KR102512360B1 - Filter information providing method for preventing mis-detection during tracking a moving target and electronic device using the same - Google Patents

Abstract

A method of providing target information in an electronic device according to various embodiments of the present disclosure comprises: a step of generating a plurality of target candidate filters for tracking a plurality of target candidates; a step of confirming at least one first target candidate filter among the plurality of target candidate filters based on a degree of overlap with other filters for each of the plurality of target candidate filters; a step of identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter; a step of confirming a target candidate filter whose reliability value is equal to or greater than a threshold among the at least one second target candidate filter as a final target filter; and a step of providing information about targets corresponding to the final target filter. Accordingly, the present invention can reduce miscapture due to movement of the target.

Description

Method for providing filter information for preventing misacquisition when tracking a moving target and electronic device using the same

Various embodiments of the present disclosure relate to a method for providing filter information for preventing misacquisition when tracking a moving target and an electronic device using the same.

In order to detect or track a moving target through infrared imaging, many tracking filters are used. In general, image-based detection or tracking of a moving target requires a technique for predicting an instantaneous change of an object along with frame analysis using an image stream that changes in real time. Through analysis of individual frames, a target in motion is detected and a positional change is calculated to extract information such as a moving direction and a moving distance of the target, and the target can be tracked through this.

In an actual embedded environment, methods that are widely used to detect or track a moving target include a nearest neighbor (NN) method that calculates the measurement value closest to the predicted value using the distance information of the measurement value as the measurement value generated from the target; There is a method using signal strength instead of using location information for data association, and a method of determining a measurement having the highest signal strength as a target and tracking it (strongest neighbor). In addition, the phase detection auto focus (PDAF) algorithm generates track candidates for m valid measurements of time k, calculates their track presence probabilities, and if this value exceeds a certain threshold The candidate can be judged as a target. A filter that is mainly used for tracking a moving target is a Kalman filter, and the Kalman filter can be optimally utilized in a linear or Gaussian noise situation. The Kalman filter has the advantage of analytically obtaining the posterior distribution for state variable estimation.

Recently, as the processing speed and throughput of computer calculations have rapidly increased, a method of tracking a moving target using block matching, optical flow, particle filter, and the like has been further demanded.

It may be difficult to accurately acquire a moving target with only the above conventional methods. When a target is detected by receiving image data from an infrared sensor, not only information about the target is received, but also measurement values of the false target are also received. That is, noise may be received together.

It is necessary to extract only the information about the true target from among multiple measurements, create a tracking track on the target, and quickly remove the false target. That is, in order to continuously track a moving target, it may be necessary to continuously track a true target while sensitively removing false targets.

The technical problem to be achieved by the present embodiment is not limited to the technical problems described above, and other technical problems can be inferred from the following embodiments.

A method for providing target information in an electronic device according to various embodiments of the present disclosure includes generating a plurality of target candidate filters for tracking a plurality of target candidates, and filtering a different filter for each of the plurality of target candidate filters. Identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree of, at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. Identifying at least one second target candidate filter among the at least one first target candidate filter based on, selecting a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter. and providing information about a target corresponding to the final target filter.

An electronic device for acquiring a moving target according to various embodiments of the present disclosure includes a memory and a processor, wherein the processor generates a plurality of target candidate filters for tracking a plurality of target candidates, and the plurality of target candidate filters. For each, at least one first target candidate filter is identified from among the plurality of target candidate filters based on the degree of overlap with other filters, and the inter-frame movement distance and inter-frame movement distance for each of the at least one first target candidate filter are determined. Based on at least one of the moving directions, at least one second target candidate filter among the at least one first target candidate filter is identified, and a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter It can be configured to identify a final target filter and provide information about a target corresponding to the final target filter.

A non-transitory computer readable storage medium according to various embodiments of the present disclosure includes a medium configured to store computer readable instructions, and when the computer readable instructions are executed by a processor, the processor causes a plurality of target candidates. Generating a plurality of target candidate filters for tracking, identifying at least one first target candidate filter among the plurality of target candidate filters based on the degree of overlap with other filters for each of the plurality of target candidate filters. identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter; identifying a target candidate filter having a reliability value greater than or equal to a threshold among the at least one second target candidate filter as a final target filter, and providing information about a target corresponding to the final target filter. , it is possible to perform a target information providing method.

According to an embodiment of the present disclosure, one or more of the following effects may exist. It monitors the moving distance and direction of the filter in real time to check whether the filter is moving abnormally, and when the filter moves to a higher value than the set threshold or moves in various directions, the filter is deleted to prevent false target misacquisition. can

According to an embodiment of the present disclosure, tracking can be performed adaptively in response to a change in size and movement of a target by dynamically adjusting a moving speed and an expansion speed of a filter according to a direct distance to a moving target. In addition, when filters are duplicated for one target, it is possible to track the true target by deleting filters with low reliability while maintaining filters with high reliability.

According to various embodiments of the present disclosure, in order to prevent misacquisition when tracking a moving target, only one true target can be finally tracked by distinguishing between a false target and a true target. Check whether the filter moves in a certain direction, whether the distance the filter moves between frames is below a certain threshold value, and if multiple filters overlap, delete or maintain the reliability value and consider the direct distance when first detecting a moving target. A filter that reaches the selection threshold first is checked as a filter for the true target, thereby reducing misacquisition due to the movement of the target.

The effects of the embodiments are not limited to the effects described above, and other effects not described can be clearly understood by those skilled in the art from the description of the claims.

