KR20230053271A - An atypical product recognition system using vision and distance measurement - Google Patents

Abstract

The present invention relates to an unstructured product recognition system using vision recognition and distance measurement based on artificial Intelligence (AI) learning. The vision recognition is performed based on artificial intelligence data learning, and the artificial intelligence data learning is performed at various angles by dividing various unstructured products into several frames. A product recognition camera for vision recognition uses a depth camera, and is characterized by measuring a height value of the product, obtaining object information, and checking overlap through the height value.

Description

An atypical product recognition system using vision and distance measurement

The present invention relates to an atypical product recognition system using vision recognition and distance measurement. More specifically, it relates to an atypical product recognition system using vision recognition and distance measurement based on artificial intelligence (AI) learning.

Unmanned stores with low labor costs are emerging in various industries, Amazon Go, which uses sensors to pay for goods, Wal-Mart, which uses an AI robot for checking inventory called Bossa Nova, and Alibaba, the largest online shopping mall in China. A typical example is Hema, which uses Alipay linked with face recognition.

A method of obtaining information from the human body and operating an unmanned store has been researched and developed. In this regard, prior art, Korea Patent Publication No. 2019-0008075 (published on January 23, 2019), personal information from a part of the user's body a configuration for acquiring personal information, transmitting the personal information to a first server, and receiving authentication of the personal information from the first server, a configuration for opening a gate for a user to enter or exit the store when the authentication device receives the authentication, and a user Disclosed is a configuration in which personal information is obtained from a body part of the user, the personal information is transmitted to a second server, and a product price is paid when authentication of the personal information is received from the second server.

However, even if barcodes are stamped on all items, it is difficult for an unfamiliar user to scan barcodes, and in the end, a method of calling a clerk or having a clerk scan is returned. In addition, if all the barcodes are not stamped on the goods, modeling and labeling must be performed on its own, but this is also not possible in small stores and only price tags are attached, so human resources and time are wasted when settling. In addition, even in the case of classifying items by image recognition, it is difficult because object recognition is significantly lowered when images are taken from different angles or lighting, and when RFID tags are attached to all items, the recognition rate is good, but all products have RFID tags , there is a problem of labor cost and cost increase.

One object of the present invention is to provide an atypical product recognition system using vision recognition and distance measurement based on artificial intelligence (AI) learning.

One embodiment of the present invention is to provide an atypical product recognition system using vision recognition and distance measurement that can be used in an unmanned store targeting products other than industrial products (irregular fields) that cannot be barcoded.

In order to recognize the product through image scanning, the captured image is trained with an artificial intelligence algorithm to increase object recognition, and the learned data is synchronized with the store terminal of each store so that the item is scanned in the store. It is possible to provide an image recognition-based unmanned payment system using artificial intelligence and big data that enables image recognition and unmanned payment in various environments including noise.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the technical problem as described above, the present invention proposes an atypical product recognition system using vision recognition and distance measurement based on artificial intelligence (AI) learning.

The vision recognition is performed based on artificial intelligence data learning, and the artificial intelligence data learning is divided into several frames for various atypical products and is performed at various angles, and the product recognition camera for vision recognition is applied with a depth camera. It is characterized in that by measuring the height value of the object information is obtained, and overlapping is confirmed through the height value.

The artificial intelligence data learning is characterized in that learning is possible even when a single product or several products are mixed, and the product recognition camera for vision recognition recognizes the top product among overlapping products to obtain the height value of the product, , It is possible to determine whether there is another product at the bottom of the corresponding product by comparing it with the height value of the corresponding product, and learning of the vertical, depth, and horizontal length of the product is performed through the height value when learning from various angles. It further includes a side camera, and the side camera is capable of recognizing overlapping products in a side direction.

According to embodiments of the present invention, images taken under various angles are trained with artificial intelligence algorithms to recognize atypical items to increase object recognition, and synchronize the learned data with store terminals of each store In the store, it is possible to check if the product is vision-recognized, and if the image is not recognized, the product image or identification code is received from the sales terminal so that the image is re-learned. There is an effect that can be paid.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

It should be noted that the technical terms used in this specification are only used to describe specific embodiments and are not intended to limit the present invention. In addition, technical terms used in this specification should be interpreted in terms commonly understood by those of ordinary skill in the art to which the present invention belongs, unless specifically defined otherwise in this specification, and are overly inclusive. It should not be interpreted in a positive sense or in an excessively reduced sense. In addition, when the technical terms used in this specification are incorrect technical terms that do not accurately express the spirit of the present invention, they should be replaced with technical terms that those skilled in the art can correctly understand. In addition, general terms used in the present invention should be interpreted as defined in advance or according to context, and should not be interpreted in an excessively reduced sense.

Also, singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "consisting of" or "having" should not be construed as necessarily including all of the various components or steps described in the specification, and some of the components or steps are included. may not be, or may further include additional components or steps.

Also, terms including ordinal numbers such as first and second used in this specification may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but other components may exist in the middle. On the other hand, when a component is referred to as “directly connected” or “directly connected” to another component, it should be understood that no other component exists in the middle.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted. In addition, in describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description will be omitted. In addition, it should be noted that the accompanying drawings are only for easily understanding the spirit of the present invention, and should not be construed as limiting the spirit of the present invention by the accompanying drawings. The spirit of the present invention should be construed as extending to all changes, equivalents or substitutes other than the accompanying drawings.

An atypical product recognition system using vision recognition and distance measurement according to an embodiment of the present invention basically counts products by vision recognition.

This kind of vision work is performed based on artificial intelligence data learning, and learning is divided into several frames and proceeds from various angles.

The atypical product recognition system using vision recognition and distance measurement according to the present invention does not require a separate learning device and can perform learning in the system itself.

