KR20140103023A - Method and electronic device for processing object - Google Patents

Abstract

The present invention relates to object processing. Disclosed are an object processing method, an object processing apparatus, and an electronic device supporting and a system supporting the same, wherein the method comprises the steps of: detecting mobile unity of objects in image information collected; and differently processing movement applications of the objects according to the size of the mobile unity.

Description

[0001] METHOD AND ELECTRONIC DEVICE FOR PROCESSING OBJECT [0002]

This disclosure relates to processing objects on an image in an electronic device.

In recent years, handsets have been supporting various user functions based on the development of hardware technology. For example, the image gathering function is one of the important functions of the terminal. As a result, studies on the usability and scalability of a variety of user functions related to the image collecting function have been actively conducted.

According to many embodiments of the present disclosure, this disclosure may provide improved object processing functionality.

According to an embodiment of the present disclosure, there is provided an image processing method comprising the steps of: detecting movement uniformity of objects in collected image information; and processing the movement application of the objects differently according to the size of the mobile unity. Method of the present invention.

The present disclosure also relates to a method and system for providing an object control module, including an input control module for supporting the reception of collected image information, a recognition module for recognizing image information provided by the input control module, an objectification module for extracting objects from the recognized image information, And an object tracking module for tracking movement of the objects, wherein the object tracking module processes the application of the objects differently according to the magnitude of the movement uniformity of the objects in the collected image information. .

The present disclosure also relates to an image processing apparatus including a main unit equipped with an object processing apparatus for processing the application of moving objects differently according to the magnitude of the mobility of objects in the collected image information, an input unit providing input information to the main unit, And a video output unit for outputting the image information, wherein the video output unit includes at least one of a memory, a CPU, and a digital watermark for data processing of the image data.

The present disclosure also relates to an electronic device for determining the mobility uniformity of objects based on an evaluation result of phase correlation results between previous image information and current image information and for differently applying the mobility application of the objects according to the magnitude of the mobility uniformity And a remote content database for storing contents to be output at the moved positions of the objects.

As discussed above, according to the present disclosure, this disclosure can support improved object processing functionality.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 schematically illustrates a configuration of an object processing apparatus supporting an object tracking function according to an embodiment of the present disclosure; FIG.
FIG. 2 is a detailed view of the configuration of the tracking module of FIG. 1; FIG.
3 is a diagram for explaining an object tracking method according to an embodiment of the present disclosure;
FIG. 4 is a view for explaining an object tracking situation according to the first embodiment of FIG. 3; FIG.
FIG. 5 is a view for explaining an object tracking situation according to the second embodiment of FIG. 3; FIG.
FIG. 6 is a view for explaining an object tracking situation according to the third embodiment of FIG. 3; FIG.
FIG. 7 is a diagram for explaining an approximation function applied during an object tracking function according to an embodiment of the present disclosure; FIG.
8 is a diagram schematically illustrating a system configuration supporting the object tracking function of the present disclosure;
Figure 9 is a block diagram of the arrangements of Figure 8;
10 schematically shows an example of an electronic device configuration to which an object processing apparatus of the present disclosure can be applied;
11 is a diagram exemplarily showing a configuration of a platform to which an object processing apparatus of the present disclosure can be applied;

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

In describing the embodiments, descriptions of techniques which are well known in the art to which this disclosure belongs and which are not directly related to the present disclosure are omitted. In addition, detailed description of components having substantially the same configuration and function will be omitted.

For the same reason, some of the elements in the accompanying drawings are exaggerated, omitted, or schematically shown, and the size of each element does not entirely reflect the actual size. Accordingly, the present disclosure is not limited by the relative size or spacing depicted in the accompanying drawings.

1 is a block diagram illustrating an object processing apparatus supporting an object tracking function according to an embodiment of the present disclosure. The object processing apparatus of the present disclosure described below can recognize a specific one of the elements included in the acquired image. The object processing apparatus of the present disclosure supports the tracking of recognized objects more smoothly. Such an object processing apparatus can be applied to various image processing techniques. The following description will be made based on a process in which the object processing apparatus supports the AR function. Accordingly, the object processing apparatus can be at least a part of an Augmented Reality Processing Device.

1, the object processing apparatus 100 of the present disclosure includes an input control module 110, a recognition module 120, a localization module 130, an object tracking module 130, (Tracking Module) < / RTI >

The object processing apparatus 100 may perform image processing on image information among the acquired input information. In this process, the object processing apparatus 100 can support the tracking function of the object included in the image. In particular, the object processing apparatus 100 can support intelligent movement application when object tracking function is supported. The intelligent movement application may include a procedure for determining whether to perform an additional object movement operation according to a result of the movement reliability of the objects included in the image. Based on this, the object processing apparatus 100 can more accurately determine the actual mobility of the objects included in the image. Then, the object processing apparatus 100 can perform the augmented reality contents application according to the movement of actual objects.

The input control module 110 may classify the input information provided to the object processing apparatus 100. [ The input control module 110 can determine the transfer route of the input information according to the function execution state of the object processing apparatus 100 at present. For example, the input control module 110 may provide the image information to the recognition module 120 when the initial image information is acquired. The image information may be obtained from an image sensor disposed in the terminal including the image sensor or object processing apparatus 100 connected to the object processing apparatus 100. [

The input control module 110 may transmit the image information to the object object tracking module 140 when the image recognition process by the recognition module 120 and the object classification process by the objectification module 130 are completed. Or the input control module 110 may simultaneously pass the image information to the recognition module 120 and the object tracking module 140. Accordingly, recognition processing and object tracking processing on image information may be performed in parallel.

The input control module 110 may control not to provide the image information to the recognition module 120 when the object tracking function is being performed. And the input control module 110 may assist in providing the image information to the recognition module 120 when the object tracking fails. The input control module 110 may also provide other input information, such as audio information or sensor information, to the object tracking module 140 when the AR content is applied to the objects being tracked.

When the recognition module 120 receives the image information from the input control module 110, the recognition module 120 can perform the recognition process. That is, the recognition module 120 may perform a feature detection process, a descriptor calculation process, and an image query process on the received image information.

Feature detection can be a collection process of feature points extracted from image information that has undergone a filtering process. At this time, the feature detection can be performed in various aspects according to various filtering information to be applied to the object processing apparatus 100. For example, in the feature detection process, the recognition module 120 may perform a discretization process for image information. The recognition module 120 may then apply certain predefined algorithms to the discretized information to process certain features.

The descriptor may be information that defines the characteristic of the corresponding image information calculated based on the detected feature points. Such a descriptor can be defined by at least one of the location of the feature points, the arrangement form between the feature points, and the intrinsic characteristics of the feature points in a predetermined part of the image information. That is, the descriptor may be a value obtained by simplifying the characteristic of a certain point of the image information. Therefore, at least one of the descriptors can be extracted from one piece of image information.