1 is a block diagram of schematic components of an electronic device according to various embodiments of the present disclosure.
2 is a schematic flowchart of a method for providing target information according to various embodiments of the present disclosure.
3 is an exemplary diagram for identifying a first target candidate filter according to various embodiments of the present disclosure.
4A to 4C are exemplary diagrams for identifying a second target candidate filter according to a moving distance according to various embodiments of the present disclosure.
5A and 5B are exemplary diagrams for identifying a second target candidate filter according to a movement direction according to various embodiments of the present disclosure.
6A to 6C are exemplary diagrams for identifying a final target candidate filter according to various embodiments of the present disclosure.
7 is a flowchart of filter size adjustment according to various embodiments of the present disclosure.
8A and 8B are exemplary diagrams related to the flow of FIG. 7 .

The terms used in the embodiments have been selected as general terms that are currently widely used as much as possible while considering the functions in the present disclosure, but they may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technologies, and the like. In addition, in a specific case, there are also terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the corresponding description. Therefore, terms used in the present disclosure should be defined based on the meaning of the term and the general content of the present disclosure, not simply the name of the term.

In the entire specification, when a part is said to "include" a certain component, it means that it may further include other components, not excluding other components unless otherwise stated. In addition, terms such as "...unit" and "...module" described in the specification mean a unit that processes at least one function or operation, which is implemented as hardware or software, or a combination of hardware and software. It can be.

The expression of “at least one of a, b, and c” described throughout the specification means 'a alone', 'b alone', 'c alone', 'a and b', 'a and c', 'b and c' ', or 'all of a, b, and c'.

A “terminal” referred to below may be implemented as a computer or portable terminal capable of accessing a server or other terminals through a network. Here, the computer includes, for example, a laptop, desktop, laptop, etc. equipped with a web browser, and the portable terminal is, for example, a wireless communication device that ensures portability and mobility. , IMT (International Mobile Telecommunication), CDMA (Code Division Multiple Access), W-CDMA (W-Code Division Multiple Access), LTE (Long Term Evolution), etc. It may include a handheld-based wireless communication device.

Hereinafter, with reference to the accompanying drawings, embodiments of the present disclosure will be described in detail so that those skilled in the art can easily carry out the present disclosure. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein.

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

In describing the embodiments, descriptions of technical contents that are well known in the technical field to which the present invention pertains and are not directly related to the present invention will be omitted. This is to more clearly convey the gist of the present invention without obscuring it by omitting unnecessary description.

For the same reason, in the accompanying drawings, some components are exaggerated, omitted, or schematically illustrated. Also, the size of each component does not entirely reflect the actual size. In each figure, the same reference number is assigned to the same or corresponding component.

Advantages and features of the present invention, and methods for achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numbers designate like elements throughout the specification.

At this time, it will be understood that each block of the process flow chart diagrams and combinations of the flow chart diagrams can be performed by computer program instructions. These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment are described in the flowchart block(s). It creates means to perform functions. These computer program instructions may also be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular way, such that the computer usable or computer readable memory The instructions stored in are also capable of producing an article of manufacture containing instruction means that perform the functions described in the flowchart block(s). The computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to generate computer or other programmable data processing equipment. Instructions for performing processing equipment may also provide steps for performing the functions described in the flowchart block(s).

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative implementations it is possible for the functions mentioned in the blocks to occur out of order. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may sometimes be executed in reverse order depending on their function.

1 is a block diagram of schematic components of an electronic device according to various embodiments of the present disclosure.

Referring to FIG. 1 , internal components of the electronic device 100 are not limited to the illustrated components. The electronic device 100 may include a processor 110 and a memory 120, and may include other components such as a communication module for transmitting and receiving data.

The electronic device 100 may include a computer, a server, a radar device, and the like, and may include an infrared sensing device or system for tracking a moving target. For example, the electronic device 100 may manage an infrared target tracking system.

The processor 110 may process a series of steps for performing a method for accurately acquiring a target of the electronic device 100 performing various target information providing methods of the present disclosure. The processor 110 may control other elements of the electronic device 100 .

The memory 120 is a data structure implemented in a predetermined storage space of the electronic device 100, and functions such as storing, searching, deleting, editing, or adding data can be freely performed. For example, the memory 120 may include fields or elements for processing functions such as storage, search, deletion, editing, or addition of data. The memory 120 may store data related to performing a method in which the electronic device 100 acquires a moving target and provides information on the target. For example, the memory 120 may store instructions or data for an execution operation of the processor 110 .

The communication module performs a function of transmitting information stored in the memory 120 of the electronic device 100 or information processed by the processor 110 to another device or receiving information from another device to the electronic device 100. is a number For example, the electronic device 100 may transmit or receive signals with other devices or the outside through a communication module.

2 is a schematic flowchart of a method for providing target information according to various embodiments of the present disclosure.

In S201, the electronic device (eg, the electronic device 100 of FIG. 1) may create a target filter for tracking the moving target. For example, the target may be a moving ship. The electronic device captures an object that can be the final target through an infrared sensor or sensor module, etc., sets it as one final target based on the moving direction, moving speed, moving distance, etc. of the captured target and tracks its movement. can

An electronic device according to an embodiment may be an infrared radar device. The electronic device may check an image of an object whose motion is to be tracked as an image through an infrared sensor or the like, and the image may be captured according to a set frame.

