JP6628670B2 - Image processing apparatus and image processing method - Google Patents

Description

  The present invention relates to an image processing device and an image processing method.

  2. Description of the Related Art Conventionally, an apparatus for editing moving image content is known. Patent Literature 1 discloses an image editing apparatus capable of deleting an image of a frame marked by a user from moving image content.

JP 2014-501466 A

  By using the conventional technology, the user can delete an image in which the subject is not captured as desired from the moving image content. Then, the user does not include an image that is not desirable for the user, such as an image in which the subject is out of focus, an image in which an obstacle hides the subject, and an image in which the subject appears in a dark state. Can create video content. However, when the image is deleted in this way, there is a problem that the record of the deleted scene is lost.

  Accordingly, the present invention has been made in view of these points, and provides an image processing apparatus and an image processing method that allow a user to delete an undesired image and leave a record of the deleted scene. The purpose is to:

  An image processing apparatus according to a first aspect of the present invention includes a plurality of first imaging data generated by imaging by a first imaging device and a plurality of second imaging data generated by imaging by a second imaging device. And an identification unit that identifies the first imaging data and the second imaging data captured at the same timing among the plurality of first imaging data and the plurality of second imaging data, A selection unit that selects one of the first imaging data and the second imaging data identified by the identification unit based on a predetermined quality condition; and a selection unit that selects the imaging data selected by the selection unit. And an output unit for outputting.

  The specifying unit may extract, for example, similar features commonly included in the plurality of first shooting data and the plurality of second shooting data, and a similarity between the extracted similar features may be equal to or greater than a predetermined threshold. The first imaging data and the second imaging data captured at the same timing are specified on the condition that

  The identification unit, when extracting at least one combination of the first imaging data and the second imaging data including the similar feature, includes first imaging time information of the first imaging data and the second imaging data. By specifying the relationship between the shooting times of the plurality of first shooting data and the shooting times of the plurality of second shooting data based on the difference between the data and the second shooting time information, shooting was performed at the same timing. The first shooting data and the second shooting data may be specified.

  The selection unit may compare one of the plurality of first shooting data and the plurality of second shooting data with the predetermined image quality of an image of a subject, which is most frequently taken, with one of the predetermined quality conditions. Select the shooting data of.

  The selecting unit compares any of the image quality of the subject having the largest face area included in the plurality of first shooting data and the plurality of second shooting data with the predetermined quality condition, One of the photographing data may be selected.

  The obtaining unit further obtains subject information specifying a subject whose quality is to be checked by the selecting unit, and the selecting unit sets the quality of an image of the subject corresponding to the subject information to the predetermined quality condition. Any one of the photographing data may be selected by comparing.

  The selection unit is a camera that captures the selected photographing data from the plurality of first photographing data and the plurality of second photographing data until a predetermined time elapses after switching the photographing data to be selected. The photographed data may be continuously selected.

  The selection unit changes the predetermined quality condition before and after a predetermined time elapses after switching the selected shooting data among the plurality of first shooting data and the plurality of second shooting data. It may be a condition.

  The image processing method according to the second aspect of the present invention provides a plurality of first photographing data generated by photographing the first photographing device and a plurality of second photographing data generated by photographing the second photographing device. Acquiring, and identifying the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data, The method includes a step of selecting one of the first shooting data and the second shooting data based on a predetermined quality condition, and a step of outputting the selected shooting data.

  Advantageous Effects of Invention According to the present invention, there is an effect that a record of a deleted scene can be left while deleting an image that the user does not want.

FIG. 2 is a diagram illustrating an outline of an image processing apparatus. FIG. 5 is a diagram illustrating an example of photographing data obtained by photographing by a user. FIG. 2 is a diagram illustrating a configuration of an image processing apparatus. FIG. 11 is a diagram for describing a process in which a specifying unit specifies a combination of pieces of shooting data shot at the same timing. 5 is a flowchart of an image processing method executed by the image processing device. 9 is a flowchart illustrating a procedure in which a specifying unit specifies shooting data shot at the same timing.