When the descriptor calculation is completed, the recognition module 120 can perform a comparison with reference data through an image query process. That is, the recognition module 120 can check whether there is reference data having the same descriptor as the calculated descriptors or descriptors within a certain error range. Reference data may be provided from an internal storage device provided for operation of the object processing apparatus 100. [ Or reference data may be provided from an external storage device such as a separate server device for operation of the object processing apparatus 100. [ The reference data may be image information that is stored beforehand for a specific image or immediately before acquiring image information currently being processed. For example, face recognition may require an external reference face database to recognize authenticated faces and identify different face differences. On the other hand, QR codes do not perform dramatic information updates in general. Therefore, only a specific rule for QR code recognition of the database is required, so that QR code can use internal reference data. The recognition module 120 can simplify the operation for the image recognition process by utilizing the reference data. The recognition module 120 may perform target object identification using reference data.

The objectification module 130 can identify various objects constituting the image information. This objectification module 130 may include Feature Matching and Initial Pose Estimation operations. That is, the objectification module 130 can extract the feature points of the objects classified in the image information. Then, the objectification module 130 may match the minutiae points of the specific objects with the constant objects of the reference data. At this time, the objectification module 130 may update the matching information if there is no matching information of the minutiae points. When the feature matching for the object is completed, the objectification module 130 may perform an initial angle evaluation of at least one object included in the image information. The objectification module 130 may provide the object tracking module 140 with object related information including at least one of matching information and initial angle information when the object processing apparatus 100 activates the object tracking function.

The object tracking module 140 receives the initial angular evaluation of the recognized target objects from the objectification module 130. And the object tracking module 140 may continuously maintain tracking through the angle operation of the target object. The object tracking module 140 may have a basic output of recognition information and object classification information included in the object angle. In particular, the object tracking module 140 of the present disclosure may apply an adaptive object movement operation based on the mobility of objects in the image information. For this, the object tracking module 140 may include a configuration as shown in FIG.

The object tracking module 140, described below, performs an operation of tracking at least one object contained on a plurality of digital images, wherein the digital images include a first image and a second image . In this case, the object tracking module 140 may be configured to determine phase correlation values between at least a portion of the first image and at least a portion of the second image, determining a position of a peak value, and using the peak value at least in part to determine a variance of the phase correlation values. And the tracking operation of the object tracking module 140 may include performing at least a portion of the variance value to perform the operation of tracking the at least one object differently.

The object tracking module 140 performs an operation of tracking the at least one object using a first process when the variance value is less than or equal to a selected value and if the variance value is greater than or equal to a selected value, The process may be used to perform an operation of tracking the at least one object.

Wherein the first process performs an operation of determining whether at least one object at a first location on a first image has moved to a second location on a second image and wherein the second location is determined using the location of the peak value .

The first process may include determining a pixel correlation between a region of a first location on the first image and a region of a second location on the second image. Wherein the first process may determine that the at least one object has moved from the first position to the second position if the pixel correlation is greater than or equal to a selected value. And the first process may perform tracking of the at least one object separately from the position of the peak value if it is determined that the at least one object has not moved from the first position to the second position.

Performing tracking of the at least one object separately from the position of the peak value may be an operation of performing a phase correlation operation on each of the at least one object with respect to the first image and the second image.

Wherein the second process is to perform tracking of the at least one object separately from the position of the peak value, wherein a phase correlation operation for each of the at least one object is performed on the first image and the second image Can be performed. Performing a phase correlation operation on each of the at least one object described above may be approximated to a selected form of the at least one object.

Hereinafter, each process of the object tracking module 140 described above will be described by giving a name corresponding to a certain configuration as an example and performing operations of the respective configurations.

FIG. 2 is a diagram illustrating the structure of the object tracking module 140 in FIG. 1 in more detail.

2, the object tracking module 140 includes an object angle predicting unit 141, a feature detecting unit 142, a descriptors calculating unit 143, And may include a matching unit 144 and a Pose estimation unit 145.

The object angle predicting unit 141 may predict the angle of at least one object included in the image information. The object angle prediction unit 141 may receive an initial angle evaluation value for at least one object included in the image information from the objectification module 130. [ Accordingly, the object angle predicting unit 141 can estimate the object angle according to the movement of the objects included in the image information based on the initial angle evaluation value of the objects. That is, the object angle predicting unit 141 can predict at which position and / or direction or angle at least one object included in the image information is moved based on the initial angle evaluation value.

More specifically, the object angle predicting unit 141 may calculate at least one of the degree of movement of the entire image information, that is, the moving distance, the moving direction, and the moving angle by comparing the previously obtained image information with the currently obtained image information have. The object angle predicting unit 141 may predict at least one object movement included in the image information based on the calculated movement level. For example, the object angle predicting unit 141 may perform phase correlation between a previous frame and a current frame. At this time, the object angle predicting unit 141 may perform a phase correlation operation by applying an FFT (Fast Fourier Transform) algorithm. Object angle prediction can be performed in real time.

Meanwhile, the object angle prediction unit 141 of the present disclosure can perform a reliability check of each object included in the previous frame and the current frames. The object angle predicting unit 141 may calculate the variance value of the phase correlation of the frames for determining the coherency. When the variance value of the phase correlation is within a predefined constant value and the moving direction of each object is valid, the object angle prediction unit 141 can predict that the objects included in the image information have moved to the predicted position. Accordingly, the object angle predicting unit 141 can control the movement distance, direction, and angle prediction through the phase correlation calculation. Here, when the movement prediction of the objects coincides with the actual movement, the object angle prediction unit 141 may determine that the object movement is effective. The validity of the moving direction of the objects can be provided from the angle evaluation unit 145.

The object angle predicting unit 141 can control to detect the actual moving direction of the objects when the variance value of the phase correlation calculation is within the predefined constant value range but the moving direction of each object is not valid. At this time, the object angle predicting unit 141 may perform phase correlation calculation by designating only objects whose movement direction is invalid, or may control to perform phase correlation of all objects.

On the other hand, the object angle predicting unit 141 can predict that the moving directions of the objects do not coincide with each other when the variance value of the phase correlation calculation deviates from the predefined constant value. In this case, the object angle predicting unit 141 may perform a phase correlation operation on each of the objects included in the image information. Then, the object angle predicting unit 141 can predict the movement distance and the direction based on the phase correlation calculation result.

When the object motion prediction unit 141 predicts the movement of the object, the feature detection unit 142 can detect the feature of the currently obtained image information. The feature detection of the image information performed by the feature detection unit 142 may be the same as the feature detection performed by the recognition module 120. [ Or the feature detection process performed by the feature detection unit 142 may be more simplified feature detection than the recognition module 120. [ That is, the feature detector 142 may perform a relatively smaller number of feature points extraction or a smaller number of feature points extraction than the feature detection performed by the recognition module 120 to support the movement tracking of the object.