According to an embodiment, the electronic device may create filters for individual targets. Filters for individual targets may be filters created to identify possible final targets. A filter for an individual target is described as a target candidate filter until it is identified as a filter for the final target. For example, a target candidate filter is a filter that identifies objects that are likely to be set as filters for the final target. A target candidate filter has a central point of the filter, and at least one target candidate filter may be generated for one target candidate.

According to an embodiment, the target candidate filter may be generated by matching the center point of the candidate target with the center point of the target candidate filter. The center point of the candidate target may refer to a center point determined by the electronic device in the image of the candidate target. For example, the center point of the candidate target may be the center point calculated through the first component (eg, x coordinate) and the second component (eg, y coordinate) of a bounding box having a minimum size that may include the candidate target. can This may be equally or similarly applied to the center point of the target candidate filter. The electronic device may create a target candidate filter in the form of a bounding box enclosing all target candidates.

In S202, the electronic device may perform a center area inspection of a plurality of target candidate filters. The center area check includes checking whether or not the center point of at least one target candidate filter (eg, the second filter) other than the target candidate filter is present within a predetermined radius based on the center point of the target candidate filter (eg, the first filter). For example, the predetermined radius may be 10 pixels, but is not limited thereto.

According to an embodiment, the electronic device may check the first target candidate filter according to the result of checking the center region. The first target candidate filter may correspond to a reliability value that can be set as a final target candidate filter among a plurality of first target candidate filters.

In an embodiment, the confidence value may be checked frame by frame for a plurality of target candidate filters. The electronic device may calculate and store a reliability value for each of a plurality of target candidate filters in a series of processes of setting a final target filter. The reliability value may be calculated by an equation that may be set by a manager or user of the electronic device. For example, the electronic device may calculate a reliability value for each of a plurality of target candidate filters until a predetermined reliability threshold is reached. When the reliability value is equal to or greater than the preset reliability threshold, that is, when the reliability value reaches the preset reliability value for the first time, the electronic device may set the corresponding target candidate filter as the final target candidate filter.

In S203, the electronic device may check whether target candidate filters overlap. If there are more than a preset number of center points of the target candidate filters within a certain radius, in S204, the electronic device determines that the reliability value is the highest among the target candidate filters (eg, the first filter) and other target candidate filters (eg, the second filter). A high target candidate filter (eg, first filter) may be set as the first target candidate filter. That is, the electronic device maintains the target candidate filter (eg, first filter) having the highest reliability value, and determines that the remaining target candidate filters (eg, second filter) are not target candidate filters for the corresponding target and deletes them. . According to an embodiment, the electronic device may perform inspection of the center area of the filter every frame.

In S205, the electronic device may check whether the filter moves in a certain direction. The electronic device may check the center point coordinate value of the target candidate filter in every frame. The coordinate values include a first component and a second component, and the first component and the second component may be coordinate values of x and y components, respectively.

According to an embodiment, the electronic device may check the movement count based on the first component difference and the second component difference of the center point coordinate values between frames of the first target candidate filter. The movement count increases when the target candidate filter moves in a certain direction (S206) and decreases when it does not move in a certain direction (S207).

In S208, the electronic device may check the inter-frame movement count of the first target candidate filter to determine whether the movement count of the corresponding target candidate filter exceeds 2. If the movement count does not exceed 2, the electronic device may maintain the corresponding target candidate filter (S209). If the movement count exceeds 2, the electronic device may delete the corresponding target candidate filter (S210). That is, the electronic device can determine whether the target candidate filter moves in a certain direction based on the inter-frame movement count for a certain period.

According to an embodiment, the electronic device may determine whether the first target candidate filter moves in a certain direction by using Equation (1) below. The electronic device may increase the movement count when Equation (1) is satisfied for both the first component and the second component for a frame within a certain period.

In Equation (1), X _{count (+)} corresponds to counting the number of times that the difference between the first components of the center point coordinate values between frames is a positive value, and X _{count (-)} corresponds to counting the number of negative values do. Y _{count (+)} corresponds to counting the number of times the difference between the second components of the center point coordinate values between frames is a positive value, and Y _{count (-)} corresponds to counting the number of times the difference is a negative value. The positive or negative count of the difference between each first component and the second component is counted through the total number of frames from the first frame to the second frame (eg, the first frame and the last frame within a certain period). . For example, a total of 10 frames may exist from the first frame to the second frame, a total of 9 motion counts may be possible, and the number of motions in the positive direction on the first component is 6 motions in the negative direction. When the number of times of checking is 3, the electronic device may decrease the movement count by determining that the first component is moved in a certain direction. The electronic device may decrease the movement count only when Equation (1) is satisfied for both the first component and the second component. The electronic device may identify a first target candidate filter having a movement count of 2 or less as a second target candidate filter through movement count calculation for consecutive frames of a predetermined period.

According to the embodiment, if a positive value is obtained by differentiating the first component of the target candidate filter of the previous frame and the first component of the current frame, the X _{count (+)} increases by 1, and if a negative value is obtained, the X _{count (-)} 1 goes up. The electronic device may check whether the target candidate filter moves in various directions. Through this, by deleting the target candidate filter exhibiting an abnormal motion, the electronic device can reduce the risk of erroneous capture of a false target.

According to an embodiment, the moving target candidate filter may move in a certain direction in 10 frames or 20 frames. For example, when a target candidate filter moves in a certain direction, the electronic device may increase a reliability value to set the corresponding target candidate filter as a final target candidate filter. The increase range of the reliability value may be set by a manager of the electronic device. The final target candidate filter may correspond to the true target. For another example, if the target candidate filter moves in various directions, the electronic device may determine the corresponding target candidate filter as a filter for a false target and delete the corresponding target candidate filter so as not to provide the information any longer.