[Overview of Image Processing Apparatus 1]
FIG. 1 is a diagram for explaining an outline of the image processing apparatus 1. The image processing apparatus 1 receives a plurality of shooting files including a plurality of shooting data shot at a plurality of different angles, and among the data shot at the same timing included in the plurality of received shooting files, the The editing data obtained by selecting and editing the photographing data that is well captured is output.

  As shown in FIG. 1A, a first user who owns a first camera 100 (first photographing device) photographs a subject at a first angle at an event such as an athletic meet or a school festival or a travel destination, A second user (for example, a family of the first user) who owns the second camera 200 (second imaging device) captures an object at a second angle at an event or a travel destination where the first user is capturing an image. Suppose you have The first photographing data photographed by the first camera 100 is stored in the storage medium of the first camera 100 as a first photographing file. Further, the second shooting data shot by the second camera 200 is stored in the storage medium of the second camera 200 as a second shooting file. Here, the first shooting data and the second shooting data are data included in one of a plurality of frames forming a video. The first shooting file and the second shooting file include sound data together with image data.

  Subsequently, as illustrated in FIG. 1B, the first user and the second user upload the first shooting file and the second shooting file to the image processing device 1 using the user terminal 2. Here, a case will be described in which the first user and the second user are family members, and the first user uploads the first shooting file and the second shooting file to the image processing apparatus 1 using the shared user terminal 2. However, the first user and the second user may upload the first shooting file and the second shooting file to the image processing device 1 using the respective user terminals.

  The image processing apparatus 1 is, for example, a server connected to the user terminal 2 via the Internet. When a first user accesses the image processing apparatus 1 using the user terminal 2, the image processing apparatus 1 Is displayed on the user terminal 2. The first user moves the first shooting file and the second shooting file stored in the first camera 100 and the second camera 200 to the user terminal 2 via a storage medium or a network, Upload the first shooting file and the second shooting file.

  Upon receiving the first shooting file and the second shooting file, the image processing apparatus 1 stores any one of the plurality of first shooting data included in the first shooting file and the plurality of second shooting data included in the second shooting file. First shooting including images shot at the same timing based on characteristic sounds (for example, a pistol sound or broadcast voice at an athletic meet) and images (for example, flashing flashes at a wedding reception) that are commonly included Data and second imaging data are specified.

  When the image processing apparatus 1 specifies the first shooting data and the second shooting data shot at the same timing, the image processing apparatus 1 selects high-quality shooting data from the first shooting data and the second shooting data shot at the same timing. I do. The quality is determined based on, for example, conditions such as whether the subject is in focus, whether the entire subject is photographed, and whether the subject is photographed with appropriate brightness.

  When the image processing apparatus 1 selects high quality photographing data, the image processing apparatus 1 outputs an editing file including the editing data as shown in FIG. The image processing apparatus 1 transmits the edited file to the user terminal 2 via, for example, the Internet. The edited file conforms to, for example, a DVD format, and a user who has received the edited file at the user terminal 2 can write the received edited file to a storage medium such as a DVD. When the user plays back the edited file on the DVD recorder, the user can view a high-quality image among images shot from different angles at the same timing. By doing so, even if the quality of the image captured by the first camera 100 is low, the user can view an image of the same subject captured by the second camera 200 at the same timing, High quality images can be continuously viewed instead of poor quality images.

  When creating the editing data, the image processing apparatus 1 does not edit the audio data, but includes the audio data added to one of the first imaging data and the second imaging data in the editing data. By doing so, it is possible to prevent the sound volume and quality from fluctuating while the user is watching the video.

  FIG. 2 is a diagram illustrating an example of photographing data obtained by photographing by a user. FIG. 2A shows a plurality of first shooting data A1, A2, A3 included in the first shooting file, and a plurality of second shooting data B1, B2 included in the second shooting file. The first photographing data and the second photographing data shown in FIG. 2 are data generated by photographing children playing the same athletic meet from different angles. The first shooting data A2 is in a state where an obstacle enters in front of the first camera 100 during shooting and a part of the subject is not shown in the hatched area. The image processing apparatus 1 deletes such low-quality images and replaces the low-quality images with images captured by the second camera 200 at the same timing, as shown in FIG. Editing data can be created.