The descriptor arithmetic section 143 can calculate the descriptor based on the feature detection result. The descriptor operation unit 143 may calculate descriptors based on the feature points detected by the feature detection unit 142 of the object tracking module 140. Here, the descriptor may be defined by a certain region or a predetermined number of feature points disposed on the image information. The descriptor operation unit 143 may provide the result to the feature matching unit 144 when the descriptor operation is completed.

The feature matching unit 144 may perform feature matching based on the descriptor calculated by the descriptor operation unit 143. [ That is, the feature matching unit 144 may perform a matching between a descriptor consisting of minutiae of a certain position of a previous frame and a descriptor consisting of minutiae of a certain position of the current frame.

The angle evaluating unit 145 may perform an evaluation as to how much the movement of the image information has occurred to some extent through the descriptor matching between the previous frame and the current frame. Based on this, the angle evaluating unit 145 can check whether the movement of the objects included in the image information coincide with each other by comparing the descriptors of the feature matching unit 144. At this time, the angle evaluating unit 145 may check whether the direction of movement of the objects included in the image information coincides with the predicted information.

The angle evaluating unit 145 can determine the movement valid state of the objects when the moving directions of the objects coincide with each other. If the object movement is valid, the angle evaluation unit 145 may apply the phase correlation calculation result to the tracking processing of the image information. Meanwhile, the angle evaluating unit 145 may perform image information correction when the moving directions of the objects do not match. The angle evaluating unit 145 may specify only objects having different moving directions to perform direction and distance correction of the objects. Or the angle evaluating unit 145 may perform direction and distance correction on all the objects included in the current image information.

The object tracking function based on the above-described uniformity of movement and the validity of the direction of movement of objects can be described in more detail with reference to FIG. 3 to FIG.

3 is a diagram for explaining an object tracking method according to an embodiment of the present disclosure. FIG. 4 shows an object tracking situation according to the first embodiment ("A") of FIG. 3, FIG. 5 shows an object tracking situation according to the second embodiment ("B" FIG. 8 is a diagram for explaining an object tracking situation according to the embodiment (" C ").

3 and 4 for the purpose of describing the first embodiment ("A") of the present disclosure, the object tracking method of the present disclosure is characterized in that the object tracking module 140 checks the image information obtained in operation 301 The object tracking module 140 of the present disclosure may perform phase correlation between the currently obtained image information and the previously acquired image information. In particular, the object tracking module 140 May detect movement of at least one object detected in advance in the current image information. The object tracking module 140 may perform image information comparison according to movement of the objects when motion of the objects is detected.

The object tracking module 140 can check whether the calculated mobile unity is equal to or greater than a reference value as a result of comparing the image information according to the movement of the objects in operation 305. [

In this case, the unity of movement may be an operation for confirming whether the moving directions of all the objects included in the image information are moved in the same or similar manner. For this purpose, the variance of the phase correlation between the current image information and the previous image information can be confirmed. When the resultant value in the two-dimensional evaluation region according to the phase correlation calculation for the entire image information appears as a peak value at a certain point, it may correspond to a case where the variance value is relatively low. If the variance value is low, the uniformity of movement can be regarded as high. If the phase correlation results of the entire image information are scattered rather than concentrated in the two-dimensional evaluation region, it may correspond to a case where the variance value is relatively high. If the variance value is high, it can be regarded as low coherence. The above-described variance value can be derived as a numerical value according to a certain calculation, and as a result, the mobile coherence can be regarded as corresponding to a certain value.

On the other hand, for the analysis of the uniformity of movement, a method of using phase correlation is described as an example, but the present disclosure is not limited thereto. That is, the above-mentioned mobility uniformity is a value indicating the extent to which the moving directions of the objects being tracked in the image information are the same or similar. Thus, a method capable of calculating the direction of movement of objects in image information can be used to analyze the mobile uniformity of the present disclosure. For example, the movement uniformity may be determined according to whether the plurality of objects randomly selected from the plurality of objects included in the image information or selected on a constant basis are moved in the same direction.

If the mobility uniformity is equal to or greater than the reference value in operation 305, the object tracking module 140 can check whether the movement of the objects is valid in operation 307. In step 305, a state in which the uniformity of movement is equal to or greater than the reference value may mean that the moving directions of the objects of the image information are substantially the same. The movement validation process of the objects in operation 307 may be a process of confirming whether the movement prediction information of the objects is valid. That is, the object tracking module 140 can predict the movement of objects in the image information and verify the prediction results as described above. The object tracking module 140 may check whether the corresponding object is actually located at the movement point predicted for the objects in operation 307. [ In this process, the object tracking module 140 may perform a selective object movement validity check on the objects being tracked included in the image information.

In more detail, the object tracking module 140 may track one or more objects from a plurality of objects being tracked in the image information. At this time, the object tracking module 140 may perform tracking on a main object of one or more objects. The dominant object may vary depending on the computation capability of the object tracking module 140. For example, a dominant object may be at least one object identified by a certain size or more among a plurality of objects classified in the image information.

Classification of objects can be performed by various information in image information. For example, if one or more boundary regions are included in the image information and at least one closed curved surface is formed by one or more boundary regions, the object tracking module 140 may classify the closed curved surface into one object. In addition, the object tracking module 140 may divide a predetermined region, which is different from the surrounding region, into objects even if the object is not a closed surface. In addition, the object tracking module 140 can divide a certain portion having shadow regions into objects in the process of analyzing image information. In addition, the object tracking module 140 may divide an area including a predetermined number or more of the descriptors described above or an area having a predetermined size or larger area analyzed by the descriptors into objects.

The object tracking method disclosed in this disclosure can assume a situation in which objects are separated in image information by performing an image information recognition and objectification process. The object tracking method of the present disclosure can provide a technique for supporting the tracking process of objects more efficiently in the above-described assumption situation. Therefore, the object tracking method of the present disclosure is not limited to the above-described object recognition and objectification processes. That is, the object tracking method of the present disclosure can be applied in a situation where objects are classified according to application of various object recognition and objecting methods.

On the other hand, when the mobility uniformity is equal to or greater than the reference value, it may correspond to a case where all the objects have substantially similar movement paths. In particular, the objects that occupy a relatively large area among the entire objects included in the image information will contribute relatively to the weight of the objects contributing to the unity of movement, as compared with other objects. Therefore, when the movement uniformity is equal to or greater than the reference value and the movement of the objects is not valid, there is a high probability that the moving directions of the objects having a relatively small area among all the objects included in the image information are different. Accordingly, when the object tracking module 140 determines the movement validity of the objects in operation 307, it is preferable that the object tracking module 140 performs the movement validity determination on the objects having a relatively small area among the objects included in the image information . For this, the object tracking module 140 may perform the movement validity determination by performing phase correlation operation on objects having a relatively small area in operation 307. [ Where the size of the predefined area may be determined or changed according to the intent of the designer or according to the experimental results.