In S211, the electronic device may check whether the movement distance between frames is less than a threshold value. When the inter-frame movement distance is less than a preset threshold, the electronic device may identify the corresponding target candidate filter as the second target candidate filter. For another example, when the movement distance between frames is equal to or greater than a preset threshold, the electronic device may delete the corresponding target candidate filter (S210).

According to the embodiment, when the electronic device uses a filter for a target detected in an image of a target being photographed, a misacquisition situation may occur in which tracking is intermittently performed on a false target. In order to solve this problem, the electronic device uses the characteristics of the moving target to determine the final target 1 using the condition that it moves below a specific speed value in the video, the condition that it moves in a certain direction, and the condition that there is only one true target. Only dogs can be selected and tracked.

According to an embodiment, since the moving target candidate filter moves at a certain speed or less within an image, it may not deviate from a certain range between the current frame and the previous frame. A threshold value for the moving distance is set using the maximum speed of the target candidate filter moving between frames, and if it is greater than or equal to the preset threshold value, the corresponding target candidate filter is deleted because it is an abnormal movement, and if it is less than the preset threshold value You can keep the filter on.

According to an embodiment, the electronic device may calculate the moving distance limiting threshold of the target candidate filter as shown in Equation (2) in consideration of the maximum speed and slant range (SR) of the moving target.

In Equation (2), the moving distance threshold (eg, set threshold) of the first target candidate filter is the maximum speed (V) of the first target candidate filter, the frame frequency (F) of the first target candidate filter , the direct distance (SR) of the first target candidate filter, the instantaneous field of view (IFov) of the first target candidate filter, and the limiting value (M). The units of indicators included in Equation (2) are, for example, the maximum speed (m/s) of the first target candidate filter, the frame frequency (Hz) of the first target candidate filter, and the serial number of the first target candidate filter. It may correspond to the distance (m), the instantaneous viewing angle (rad) between frames of the first target candidate filter, and the limiting value (1/rad). The limit value corresponds to a kind of experimental value, and different experimental values may exist depending on the target. The electronic device may apply the limit value by classifying the type of target set by the manager or the type of captured target.

According to an embodiment, the electronic device calculates a movement distance restriction threshold of a first target candidate filter, calculates a movement distance from a position of the first target candidate filter in a previous frame to a position of the first target candidate filter in a current frame, and If the distance traveled is greater than or equal to the threshold value, the corresponding filter can be deleted. That is, the electronic device generally sets the distance that the target candidate filter can move for a predetermined time as a threshold value, so that when the movement distance of the target candidate filter is greater than or equal to the threshold value, the electronic device can identify the target candidate filter as a false target. For another example, when the distance moved is less than the threshold value, the electronic device may continuously track the target by maintaining a corresponding target candidate filter. That is, when the moving distance of the target candidate filter is less than the threshold value, the electronic device may determine that the electronic device is highly likely to be a true target.

According to an embodiment, the electronic device may perform a series of operations of S205 to S211 in parallel. The electronic device may identify, as a second target candidate filter, a first target candidate filter in which a movement distance between frames is less than a preset threshold and a movement count of a first component difference and a second component difference of center point coordinate values between frames is 2 or less. there is.

According to an embodiment, the electronic device updates a reliability value for each of the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. can do. This may be performed after S209 and between S211 and S212. In addition, reliability values of the plurality of target candidate filters may be continuously updated in the processes from S202 to S212. That is, the electronic device may check the reliability value of each of the plurality of target candidate filters in order to set the final target filter.

According to the embodiment, when the reliability value of each of the second target candidate filters is less than the reliability threshold value in performing the operations up to S212, the electronic device may return to S202 and perform operations on the second target candidate filters. . That is, the electronic device may perform an iterative process by returning to S202 after S212 until the operation of S213 for confirming the final target filter is performed.

In S212, the electronic device may check whether the reliability value of at least one second target candidate filter is greater than or equal to a threshold value. The electronic device may check the threshold based on the direct distance in the first frame of the second target candidate filter.

According to an embodiment, when the electronic device starts detecting a moving target, when a large distance to the target remains, the electronic device may capture the moving target in a small size every week. In this case, the target must be determined carefully while updating the reliability value using a large number of frames. The electronic device may set a high threshold for selection of a final target filter for determining a moving target, and may set the final target filter as a final target filter when a reliability value that increases every frame is greater than or equal to the threshold.

According to the embodiment, the electronic device may perform operations of S202 after S212, but may perform operations from S201 by creating a new filter for a plurality of targets. This may correspond to a case in which the reliability value of the second target candidate filter is significantly lower than the reliability threshold value and is not worthy of being set as the final target filter.

According to the embodiment, when the distance to the moving target is short, the electronic device can capture the target in the image in a large size while reducing the number of frames that can be utilized until detection is confirmed. In this case, since the intensity of the signal is also greater than that in the case of a long distance, the moving target can be determined as the final target even if a certain reliability value is secured. Since the electronic device cannot proceed to the final tracking mode even if the moving target is properly detected if the threshold for final target filter selection from short distance to final is large, the electronic device can dynamically adjust the threshold of the final target filter according to the direct distance. .

According to an embodiment, the electronic device may set a final target filter through a threshold value according to Equation (3).

