KR102492567B1 - Camera device and acquisition system for content and image data package acquisition - Google Patents

Abstract

The present invention relates to a camera device for acquiring content and image data packages. The camera device includes: a photographing part for obtaining a video image by photographing an object; a content information acquisition part that acquires content information of the object in a non-contact manner; a matching storage part for matching, integrating, and storing the image and content information of the object; a central control part for controlling the operation and data communication of the photographing part, the information acquisition part, and the matching storage part; and a communication part for transmitting and receiving data stored in the matching storage part by wire or wirelessly by the central control part.

Description

Camera device and acquisition system for content and image data package acquisition}

The present invention relates to a camera device and an image data collection system, and more particularly, to a camera device and a collection system capable of quickly and effectively collecting and securing artificial intelligence learning data such as object recognition.

In an image capturing system including cameras connected to external equipment through a communication network, the cameras communicate with external equipment such as a host device and a user terminal, but the cameras also communicate with each other in a peer to peer (P2P) method. You may. Nonetheless, in the related art, cameras mainly communicate with external equipment to provide services. In this case, communication between the cameras is generally not performed so that each of the cameras can operate individually.

Meanwhile, a camera including an artificial intelligence function is being developed. Artificial intelligence technology consists of deep learning (machine learning) and element technologies using deep learning. Deep learning is an algorithm that classifies/learns the characteristics of input data by itself, and element technology is a technology that uses deep learning to mimic the functions of the human brain, such as cognition and judgment. techniques may be included. Visual understanding is a technology for recognizing and processing an object as if it were human vision, and may include object recognition, object tracking, image search, person recognition, scene understanding, space understanding, image improvement, and the like.

Inference/prediction is a technique of logically inferring and predicting information by judging information, and may include knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and may include knowledge construction (data creation/classification) and knowledge management (data utilization).

However, object recognition technology using such artificial intelligence technology not only requires a lot of image data collection to improve the performance of object recognition models, but also requires data pre-processing tasks such as labeling tasks for objects in image images. There is a problem that it is not easy to secure high-quality data for AI model training, such as data collection and data preprocessing, in terms of cost and time.

An object of the present invention to solve the above-described problems is not only to efficiently secure high-quality image data, but also to reduce the time and cost of data pre-processing, such as image data labeling, to quickly and effectively collect and It is intended to provide a camera device that can be secured.

In addition, an object of the present invention is to provide a video data collection system that can quickly, accurately and effectively acquire high-quality data that can be used in various industries such as artificial intelligence and IoT technology using easily portable mobile devices. to be.

A first means of the present invention for solving the above problems is a camera device for obtaining contents and an image data package, comprising: a photographing unit for acquiring a video image by photographing an object; a content information acquisition unit that acquires content information of an object in a non-contact manner; a matching storage unit for matching, integrating, and storing the video image and content information of the object; a central control unit controlling operations and data communication of the photographing unit, the information acquisition unit, and the matching storage unit; and a communication unit for transmitting/receiving the data stored in the matching storage unit by the central control unit by wire or wirelessly.

Here, the information acquisition unit may include object content information, characterized in that it is a data receiving module including a barcode scanner, RF receiver, Bluetooth, NFC reader and beacon receiver.

In addition, the matching storage unit may include a matching unit for matching a video image of a closest time with content information by comparing a capture time of an acquired video image and an acquisition time of content information; a package unit for merging the matched video image and content information and converting them into a video data package; and a package storage unit for storing the converted image data package.

And, the second means of the present invention to solve the above problems, the contents and image data package collection system, a photographing unit for acquiring a video image by photographing an object, and content information acquisition for acquiring the content information of the object in a non-contact manner unit, a matching storage unit for matching and integrating and storing the video image and content information of the object, and a central control unit for controlling the operation and data communication of the photographing unit, the information acquisition unit, and the matching storage unit, and the central control unit A package data acquisition terminal provided with a communication unit for transmitting and receiving the data stored in the matching storage unit by wire or wirelessly; and an artificial intelligence server that is connected to the camera device through a network, receives data stored in the matching storage unit, processes the video image and content information of the object, and is used as learning data for machine learning or deep learning.

Here, the package data obtaining terminal may be a mobile device including a smart phone and a tablet PC, and the artificial intelligence server may include metadata of image data or information about the object received from the image capturing terminal. It may be applied as labeling data for artificial intelligence learning and used as machine learning or deep learning training data.

The effect of the present invention for solving the above problems is to provide a camera device capable of acquiring the content information of the object together with the captured video image while photographing the object, and the content information (content information) of the object together with the image information of the object. , status, meta information, etc.), not only can efficiently secure high-quality image data, but also reduce the time and cost of data pre-processing such as image data labeling, so that AI learning data can be collected and stored quickly and effectively. A camera device that can be secured is provided.