If there is no dominant object in the image information, the object tracking module 140 may perform phase correlation calculation for each of the objects being tracked to perform movement validity determination. In the absence of the dominant object, a plurality of objects of similar size may be arranged in the image information. If multiple objects of similar size are placed, it is unlikely that an object will be able to distinguish accurately from the entire movement direction. Accordingly, the object tracking module 140 performs a phase correlation operation on each of the objects without performing a separate object designation in order to determine movement validity when there is no dominant object, or when objects of similar sizes are disposed, Can be performed. At this time, the object tracking module 140 may perform sampling on all the objects and determine the movement validity of all the objects based on the determination of the movement validity of the sampled objects.

If there are objects moved to the predicted point in operation 307, the object tracking module 140 regards that the object movement is valid and can perform the movement application of the objects in operation 309. [ That is, the object tracking module 140 may determine that the predicted result is correct and apply object tracking accordingly. The object tracking module 140 may also perform specific content application at the predicted point. For example, the object tracking module 140 may support the content output provided for the augmented reality application at the predicted point. In the operation 305 to operation 309, the movement of objects in the image information may correspond to the same state as shown in FIG.

In FIG. 4, three objects 41, 42, and 43 are arranged in the image information area 40. FIG. 4, the object tracking module 140 includes a plurality of objects 41, 42 and 43 such as a background object 43, a first object Obj1, 2 object (Obj2) 42. In this case, The background object 43, the first object 41 and the second object 42 may be selected in the recognition and objectification process for the image information 40. The object tracking module 140 may receive information about the objects 41, 42, and 43 from the objectification module 130.

4, the object tracking module 140 detects the phase difference between the current image information and the previous image information for the plurality of objects 41, 42, and 43 when tracking the plurality of objects 41, 42, The variance value calculation of the correlation calculation can be performed. The variance value of the phase correlation of objects having the same or similar moving directions can be calculated as a value concentrated at a certain point on a two-dimensional plane or a peak value at a certain point. If the direction of movement is different, the variance of the phase correlation may not be concentrated at a certain point but may appear as a scattered value in two dimensions. This property can be defined as the mobility uniformity with respect to the moving direction of the objects as described above. Therefore, since it is assumed that the moving directions of the objects 41, 42, and 43 coincide with each other in FIG. 4, a relatively high mobility uniformity value can be detected in calculating the variance value of the phase correlation.

4, when the background object 43, the first object 41, and the second object 42 are moved in the same direction, the object tracking module 140 detects an error according to the movement prediction result on the objects It is possible to perform movement tracking in a state in which it hardly occurs. Also, when the object mobility is high, the error of the mobility mapping of the actual object to the predicted position is small, so the amount of computation according to the mobility can be reduced. An example of a real situation when the object movement uniformity is high is movement of the image sensor or movement of the device equipped with the image sensor. That is, when the image sensor itself moves without moving the individual objects on the image corresponding to the subject, it may correspond to a situation where the object movement uniformity is high.

3 and 5 for a description of the second embodiment ("B") of the present disclosure. 3, if the mobility uniformity is equal to or greater than the reference value and there is no movement validity of the objects in operation 307, the object tracking module 140 branches to Operation 311, Respectively. If the mobility uniformity in operation 305 is equal to or greater than the reference value, the movement of the objects included in the image information may be substantially similar as described above. If there is no object movement validity in operation 307, it may correspond to a case where at least one of the objects included in the image information is different from the moving direction of all objects. Or if the object movement is not valid, it may correspond to the case where the actual object is not located at the predicted position in the object tracking process.

The object tracking module 140 can confirm the movement of all the objects being tracked in the image information and predict the movement of each object based on the movement. Then, the object tracking module 140 can check whether there are actual objects at the predicted positions. To this end, the object tracking module 140 may compare features of the location of the specific object with the characteristics of the predicted location of the current image information in the previous image information. If the location characteristic of the specific object of the previous image information differs from the predicted location characteristic of the current image information, the object tracking module 140 may determine that the object movement is not valid. In this process, the object tracking module 140 can check whether the actual object is located at the predicted position through the comparison of the at least one descriptor. Or the object tracking module 140 may perform a normalized cross correlation (NCC) comparison on the image to perform an actual object position check.

In operation 311, the object tracking module 140 may individually perform phase correlation of one or more objects included in the image information. In this process, the object tracking module 140 may perform a phase correlation operation on each of the objects being tracked included in the image information. Alternatively, the object tracking module 140 may specify certain objects among the entire objects being tracked included in the image information, and perform phase correlation of the specified objects. For example, the object tracking module 140 may specify objects that are not in motion enabled and may perform phase correlation operations on the specified objects.

On the other hand, if it is determined that there is no object movement validity, the object tracking module 140 performs an individual phase correlation operation on only objects having a relatively small area excluding the dominant objects among the objects being tracked included in the image information can do. Or the object tracking module 140 may perform an individual phase correlation operation on only objects having a predetermined size or smaller in the image information. This application process can be applied differently according to the object movement validity criterion. That is, when the actual position and the predicted position of the selected specific object are detected differently and the movement tracking module does not have the movement validity, the object tracking module 140 performs phase correlation operation for all objects, Can be performed. In this case, when the object tracking module 140 performs the phase correlation operation on some objects, the object tracking module 140 can perform processing on the objects other than the dominant object or processes on the objects having a region smaller than a predetermined size will be.

The object tracking module 140 may detect, in the current image information, a descriptor identical to at least one descriptor included in an object having a different moving direction from the previous image information. The object tracking module 140 can track the location of the corresponding object through checking the location of the matching descriptor. When the phase correlation calculation result for the object movement detection is derived, the object tracking module 140 can perform the movement correction of the designated objects according to the result value in operation 313 (Operation). After performing the motion compensation, the object tracking module 140 may support application of the augmented reality contents to the objects whose movement position, angle, and direction are corrected.

In operation 307, the object tracking module 140 may check movement effectiveness of certain objects without discriminating movement validity of each object. For example, the object tracking module 140 can check movement validity only for objects having an area smaller than a predetermined size in operation 307. [

5 illustrates an example in which the image information 40 includes a background object 43, a first object Obj1 41, and a second object Obj2 42. FIG. The moving direction of the first object 41 and the second object 42 may be different from the moving direction of all the objects. Here, the background object 43 may act as a leading object in predicting the moving direction of the image information 40. In addition, the first object 41 and the second object 42 having a smaller area than the background object 43 may be objects for judging movement validity.