In Equation (3), SR is a direct distance, and C is an experimental value and may be a constant. In addition, the reference value may be applied only when the direct distance is 1000 m or more. According to the embodiment, when there is one second target candidate filter whose reliability value is greater than or equal to the threshold value, the electronic device determines tracking through the remaining second target candidate filters as misacquisition (e.g., false targets). so) the remaining second target candidate filters may be deleted.

In S213, the electronic device may check the final target filter. The electronic device may set one target candidate filter having a reliability value of the second target candidate filter equal to or greater than a threshold value as a final target filter. In S214, the electronic device may provide tracking information on a target corresponding to the final target filter. The tracking information may include tracking information of the entire process for the target of the corresponding filter set as the final target filter in all processes of FIG. 2 and tracking information after being set as the final target filter.

3 is an exemplary diagram for identifying a first target candidate filter according to various embodiments of the present disclosure.

Referring to FIG. 3 , an electronic device (eg, the electronic device 100 of FIG. 1 ) may create three filters for one target. Each filter may correspond to the first filter 310 , the second filter 320 , and the third filter 330 . The electronic device may check whether or not a preset number (eg, two) or more of the center points of other filters exist within a predetermined radius from the center point of each filter with respect to the moving target. If there are more than a predetermined number, the electronic device may check the reliability value of each target candidate filter and identify a target candidate filter having the highest reliability value as the first target candidate filter. The overlapping inspection area shown in FIG. 3 may be set within a certain radius (eg, within 10 pixels) from the center point of each target candidate filter, but is not limited thereto.

Referring to FIG. 3 , the electronic device may check the reliability value of the first filter 310 as 0.9, the reliability value of the second filter 320 as 0.5, and the reliability value of the third filter 330 as 0.3. That is, the electronic device may retain only the first filter 310 having the highest reliability value and delete the second filter 320 and the third filter 330 . This may correspond to the process of S202 to S204 of FIG. 2 . The electronic device may identify the first target candidate filter according to FIG. 3 .

4A to 4C are exemplary diagrams for identifying a second target candidate filter according to a moving distance according to various embodiments of the present disclosure. 4A to 4C may correspond to images of individual frames captured in the order of time. For example, FIG. 4A may be an image of a first frame, FIG. 4B may be an image of a second frame, and FIG. 4C may be an image of a third frame.

In FIG. 4A , the electronic device (eg, the electronic device 100 of FIG. 1 ) may check the first target candidate filter. 410 of FIG. 4A may indicate a state in which the electronic device identifies the first target candidate and checks the first target candidate filter.

Referring to FIG. 4B , 420 may mean a state in which the electronic device maintains the first target candidate filter. That is, 420 may correspond to a state in which the first target candidate filter in FIG. 4A is maintained by confirming that the movement distance is less than the threshold value for the inter-frame movement distance. The electronic device may determine the inter-frame movement distance of the first target candidate filter as 3 in consideration of the photographing time from FIGS. 4A to 4B. In this case, the electronic device may determine that the movement distance of the first target candidate filter is less than the threshold value and update the reliability value of the corresponding filter by increasing it. The electronic device continuously compares reliability values for each of the first target candidate filter and the second target candidate filter in S212 of FIG. 2, so that the reliability value after checking the moving distance as shown in FIG. In this case, branching to S213 may be performed to confirm the corresponding filter as the final target filter. That is, the electronic device can identify the corresponding target candidate filter as the final target filter at the moment when the reliability values of the plurality of target candidate filters are greater than or equal to the threshold value of the reliability values.

Referring to FIG. 4C , 430 may mean a state in which the electronic device deletes the first target candidate filter. That is, 430 determines that the filter created in FIG. 4a has moved by an excessive distance in the process of moving from FIG. 4b to FIG. 4c after confirming that the filter generated in FIG. can respond to the situation. The electronic device may determine the movement distance of the first target candidate filter as 15 in consideration of the photographing time from FIGS. 4B to 4C. In this case, the electronic device may determine that the movement distance of the first target candidate filter is equal to or greater than the threshold value, and may update the reliability value of the corresponding filter by decreasing it.

5A and 5B are exemplary diagrams for identifying a second target candidate filter according to a movement direction according to various embodiments of the present disclosure.

Referring to FIG. 5A , step 510 may correspond to an electronic device (eg, the electronic device 100 of FIG. 1 ) identifying a filter moving in a certain movement direction among first target candidate filters as a second target candidate filter. . This may be a normal movement because the movement of the filter is in a certain direction or in a somewhat consistent direction. The electronic device continuously compares reliability values for each of the first target candidate filter and the second target candidate filter in S212 of FIG. 2 , and after confirming the moving direction as shown in FIG. 5A, the reliability value reaches the reliability value threshold. In this case, branching to S213 may be performed to confirm the corresponding filter as the final target filter. That is, the electronic device can identify the corresponding target candidate filter as the final target filter at the moment when the reliability values of the plurality of target candidate filters are greater than or equal to the threshold value of the reliability values.

Referring to FIG. 5B , step 520 may correspond to the electronic device deleting the filters moving in various moving directions among the first target candidate filters. This may be an abnormal movement because the movement of the filter is in various directions or inconsistent directions.

6A to 6C are exemplary diagrams for identifying a final target candidate filter according to various embodiments of the present disclosure. This may be an example of a process in which the electronic device identifies a target candidate filter having a reliability value of at least one second target candidate filter equal to or greater than a threshold value as a final target candidate filter in S212 of FIG. 2 . 6A and 6B may be examples when the direct distance of the plurality of target candidate filters is 2000 m, and FIG. 6C may be an example when the direct distance of the plurality of target candidate filters is 3000 m. 6A and 6B show inter-frame reliability value updates of a plurality of target candidate filters according to the lapse of time. In the example of FIG. 6A, after a certain amount of time has passed, FIG. 6B may be an example.