In addition, the present invention simultaneously obtains a video image of an object and content information of the object using a content information acquisition terminal such as a mobile device, and packages and stores the image data and object content information data based on the acquisition time, It provides a video data collection system that can quickly, accurately and effectively acquire high-quality data that can be used in various industries such as artificial intelligence and IoT technology.

1 is a block diagram showing a detailed block configuration of a camera device for acquiring content and image data packages according to an embodiment of the present invention.
2 is a schematic diagram in which a camera device for acquiring content and image data packages according to an embodiment of the present invention is applied to an electronic passport.
3 is a diagram showing a detailed block configuration of an image data package collection system according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, this means that it may further include other components, not excluding other components, unless otherwise stated, and one or more other characteristics. However, it should be understood that it does not preclude the possibility of existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

As used throughout the specification, the terms "about", "substantially", etc., are used at or approximating that value when manufacturing and material tolerances inherent in the stated meaning are given, and do not convey an understanding of the present invention. Accurate or absolute figures are used to help prevent exploitation by unscrupulous infringers of the disclosed disclosure. The term "step of (doing)" or "step of" as used throughout the specification of the present invention does not mean "step for".

In this specification, a "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

In this specification, some of the operations or functions described as being performed by a terminal, device, or device may be performed instead by a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, apparatus, or device connected to the server.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.

1 is a block diagram showing a detailed block configuration of a camera device for acquiring content and image data packages according to an embodiment of the present invention.

As shown in FIG. 1 , a camera device 100 for acquiring contents and an image data package according to an embodiment of the present invention includes a photographing unit 110 that acquires a video image by photographing an object; a content information acquisition unit 120 that obtains content information of an object in a non-contact manner; Matching storage unit 130 for matching, integrating, and storing the video image and content information of the object; a central control unit 140 that controls operations and data communication of the photographing unit 110, the information acquisition unit, and the matching storage unit 130; And it may be configured to include a communication unit 150 for transmitting and receiving data stored in the matching storage unit 130 by the central control unit 140 by wire or wirelessly.

In this way, the camera device 100 for obtaining content and image data packages according to an embodiment of the present invention is capable of acquiring content information of an object together with a captured video image while photographing an object. By providing image information of the object and matching and storing the content information (content, state, meta information, etc.) of the object, not only can high-quality image data be efficiently secured, but also data pre-processing such as image data labeling processing It is possible to collect and secure AI learning data quickly and effectively by reducing the time and cost of AI. In addition, there is a great advantage in that it can be used as a video recording terminal that can be used quickly and directly for various services using the Internet of Things (IoT).

Hereinafter, components of the camera device 100 for acquiring content and image data packages according to an embodiment of the present invention will be described in detail with reference to the drawings.

As shown in FIG. 1 , the camera device 100 for obtaining content and image data packages according to an embodiment of the present invention includes a photographing unit 110, a scanner 121, a receiver 123, and a reader 125. It is configured to include a content information data receiving module, a matching storage unit 130, a central control unit 140 and a communication unit 150.

Here, the photographing unit 110 is a device that obtains image data by capturing an image of an object as the camera device 100, and may be the digital camera device 100. A digital camera may include a CMOS or CCD image sensor, where CMOS (Complimentary Metal Oxide Semiconductor) is an imaging semiconductor device, and CCD (Charge-coupled device) is a sensor that converts light into electric charge to obtain an image, It is a chip in which many photodiodes are gathered. When light shines on the photodiode, electrons are generated according to the amount of light grains. It is an element that creates In addition, it may include a camera body, a lens that collects light reflected on an object, and other control devices, and the photographed optical signal is converted into image digital data through the above-described CMOS or CCD image sensors to be obtained. It is also possible to check immediately through a display device.

In addition, the content information acquisition unit 120 that acquires the content information of the object in a non-contact manner at the same time that the camera device 100 photographs the object may be a data receiving module that receives data wirelessly or optically, such as a barcode or QR code. A scanner 121 for reading code information, a receiver 123 that receives data through short-range wireless communication such as NFC, Bluetooth, and Beacon, or a reader 125 that reads signals such as RFID may be a device.

More specifically, as shown in FIG. 1, a barcode 15 containing content information of the object may be provided on the surface of the ramen box 10, which is an object. Obtaining the content and image data package according to an embodiment of the present invention When the barcode scanner 121 (the content information acquisition unit 120) provided in the camera device 100 for scanning the barcode 15 location part scans the barcode 15 part, the object included in the barcode Read and obtain content information.

Here, the scanner 121 is provided with a device that emits laser light to the barcode 15, and in the laser light of the barcode 15, the black part reflects a small amount of light and the white part reflects a large amount of light. , The reflected laser light signal is converted into a digital signal through a decoder that reads the signal, and the converted digital signal is read into pre-stored content information of the object to obtain information.