The object tracking module 140 can determine whether the objects 41, 42 and 43 are moved in the moving validation process even if the moving uniformity of the objects 41, 42 and 43 in FIG. 42, and 43 are not located at the predicted positions of the objects 41, 42, and 43, respectively. That is, the object tracking module 140 can confirm that the object is moved in the horizontal direction by the background object 43. The object tracking module 140 estimates the predicted position for the other objects (e.g., the first object 41 and the second object 42) based on the horizontal movement direction and the movement distance of the background object 43 . Then, the object tracking module 140 can check whether the features corresponding to the first object 41 and the second object 42 are detected at the estimated position.

Here, it is assumed that the first object 41 and the second object 42 are substantially moved in a different direction from the background object 43. [ Therefore, the object tracking module 140 can not detect the characteristics of the first object 41 and the second object 42 at the predicted position. In this case, the object tracking module 140 may determine that there is no movement validity of the object. Then, the object tracking module 140 can detect the actual movement position of the first object 41 and the second object 42 by phase-correlating the previous image information and the current image information. Here, the object tracking module 140 may not perform a phase correlation operation on the background object 43. The object tracking module 140 may perform phase correlation only on the area of the first object 41 and the area of the second object 42 in the previous image information.

3 and 6, if the mobility uniformity is equal to or less than the reference value in operation 305, the object tracking module 140 determines whether the mobile coherence is equal to or smaller than the reference value in step 315 (step < RTI ID = 0.0 > (Operation), so that the phase correlation of the objects can be performed. In this case, when the coherence is less than or equal to the reference value, the phase correlation dispersion value of the objects included in the image information may correspond to a predetermined value or more. That is, there may be a case where there is little or no coherence of the objects included in the image information. In this case, the object tracking module 140 may perform a phase correlation operation on each of the objects included in the image information. When the phase correlation operation for each of the objects is completed, the object tracking module 140 detects the actual movement position of each of the objects based on the operation result, and performs the movement application of the objects in operation 317. Upon application of the objects, the object tracking module 140 may support applying the augmented reality contents to each object.

6 illustrates the environment of the third embodiment in which the mobile unity of the objects 41 and 42 is equal to or less than the reference value. In particular, the image information 40 shown in FIG. 6 may be a situation in which the first object Obj1 41 and the second object Obj2 42 are disposed as a main object in a state in which the background object is hardly disposed have. The image information 40 includes a first object 41 and a second object 42 because the first object 41 and the second object 42 are disposed throughout the image information area 40 as shown. May be the dominant objects of the image information 40. FIG. Therefore, since the first object 41 and the second object 42 move in different directions as shown in the drawing, the image information 40 can be detected to have a significantly lower unity of movement. The object tracking module 140 of the present disclosure can then determine that the mobile coherence of the initiative objects is below the reference value. The object tracking module 140 may perform phase correlation on each of the objects 41 and 42 to assist in detecting the actual moved position.

In the above description, a description will be given of a process of performing phase correlation calculation after evaluating object movement effectiveness according to the result of comparing movement uniformity with reference value for supporting object tracking function, or performing phase correlation calculation without evaluation of object movement effectiveness Respectively. Where other embodiments of the present disclosure may be designed to support multiple reference value comparisons for mobile coherence.

In more detail, the object tracking module 140 may perform object movement application without evaluating the object movement validity if the mobile coherence is equal to or greater than a predefined first reference value. For example, when all the objects (for example, the background object 43, the first object 41, and the second object 42) included in the image information 40 are moved by the same distance in the same direction as in FIG. 4 The highest mobility uniformity can be detected. In this case, a separate object movement validity evaluation may be omitted.

5, when the moving directions of the objects included in the image information 40 (e.g., the background object 43, the first object 41, and the second object 42) are different, It is necessary to perform object movement validity evaluation. Accordingly, the object tracking module 140 can support omitting the object movement validity evaluation when the object movement application is performed when the mobility uniformity value is equal to or larger than the predefined first reference value.

In addition, the object tracking module 140 can support the object movement validity evaluation for at least one object when the object coherence value is less than or equal to the first reference value and equal to or greater than the second reference value. Or the object tracking module 140 performs the movement effectiveness evaluation on the objects when the mobile coherence value is equal to or less than the first reference value and equal to or greater than the second reference value. And the object tracking module 140 may support performing phase correlation of objects without object movement validity. Here, the object tracking module 140 may control to perform phase correlation operation on objects other than the dominant object or objects having an area smaller than a predetermined size. Meanwhile, the object tracking module 140 may perform the processing according to the third embodiment of the present disclosure when the mobile coherence value is equal to or less than the second reference value.

The object tracking module 140 may apply an object area approximation method as shown in FIG. 7 when performing phase correlation in the movement detection process of the objects in FIGS. 3 to 6 described above.

FIG. 7 is a view for explaining an object region approximation function during the object tracking function of the present disclosure.

7, when the object area of the actual object 50 obtained from the image information 40 is not in a shape having sides parallel to the outline of the image information 40 as shown in the figure, The controller 140 may construct an object area of the virtual objects 51, 52 and 53 through object area approximation and map the actual object 50 to at least one of the virtual objects 51, 52 and 53. At this time, the virtual objects 51, 52, and 53 may be disposed in adjacent areas of the point where the actual object 50 is disposed. Accordingly, even if the tracking (position detection) operation is performed on the actual object 50 based on at least one of the virtual objects 51, 52, and 53 corresponding to the actual object 50, an appropriate object tracking function can be supported .

The virtual objects 51, 52, and 53 may have a side parallel to the outline of the image information 40 and may have a rectangular shape, for example. When the object tracking module 140 scans the data contained in the image information 40, it can perform a scan in a horizontal direction or a vertical direction. When at least one virtual object 51, 52, 53 arranged to be aligned with the outline of the image information 40 is mapped to the real object 50, the object tracking module 140 determines Object position detection can be performed more quickly, and the amount of computation at the time of detection can be reduced.

On the other hand, the actual location of the actual object 50 can be calculated from the previous image information through the recognition module 120 and the objectification module 130. [ The object tracking module 140 may perform a mapping operation of the virtual objects 51, 52, and 53 with respect to the actual object 50 based on the position value in the previous image information. In addition, the object tracking module 140 may perform a mapping operation of the virtual objects 51, 52, and 53 with respect to the predicted movement position with respect to the actual object 50. [ That is, the object tracking module 140 may perform the tracking (position detection) operation by applying the above-described virtual objects 51, 52, and 53 to the detection of the position of the actual object 50 in the current image information.

In FIG. 7, three virtual objects 51, 52, and 53 are illustrated. Each of the virtual objects 51, 52, and 53 may have a predetermined size based on the actual object 50. For example, the first virtual object 51 may be composed of a maximum size rectangle that can be disposed inside an object area of the real object 50 through object area approximation, And can have a parallel condition. The third virtual object 53 may be composed of a rectangle of the maximum size including the vertices of the object area of the actual object 50 through object area approximation. The second virtual object 52 is composed of rectangles set based on the intermediate values of the first virtual object 51 and the second virtual object 52 through object region approximation.