It should be noted that the first shooting data and the second shooting data are shot by different cameras, respectively, and when the time set in the camera is incorrect, the second shooting data B1 and B2 correspond to any of the first shooting data. I don't know if they were shot at the same time. The image processing apparatus 1 determines which first shooting data and which second shooting data are shot at the same timing among the plurality of first shooting data and the plurality of second shooting data whose shooting timings are unknown. To identify. Then, edit data including high-quality shooting data of the first shooting data and the second shooting data shot at the same timing is created. By doing so, the user can leave a record of the deleted scene while deleting the image not desired by the user.
Hereinafter, the configuration and operation of the image processing apparatus 1 will be described in detail.

[Configuration of Image Processing Apparatus 1]
FIG. 3 is a diagram illustrating a configuration of the image processing apparatus 1. The image processing device 1 includes a communication unit 11, a storage unit 12, and a control unit 13.
The communication unit 11 is, for example, a communication controller, and transmits and receives data to and from the user terminal 2 via a network such as the Internet. The communication unit 11 receives, for example, photographing data from the user terminal 2 and transmits composite data to the user terminal 2.

  The storage unit 12 is a storage medium such as a ROM (Read Only Memory), a RAM (Random Access Memory), and a hard disk. The storage unit 12 stores a program executed by the control unit 13 and data necessary for a process executed by the control unit 13. Further, the storage unit 12 stores the photographing data received from the user terminal 2.

  The control unit 13 is, for example, a CPU (Central Processing Unit), and functions as an acquisition unit 131, a specification unit 132, a selection unit 133, and an output unit 134 by executing a program stored in the storage unit 12.

The acquisition unit 131 includes a first shooting file including a plurality of first shooting data generated by the first camera 100 and a second shooting file including a plurality of second shooting data generated by the second camera 200. 2. Acquire a shooting file from the user terminal 2. The acquisition unit 131 causes the storage unit 12 to store the acquired first photography file and second photography file.
In addition, the acquisition unit 131 acquires various setting information such as quality conditions used by the selection unit 133 to select photographing data and subject information for identifying a subject whose quality is to be checked.

  The specifying unit 132 specifies the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data. Specifically, the specifying unit 132 extracts the similar feature included in each of the plurality of first shooting data and the plurality of second shooting data, and determines the similarity between the extracted similar features. The first shooting data and the second shooting data shot at the same timing are specified on condition that they are equal to or larger than a predetermined threshold.

  A similar feature is, for example, a sound or image change pattern. When extracting a feature of a sound, the specifying unit 132 extracts a change pattern of the sound as a feature when the level of the sound has changed by a predetermined threshold or more between a plurality of adjacent first imaging data. When the plurality of first shooting data and the plurality of second shooting data are data shot at an athletic meet, the pistol sound indicating the start of the competition is louder than other sounds. Therefore, a high-level sound that was not present in the first and second shooting data shot immediately before is recorded in the first and second shooting data shot at the timing of the pistol sound. It is thought that it is. Therefore, when the first photographing data includes a sound that has changed by a predetermined threshold or more as compared with the immediately preceding first photographing data, the specifying unit 132 determines the plurality of first photographing data in which the sound is recorded. And the sound change pattern. For example, when it takes 0.3 seconds from the sounding of the pistol sound to the disappearance of the sound, the identifying unit 132 outputs the plurality of first shooting data for 0.3 seconds and the sound corresponding to each of the first shooting data. The level is specified, and the specified information is stored in the storage unit 12.

  Subsequently, the specifying unit 132 searches for a plurality of second shooting data in the second shooting data, and specifies a plurality of second shooting data including an equivalent sound pattern. The specifying unit 132 specifies, for example, the second shooting data including the sound whose sound has changed by a predetermined threshold or more as compared with the immediately preceding second shooting data, and then performs the first shooting in the subsequent second shooting data. Check if the sound level is changing as well as the data.

  The specifying unit 132 compares the sound pattern extracted from the first image data with the sound pattern extracted from the second image data, and determines the similarity. The identification unit 132 calculates the similarity by calculating a correlation value between a plurality of sound levels corresponding to the plurality of first shooting data and a plurality of sound levels corresponding to the plurality of second shooting data, for example. Determine the degree. When the similarity is equal to or larger than the predetermined threshold, the specifying unit 132 determines that the plurality of first shooting data and the plurality of second shooting data including the same sound change pattern have been shot at the same timing. I do.

