WO2022019651A1

WO2022019651A1 - Event video recording device, and video-providing device and method

Info

Publication number: WO2022019651A1
Application number: PCT/KR2021/009418
Authority: WO
Inventors: 김현민; 정임수
Original assignee: (주)텔레컨스
Priority date: 2020-07-21
Filing date: 2021-07-21
Publication date: 2022-01-27
Also published as: KR20220011472A

Abstract

The present invention relates to an event video recording device, and a video-providing device and method. An event video-providing method of the video-providing device according to an embodiment comprises the steps of: acquiring a video recorded in response to the occurrence of an event; analyzing motion patterns of a subject moving in the acquired video; inserting identification information about the motion patterns of the subject into the video according to the analysis result, and storing the identification information; and receiving a signal requesting a search of the video, and searching for and providing the video on the basis of the identification information.

Description

Event video recording device, video providing device and video providing method

An embodiment of the present invention relates to an event video recording apparatus, an image providing apparatus, and an image providing method.

A black box is an automatic flight data recording device that is originally installed on airplanes, etc., and plays an important role in determining the cause of an accident.

Recently, in order to solve the problem of securing witnesses and the reliability of witnesses in the event of a car accident, the person turns into an assailant, or the location of responsibility is unclear due to insufficient on-site preservation and unclear identification of intersection signals. have.

A black box of a parked vehicle can perform regular recording and event recording. Continuous recording continuously records surveillance images of a parked vehicle, and has disadvantages in that the battery is quickly consumed and a large amount of storage space is required.

In order to secure this disadvantage, event recording may be performed. Event recording is a method of storing a surveillance image only when it is determined that an event has occurred in a parked vehicle. The event referred to herein may include motion detection in which a motion occurs near the vehicle and impact detection in which an impact is detected in the vehicle.

However, even when the event recording method is selected, the user needs to analyze the video recorded in the black box. When analyzing an image, a singularity is usually discovered by replaying the recorded image over several hours. Therefore, there is a problem that a lot of time is required for such a black box image analysis.

In order to solve the above-mentioned problems, an object of the present invention is to provide an apparatus and method for searching and reproducing only images related to a desired event when analyzing a black box image.

An event image providing method according to the present invention for achieving the above object includes the steps of: acquiring a photographed image according to the occurrence of an event; analyzing a motion pattern of a moving subject in the acquired image; inserting and storing identification information of the motion pattern of the subject into the image according to the analysis result; and receiving a signal for requesting the image search, and searching for and providing an image based on the identification information.

In one embodiment, the acquiring of the event image captured while the parking state of the vehicle is maintained may include receiving the event image from an image recording device mounted on the vehicle or accessing the memory of the image recording device to obtain the event image. characterized.

In an embodiment, the analyzing of the motion pattern of the moving subject may include: detecting the moving subject in the image; and determining an operation pattern using deep learning technology based on the detected appearance position and movement trajectory of the subject.

In an embodiment, the determining of the motion pattern using the deep learning technique includes applying the detected position and movement trajectory of the subject to the modeled motion pattern classified based on a plurality of training samples to operate the subject. and determining an operation pattern model corresponding to .

In an embodiment, the plurality of training samples include an appearance position and movement trajectory of the subject, and the motion pattern model includes identification information for pattern identification.

An event image providing apparatus according to an embodiment of the present invention includes: an image acquisition unit for acquiring a photographed image according to the occurrence of an event; a pattern analyzer for analyzing a motion pattern of a moving subject in the acquired image; a controller for inserting and storing identification information of the motion pattern of the subject into the image according to the analysis result, and searching for an image based on the identification information; and a display unit for outputting the searched image according to the instruction of the control unit.

In one embodiment, it characterized in that it further comprises a storage unit for storing the image in which the identification information of the motion pattern of the subject is inserted.