If the descriptor is detected based on the first virtual object 51 including the points of the actual object 50 and the position of the actual object 50 is detected, the accuracy is relatively higher than that of the other virtual objects 52 and 53 It can be the highest. However, since the comparison area is relatively small, the amount of computation can be increased because it is required to be compared with more areas in the image information 40 relatively. On the other hand, when the position detection is performed based on the third virtual object 53, even a descriptor which is not related to the actual object 50 may include a comparison object, and an error in position detection may be relatively large. However, since it is compared with a relatively large area, it is possible to perform calculation more quickly in comparison with the currently collected image information 40. The second virtual object 52 may provide an intermediate effect of the first virtual object 51 and the third virtual object 53. [ The manner of operating at least one of the virtual objects 51, 52, and 53 may be changed according to the designer's option.

In the above description, object region approximation has been described with reference to a graphic object having four sides and four angles, but the present disclosure is not limited thereto. That is, the object tracking module 140 can approximate an object having a shape that is easier for the object tracking module 140 to recognize, even for an object having more sides, more angles, or less sides and angles than the above-described shapes. For example, it is possible to generate virtual objects 51, 52, 53 of a similar shape according to the generation method of the virtual objects 51, 52, 53 with respect to the triangular figure or the octagonal figure.

FIG. 8 is a diagram schematically illustrating a configuration of a server device-based system for supporting an object tracking function according to an embodiment of the present disclosure.

8, the object processing system 10 of the present disclosure may include an electronic device such as a user terminal 101, a server device 200 and a communication network 300. [

The object processing system 10 of the present disclosure including the above configuration can mount the object tracking module 140 supporting the object tracking function described above in the user terminal 101 and support the object tracking function based on the object tracking module 140 . The object processing system 10 of the present disclosure can support forming a communication channel between the server device 200 and the user terminal 101 through the communication network 300 using the communication module of the user terminal 101. [ Accordingly, various information required in supporting the object tracking function can be provided through the server device 200. Alternatively, the object processing system 10 of the present disclosure may receive and store data stored in the server device 200 by the user terminal 101, and may support the object tracking function based on the stored data.

The user terminal 101 can access the server 200 through the communication network 300. Then, the user terminal 101 may provide the acquired image information to the server apparatus 200. In particular, the user terminal 101 can provide the acquired image information to the server device 200 in real time. Then, the server apparatus 200 may perform a phase correlation operation for object tracking based on the received image information and provide the resultant value to the user terminal 101. The user terminal 101 can omit the operation for object tracking in the image information based on the values provided by the server device 200 and can support data processing for easier object tracking. Meanwhile, the user terminal 101 may receive the remote reference data and the content data provided by the server device 200. Then, the user terminal 101 can recognize and objectify the image information using the remote reference data. Also, the user terminal 101 may control the content data to be applied to the augmented reality service.

The communication network 300 may be disposed between the user terminal 101 and the server device 200. The communication network 300 can form a communication channel between the two configurations (e.g., the user terminal 101 and the server 200). The communication network 300 includes a communication network 300, The communication network 300 may be composed of devices supporting the Internet network when the server device 200 connects the communication device through the Internet network, The communication network 300 of the present disclosure is not limited to a specific communication method or a communication module but may be a communication network including a user terminal 101 and a server device 200 of the present invention are applied to various devices and methods capable of performing data transmission /

The server device 200 can support the connection of the user terminal 101. [ The server device 200 may support the object tracking function and the augmented reality service function at the request of the user terminal 101. [ To this end, the server device 200 may store remote reference data for supporting the object tracking function. Also, the server apparatus 200 may store content data to be applied to the augmented reality to support the augmented reality service function. The server device 200 may perform at least one of a recognition process of an image information, an objectification process, and an object tracking process according to a request of the user terminal 101. The server device 200 may provide a result of the process in response to a request from the user terminal 101.

FIG. 9 is a block diagram illustrating in more detail an exemplary configuration of a user terminal (Client) 101 and a server 200 in the configuration of FIG. The block diagram illustrates a configuration of an object processing system 10 supporting an Augmented Reality (AR) service according to at least one embodiment described above. The object processing system 10 may include a main unit 160 (e.g., an AR processing unit).

The main unit 160 includes a camera input unit 151, a media input unit 152, an audio input unit 153, a plurality of sensor input units 154 ) From a variety of input devices. The sensor input unit 154 may include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a temperature sensor, a gravity sensor, or the like, and may sense various inputs from various sensors. The main unit 160 may use a memory 181, a central processing unit (CPU) 182, a graphic processing unit (GPU) 183, and the like for input data processing. The main unit 160 may use a remote reference DB (Data Base) 201 provided by the server apparatus 200 for identification and recognition of targets. The output of the main unit 160 may include identification information and localization information. The object classification information can be used to confirm the 2D / 3D angle of the target object. The identification information can be used to identify what the target is.

The AR content management unit 170 receives contents from a remote contents DB 202 or a local contents DB 187 provided in the server 200 and contents The video output unit 184 and the audio output unit 185 may be used to combine them in the final output process.

The main processing unit 100 of the present disclosure described above can be mounted on the main unit 160 of the above-described configuration of the user terminal 101. [ The object processing apparatus 100 may also be installed in the user terminal 101 in a form including a configuration of the main unit 160 and the AR content management unit 170.

10 is a diagram showing a configuration of an electronic device to which the object tracking function of the present disclosure is applied. That is, the electronic device 500 shown in FIG. 10 may be an example of an electronic device on which the object tracking module 140 described above is mounted.

Referring to FIG. 10, the electronic device 500 may include an application processor 510 and a call processor 520. The call processor 520 performs signal transmission / reception with an RF unit (Radio Frequency) unit 522 and is capable of performing signal transmission / reception with a memory 523 and a SIM card (SIM card) have. The call processor 520 may communicate with the application processor 510 to support the processing of the RF unit 522, the memory 523, and the SIM card 521, among the functions processed by the application processor 510 have. The object processing apparatus 100 described above may be installed in any one of the application processor 510 and the call processor 520 in the configuration of the electronic device 500. Or the object processing apparatus 100 may be provided as separate independent hardware devices in addition to the above-described configurations of the electronic device 500 and may be disposed in a certain area of the electronic device 500. [

The application processor 510 receives power from a power management unit 570 to which a battery 571 is connected. The application processor 510 performs signal transmission and reception with various communication modules other than the RF module 522 such as a WiFi module 581, a BT module 582, a GPS module 583, and an NFC module 584, May support the functions performed by the modules 581, 582, 583, 584. The application processor 510 may be connected to a user input unit 511 including a touch input, a pen input, a key input, and the like. The application processor 510 includes a display unit 512, a camera unit 513, a motor 515, an audio codec 530, a memory / External Memory) 516, and the like. The audio processing unit 530 may include a microphone (MIC), a speaker, a receiver, an earphone connection unit, and the like. The application processor 510 may be coupled to a sensor hub 514. The sensor hub 514 may be connected to a sensor unit 590 including various sensors. The sensor unit 590 includes a magnetic sensor 591, a gyro sensor 592, an acceleration sensor 593, a barometer sensor 594, a grip sensor A humidity sensor 596, a temperature / humidity sensor 596, a proximity sensor 597, an illuminance sensor 598, an RGB sensor 599, , And a gesture sensor (589).