  The specifying unit 132 may extract a human voice, music, or the like as a feature. For example, the identification unit 132 may be configured to perform the first shooting data shooting at the same timing based on a voice change pattern or a music change pattern commonly included in the plurality of first shooting data and the plurality of second shooting data. And the second imaging data can be specified.

  In addition, the specifying unit 132 can use a change pattern in which the flash blinks or a pattern in which the subject changes as the change pattern of the image. For example, when the first image data and the second image data are generated by being imaged indoors, such as image data of a wedding reception, the flash used by the camera of many people is synchronized with the flashing timing. It is considered that the luminance of the first photographing data and the second photographing data changes. Therefore, the specifying unit 132 can also specify the first shooting data and the second shooting data shot at the same timing based on the luminance change pattern of the image in the first shooting data and the second shooting data.

  The specifying unit 132 uses the predetermined shooting time information included in the first shooting data and the second shooting data in order to efficiently specify the first shooting data and the second shooting data that include the same feature. Similar features may be extracted from the first shooting data and the second shooting data within the range. If the user sets the time on the first camera 100 and the second camera 200, it is highly likely that the correct time is set, if not accurately. It is considered that relatively close photographing time information is recorded in association with the photographing time information. Therefore, when the identifying unit 132 detects a sound or a change pattern of an image characteristic of the first shooting data, the shooting time information within a predetermined range corresponds to the shooting time information corresponding to the first shooting data. By searching for a similar sound or a change pattern of an image in the attached second photographing data, a similar feature can be efficiently extracted.

  When at least one combination of the first shooting data and the second shooting data including similar features is extracted, the specifying unit 132 determines the first shooting time information of the first shooting data and the second shooting data of the second shooting data. By specifying the relationship between the shooting time of the plurality of first shooting data and the shooting time of the plurality of second shooting data based on the difference with the time information, the first shooting data and the second shooting data shot at the same timing are specified. The shooting data may be specified. For example, upon extracting at least one combination of the first shooting data and the second shooting data including similar features, the specifying unit 132 includes the combination in the plurality of first shooting data based on the difference between the shooting time information. By correcting at least one of the plurality of pieces of first shooting time information and the plurality of pieces of second shooting time information included in the plurality of pieces of second shooting data, the shooting times of the plurality of pieces of first shooting data and the plurality of pieces of second shooting data are corrected. Specify the relationship between the data and the shooting time. By doing so, the specifying unit 132 can reduce the time required for specifying a plurality of first shooting data and a plurality of second shooting data shot at the same timing.

  Further, the specifying unit 132 may extract similar features from the first shooting data and the second shooting data included in the same scene. The specifying unit 132 determines that the scenes are the same when, for example, a common subject appears in the first shooting data and the second shooting data.

  As an example, when an image of a red or white large ball used in a large ball rolling competition of an athletic meet is commonly included in a plurality of first shooting data and a plurality of second shooting data, a plurality of second shots in which the big ball is captured It is conceivable to extract whether or not similar features are included in one shooting data and a plurality of second shooting data. When the first shooting data and the second shooting data are data shot at a travel destination, the specifying unit 132 can determine that the scene is the same when a common building is shown. As described above, the identifying unit 132 can reduce the processing time by extracting similar features from the first shooting data and the second shooting data included in the same scene, and determine whether or not shooting has been performed at the same timing. Accuracy of the determination can be improved.

  The specifying unit 132 specifies that the similarity between the similar features extracted from each of the first shooting data and the second shooting data is equal to or more than a predetermined threshold value in order to specify the combination of the shooting data shot at the same timing. In some cases, identification information common to the first imaging data and the second imaging data is added. The identifying unit 132 assigns identification information different from the imaging time information assigned by the video camera that outputs the first imaging data and the second imaging data, but the identifying unit 132 rewrites the imaging time information to Identification information may be added.

  FIG. 4 is a diagram for describing a process in which the specifying unit 132 specifies a combination of pieces of shooting data shot at the same timing. FIG. 4A shows a part of the first photographing file and the second photographing file received from the user terminal 2. In the second shooting file, it is assumed that the scene is switched between B14 and B21.

