc., and achieve the effect of ensuring efficiency

Pending Publication Date: 2020-05-19
SUNING CLOUD COMPUTING CO LTD
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, the anti-theft monitoring of goods in unmanned stores mostly relies on RFID radio frequency identification technology, and it is necessary to affix an anti-theft label to each product in advance, which is costly and inconvenient to use
Even if face recognition technology is applied to identify and confirm customers' behaviors such as entering and leaving the store, there is still a risk of violating customers' privacy by identifying customers' faces

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
  • Object positioning method and device and computer system
  • Object positioning method and device and computer system
  • Object positioning method and device and computer system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Take the use of the Yolov3 model to detect the images taken by the unmanned store and identify the location of the customer as an example, such as figure 1 As shown, the above method can be realized through the following steps:

[0053] The Yolov3 model is a general-purpose target detection model that can be used to process images and extract target objects in images, such as people and commodities.

[0054] However, this model can only be used to detect three-channel RGB color images, and cannot fuse depth images with color images, nor can it detect RGBD images obtained after fusion.

[0055] RGB is a commonly used color standard in the industry. A variety of colors can be obtained by changing the values ​​​​of the three color channels of red, green, and blue and superimposing them. This standard can almost include the perception of human vision. of all colors.

[0056] RGBD adds an Alpha channel based on the three channels of RGB, and adds additional information from ...

Embodiment 2

[0096] Corresponding to the above method, the present application provides a method for locating an object, such as image 3 As shown, the method includes:

[0097] 310. Receive a color image and a depth image corresponding to the color image;

[0098] 320. Perform image fusion on the color image and the depth image to obtain a target image, the target image is an RGBD image, the Alpha channel of the target image corresponds to the depth image, and the RGB channel corresponds to the color image;

[0099] Preferably, before performing image fusion on the color image and the depth image, the method further includes:

[0100] 321. Perform an image normalization operation on the depth image according to a preset method and preset parameters.

[0101] Preferably, before performing image fusion on the color image and the depth image, the method further includes:

[0102] 322. Perform image registration on the normalized depth image and the color image.

[0103] Preferably, the c...

Embodiment 3

[0119] Corresponding to the above method, the present application provides an object positioning device, such as Figure 4 As shown, the device includes:

[0120] A receiving module 410, configured to receive a color image and a depth image corresponding to the color image;

[0121] The image processing module 420 is configured to perform image fusion on the color image and the depth image to obtain a target image, the target image is an RGBD image, the Alpha channel of the target image corresponds to the depth image, and the RGB channel corresponds to the depth image. described color image;

[0122] The matching module 430 is configured to input the target image into a preset model for recognition, and locate the position of the target object in the target image. The input layer of the preset model includes RGB channels and Alpha channels.

[0123] Preferably, the image processing module 420 is also used to perform image registration on the color image and the depth image.

...

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 an object positioning method, an object positioning device, and a computer system. The object positioning method comprises the steps of: receiving a color image and a depth image corresponding to the color image; performing image fusion on the color image and the depth image to obtain a target image, wherein the target image is an RGBD image, an Alpha channel of the targetimage corresponds to the depth image, and an RGB channel corresponds to the color image; and inputting the target image into a preset model for identification, and positioning the position of a targetobject in the target image, wherein an input layer of the preset model comprises an RGB channel and an Alpha channel. Compared with the identification only based on the color image, the object positioning method and the object positioning device improve the target object positioning efficiency and accuracy rate, can realize tracking of the displacement route of the target object according to theposition of the target object, can track a shopping route of a customer when being applied to an unmanned store, guarantee the goods safety, can be further used for analyzing customer purchasing behaviors, and enhance customer purchasing experience.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to an object positioning method, device and computer system. Background technique [0002] With the development of Internet technology, unmanned stores have gradually become a boom in the new retail field. In the existing technology, most of the anti-theft monitoring of goods in unmanned stores relies on RFID radio frequency identification technology, and it is necessary to affix an anti-theft label for each commodity in advance, which is costly and inconvenient to use. Even if face recognition technology is applied to identify and confirm customers' behaviors such as entering and leaving stores, there is still a risk of infringing on customers' privacy by identifying customers' faces. Contents of the invention [0003] In order to solve the deficiencies of the prior art, the main purpose of the present invention is to provide a method for locating an object so as to realize the ...

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): G06T7/70G06T7/80G06T7/33
CPCG06T7/70G06T7/80G06T7/344G06T2207/10024G06T2207/10028G06T2207/20221G06T2207/20081
Inventor 刘水清杨现孙皓
Owner SUNING CLOUD COMPUTING CO LTD
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