11 is a diagram illustrating an exemplary platform in which the object tracking function of the present disclosure is applied.

Referring to FIG. 11, the platform to which the object tracking function of the present disclosure is applied is roughly divided into an application layer 610, an application framework layer 630, a library layer 650, Kernel < / RTI > layer 670.

The kernel layer 670 may comprise, for example, a Linux kernel. The kernel layer 670 is the core of the operating system, and is used by hardware drivers in driving electronic devices, hardware and processor security in electronic devices, efficient management of system resources, memory management, and hardware abstraction Providing an interface to hardware, multi-process, and service connection management. The kernel layer 670 includes a display driver 671, a camera driver 672, a BT driver 673, a shared memory driver 674, (IPC) driver 675, a USB driver 676, a keypad driver 677, a WiFi driver 678, an audio driver 679, , And a power management unit (Power Management) 680 may be disposed. The kernel layer 670 may be implemented in accordance with the present disclosure for tracking and processing one or more objects contained in an image by the driver or an additional driver (e.g., various sensor drivers) Lt; / RTI >

The library layer 650 may be located between the kernel layer 670 and the application layer 610 and may serve as an intermediary to exchange data between different hardware or software. Thus, a standardized interface can be provided, various environment support, and system can be interworked with other tasks. The library layer 650 includes a surface manager 651, a media framework 652, an SQLite 653, an OpenGL / ES 654, a FreeType 655, a Webkit 656, (657), SSL (658), Libc (659), and the like. Library layer 650 may be configured to support operations according to this disclosure that track and process one or more objects included in an image in the present disclosure. For example, the library layer 650 can manage how various applications (e.g., AR applications) that are executed appear on the screen and support 2D / 3D graphical representation of the acquired image information.

Library layer 650 may include an Android Runtime 690 configuration. The Android runtime 690 may reside on the kernel layer 670 and may support efficient memory usage, data structures for data sharing between processes, and so on. The Android runtime 690 can provide essential functions such as a container, a utility, an input / output (I / O), and the like. The Android runtime 690 may include Core Libraries 691 and Dalvik Virtual Machine 692. The Dalvik Virtual Machine 692 can support a widget function of an electronic device for which an object tracking function is supported, a function requiring real-time execution, and a function requiring periodical execution according to a preset schedule.

The application framework layer 630 represents an application program interface (API) of the operating system, and may include a program serving as a basis for applications in the application layer 610. The application framework layer 630 is compatible with any application and may be capable of reusing, moving, or exchanging components. The application framework layer 630 may include a support program, a program for connecting other software components, and the like. The application framework layer 630 includes an Activity Manager 631, a Window Manager 632, a Content Providers 633, a View System 634, A Notification Manager 635, a Package Manager 636, a Telephony Manager 637, a Resource Manager 638, a Location Manager 639, .

The application framework layer 630 may be configured to support operations according to this disclosure for tracking and processing one or more objects contained in an image by the Manager or an additional manager as described above. For example, through the activity manager 631, it is possible to support smooth navigation between applications running in other processes, and through the package manager 636, which applications are installed in the electronic device, To perform a function. The application framework layer 630 may further include one or more managers corresponding to the object tracking module 140 in the present disclosure and may be configured to perform image acquisition in the AR application via the managers, Motion detection for objects, determination of mobility uniformity according to movement of objects, determination of movement validity of objects, processing of moving objects, and the like. For example, the application framework layer 630 may determine phase correlation values between objects from the acquired image, determine the location of the peak value among the phase correlation values, and use the peak values to determine the phase correlation values It is possible to support an operation of calculating a variance value.

The application layer 610 may include various programs that are driven and displayed within the electronic device. For example, a UI application related to various menus and the like in the electronic device, an application downloaded and stored through an external device or a network, and an application that can be installed or deleted by a user can be included. Such an application layer 610 may be used for augmented reality services, Internet telephony services by network connection, VOD service, Web album service, SNS, location based service (LBS), map service, Service, a text / multimedia message service, a mail service, an address book service, a media playback service, and the like. In addition, various functions such as game and schedule management can be performed. For example, the application layer 610 may include a home application 611, a dialer application 612, an SMS / MMS application 613, an IM application 614, a browser A browser app 615, a camera app 616, an alarm app 617, a calculator app 618, a contacts app 619, a voice dial app A calendar app 622, a media player app 623, an album app 624, a clock app 625, an email app 621, a calendar app 620, an email app 621, Etc. may be disposed.

The platform as described above can be used universally in various other devices, including electronic devices according to the present disclosure. And the platform according to the present disclosure may be stored or loaded in at least one of the memory and the processor as described above or in a separate processor.

An overview of an operation according to the present disclosure (e.g., an object tracking and processing operation in an image obtained at the time of performing an AR service) with reference to FIGS. 10 and 11 is as follows.

For example, in the present disclosure, the image data collected through the camera section 513, the voice data via the microphone (MIC), the sensor section 590 through the sensor hub 514, and the GPS 583 Various data can be input. The various data to be input may be processed by an operation specified by the application processor 510. Also, in the present disclosure, the WiFi module 581, the WiFi module 581, the WiFi module 582, the WiFi module 583, and the WiFi module 583 are provided for the case where data must be interlocked with the server device 200 or another electronic device, BT module 582, NFC module 584, and the like. The data required for the operation in the present disclosure can be stored using the main memory 523 or the external memory 516 and the result obtained through calculation using the module such as the display unit 512 or the speaker Can be provided to the user again.

In view of the software of the operating system of the electronic device (e.g., Android), this operation is performed by various drivers (e.g., camera driver 672, audio driver 679 , mic), sensor driver, etc.) can perform various input data receiving operations. For example, the electronic device may perform an operation of receiving input data (e.g., an image) from the camera section 513 via the camera driver 672 to support the AR service.

The electronic device may also include various modules (e.g., a surface manager 651, a media framework 652, an SQLite 653, an OpenGL / ES 652, and so on) provided by the library layer 650 to drive a specified operation based on the input data. (654), Webkit (656), Libc (659), etc.). For example, in library layer 650, a library (Libc 659) can be used to essentially handle most operations and media framework 652 can be used to manipulate media data such as input video / audio Can be utilized. According to one embodiment, the electronic device may perform operations (e.g., object region approximation operations, and the like) associated with object tracking and processing in the images obtained during AR service execution, via Libc 659. The electronic device may also receive media (e.g., video, audio, and / or video) associated with the AR service via various codecs (e.g., AVC (H.264), H.263, MP3, MPEG- , Images).