  The specifying unit 132 extracts a pistol sound from the first shooting data A12 and the second shooting data B13. In addition, the specifying unit 132 extracts a broadcast voice from the first shooting data A17 and the second shooting data B22. The specifying unit 132 extracts cheers in the first photographing data A14, but there is no photographing data in which cheers are extracted in the second photographing file. In such a case, the specifying unit 132 assigns ID = 0001 as identification information to the first shooting data A12 and the second shooting data B13 from which the pistol sound is extracted, and the first shooting data A17 from which the broadcast voice is extracted. And ID = 0002 is assigned to the second photographing data B22.

  In addition, the specifying unit 132 may generate a plurality of first shooting data and a plurality of second shooting data that are shot at the same timing based on the first shooting data and the second shooting data including similar features to which the same identification information is added. By associating with the photographing data, the combination of the first photographing data and the second photographing data photographed at the same timing is specified. FIG. 4B is a diagram illustrating a state in which the specifying unit 132 associates a plurality of first shooting data with a plurality of second shooting data. In FIG. 4B, the first photographing data A11, A12, A13, A16, A17, and A18 are associated as data photographed at the same timing as the second photographing data B12, B13, B14, B21, B22, and B23. Have been.

  The selection unit 133 selects any one of the first imaging data and the second imaging data specified as the imaging data shot at the same timing by the identification unit 132 based on a predetermined quality condition. The quality conditions include whether the subject is in focus, whether the entire subject is captured, whether the subject is captured with appropriate brightness, and the like. The selection unit 133 quantifies the quality according to the degree to which each piece of image data satisfies each quality condition, and selects image data indicating a high quality numerical value. The selection unit 133 may weight the plurality of quality conditions based on the priority specified by the user and quantify the quality.

  FIG. 4C is a diagram illustrating an example of an edit file created by the selection unit 133 selecting high-quality shooting data. In FIG. 4C, A13 to A16 are selected after B11 to B13, and B22 to B24 are selected after A13 to A16.

  The selection unit 133 compares, for example, the quality of the image of the subject that appears most frequently in the plurality of first shooting data and the plurality of second shooting data with a predetermined quality condition, and thereby selects one of the shooting data. Select Specifically, the selection unit 133 assigns a subject ID to each of the types of the subjects specified based on the colors and shapes of the subjects included in the plurality of first shooting data and the plurality of second shooting data, and Information indicating the subject ID of the subject included in the photographing data is stored in the storage unit 12. Then, the subject corresponding to the subject ID included most in all the photographing data is specified as the subject most frequently photographed.

  When the plurality of first shooting data and the plurality of second shooting data are, for example, data obtained by shooting an event of a user's child at school, it is considered that the frequency of the user's child is high. Therefore, the selection unit 133 determines the subject whose quality is to be checked based on the frequency of the shooting as described above, so that the shooting data in which the subject to be shot by the user is shot with high quality is determined. Can be selected.

  The selecting unit 133 compares one of the plurality of pieces of first shooting data and the plurality of pieces of second shooting data with an image quality of an object having the largest face area with a predetermined quality condition, thereby performing one of the shootings. Data may be selected. Specifically, the selection unit 133 recognizes one or more face regions included in the plurality of first shooting data and the plurality of second shooting data, and among the one or more recognized face regions, Select photographing data with good quality of a large face image. When the plurality of first shooting data and the plurality of second shooting data are, for example, data obtained by shooting an event of a user's child at a school, it is highly possible that the user's child is shot so as to be larger. Therefore, the selecting unit 133 can select photographing data in which the image quality of the target child photographed by the user is good by selecting photographing data in which the quality of the largest face image is good.

  Further, the selection unit 133 may select one of the imaging data by comparing the quality of the image of the subject corresponding to the subject information acquired by the acquisition unit 131 from the user terminal 2 with a predetermined quality condition. . The subject information is, for example, information for specifying an image of a subject selected by the user in one or more pieces of photographing data among the plurality of first photographing data and the plurality of second photographing data. The selecting unit 133 specifies a subject similar to the subject indicated by the subject information in the plurality of first shooting data and the plurality of second shooting data, and selects shooting data having good image quality of the specified subject. By doing so, the selection unit 133 can select photographing data with good image quality of a subject that the user desires to have good image quality.