Referring to FIG. 6A , when the direct distance is 2000 m, the electronic device (eg, the electronic device 100 of FIG. 1 ) may set the final target filter selection reference value (eg, the reliability threshold value) to 15. In FIG. 6A , since the reliability values of the plurality of target candidate filters 611, 612, 613, and 614 are 3, 5, 11, and 4, respectively, it is less than the reference value of 15. For example, the plurality of target candidate filters 611, 612, 613, and 614 of FIG. 6A are target candidate filters (eg, the first target candidate filter and the second target candidate filter) before branching from S212 to S213 of FIG. filters, etc.).

Referring to FIG. 6B , the electronic device may update the reliability value of each target candidate filter by performing operations S201 to S212 of FIG. 2 . Since the reliability values of the plurality of target candidate filters 621, 622, 623, and 624 of FIG. 6B are 5, 6, 15, and 3, respectively, in the same frame, the electronic device selects a filter whose reliability value is 15 or more, which is the threshold value of the reliability value ( 623) and the remaining filters 621, 622, and 624 may be deleted. That is, one filter 623 among the plurality of target candidate filters 621, 622, 623, and 624 of FIG. 6B may be the final target filter.

Referring to FIG. 6C , when the direct distance is 3000 m, the electronic device may set the final target filter selection reference value to 30. Here, the reference value corresponds to the threshold value set by Equation (3), and the reference value is set larger as the direct distance increases. This may be because the size of the target filter to be checked between frames is small when checking the final target filter for a target located relatively far away. In FIG. 6C, since the reliability values of the plurality of target candidate filters 631, 632, 633, and 634 are 6, 8, 22, and 17, respectively, the reference value is less than 30. For example, the plurality of target candidate filters 631, 632, 633, and 634 of FIG. 6C are target candidate filters (eg, the first target candidate filter and the second target candidate filter) before branching from S212 to S213 of FIG. filters, etc.). That is, even when the direct distance is 3000 m as shown in FIG. 6C, according to the update of inter-frame reliability values of the plurality of target candidate filters according to the lapse of time from FIGS. The filter can be identified as the final target filter.

Referring to FIGS. 6A to 6C , the direct distance of the plurality of target candidate filters may correspond to the first direct distance when generating the plurality of target candidate filters in S201 of FIG. 2 . For example, in FIGS. 6A and 6B , a direct distance is 2000 m, and a threshold value of a reliability value may be smaller than a direct distance (eg, 3000 m) classified as a relatively short distance. In the case of a short distance, since the size of a target candidate filter to be checked between frames may be larger than that of a target candidate filter located at a long distance, the electronic device sets the reliability value threshold to a small value (e.g., in Equation (3) above). based on the reference value), it is possible to check the final target candidate filter more quickly than the distant target candidate filter. As another example, FIG. 6C shows a case in which a direct distance is 3000 m, and a threshold value of a reliability value may be greater than a direct distance (eg, 2000 m) classified as a relatively long distance. In the case of a long distance, since the size of a target candidate filter to be checked between frames may be smaller than that of a target candidate filter located at a short distance, the electronic device sets the threshold of the reliability value to a large value so that the final target is slower than the target candidate filter at a short distance. You can check candidate filters. Accordingly, the electronic device may consume a relatively longer processing time for a distant target than for a short target in identifying the final target candidate filter.

7 is a flowchart of filter size adjustment according to various embodiments of the present disclosure.

In S710, the electronic device (eg, the electronic device 100 of FIG. 1 ) may check the filter size of each of a plurality of target candidate filters. The filter size may correspond to the area of the filter that includes the target.

In S720, the electronic device may set a filter size expansion threshold. A filter size expansion threshold may be set based on direct distances on frames of a plurality of target candidate filters. According to an embodiment, the target candidate filter may be designed to adjust the maximum distance that the target candidate filter can move between two consecutive frames and the maximum size that the target candidate filter can expand according to the direct distance.

In S730, the electronic device may adjust a filter size for each target candidate filter. The filter size is adjusted according to the expansion threshold. The expansion threshold is a kind of experimental value, and may be set in consideration of an area occupied by a target within the area of a generated target candidate filter.

According to the embodiment, when the direct distance is relatively long (eg, 2000 m or more), the electronic device needs to limit the maximum possible movement distance to be short based on the fact that the pixel movement amount of the target candidate filter is not large. When the target candidate filter misses the target, the electronic device must search for the moving target while expanding the target candidate filter to an appropriate size because the size of the moving target in the image is not large. If the target candidate filter is enlarged too much, the electronic device may erroneously capture a false target as a true target. To prevent this, the target candidate filter size may be expanded in consideration of the size of the target.

According to the embodiment, when the direct distance is relatively short (eg, less than 2000 m), the electronic device needs to increase the maximum possible movement distance based on the large pixel movement amount of the target candidate filter. The electronic device can greatly expand the size of the filter for re-detection within the image when the target candidate filter misses the corresponding target because the size of the image is large for a target at a short distance.

According to an embodiment, the electronic device may adjust the size of the target candidate filter in consideration of a long or short distance. This may be determined by comparison with an extension threshold set by a manager, and the electronic device may continuously adjust a filter size in order not to miss a moving target within an image through a target candidate filter. In addition, the electronic device can adjust the size of the final target filter in the same or similar manner.

8A and 8B are exemplary diagrams related to the flow of FIG. 7 . 8A is an exemplary diagram 810 when the direct distance is a long distance, and FIG. 8B is an exemplary diagram 820 when the direct distance is a short distance.

Referring to FIG. 8A , an electronic device (eg, the electronic device 100 of FIG. 1 ) may adjust a filter size according to a direct distance of a target candidate filter. For example, when the direct distance is 2000 m, the electronic device may determine the maximum movable distance by calculating the movable distance between the center points of the inter-frame filter, and expand the filter size considering the maximum movable distance.

Referring to FIG. 8B , when the direct distance is 1000 m, the electronic device may expand the filter size based on an expansion threshold different from that in FIG. 8A. Since FIG. 8B has a shorter direct distance than FIG. 8A , the electronic device may determine that the direct distance is shorter and expand the filter size to a size larger than the filter size in the long distance (eg, FIG. 8A ).

According to an embodiment, the electronic device may adaptively expand the size of the filter through a direct distance of a target moving between frames based on an expansion threshold set through an experimental value. Accordingly, the electronic device may position the target within a capturing area (eg, filter size) of a filter for capturing the moving target.

A method for providing target information in an electronic device according to various embodiments of the present disclosure includes generating a plurality of target candidate filters for tracking a plurality of target candidates, and filtering a different filter for each of the plurality of target candidate filters. Identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree of, at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. Identifying at least one second target candidate filter among the at least one first target candidate filter based on, selecting a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter. and providing information about a target corresponding to the final target filter.

In the method for providing target information in an electronic device according to various embodiments of the present disclosure, the checking of the first target candidate filter may include within a predetermined radius based on a central point of a target candidate filter among the plurality of target candidate filters. Checking whether or not the center point of at least one target candidate filter other than the target candidate filter exists, and if the center point of the at least one target candidate filter exists within the predetermined radius as a result of the check, the target candidate filter The method may include identifying a target candidate filter having the highest reliability value among filters and the at least one target candidate filter as a first target candidate filter.

In the method for providing target information in an electronic device according to various embodiments of the present disclosure, the checking of the second target candidate filter may include selecting a first target candidate filter having an inter-frame movement distance less than a preset threshold value as a second target candidate filter. It may include checking with a target candidate filter.

In the method for providing information on a target in an electronic device according to various embodiments of the present disclosure, a predetermined threshold value for a movement distance between frames is a maximum speed (V) of a first target candidate filter and a frequency of the first target candidate filter. (F), a slant range (SR) of the first target candidate filter, an instantaneous field of view (IFov) between frames of the first target candidate filter, and a limiting value (M).

In the method for providing target information in an electronic device according to various embodiments of the present disclosure, the checking of the second target filter may include determining a center point coordinate value between frames while an inter-frame movement distance is less than a predetermined threshold value. and identifying a first target candidate filter having a shift count of 1 component difference and a second component difference of 2 or less as a second target candidate filter.

A method for providing target information in an electronic device according to various embodiments of the present disclosure may include the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. The method may further include updating a reliability value for each of one first target candidate filter.

A method for providing information on a target in an electronic device according to various embodiments of the present disclosure includes checking the threshold based on a SR of the second target candidate filter, wherein C is the direct distance (SR) of the second target candidate filter. It may be a constant set according to the distance.

A method for providing target information in an electronic device according to various embodiments of the present disclosure includes the steps of checking a filter size of the plurality of target candidate filters, and expanding based on direct distances to each of the plurality of target candidate filters. The method may further include setting a threshold value and adjusting a filter size for each of the plurality of target candidate filters according to the expansion threshold value.

An electronic device for acquiring a moving target according to various embodiments of the present disclosure includes a memory and a processor, wherein the processor generates a plurality of target candidate filters for tracking a plurality of target candidates, and the plurality of target candidate filters. For each, at least one first target candidate filter is identified from among the plurality of target candidate filters based on the degree of overlap with other filters, and the inter-frame movement distance and inter-frame movement distance for each of the at least one first target candidate filter are determined. Based on at least one of the moving directions, at least one second target candidate filter among the at least one first target candidate filter is identified, and a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter It can be configured to identify a final target filter and provide information about a target corresponding to the final target filter.

A non-transitory computer readable storage medium according to various embodiments of the present disclosure includes a medium configured to store computer readable instructions, and when the computer readable instructions are executed by a processor, the processor causes a plurality of target candidates. Generating a plurality of target candidate filters for tracking, identifying at least one first target candidate filter among the plurality of target candidate filters based on the degree of overlap with other filters for each of the plurality of target candidate filters. identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter; identifying a target candidate filter having a reliability value greater than or equal to a threshold among the at least one second target candidate filter as a final target filter, and providing information about a target corresponding to the final target filter. , it is possible to perform a target information providing method.

On the other hand, preferred embodiments of the present invention have been disclosed in the present specification and drawings, and although specific terms have been used, 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. It is not intended to limit the scope of the invention. It is obvious to those skilled in the art that other modified examples based on the technical idea of the present invention can be implemented in addition to the embodiments disclosed herein.

An electronic device or terminal according to the above-described embodiments includes a processor, a memory for storing and executing program data, a permanent storage unit such as a disk drive, a communication port for communicating with an external device, a touch panel, and a key ), user interface devices such as buttons, and the like. Methods implemented as software modules or algorithms may be stored on a computer-readable recording medium as computer-readable codes or program instructions executable on the processor. Here, the computer-readable recording medium includes magnetic storage media (e.g., read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM) ), and DVD (Digital Versatile Disc). A computer-readable recording medium may be distributed among computer systems connected through a network, and computer-readable codes may be stored and executed in a distributed manner. The medium may be readable by a computer, stored in a memory, and executed by a processor.

This embodiment can be presented as functional block structures and various processing steps. These functional blocks may be implemented with any number of hardware or/and software components that perform specific functions. For example, an embodiment is an integrated circuit configuration such as memory, processing, logic, look-up table, etc., which can execute various functions by control of one or more microprocessors or other control devices. can employ them. Similar to components that can be implemented as software programming or software elements, the present embodiments include data structures, processes, routines, or various algorithms implemented as combinations of other programming constructs, such as C, C++, Java ( It can be implemented in a programming or scripting language such as Java), assembler, or the like. Functional aspects may be implemented in an algorithm running on one or more processors. In addition, this embodiment may employ conventional techniques for electronic environment setting, signal processing, and/or data processing. Terms such as “mechanism”, “element”, “means” and “composition” may be used broadly and are not limited to mechanical and physical components. The term may include a meaning of a series of software routines in association with a processor or the like.

The foregoing embodiments are merely examples and other embodiments may be implemented within the scope of the claims described below.

Claims (11)

A method for providing target information in an electronic device,
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
Further comprising updating a reliability value for each of the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. , how to provide target information. According to claim 1,
The step of identifying the first target candidate filter
checking whether a central point of at least one target candidate filter other than the target candidate filter exists within a predetermined radius based on the central point of the target candidate filter among the plurality of target candidate filters; and
As a result of the check, if there are more than a preset number of center points of the at least one target candidate filter within the predetermined radius, a target candidate filter having the highest reliability value among the target candidate filter and the at least one target candidate filter is selected as the first target. A method of providing target information, comprising identifying a candidate filter. A method for providing target information in an electronic device,
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
Checking the second target candidate filter
Checking a movement count according to whether the following Equation (1) is satisfied based on the first component difference and the second component difference between center point coordinate values between frames of the first target candidate filter; and
The movement count is decreased when the following Equation (1) is satisfied, and the movement count is increased when the following Equation (1) is not satisfied, so that the first target candidate filter having the movement count of 2 or less is converted into a second target Including the step of checking with a candidate filter,
X _{count (+)} and Y _{count (+)} in Equation (1) below correspond to the case where the difference between the first component and the difference between the second components of the center point coordinate values between frames is a positive value,
X _{count (-)} and Y _{count (-)} in Equation (1) below correspond to the case where the difference between the first component and the difference between the second components of center point coordinate values between frames is a negative value.
Equation (1)

According to claim 1,
Checking the second target candidate filter
A method of providing target information, comprising: identifying a first target candidate filter having an inter-frame movement distance less than a preset threshold as a second target candidate filter. A method for providing target information in an electronic device,
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
Checking the second target candidate filter
Identifying a first target candidate filter having an inter-frame movement distance less than a preset threshold as a second target candidate filter,
The preset threshold is the maximum speed (V) of the first target candidate filter, the frame frequency (F) of the first target candidate filter, the slant range (SR) of the first target candidate filter, and the first target candidate filter Based on an instantaneous field of view (IFov) and a limiting value (M) of , the target information providing method is determined by Equation (2) below.
Equation (2)

A method for providing target information in an electronic device,
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
Checking the second target candidate filter
Identifying a first target candidate filter having a movement distance between frames less than a predetermined threshold value and a movement count of a first component difference and a second component difference of center point coordinate values between frames of 2 or less as a second target candidate filter. How to provide target information. delete A method for providing target information in an electronic device,
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
The step of checking with the final target filter
Checking the threshold value by Equation (3) based on the straight distance (SR) of the second target candidate filter,
C in Equation (3) below is a constant set according to the direct distance, target information providing method.
Equation (3)

A method for providing target information in an electronic device,
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
checking filter sizes of the plurality of target candidate filters;
setting an extension threshold based on direct distances for each of the plurality of target candidate filters; and
The method of providing target information further comprising adjusting a filter size for each of the plurality of target candidate filters according to the expansion threshold. An electronic device for capturing a moving target,
Memory; and
contains a processor;
the processor,
create a plurality of target candidate filters for tracking the plurality of target candidates;
Identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with other filters for each of the plurality of target candidate filters;
Based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter, at least one second target candidate filter among the at least one first target candidate filter is identified;
Identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter;
configured to provide information about a target corresponding to the final target filter;
the processor,
Based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter, a reliability value for each of the at least one first target candidate filter is updated. As a non-transitory computer-readable storage medium,
a medium configured to store computer readable instructions;
The computer readable instructions, when executed by a processor, cause the processor to:
generating a plurality of target candidate filters for tracking the plurality of target candidates;
identifying at least one first target candidate filter among the plurality of target candidate filters based on an overlapping degree with another filter for each of the plurality of target candidate filters;
Identifying at least one second target candidate filter among the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. ;
identifying a target candidate filter having a reliability value greater than or equal to a threshold value among the at least one second target candidate filter as a final target filter; and
providing information about a target corresponding to the final target filter;
Further comprising updating a reliability value for each of the at least one first target candidate filter based on at least one of an inter-frame movement distance and an inter-frame movement direction for each of the at least one first target candidate filter. , A non-transitory computer-readable storage medium for performing a target information providing method.

Images