Also, the data receiving module such as the receiver 123 and the reader 125 is a device capable of receiving and obtaining content information of an object at a short distance without contact, and may be a short-distance wireless communication device.

Here, short-distance wireless communication refers to communication that exchanges information between various information processing devices at a short distance using radio waves as a transmission medium of information, and devices such as Bluetooth, IrDA, HomeRF, beacon, NFC, and RFID are used. communication may be used. Bluetooth is a field of exchanging information with nearby information devices installed on mobile phones, IrDA is a field of data exchange between information devices in a short distance using infrared rays, and HomeRF is a field of home electronic products centered on home phones and PCs. It can be used as a device that acquires the content information of an object in a non-contact manner at a close distance, such as being developed with a focus on the Home Automation field through information exchange. Therefore, the content information acquisition unit 120 applied to the embodiment of the present invention can be any device or technology capable of obtaining content information of an object in a non-contact manner using various technologies other than the above-described short-range wireless communication device.

In addition, the matching storage unit refers to a storage device that matches, integrates, and stores the video image and content information of the object described above. It is configured to include a matching unit 131 that matches content information, a package unit 133 that merges the matched video image and content information and converts them into a video data package, and a package storage unit that stores the converted video data package. It can be.

Here, the matching unit 131 is a component that matches the video image obtained by being photographed and the information acquired by the content information acquisition unit 120, and the criteria for matching are the acquisition time of the video acquired by being photographed and the content information acquisition unit ( In step 120), data paired with each other are matched based on the time at which the content information of the object is acquired. By applying such a matching method, it is possible to match accurate information about time and changed images of an object, and accurate labeling information about an acquired video image can be obtained from the matched information. That is, the content information of the object can change over time, and the video image in its state can also change over time.

Therefore, the package unit 133 merges the matched video image and the content information to convert the video data into a paired data package, and converts the content information of the object acquired at the time the video image is acquired into a single package. As a device for packaging in pairs, it is possible to convert an image captured and acquired into meta data or content data into one package format data. Such package data corresponds to labeling as pre-processing of data to be used for artificial intelligence, which will be described later, and pre-processed high-quality data can be obtained very efficiently and can be immediately applied to various data use technologies.

And, as shown in FIG. 1, the storage unit is a storage device such as a memory, and stores a video image obtained by being photographed, content information of an object acquired, and information packaged by the package unit 133 including all of them. All of the corresponding information including time information obtained may be stored.

The central control unit 140 is a device for controlling the operation and data communication of the photographing unit 110, the information acquisition unit, and the matching storage unit 130, and may include a device such as a microcontroller unit (MCU) or CPU. The camera of the photographing unit 110, the scanner 121 of the object content information acquisition unit 120, the receiver 123, the reader 125, the matching unit 131 of the matching storage unit 130, and the package Contents and image data package according to an embodiment of the present invention by integrally controlling the unit 133, the storage unit, and the communication unit 150 connected to a network such as Wi-Fi (YiFi), and communicating signals or data between components. The acquisition camera device 100 may be integrated and controlled.

FIG. 2 shows a schematic diagram in which the camera device 100 for acquiring content and image data packages according to an embodiment of the present invention is applied to an electronic passport.

As shown in FIG. 2, looking at an example in which the camera device 100 for acquiring content and image data packages according to an embodiment of the present invention is applied to an electronic passport, the electronic passport is photographed by the camera device 100, At the same time, the object content information acquisition unit 120 reads the content information of the ePassport by the scanner 121 or reader 125 or by the receiver 123 in the information transmission module such as an RFID chip or barcode provided in the ePassport. receive information.

The electronic passport is a machine readable passport equipped with an integrated circuit chip containing biometric data. say The electronic passport has a built-in contactless electronic chip, and it is known that there is little possibility of leakage of personal information because it can be read only by special reading equipment at a short distance within 5 cm. can only be collected. Alternatively, it is also possible to obtain text information obtained by scanning the text of a video image photographed by the camera unit of the electronic passport.

And, as shown in FIG. 2, the video image of the ePassport captured by the camera unit and the content information of the permitted object obtained from the object content information are received and the time taken and the time obtained by the matching unit 131 are recorded. They are matched based on standards, packaged as one pair through the packaging unit 133, and the packaged data is stored in the storage unit.

In this way, the camera device 100 for obtaining contents and video data packages according to an embodiment of the present invention does not merely capture and acquire video image data, but simultaneously acquires content information of a corresponding object through a data receiving module, By packaging and storing video image data and object content information data based on the acquisition time, it provides a device that can quickly, accurately and effectively acquire high-quality data that can be used in various industries such as artificial intelligence and IoT technology. .

3 is a diagram showing a detailed block configuration of a content and image data package collection system 1000 according to an embodiment of the present invention.

As shown in FIG. 3, the content and image data package collection system 1000 according to an embodiment of the present invention includes a photographing unit 210 that acquires a video image by photographing a water tank as an object, and content information of the object ( A content information acquisition unit 220 that acquires information such as ID of the tank, current water temperature of the tank, lamp operation time, and water replacement date of the tank) in a non-contact manner, and matching, integrating, and storing the video image and content information of the object The matching storage unit 230, the photographing unit 210, the central control unit 240 that controls the operation and data communication of the information acquisition unit and the matching storage unit 230, and the matching by the central control unit 240 The data stored in the storage unit 230 is connected to the data package acquisition terminal 200 including the communication unit 250 that transmits and receives the data stored in the storage unit 230 by wire or wirelessly, and the package acquisition terminal is connected to the network and stored in the matching storage unit 230. It may be configured to include an artificial intelligence server 300 that receives data and processes the video image and content information of the object to be used as learning data for machine learning or deep learning.

Here, the package data acquisition terminal 200, as shown in FIG. 3, is a camera device for obtaining content and image data packages, and may be a mobile device including a smartphone and a tablet PC, as shown in FIG. As described above, a communication unit capable of transmitting and receiving data by being connected to a photographing unit 210 such as a camera device, a data receiving module such as Bluetooth, an RF reader 225, an OCR reader 225, and a wireless communication network such as Wi-Fi. 250, and may include a matching unit 231, a package unit 233, and a package storage unit 235 including a storage unit by means of a built-in CPU and a memory device.

In addition, the contents and image data package collection system 1000 according to an embodiment of the present invention is connected to the package acquisition terminal through a network and receives data stored in the matching storage unit 130 to receive the video image and contents of the object. It may be provided including an artificial intelligence server 300 that processes information and is used as learning data for machine learning or deep learning. It may be used as machine learning or deep learning training data by applying it as metadata for data or labeling data for artificial intelligence learning.

That is, as shown in FIG. 3, the contents and image data package collection system 1000 according to an embodiment of the present invention includes a communication unit 350, an AI DB 310 for storing received data, and artificial intelligence model learning. Equipped with an artificial intelligence server 300 including a data pre-processing unit 320 that processes data necessary for processing, and a model learning unit 330 that learns an artificial intelligence model such as machine learning or deep learning based on the received data. And, the artificial intelligence server 300 receives the package data including the video image and content information of the object obtained by connecting the data package acquisition terminal 200 to a network such as the Internet, and the packaged data is added to the image image of the object. It is possible to provide a system that can be used as training data for machine learning or deep learning models quickly and efficiently in that it can be used as labeled image data in that it includes content information of an appropriate object.

Data labeling refers to processing data in a form in which AI can learn on its own in order to enhance artificial intelligence algorithms. The image data package collection system 1000 according to an embodiment of the present invention obtains package data. If the contents of the video image obtained in unit 220 are labeled and input to the artificial intelligence model, artificial intelligence can apply it to object recognition artificial intelligence technology that recognizes similar images while learning data based on the data. In that, it provides an image data package collection system 1000 capable of collecting fast, efficient and high-quality data that can be applied to big data technology required for artificial intelligence technology and the like.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts should be construed as being included in the scope of the present invention. do.

100: camera device
200: package data acquisition terminal
110, 210: shooting unit
120, 220: package data acquisition unit
130: matching storage unit
140, 240: central control unit
150, 250, 350: communication department
300: artificial intelligence server
310: AI DB
320: data pre-processing unit
330: model learning unit
1000: image data package collection system

Claims (6)

delete delete delete A photographing unit that acquires a video image of an object photographed from a camera device, a content information acquisition unit that acquires content information of an object in a non-contact manner, and a matching storage unit that matches, integrates, and stores the video image and content information of the object Obtain package data including a central control unit that controls operations and data communication of the photographing unit, the information acquisition unit, and the matching storage unit, and a communication unit that transmits and receives the data stored in the matching storage unit by the central control unit by wire or wirelessly terminal; and
Including an artificial intelligence server that is connected to a network and receives data stored in the matching storage unit and processes the video image and content information of the object to be used as machine learning or deep learning learning data,
The matching storage unit,
a matching unit which compares a capturing time of the video image and an acquisition time of the content information, and matches the video image at the closest time with the content information; a package unit for merging the matched video image and content information and converting them into a labeled video data package; a package storage unit for storing the converted image data package;
The artificial intelligence server,
Contents and video data package collection system, characterized in that the image similar to the video image is recognized by inputting the converted video data package as machine learning or deep learning learning data. delete delete

Images