In an embodiment, the control unit receives a signal requesting an image search from an external terminal, searches for an image based on the identification information, and controls to transmit the searched image to the external terminal, characterized in that do.

In an embodiment, the control unit detects a moving subject in the acquired image, and determines the motion pattern using deep learning technology based on the detected appearance position and movement trajectory of the detected subject.

In an embodiment, the controller determines a motion pattern model corresponding to the motion of the subject by applying the detected appearance position and movement trajectory of the subject to a modeled motion pattern classified based on a plurality of training samples. do it with

An image recording apparatus according to another embodiment of the present invention includes at least one camera unit for capturing a real-time image; an input unit for converting a user's input operation into an input signal; and monitoring the occurrence of an event by analyzing the image, generating an image of a preset time when an event occurs, analyzing the motion pattern of the moving subject in the generated image, and receiving identification information of the motion pattern of the subject according to the analysis result and a control unit for inserting and storing the image, wherein the control unit receives an event image search request signal from the input unit, and searches for and provides the image based on the identification information.

In one embodiment, the event video recording apparatus includes a first memory unit for temporarily storing the image captured by the camera unit; and a second memory unit configured to store an event image generated by the occurrence of an event along with the identification information according to an instruction of the control unit.

In an embodiment, when a moving subject is detected in the real-time image, the controller considers that an event has occurred.

In one embodiment, the control unit is characterized in that it determines the motion pattern using a deep learning technology based on the detected appearance position and movement trajectory of the subject.

The apparatus and method according to an embodiment of the present invention have the effect of rapidly performing a black box image analysis.

The effect according to the present invention is not limited by the contents exemplified above, and more various effects are included in the present specification.

1 is a block diagram schematically showing the configuration of a system for providing an event image of a vehicle according to an embodiment of the present invention.

2 is a block diagram schematically showing the configuration of an image recording apparatus 100 according to an embodiment of the present invention.

3 is a block diagram schematically showing the configuration of an image analysis apparatus according to an embodiment of the present invention.

4 is a flowchart illustrating a process in which an image recording apparatus performs an event recording mode according to an embodiment of the present invention.

5 is a flowchart illustrating a process of providing an image by an image providing apparatus according to an embodiment of the present invention.

6 is an exemplary diagram for explaining an operation pattern according to an embodiment of the present invention.

7 is a block diagram schematically showing the configuration of an image recording apparatus according to another embodiment of the present invention.

8 is a flowchart illustrating a process in which an image recording apparatus provides an image according to an embodiment of the present invention.

Embodiments will be described herein with reference to the accompanying drawings, however, the principles disclosed herein may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. For example, although a vehicle is described as a main embodiment for an object on which the video recording apparatus is mounted, it will be clear to those skilled in the art that this is only an example and may be mounted on various objects. In the detailed description of the invention, detailed descriptions of well-known features and techniques may be omitted to avoid unnecessarily obscuring features of the embodiments.

Throughout the specification and claims, when a part includes a certain element, it means that other elements may be further included, rather than excluding other elements, unless specifically stated to the contrary.

In this specification, an event is a trigger that starts recording video when a special situation that requires video recording (eg, impact of an object, rapid deceleration of an object, rapid acceleration, or sudden braking, exceeding a preset speed, etc.) occurs ) is a type of Here, the situation requiring video recording resolves conflicts between the perpetrators/victims of the event that occurred (eg, legal, mental, temporal, and economic problems), and conflicts between insurance companies/insurers in vehicle repairs due to the occurrence of the event. In this case, it means a situation in which video recording at the time of the occurrence of an event is likely to be used as an important means of resolving conflicts.

On the other hand, an impact caused by a user's general actions, such as simply closing a door or a trunk, does not cause a series of conflicts as described above, so video recording is unnecessary, and it is not judged as an event.

In the present invention, when a single event or a plurality of different events are detected, video recording and storage are started. That is, video recording and storage can be started when an impact is detected, or video recording and storage can be started when a special situation (eg, airbag deployment due to a defect in the vehicle, sudden vehicle start, etc.) occurs due to a technical defect of the target.