  In order to prevent the photographing data selected by the selecting unit 133 from frequently switching between the first photographing data and the second photographing data, the selecting unit 133 includes a plurality of first photographing data and a plurality of second photographing data. The photographing data obtained by the camera that has photographed the selected photographing data may be continuously selected until a predetermined time (for example, 5 seconds) elapses after switching the photographing data to be selected. That is, after selecting the first shooting data, the selection unit 133 keeps the quality of the first shooting data until the quality of the second shooting data improves and a predetermined time elapses after selecting the second shooting data. Even if the quality of the second shooting data is better, the selection of the second shooting data is continued.

  In addition, the selection unit 133 sets a predetermined quality condition different before and after a predetermined time has elapsed after switching the selected shooting data among the plurality of first shooting data and the plurality of second shooting data. It may be. For example, the selector 133 switches the quality of the first shooting data corresponding to the same timing until a predetermined time elapses after switching the shooting data to be selected from the first shooting data and the second shooting data. It is assumed that the imaging data is switched on the condition that the difference from the quality of the second imaging data is equal to or more than a predetermined threshold. By doing so, it is possible to prevent the screen from being switched even though the quality of the first shooting data and the quality of the second shooting data are not much different.

  The output unit 134 outputs an edit file including edit data constituted by the photographing data selected by the selection unit 133. The output unit 134 outputs, for example, as shown in FIG. 4C, an edited file including photographing data of good quality. The output unit 134 may transmit the edited file to the user terminal 2 via the communication unit 11, or may transmit the edited file to a device that writes data to a storage medium such as a DVD.

[Operation Flowchart of Image Processing Apparatus 1]
Subsequently, a procedure of an image processing method executed by the image processing apparatus 1 will be described.
FIG. 5 is a flowchart of an image processing method executed by the image processing apparatus 1. First, the acquiring unit 131 receives the first photographing file and the second photographing file transmitted from the user terminal 2, and acquires a plurality of first photographing data and a plurality of second photographing data included in these files. (S21).

  Subsequently, the specifying unit 132 specifies the first shooting data and the second shooting data shot at the same timing from among the plurality of first shooting data and the plurality of second shooting data (S22), and FIG. A photographing data string as shown in FIG.

  Subsequently, the selection unit 133 selects high quality imaging data from the first imaging data and the second imaging data captured at the same timing. At this time, the selection unit 133 determines whether or not a predetermined time has elapsed since the switching of the high quality imaging data (S23). When a predetermined time has elapsed since the switching of the imaging data (YES in S23), the selection unit 133 selects imaging data with good quality (S24). If the predetermined time has not elapsed since the switching of the photographing data (NO in S23), the selecting unit 133 continues the photographing data included in the photographing file corresponding to the selected photographing data regardless of the quality. To select (S25).

  When the selecting unit 133 executes the selecting process on all the photographing data (YES in S26), the output unit 134 outputs an editing file including the editing data as shown in FIG. 4C (S27). .

FIG. 6 is a flowchart illustrating a procedure of Step S22 in which the specifying unit 132 specifies the photographing data photographed at the same timing.
First, the specifying unit 132 extracts characteristic sounds and images included in the plurality of first shooting data (S221). Then, the specifying unit 132 selects, from the plurality of first shooting data, first shooting data in which a characteristic sound or image is extracted (S222). At this time, when a characteristic sound or image is included over a plurality of first shooting data, the specifying unit 132 may extract the plurality of first shooting data. Subsequently, the specifying unit 132 selects second shooting data to be searched for a feature similar to the feature included in the extracted first shooting data (S223).

  The specifying unit 132 calculates the similarity between the feature included in the selected second shooting data and the feature included in the first shooting data selected in step S222, and when the calculated similarity is equal to or greater than a predetermined threshold. It is determined whether or not there is (S224). When determining that the similarity is equal to or greater than the threshold (YES in S224), the specifying unit 132 assigns identification numbers to the first imaging data and the second imaging data that include similar features (S225). If the identifying unit 132 determines that the similarity is smaller than the threshold (NO in S224), the processing proceeds to step S226.