In addition, the electronic device can utilize various functions provided by the library layer 650 to efficiently express the processed operation results. For example, OpenGL / ES 654 and Surface Manager 651 can be utilized for a 3D graphic effect. According to one embodiment, the electronic device may support 3D graphics according to the AR service by the OpenGL / ES 654, and may also support a hardware (H / W) acceleration function according to the electronic device. Thereby, the electronic device can use a mixture of three-dimensional graphics and two-dimensional graphics in an application (for example, an AR application). The electronic device may display the operation result processed in the library layer 650 on the display unit 512 through the display driver 671 of the kernel layer 670. [

Electronic devices can also use a database manager, such as SQLite 653, for data management. In addition, the electronic device can use the Webkit 656 to interact with the web, and various applications (e.g., AR applications) or various services (e.g., web applications) can be used through the application framework layer 630 for high- service (e.g., AR service).

The above-described arrangements are not intended to limit the features or the technical scope of the present disclosure, but merely illustrate implementations to which the features of the present disclosure may be applied. The configuration of at least some of the systems or devices shown in Figs. 10 and 11 may be applied for the technical implementation of the present disclosure. Also, those skilled in the art will appreciate that the above-described arrangements may be added, omitted, or modified in embodiments of the present disclosure. In addition, other configurations may be added according to the needs of the embodiments described in this disclosure. One or more methods, operations, and algorithms described in this disclosure may be implemented using one or more of the configurations described in the above-described implementation examples. For example, an AR platform focused on an image base to support object tracking and processing on an image according to the present disclosure may be implemented in an electronic device.

On the other hand, the user terminal and the electronic device described above may further include various additional modules depending on the providing mode. That is, the user terminal, the electronic device, and the like may be a short-range communication module for short-range communication in the case of a communication terminal, an interface for data transmission / reception by the wired communication method or the wireless communication method of the terminal and the electronic device, An Internet communication module for performing digital broadcasting and a digital broadcasting module for performing digital broadcasting reception and reproduction functions, and the like. These components can not be enumerated because of a wide variety of variations depending on the convergence trend of the digital device, but it is also possible that components having the same level as the above-mentioned components are further included in the device have. Also, it goes without saying that the user terminal and the electronic device of the present disclosure may be excluded from the specific configurations in the above configuration or may be replaced with other configurations in accordance with the provision mode thereof. Which will be readily apparent to those skilled in the art.

The user terminal and the electronic device according to the embodiments of the present disclosure may also include all mobile communication terminals operating based on communication protocols corresponding to various communication systems, A portable game terminal, a smart phone, a notebook PC, a notebook PC, a slate PC (portable music player), a digital music player, a PDA , Tapbooks, and handheld PCs, as well as multimedia and related applications.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, And is not intended to limit the scope of the present disclosure. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present disclosure are possible in the exemplary embodiments disclosed herein.

10: Object processing system 100: Object processing device
110: input control module 120: recognition module
130: objectification module 140: object tracking module
101: user terminal 200: server device
300: network 500: electronic device

Claims (22)

A method of operating an electronic device,
The method comprising: tracking at least one object contained on a plurality of digital images, the digital images comprising a first image and a second image,
Determining phase correlation values between at least a portion of the first image and at least a portion of the second image;
Determining a position of a peak value among the phase correlation values; And
Determining a variance of the phase correlation values using at least some of the peak values;
≪ / RTI > 2. The method of claim 1, wherein the tracking operation performs at least some of the variance values to track the at least one object. 3. The method of claim 2, wherein the act of performing the object tracking differently
Tracing the at least one object using a first process when the variance value is less than or equal to a selected value;
And tracking the at least one object using a second process if the variance value is greater than or equal to a selected value. 4. The method of claim 3, wherein said first process comprises determining whether at least one object at a first location on a first image has moved to a second location on a second image, A method of determining using a position of a value. 5. The method of claim 4, wherein the first process performs an operation of determining a pixel correlation between a region of a first location on the first image and a region of a second location on the second image. 6. The method of claim 5, wherein the first process includes determining that the at least one object has moved from the first position to the second position if the pixel correlation is greater than or equal to a selected value . 5. The method of claim 4, further comprising performing tracking of the at least one object separately from the position of the peak value if it is determined that the at least one object has not moved from the first position to the second position How to. 8. The method of claim 7, wherein the step of performing tracking of the at least one object separately from the position of the peak value comprises performing a phase correlation operation on each of the at least one object with respect to the first image and the second image ≪ / RTI > 4. The method of claim 3, wherein the second process performs tracking of the at least one object separately from the location of the peak value. 10. The method of claim 9, wherein the step of performing tracking of the at least one object, apart from the location of the peak value, comprises performing a phase correlation operation on each of the at least one object with respect to the first image and the second image ≪ / RTI > 11. The method according to any one of claims 8 to 10, wherein the act of performing a phase correlation operation on each of the at least one object further comprises approximating the at least one object in a selected form. In an electronic device,
A memory configured to store a plurality of digital images; And
And a processor configured to process the images,
Wherein the processor is configured to track at least one object contained on a plurality of digital images, the digital images comprising a first image and a second image,
The processor comprising:
Determining phase correlation values between at least a portion of the first image and at least a portion of the second image;
Determining a position of a peak value among the phase correlation values;
And to use at least some of the peak values to determine a variance of the phase correlation values. 13. The apparatus of claim 12, wherein the processor uses at least some of the variance values to perform the operation of tracking the at least one object differently. 13. The system of claim 12, wherein the processor
A first process for tracking the at least one object when the variance value is less than or equal to a selected value;
And a second process of tracking the at least one object if the variance value is greater than or equal to a selected value. 15. The method of claim 14, wherein the first process determines whether at least one object at a first location on a first image has moved to a second location on a second image, . 16. The apparatus of claim 15, wherein the first process determines a pixel correlation between a region of a first location on the first image and a region of a second location on the second image. 17. The apparatus of claim 16, wherein the first process determines that the at least one object has moved from the first position to the second position if the pixel correlation is greater than or equal to a selected value. 16. The method of claim 15, wherein, if the first process determines that the at least one object has not moved from the first location to the second location, separate from the location of the peak value, A device to perform. 19. The apparatus of claim 18, wherein the first process performs phase correlation for each of the at least one object with respect to the first image and the second image. 15. The apparatus of claim 14, wherein the second process performs tracking of the at least one object separately from the position of the peak value. 21. The apparatus of claim 20, wherein the second process performs phase correlation for each of the at least one object with respect to the first image and the second image. 22. The apparatus according to any one of claims 19 to 21, wherein at least one of the first process and the second process approximates the at least one object in a selected form.

Images