Hereinafter, in describing the event of the present invention, a mounting target is a vehicle, and an event is an impact as an example.

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

The event image providing system may include an image recording apparatus 100 , an image providing apparatus 200 , and a user terminal 300 installed in the vehicle 10 .

The image recording apparatus 100 is mounted on a vehicle and serves as a black box for generating a photographed image of the vehicle and surroundings of the vehicle.

The image providing apparatus 200 may be implemented as, for example, a workstation, a server, a general computer, other electronic devices capable of performing communication, or similar devices.

The image providing apparatus 200 is a computing device that acquires an image captured by the image recording apparatus 100 , analyzes and stores the event image, performs a search upon request for a search for the event image, and provides a search result. Also, the image providing apparatus 200 may reproduce the analyzed event image.

The user terminal 300 is implemented as an electronic device or similar device capable of performing, for example, a smart phone, PDA, tablet PC, notebook computer, laptop computer, personal computer, other communication, receiving user input, and outputting a screen. can be

The image recording apparatus 100 may be connected to the image providing apparatus 200 through a wired/wireless communication network.

The user terminal 300 may be connected to the image recording apparatus 100 or the image providing apparatus 200 through a communication network.

The user terminal 300 may access the image recording apparatus 100 or the image providing apparatus 200 through a wired/wireless communication network to request a search for an event image or to display a received image.

The image recording apparatus 100 may be entirely hardware, or may have aspects that are partly hardware and partly software. For example, the control unit 150 included in the video recording apparatus 100 may collectively refer to hardware and related software for processing and/or exchanging data of a specific format and content in an electronic communication method. That is, as used herein, “unit”, “module”, “device” or “system” refers to hardware, a combination of hardware and software, or a computer-related entity such as software. For example, as used herein, a part, module, device, or system is a running process, a processor, an object, an executable, a thread of execution, a program, and/or a computer. (computer), but is not limited thereto. For example, both an application running on a computer and a computer may correspond to a part, module, device, or system of the present specification.

The image recording apparatus 100 may include a camera unit 110 , a first memory 120 , a second memory 130 , an input unit 140 , and a control unit 150 .

The camera unit 110 is a means for capturing an image, and includes an optical lens and an image sensor.

The camera unit 110 may capture continuous images projected to the field of view of the optical lens. In an embodiment, the camera unit 110 converts the photographed analog image signal into a digital image signal. For this reason, the image recording apparatus 100 may acquire image data such as color, black and white, infrared rays, etc. by photographing the exterior of the vehicle and/or the interior of the vehicle. In some embodiments, the camera unit 110 detects only an analog video signal, and the above-described conversion processing may be performed by the control unit 150 below.

In some embodiments, the number of camera units 110 may be plural. In this case, the image recording apparatus 100 may include a plurality of channels connected to the plurality of camera units 110 . For example, a front camera for acquiring an image of the front of the vehicle may be connected to a first channel, and a rear camera for acquiring an image of the rear of the vehicle may be connected to a second channel.

The first memory 120 is provided with a buffer function for temporarily storing the acquired image, and as a volatile memory, it may be implemented as a typical double data rate (DDR) RAM.

In the second memory 130 , the image data obtained from the camera unit 110 by writing data of the controller 150 , preferably image data selected from among the image data temporarily stored in the first memory 120 are recorded. As a data storage medium to be stored, it may be implemented as an SD card, a flash memory such as a USB memory, an EEPROM, a hard disk, or the like.

The control unit 150 analyzes the image to determine whether an event has occurred, and when it is determined that the event has occurred, controls the overall operation of the event image capturing and recording apparatus such as an operation of storing the recorded image, and a micro control unit (MCU). ), may be implemented as a kind of application processor (AP) such as a central processing unit (CPU). The operation of the control unit 150 will be described in more detail below with reference to FIG. 4 .