  When the determination of the presence or absence of the feature included in the first shooting data selected in step S222 has not been completed for all the second shooting data (NO in S226), the specifying unit 132 returns to step S223. Steps S223 to S225 are executed for the undetermined second photographing data. If the determination unit 132 determines that all of the second shooting data does not include the feature included in the first shooting data selected in step S222 (YES in S226), the determination unit 132 determines that all of the first shooting data have been processed. It is determined whether or not the search for the second shooting data has been completed for the feature extracted in (2) (S227). If the processing has not been completed for all the features extracted from the first shooting data (NO in S227), the specifying unit 132 returns to step S222 and executes steps S222 to S226.

If the specifying unit 132 specifies a combination of the first shooting data and the second shooting data having similar features with respect to all the features extracted from the first shooting data (YES in S227), the specifying unit 132 has similar features. All the first shooting data and the second shooting data are rearranged so that the first shooting data and the second shooting data are at the same playback position, and shooting is performed at the same timing as shown in FIG. The combination of the obtained first image data and second image data is specified (S228).
After that, the control unit 13 can output the edited data by executing the processing after step S23 shown in FIG.

[Modification 1]
In the above description, an example in which the acquiring unit 131 acquires two photographing files has been described, but the acquiring unit 131 may acquire three or more photographing files. In this case, the specifying unit 132 extracts a similar feature commonly included in at least two or more of the plurality of pieces of photographing data in the plurality of photographing files acquired by the acquiring unit 131, and captures images at the same timing. And specify a plurality of shooting data. Then, the selection unit 133 selects one piece of photographing data based on the quality condition from a plurality of pieces of photographing data photographed at the same timing. By doing so, the user can see the highest quality shooting data among the three or more shooting data.

[Modification 2]
In the above description, the example in which the image processing apparatus 1 acquires a plurality of pieces of photographing data from one user terminal 2 has been described, but the image processing apparatus 1 acquires a plurality of pieces of photographing data from a plurality of different user terminals 2. May be. By doing so, the image processing apparatus 1 acquires, for example, a large number of pieces of photographing data obtained by photographing a large number of people who have participated in one event, and has the best quality among the large number of pieces of acquired photographing data. Edit data can be created by combining the shooting data.

  At this time, the image processing apparatus 1 may receive, from the user terminal 2 of the user who wants to create the composite data, a designation as to which combination of the multiple pieces of image data to create the composite data. For example, the image processing apparatus 1 transmits a thumbnail image of photographing data that can be edited to the user terminal 2 and selects high-quality photographing data from photographing data corresponding to the thumbnail image selected by the user to edit the photographing data. Create data. By doing so, the user can acquire video content in which the subject to be recorded is well reflected.

[Effects of Image Processing Device 1 of Present Embodiment]
As described above, in the image processing apparatus 1, the acquisition unit 131 acquires a plurality of first imaging data and a plurality of second imaging data generated by imaging an object from a plurality of different angles, and 132 specifies the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data. Then, the selection unit 133 selects one of the first shooting data and the second shooting data that are shot at the same timing specified by the specifying unit 132 based on a predetermined quality condition. By doing so, the user can leave a record of the deleted scene while deleting unsuccessful failure images that the user does not want when the subject is photographed from a plurality of angles at the same timing.

  The specifying unit 132 extracts similar features included in each of the plurality of first shooting data and the plurality of second shooting data, and sets a condition that a similarity between the extracted similar features is equal to or greater than a predetermined threshold. , The first shooting data and the second shooting data shot at the same timing are specified. By doing in this way, even when the information regarding the photographing time is not included in the plurality of first photographing data and the plurality of second photographing data, the specifying unit 132 can store the photographing data photographed at the same timing. Can be identified.

  The selection unit 133 can also select shooting data based on the quality of the subject appearing at the highest frequency, the subject showing the largest face, and the subject specified by the user. By doing so, the selection unit 133 can select shooting data with good image quality of the target subject that was shot by the user.

  In addition, the selection unit 133 switches the selected photographing data among the plurality of first photographing data and the plurality of second photographing data until a predetermined time elapses from a camera that has photographed the selected photographing data. Continue to select the photographed data. By doing so, it is possible to prevent the photographic data from being frequently switched when reproducing the edited data.