On the other hand, the atypical product recognition system using vision recognition and distance measurement has the advantage of being able to learn even when a single product or several products are mixed.

Annotation is performed through its own model installed in the system, and for products that are difficult to annotate by artificial intelligence, learning is conducted manually using a separate annotation system.

The product recognition camera for vision recognition is applied with a depth camera, and it is possible to obtain object information by measuring the height value of the product, and to check overlapping through the height value.

Among the overlapping products, the upper product is recognized to obtain the height value of the corresponding product, and it is possible to determine whether there is another product at the bottom of the corresponding product by comparing the height value of the corresponding product, and through the height value when learning from various angles. It is possible to learn the length, depth, and width of a product.

An auxiliary camera (side camera) can also perform the same function to increase overlapping and product recognition accuracy. Meanwhile, a monitor for checking payment details is included at the checkout counter, and various information can be provided to the user through the corresponding monitor.

Each component is generally connected through a network. For example, at least one store terminal may be connected to an unattended payment service providing server through a network. Also, the unattended payment service providing server may be connected to at least one store terminal, at least one scanner, and at least one sales terminal through a network. In addition, at least one scanner may be connected to a store terminal and an unattended payment service providing server through a network. Also, at least one sales terminal may be connected to at least one store terminal and an unmanned payment service providing server through a network.

At least one store terminal identifies a product, which is an object in the product image, using a web page, app page, program, or application related to an artificial intelligence image object recognition-based unmanned payment service, and transmits the identification information to the sales terminal for payment and settlement. It may be a terminal that makes this happen. To this end, at least one store stage may be a terminal that models an object in a product image and performs labeling to identify it. In addition, at least one store terminal may be a terminal capable of recognizing a product in synchronization with a result of learning and re-learning in an unmanned payment service providing server. In addition, at least one store terminal may be a terminal that is connected to a scanner and a sales terminal, identifies a product image scanned or photographed by the scanner, and transmits an identification code to the sales terminal so that the sales terminal can pay for the product. In addition, at least one store terminal may be a terminal that may be deleted when connected to the unmanned payment service providing server through the cloud, or may be implemented by being integrated with a sales terminal. At this time, the sales terminal may be a terminal that implements the function and operation of the store terminal in any one or a combination of at least one of SaaS (Software as a Service), PaaS (Platform as a Service), and IaaS (Infrastructure as a Service). there is. The reverse is also true (Vice Versa).

Here, at least one store terminal may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop, a desktop, a laptop, and the like equipped with a navigation system and a web browser. At this time, at least one store terminal may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one store terminal is, for example, a wireless communication device that ensures portability and mobility, and includes navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Communication System) Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, It may include all kinds of handheld-based wireless communication devices such as a smartphone, a smartpad, and a tablet PC.

An artificial intelligence learning system according to an embodiment of the present invention may include a plurality of learning data collection devices, a learning data generating device, a plurality of annotation devices, and an artificial intelligence learning device.

Since the components of the artificial intelligence learning system according to an embodiment are merely functionally distinct elements, two or more components are integrated and implemented in an actual physical environment, or one component is implemented in an actual physical environment. may be implemented separately from each other.

The learning data generating device may receive attributes of a project related to artificial intelligence (AI) learning from the artificial intelligence learning device. The learning data generation device performs data structure design, collected data refinement, data processing, data expansion, and data verification for artificial intelligence (AI) learning, based on the user's control and the attributes of the received project. can do.

First of all, the learning data generating device may design a data structure for artificial intelligence (AI) learning. For example, the learning data generating device may define an ontology for artificial intelligence (AI) learning and a classification system of data for artificial intelligence (AI) learning based on the properties of the user's control and the received project. can

The learning data generating device may collect data for artificial intelligence (AI) learning based on the designed data structure. To this end, the learning data generating device may receive sensing data, 3D point cloud data, 2D images, and distance information from the learning data collecting device. However, it is not limited thereto, and the learning data generating device may perform web crawling or download data from an external organization's device.

As described above, although preferred embodiments of the present invention have been disclosed in the present specification and drawings, it is in the technical field to which the present invention belongs that other modified examples based on the technical spirit of the present invention can be implemented in addition to the embodiments disclosed herein. It is self-evident to those skilled in the art. In addition, although specific terms have been used in the present specification and drawings, they are only used in a general sense to easily explain the technical content of the present invention and help understanding of the present invention, but are not intended to limit the scope of the present invention. Accordingly, the foregoing detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of the present invention should be selected by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

Claims (5)

In an atypical product recognition system using vision recognition and distance measurement based on artificial intelligence (AI) learning,
The vision recognition is performed based on artificial intelligence data learning, and the artificial intelligence data learning is divided into several frames for various unstructured products and made at various angles. According to claim 1,
The product recognition camera for vision recognition is applied with a depth camera, and an atypical product recognition system using vision recognition and distance measurement, characterized in that by measuring the height value of the product to obtain object information and confirming overlapping through the height value. . According to claim 1,
The artificial intelligence data learning is an atypical product recognition system using vision recognition and distance measurement, characterized in that learning is possible even when a single product or several products are mixed. According to claim 2,
The product recognition camera for vision recognition recognizes an upper product among overlapping products, obtains a height value of the corresponding product, compares the height value of the corresponding product to determine whether there is another product at the bottom of the corresponding product, and can determine whether there is another product at the bottom of the corresponding product, and various angles. Atypical product recognition system using vision recognition and distance measurement, characterized in that for learning the vertical, depth, and horizontal length of the product through the height value when learning in. According to claim 1,
An atypical product recognition system using vision recognition and distance measurement, further comprising a side camera, wherein the side camera recognizes overlapping of products in a lateral direction.