The input unit 140 converts a user's input operation into an input signal and transmits it to the control unit 150 . The input unit 140 may be simply implemented as a button or the like. For example, the input unit 140 may receive a selection of any one of the regular recording mode and the event recording mode from the user, convert it into a corresponding signal, and transmit it to the controller 150 .

The controller 150 controls the overall operation of the image recording apparatus 100 and each component. In particular, as will be described later, the controller 150 controls the camera unit 110 according to the recording mode selected from the regular recording mode and the event recording mode to display an image at a preset frame rate (eg, 16 frames per second). create

The controller 150 may generate an image for a preset time based on the time when the event occurs.

The image captured by the camera unit 110 is first temporarily stored in the first memory 120 and then moved to the second memory 130 . The plurality of image files stored in the second memory 130 are made into one moving picture file in units of a preset time (eg, 1 minute).

The user may also view the video stored in the second memory 130 in the video recording apparatus 100 or insert it into another computer device, for example, the image analysis apparatus 200 to view. In some cases, it is also necessary to transmit the video stored in the second memory 130 to an external device, for example, the user terminal 300 . Since the video recording apparatus 100 is installed in a moving vehicle, a wireless network must be used to transmit the video.

The image analysis apparatus 200 may include an input unit 210 , a display unit 220 , an image acquisition unit 230 , a pattern analysis unit 240 , a control unit 250 , and a storage unit 260 .

The input unit 210 converts a user's input operation into an input signal and transmits it to the control unit 250 . The input unit 210 may be implemented as, for example, a keyboard, a mouse, a touch sensor on a touch screen, a touch pad, a keypad, a voice input, or other input processing devices that are possible in the present, past or future. The input unit 210 may receive, for example, a user's information provision request input and transmit it to the control unit 250 .

The display unit 220 outputs a screen under the control of the control unit 250 . The display unit 220 may be embodied as, for example, a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), a projector, or other display devices capable of present, past or future. The display unit 220 may display, for example, an interface page for providing information or an information provision result page. According to an embodiment, a component that uses another method for transmitting information to a user such as voice output or vibration instead of screen output may be used instead of the display unit 220 .

The image acquisition unit 230 acquires an image captured according to the occurrence of an event while the parking state of the vehicle is maintained. The image acquisition unit 230 may be a communication module or a module capable of accessing image information stored in the second memory 130 like an SD card recognition unit.

For example, the image acquisition unit 230 may receive and acquire an image recorded in the event recording mode from the image recording apparatus 100 through the communication module. Also, the image acquisition unit 230 may acquire an image stored in the SD card of the image recording apparatus 100 through the SD card recognition unit.

The pattern analysis unit 240 recognizes a moving subject in the image obtained by the image acquisition unit 230 and analyzes the motion pattern of the subject.

The pattern analysis unit 240 may compare the motion pattern stored in advance with the motion pattern of the subject according to the analysis result, and transmit identification information of the motion pattern selected according to the comparison result to the controller 250 .

The controller 250 controls the overall operation of the device 200 and each component. In particular, when receiving identification information from the pattern analysis unit 240 according to the information input from the input unit 210 as described below, the control unit 250 inserts the identification information into the image and stores it in the storage unit 260, and the An image search is performed based on the identification information. The control unit 250 may output the searched image through the display unit 220 .

A plurality of images are analyzed, and an image selected according to the analysis result is displayed through the display unit 220 .

In particular, when receiving a request for an image search corresponding to a specific operation pattern from the user terminal 300 , the controller 250 searches for an image based on the identification information and transmits the searched image to the user terminal 300 .

In the exemplary embodiment of the present invention, the pattern analysis unit 240 and the control unit 250 are exemplified as being processed by a separate arithmetic unit, but may be processed by a single arithmetic unit.

The storage unit 260 is installed in the image analysis apparatus 200 to store a program code for performing an event image providing method, and/or an installation package (installation program code) for installing the program. Hereinafter, a program code for performing a method for providing item information distribution according to an event and/or an installation package (installation program code) for installing the program will be referred to as a virtual input interface program.

The data is stored under the control of the controller 250 and the requested data is transmitted to the controller 250 .

2 and 4 , in step S110 , the video recording apparatus 100 receives the event recording mode selected through the input unit 140 and enters the event recording mode.

In step S120 , the image recording apparatus 100 captures an image in real time by the camera unit 110 , and the generated image is temporarily stored in the first memory 120 .

In step S130, the video recording apparatus 100 monitors this occurrence. The image recording apparatus 100 detects a moving subject by analyzing the image temporarily stored in the first memory 120 . When a moving subject is detected, it is determined that an event has occurred.

In another modified example, when the image recording apparatus 100 includes a separate sensor, when an impact or the like is sensed by the sensor, it may be determined that an event has occurred.

When the controller 150 of the video recording apparatus 100 determines that an event has occurred, the process proceeds to step S140 and generates an image stored in the first memory 120 for a predetermined time (eg, 1 minute) based on the event occurrence time. 2 is stored in the memory 130 . For example, it may be 20 seconds before the event occurrence time and 40 seconds after the event occurrence time.

At this time, the controller 150 of the image recording apparatus 100 may store an event occurrence time and an event occurrence location together.

In another modified example, if it is determined that an event has occurred, an event occurrence alarm may be notified to a preset user terminal 300 . When an event occurrence alarm is notified, only information for notifying the occurrence of an event may be provided, and an image generated when an event occurs may also be provided.

5 is a flowchart illustrating a process of providing an image of an image providing apparatus according to an embodiment of the present invention, and FIG. 6 is an exemplary diagram illustrating an operation pattern according to an embodiment of the present invention.

In step S200 , the image providing apparatus 200 acquires a recorded event image from the image recording apparatus 100 . The event image is an image of an event occurring in the vehicle while the parking state of the vehicle is maintained.

In step S210, the image providing apparatus 200 analyzes the event image to analyze the motion pattern of the subject.

The image providing apparatus 200 analyzes the event image to determine the appearance position and movement trajectory of the subject, compares it with a preset motion pattern model, checks whether there is an associated motion pattern model, and determines whether there is a motion pattern model associated with the event image according to the comparison result. Extracts the identifier of the operation pattern.

The motion pattern model is a classification model classified according to the appearance direction of the subject and the movement trajectory of the subject, and may be generated based on a plurality of training samples. The operation pattern model may include a pattern identifier. Here, the pattern identifier is identification information for respectively identifying a plurality of operation patterns of each training sample.

Referring to FIG. 6 , the motion pattern is a first pattern in which the appearance direction of the subject is the left side of the vehicle, the movement trajectory is in the upper-left to lower-right direction or vice versa (lower-right to upper-left direction), and the first pattern in which the movement trajectory is parallel to the vehicle. 2 patterns, a third pattern that is in the upper left to lower left direction or vice versa (lower left to upper right), and a seventh pattern in which a movement trajectory is perpendicular to the vehicle. A fourth pattern in which the next subject appears on the right side of the vehicle and the movement trajectory is in the upper-left to lower-right direction or vice versa (lower-right to upper-left), a fifth pattern in which the movement trajectory is parallel to the vehicle, and from the upper-left to lower-left direction or vice versa (lower left to right), a sixth pattern, and an eighth pattern in which the movement trajectory is perpendicular to the vehicle. Each operation pattern may be assigned an identifier from 01 to 08. These operation patterns and identifiers are only examples and are not limited thereto.

In an embodiment of the present invention, motion pattern modeling based on deep learning has been exemplified, but is not limited thereto.

The motion pattern model may be modeled and provided by the manufacturer of the image recording apparatus 100 . Alternatively, it may be modeled and provided by a designer of the image providing apparatus 100 .

In another modified example, since the event refers to various special situations that require video recording, such as sudden braking and sudden acceleration, in addition to contact with a subject, physical quantities such as speed and speed change may be further referenced.

In step S220, the image providing apparatus 200 inserts and stores identification information (identifier) of the motion pattern of the subject into the image according to the analysis result.

When the video providing apparatus 200 receives a request to search for an event video in step S230, it searches for an event video based on the identifier in step S240. The event image search request may be performed by the user of the image providing apparatus 200 through the input unit 210 , and an external terminal connected to the image providing apparatus 200 , for example, the image recording apparatus 100 and/or the user It may be received from the terminal 300 .

In step S250, the image providing apparatus 200 provides the searched event image.

The image providing apparatus 200 provides the searched event image to the event image search requester. For example, when the user terminal 300 requests a search for an event video, the searched event video is provided to the user terminal 300, and when the video recording apparatus 100 requests a search for an event video, the searched event video is displayed. It may be provided to the image recording apparatus 100 .

By inserting the motion pattern identifier into the event image as described above, the user can easily search only the event image corresponding to the desired motion pattern.

7 is a block diagram schematically showing the configuration of an image recording apparatus 101 according to another embodiment of the present invention. In the video recording apparatus 101 according to another embodiment of the present invention, the same reference numerals are given to the same components as those of the video recording apparatus 100 of FIG. 2 , and detailed descriptions thereof will be omitted.

The video recording apparatus 101 may be entirely hardware, or may have aspects that are partly hardware and partly software.

The image recording apparatus 100 may include a camera unit 110 , a first memory 120 , a second memory 130 , an input unit 140 , a control unit 151 , and a display unit 160 .

In the second memory 130 , the image acquired by the camera unit 110 by writing data of the controller 150 , preferably the image data being temporarily stored and/or stored in the first memory 120 , is stored in the second memory 130 . As a data storage medium that is recorded and stored, it may be implemented as an SD card, a flash memory such as a USB memory, an EEPROM, a hard disk, or the like.

The control unit 151 analyzes the image to determine whether an event has occurred, and if it is determined that the event has occurred, controls the overall operation of the event image capturing and recording device, such as analyzing the recorded image and storing it together with the operation pattern, , may be implemented as a kind of application processor (AP), such as a micro control unit (MCU) or a central processing unit (CPU). The operation of the control unit 151 will be described in more detail below with reference to FIG. 8 .

The input unit 140 converts a user's input operation into an input signal and transmits it to the control unit 151 . The input unit 140 may be simply implemented as a button or the like. For example, the input unit 140 may receive a selection of any one of the regular recording mode and the event recording mode from the user, convert it into a corresponding signal, and transmit it to the controller 150 .

The controller 151 controls the overall operation of the image recording apparatus 100 and each component. In particular, as will be described later, the controller 151 controls the camera unit 110 according to a recording mode selected among the regular recording mode and the event recording mode to display an image at a preset frame rate (eg, 16 frames per second). create

The controller 151 generates an image for a preset time based on the time when the event occurs, recognizes a moving subject in the generated image, and analyzes the motion pattern of the subject.

The controller 151 compares the motion pattern stored in advance with the motion pattern of the subject according to the analysis result, inserts identification information of the motion pattern selected according to the comparison result into the event image, and then stores it in the second memory 130 .

The controller 151 uses the identification information when searching for an event video later.

The controller 151 may include an expression in which a plurality of event operation patterns are expressed in letters and/or graphically in all or part of the shape of the vehicle to the user in order to facilitate the search for the event image.

Similar to that illustrated in FIG. 6 , the controller 151 may graphically display the event operation pattern on the display unit 160 in a plan view of the entire vehicle.

The user selects a desired event operation pattern from among the plurality of operation patterns displayed on the display unit 160 , so that the control unit 151 searches based on the identification information included in the event image and displays the selected event image on the display unit 160 . can be provided through

The display unit 160 outputs a screen under the control of the control unit 151 . The display unit 160 may be implemented as, for example, a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), a projector, or other display devices capable of present, past or future. The display unit 160 may display, for example, an interface page for providing information or an information providing result page. According to an embodiment, a component that uses another method of delivering information to a user, such as voice output or vibration, instead of screen output, may be used instead of the display unit 160 .

7 and 8 , in step S310 , the video recording apparatus 101 receives the event recording mode selected through the input unit 140 and enters the event recording mode.

In step S320 , the image recording apparatus 101 captures an image in real time by the camera unit 110 , and the generated image is temporarily stored in the first memory 120 .

In step S330, the video recording apparatus 100 monitors the occurrence of an event. The image recording apparatus 100 detects a moving subject by analyzing the image temporarily stored in the first memory 120 . When a moving subject is detected, it is determined that an event has occurred.

When the controller 150 of the video recording apparatus 100 determines that an event has occurred, the process proceeds to step S340 and generates an image for a predetermined time (eg, 1 minute) based on the event occurrence time of the image stored in the first memory 120 . do. For example, it may be 20 seconds before the event occurrence time and 40 seconds after the event occurrence time.

In step S350 , the controller 150 of the image recording apparatus 100 analyzes the generated event image to analyze the motion pattern of the subject. The motion pattern may include an appearance position of the subject and a movement trajectory of the subject.

The controller 150 of the image recording apparatus 100 analyzes the event image to determine the appearance position and movement trajectory of the subject, and compares it with a preset motion pattern model to check whether there is an associated motion pattern model.

If there is an associated motion pattern model, an identifier assigned to the corresponding motion pattern model is extracted in step S370, and the extracted identifier is inserted into the corresponding event image. Preferably, the identifier is inserted into the first part of the event image and stored in the second memory 130 .

When a request for a search for an event video of a specific motion pattern is received through an event video search interface in step S380, a plurality of stored event videos are searched for based on the identifier in step S390. An event image including an identifier corresponding to the specific operation pattern is selected.

In step S400 , the image recording apparatus outputs the selected event image to the display unit 160 .

When there are a plurality of selected event images, they may be output in ascending or descending order of time.

In an embodiment of the present invention, the image recording apparatus models a motion pattern based on deep learning and continuously learns an image by continuous video recording and event occurrence, thereby continuously strengthening the function of determining the motion pattern.

According to an embodiment of the present invention, since a user can selectively reproduce only an image for a specific event through the image recording device, an image search time can be effectively shortened.

Operations by the image recording apparatus, the image providing apparatus, and the method according to the above-described embodiments may be implemented, at least in part, by a computer program. Here, the program for implementing the present embodiment is configured in the form of functional program instructions and codes that can be executed in the arithmetic device. The computing device is a device having one or more alternative and special purpose processors, memory, storage, and networking components (either wireless or wired). The computing device may run, for example, an operating system compatible with Microsoft's Windows, Apple OS X or iOS, a Linux distribution, or an operating system such as Google's Android OS.

The operations described above and their associated units, modules, etc. may be implemented in software, firmware, hardware, or any combination thereof. For example, a software module may be implemented with a program product consisting of a computer-readable medium containing program code, which may be executed by a processor for performing any or all steps, operations, or processes described. .

Functional program instructions and codes for implementing the present embodiment may be easily understood by those skilled in the art to which this embodiment belongs.

In addition, operations performed by the image recording apparatus and the image providing apparatus and method may be recorded in a computer-readable recording medium. A computer-readable recording medium in which a program for implementing the operation by the image recording apparatus, the image providing apparatus and the method according to the embodiments is recorded and includes all types of recording devices in which computer-readable data is stored do. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed in network-connected computer systems, and the computer-readable code may be stored and executed in a distributed manner.

Although the present invention as described above has been described with reference to the embodiments shown in the drawings, it will be understood that these are merely exemplary and that various modifications and variations of the embodiments are possible therefrom by those of ordinary skill in the art. However, such modifications should be considered to be within the technical protection scope of the present invention. Accordingly, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

Claims

In the event video providing method of the video providing device,

acquiring a photographed image according to the occurrence of an event;

analyzing a motion pattern of a moving subject in the acquired image;

inserting and storing identification information of the motion pattern of the subject into the image according to the analysis result; and

receiving a signal for requesting the image search, and searching for and providing an image based on the identification information;

A method of providing an event video comprising a.
According to claim 1,

The step of acquiring the event image taken while the parking state of the vehicle is maintained,

The event image providing method, characterized in that the event image is obtained by receiving the event image from an image recording device mounted on a vehicle or by accessing a memory of the image recording device.
According to claim 1,

The step of analyzing the motion pattern of the moving subject,

detecting a moving subject in the image; and

Determining a motion pattern using deep learning technology based on the detected subject's appearance location and movement trajectory

Event video providing method comprising a.
4. The method of claim 3,

The step of determining the motion pattern using the deep learning technology is,

An event image providing method, characterized in that the motion pattern model corresponding to the motion of the subject is determined by applying the detected appearance position and movement trajectory of the subject to the modeled motion pattern classified based on a plurality of training samples.
5. The method of claim 4,

The plurality of training samples include an appearance position and movement trajectory of the subject,

The operation pattern model is an event image providing method, characterized in that it includes identification information for pattern identification.
an image acquisition unit for acquiring a photographed image according to the occurrence of an event;

a pattern analyzer for analyzing a motion pattern of a moving subject in the acquired image;

a controller for inserting and storing identification information of the motion pattern of the subject into the image according to the analysis result, and searching for an image based on the identification information; and

A display unit for outputting the searched image according to the instruction of the control unit

An event video providing device comprising a.
7. The method of claim 6,

a storage unit for storing the image in which identification information of the motion pattern of the subject is inserted;

An event video providing device further comprising a.
7. The method of claim 6,

The control unit receives a signal for requesting an image search from an external terminal, searches for an image based on the identification information, and controls to transmit the searched image to the external terminal.
7. The method of claim 6,

The control unit detects a moving subject from the acquired image, and determines an operation pattern using deep learning technology based on the detected position of appearance and movement trajectory of the subject.
10. The method of claim 9,

The control unit applies an appearance position and movement trajectory of the detected subject to a modeled motion pattern classified based on a plurality of training samples to determine a motion pattern model corresponding to the motion of the subject. Device.
One or more camera units for capturing real-time images;

an input unit for converting a user's input operation into an input signal; and

Analyze the image to monitor the event occurrence, generate an image of a preset time when an event occurs, analyze the motion pattern of the moving subject in the generated image, and generate identification information of the motion pattern of the subject according to the analysis result in the image Control unit to be inserted and saved in

including,

The control unit receives an event image search request signal from the input unit, and searches for and provides an image based on the identification information.
12. The method of claim 11,

a first memory unit for temporarily storing the image captured by the camera unit; and

a second memory unit configured to store an event image generated by the occurrence of an event along with the identification information according to an instruction of the control unit;

Event video recording apparatus further comprising a.
12. The method of claim 11,

The controller is an event video recording apparatus, characterized in that when a moving subject is detected in the real-time image, it is considered that an event has occurred.
14. The method of claim 13,

The control unit is an event video recording apparatus, characterized in that for determining the motion pattern using a deep learning technology based on the detected position and movement trajectory of the subject.
15. The method of claim 14,

The control unit determines a motion pattern model corresponding to the motion of the subject by applying the detected appearance position and movement trajectory of the subject to the modeled motion pattern classified based on a plurality of training samples. Device.