  As described above, the present invention has been described using the embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It is apparent to those skilled in the art that various changes or improvements can be made to the above embodiment. It is apparent from the description of the appended claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

For example, in the above description, an example is shown in which the composite file conforms to the DVD format, but the composite file may conform to another format such as Blu-ray.
Further, in the above description, an example is described in which the image processing apparatus 1 is a server connected to the user terminal 2 via the Internet, but the image processing apparatus 1 may be a PC (Personal Computer) or a server such as a server on the cloud. Other devices may be used.

1 image processing device 2 user terminal 11 communication unit 12 storage unit 13 control unit 131 acquisition unit 132 identification unit 133 selection unit 134 output unit 100 first camera 200 second camera

Claims (9)

An acquisition unit configured to acquire a plurality of first imaging data generated by imaging by the first imaging device and a plurality of second imaging data generated by imaging by the second imaging device;
A specifying unit that specifies the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data;
The identifying unit identifies the image by comparing the quality of the image of the subject most frequently appearing in the plurality of first shooting data and the plurality of second shooting data acquired by the acquiring unit with a predetermined quality condition. A selecting unit that selects one of the first shooting data and the second shooting data,
An output unit that outputs the imaging data selected by the selection unit,
An image processing apparatus having: An acquisition unit configured to acquire a plurality of first imaging data generated by imaging by the first imaging device and a plurality of second imaging data generated by imaging by the second imaging device;
A specifying unit that specifies the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data;
The identification is performed by comparing the quality of an image of a subject having the largest face area included in the plurality of first shooting data and the plurality of second shooting data acquired by the acquisition unit with a predetermined quality condition. A selection unit that selects any one of the first imaging data and the second imaging data specified by the unit;
An output unit that outputs the imaging data selected by the selection unit,
An image processing apparatus having: The specifying unit extracts a similar feature commonly included in the plurality of first shooting data and the plurality of second shooting data, and a similarity between the extracted similar features is equal to or greater than a predetermined threshold. On the condition that the first photographing data and the second photographing data photographed at the same timing are specified,
The image processing apparatus according to claim 1 or 2. The identification unit, when extracting at least one combination of the first imaging data and the second imaging data including the similar feature, includes first imaging time information of the first imaging data and the second imaging data. By specifying the relationship between the shooting times of the plurality of first shooting data and the shooting times of the plurality of second shooting data based on the difference between the data and the second shooting time information, shooting was performed at the same timing. Specifying the first shooting data and the second shooting data,
The image processing device according to claim 3 . The obtaining unit further obtains subject information that specifies a subject whose quality is to be checked by the selecting unit,
The selecting unit selects one of the photographing data by comparing the quality of the image of the subject corresponding to the subject information with the predetermined quality condition,
The image processing apparatus according to any one of claims 1 to 4. The selection unit is a camera that captures the selected photographing data from the plurality of first photographing data and the plurality of second photographing data until a predetermined time elapses after switching the photographing data to be selected. Continue to select the captured data,
The image processing apparatus according to any one of claims 1 to 5. The selection unit changes the predetermined quality condition before and after a predetermined time elapses after switching the selected shooting data among the plurality of first shooting data and the plurality of second shooting data. Condition
The image processing apparatus according to any one of claims 1 to 6. Obtaining a plurality of first shooting data generated by shooting by the first shooting device and a plurality of second shooting data generated by shooting by the second shooting device;
Identifying the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data;
By comparing the quality of the image of the subject that appears in the acquired plurality of first shooting data and the plurality of second shooting data with the highest frequency with a predetermined quality condition, the specified first shooting data and the specified Selecting any one of the second photographing data;
Outputting the selected shooting data;
An image processing method comprising: Obtaining a plurality of first shooting data generated by shooting by the first shooting device and a plurality of second shooting data generated by shooting by the second shooting device;
Identifying the first shooting data and the second shooting data shot at the same timing among the plurality of first shooting data and the plurality of second shooting data;
By comparing the quality of the image of the subject with the largest face area included in the acquired plurality of first shooting data and the plurality of second shooting data with a predetermined quality condition, the specified first shooting image is obtained. Selecting one of the photographing data from the data and the second photographing data;
Outputting the selected shooting data;
An image processing method comprising: