JP7133433B2 - Generation device, generation method, generation program - Google Patents

Description

The present invention relates to a generating device, a generating method, and a generating program.

Conventionally, techniques for editing moving image information according to display time and the like have been provided.

JP 2006-011358 A

However, with the above-described conventional technology, it is not always possible to provide a user with an appropriately edited moving image. For example, with the above-described conventional technology, if the video information is simply edited to shorten the time, it may be difficult to provide the user with the content of the important parts included in the video information. Therefore, with the above-described conventional technology, it is not always possible to provide a user with an appropriately edited moving image.

The present application has been made in view of the above, and an object thereof is to provide a generating apparatus, a generating method, and a generating program capable of providing a user with an appropriately edited moving image.

The generation device according to the present application adds a weight indicating the importance of a plurality of scenes that constitute a moving image when an object displayed in the moving image satisfies a predetermined condition. and an adding unit, and a generating unit that generates an edited moving image composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the adding unit.

According to one aspect of the embodiment, it is possible to provide a user with an appropriately edited moving image.

FIG. 1 is a diagram illustrating an example of generation processing executed by a generation device according to an embodiment. FIG. 2 is a diagram illustrating an example of processing of an edited moving image generation method executed by the generation device according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of a generating device according to the embodiment; 4 is a diagram illustrating an example of a moving image information storage unit according to the embodiment; FIG. 5 is a diagram illustrating an example of a dictionary information storage unit according to the embodiment; FIG. 6 is a diagram illustrating an example of a weight information storage unit according to the embodiment; FIG. FIG. 7 is a flowchart illustrating an example of the flow of generation processing executed by the generation device according to the embodiment. FIG. 8 is a diagram illustrating an example of processing of an edited moving image generation method executed by a generation device according to a modification. FIG. 9 is a hardware configuration diagram showing an example of a computer that implements the functions of the generation device.

Embodiments (hereinafter referred to as "embodiments") for implementing the generation device, generation method, and generation program according to the present application will be described in detail below with reference to the drawings. Note that the generation device, generation method, and generation program according to the present application are not limited to this embodiment. Further, each embodiment can be appropriately combined within a range that does not contradict the processing contents. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. Example of generation processing indicated by generation device]
An example of generation processing executed by the generation device according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of generation processing executed by a generation device according to an embodiment. Specifically, the generating device 100 edits the moving image received from the user and provides the edited edited moving image to the user. Note that an example of editing a moving image shot by a user will be shown below.

As shown in FIG. 1 , the generation system 1 includes a terminal device 10 and a generation device 100 . The terminal device 10 and the generating device 100 are communicably connected by wire or wirelessly via a predetermined communication network (not shown). Note that the generation system 1 shown in FIG. 1 may include multiple terminal devices 10 and multiple generation devices 100 .

The terminal device 10 according to the embodiment is an information processing device used by a user who accesses content such as web pages displayed on a browser and content for applications. For example, the terminal device 10 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like. The example of FIG. 1 shows a case where the terminal device 10 is a smartphone used by a user. In addition, below, the terminal device 10 may be described as a user. That is, hereinafter, the user can also be read as the terminal device 10 .

The generation device 100 according to the embodiment is realized by, for example, a server device. Specifically, when an object displayed in a moving image satisfies a predetermined condition, the generation device 100 assigns a weight indicating the importance of a plurality of scenes that constitute the moving image and are scenes corresponding to the object. to add. Based on these weights, the generating device 100 generates an edited moving image composed of a predetermined number of scenes among the plurality of scenes.

An example of generation processing by the generation device 100 will be described below along the flow with reference to FIG. 1 .

First, as shown in FIG. 1, the generating device 100 receives information about the moving image MO1 from the terminal device 10 used by the user U1 (step S1). For example, the generating device 100 receives information about the moving image MO1 from the user U1 via an application or the like provided to the user U1.

Next, the generation device 100 classifies objects displayed in the moving image MO1 received from the user U1 into humans and objects other than humans (step S2). Specifically, the generating device 100 classifies the objects displayed in the moving image MO1 into humans and non-human objects using conventional techniques such as machine learning. Objects other than humans as used herein include animals, living things, mobile objects, food, toys, and the like.

For example, assume that an object other than a person is food. In this case, the generation device 100 inputs the moving image MO1 to the learning model that has learned about people and food, and outputs a result of classifying objects displayed in the moving image MO1 into people and food.

The generation device 100 then refers to the dictionary information storage unit and adds the weights of the scenes forming the moving image MO1 (step S3). Specifically, the generation device 100 refers to the dictionary information storage unit that stores information in which objects such as humans and objects other than humans are associated with weights, and displays the weights in the scenes forming the moving image MO1. The weight of the object to be processed is added for each frame of the moving image MO1. Accordingly, the generating device 100 calculates the accumulated weight corresponding to the time of the moving image MO1 by accumulating the weight for each frame of the moving image MO1.

For example, it is assumed that the moving image MO1 is a moving image in which people and food are displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight of food is "+5" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight corresponding to the object stored in the dictionary information storage unit is "-5" when the person is not displayed in the moving image. In this case, the generation device 100 adds “+5” as the weight when the first scene is a scene in which food is displayed. As a result, the accumulated weight becomes "+5" by adding "+5" to the initial weight "0".

Then, the generation device 100 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+12" by adding "+7" to "+5". Then, the generation device 100 adds "-5" as the weight when the next scene is a scene in which no person is displayed. As a result, the accumulated weight becomes "+7" by adding "-5" to "+12". Then, the generation device 100 adds “+7” as the weight when the next scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the generation device 100 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". In this way, the generating device 100 calculates the accumulated weight corresponding to the time of the moving image MO1 by accumulating the weight for each frame of the moving image MO1.

Also, for example, it is assumed that the moving image MO1 is a moving image in which a plurality of people are displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight of a predetermined number of people is "0" as the weight corresponding to the object stored in the dictionary information storage unit. In this case, the generation device 100 adds “+7” as the weight when the first scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+7" by adding "+7" to the initial weight "0".

Then, the generation device 100 adds "0" as the weight when the next scene is a scene in which a predetermined number of people are displayed. As a result, the accumulated weight becomes "+7" by adding "0" to "+7". Then, the generation device 100 adds “+7” as the weight when the next scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the generation device 100 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". In this way, the generating device 100 calculates the accumulated weight corresponding to the time of the moving image MO1 by accumulating the weight for each frame of the moving image MO1.

Also, for example, it is assumed that the moving image MO1 is a moving image in which a person is displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. Also, if a scene in which the coordinates of a person do not change continues three times in a row, the weight is further increased by "+10". In this case, the generation device 100 adds “+7” as the weight when the first scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+7" by adding "+7" to the initial weight "0".

Then, the generation device 100 adds "+7" as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the generation device 100 adds "+7" as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". Then, the generation device 100 adds "+7" as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. Thus, the accumulated weight becomes "+28" by adding "+7" to "+21". In addition, the generation device 100 further adds the weight “+10” when scenes in which the coordinates of the person do not change continue three times in a row. As a result, the accumulated weight becomes "+38" by adding "+10" to "+28". In this way, the generating device 100 calculates the accumulated weight corresponding to the time of the moving image MO1 by accumulating the weight for each frame of the moving image MO1.

Note that the generating apparatus 100 accumulates the weight for each frame of the moving image MO1, so that the weight is accumulated for each time in the moving image, not limited to the calculation process of calculating the accumulated weight corresponding to the time of the moving image MO1. Thus, the accumulated weight corresponding to the time of the moving image MO1 may be calculated. For example, the generation device 100 may calculate the accumulated weight corresponding to the time of the moving image MO1 by accumulating the weight for each second.

Subsequently, the generating device 100 selects scenes based on the weight of each scene and generates the edited moving image EM1 (step S4). Specifically, the generating device 100 selects scenes whose weights are greater than or equal to a predetermined threshold. Then, the generating device 100 generates an edited moving image EM1 composed of the selected scenes.

Here, a method for generating the edited moving image EM1 will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of processing of a method for generating an edited moving image executed by the generating device 100 according to the embodiment. As shown in FIG. 2, FIG. FG1 shows the change of the weight corresponding to the time of the moving image MO1. The vertical axis of FIG. FG1 indicates the added weight value. The horizontal axis of FIG. FG1 indicates the time in the movie MO1. Diagram FG1 includes a representation of a predetermined weight threshold. For example, in FIG. FG1, a plurality of scenes SE1, SE2, and SE3 within a predetermined range are scenes having a predetermined weight threshold or more.

Also, as shown in FIG. 2, FIG. FG2 shows a moving image including a plurality of scenes SE1, SE2, and SE3 within a predetermined range that are equal to or greater than a predetermined weight threshold. That is, this moving image corresponds to the edited moving image EM1.

For example, the generating device 100 assumes that the weight threshold is "70". In this case, the generating device 100 selects a plurality of scenes SE1, SE2, and SE3 within a predetermined range whose weight is equal to or greater than the weight threshold from the moving image MO1. Then, the generating device 100 generates the edited moving image EM1 based on the multiple selected scenes.

Returning to FIG. 1, an example of generation processing according to the embodiment will be described. The generating device 100 provides the user U1 with information on the edited moving image EM1 as an edited moving image corresponding to the moving image MO1 (step S5).

In this way, the generation device 100 according to the embodiment adds weights indicating the degrees of importance of a plurality of scenes forming the moving image when the object displayed in the moving image satisfies a predetermined condition. Based on these weights, the generating device 100 generates an edited moving image composed of a predetermined number of scenes among the plurality of scenes. As a result, the generation device 100 according to the embodiment can select a scene in which a specific object is displayed, thereby providing a user with an appropriately edited moving image. This point will be explained. To explain using the example of FIG. 1, the generation device 100 selects a scene in which the specific object is displayed by increasing the weight of the specific object included in the moving image MO1 received from the user U1. do. Then, the generating device 100 generates an edited moving image EM1 composed of the selected scenes. Further, to explain using the example of FIG. 2, the generation device 100 adds the weights of the plurality of scenes forming the moving image MO1 so as to accumulate the weights for each frame of the moving image MO1. As a result, the generation device 100 selects a plurality of scenes showing weights equal to or greater than a predetermined threshold, thereby preventing the scenes in the edited moving image from being jumpy and reducing deterioration in the quality of the edited moving image. can. Therefore, the generating device 100 can select a scene in which a specific target object is displayed with high accuracy. Therefore, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. .

[2. Configuration of generation device]
Next, the configuration of the generation device 100 according to the embodiment will be described using FIG. FIG. 3 is a diagram illustrating a configuration example of the generation device 100 according to the embodiment. As shown in FIG. 3, the generation device 100 has a communication unit 110, a storage unit 120, and a control unit .

(Regarding communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from the terminal device 10 .

(Regarding storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or an optical disk. Storage unit 120 has moving image information storage unit 121 , dictionary information storage unit 122 , and weight information storage unit 123 .

(Regarding the moving image information storage unit 121)
The moving image information storage unit 121 according to the embodiment stores information related to moving images received from users. Here, FIG. 4 shows an example of the moving image information storage unit 121 according to the embodiment. In the example shown in FIG. 4, the moving image information storage unit 121 has items such as "moving image ID", "user ID", and "moving image".

“Movie ID” is an identifier for identifying a movie. "User ID" is an identifier that identifies a user. “Movie” is information about a movie received from the user associated with the “user ID”. For example, in FIG. 4, "M1" identified by the movie ID has "MO1" as the movie received from "U1" identified by the user ID. In the example shown in FIG. 4, moving images are represented by abstract codes such as "MO1", but the moving images may be information or the like indicating a specific file format of the moving images.

(Regarding dictionary information storage unit 122)
The dictionary information storage unit 122 according to the embodiment stores information about weights corresponding to objects. Here, FIG. 5 shows an example of the dictionary information storage unit 122 according to the embodiment. In the example shown in FIG. 5, the dictionary information storage unit 122 has items such as "dictionary ID", "item", and "weight".

"Dictionary ID" is an identifier that identifies an item of an object stored in the dictionary. The “item” is information about the item of the type of object associated with the “dictionary ID”. Also, "item" includes information about the manner in which the object is displayed in the moving image. "Weight" is information about the weight corresponding to the item of the object associated with the "dictionary ID". For example, in FIG. 5, "D1" identified by the dictionary ID has an item of "food" and a weight of "+5".

(Regarding weight information storage unit 123)
The weight information storage unit 123 according to the embodiment stores information regarding added weights of moving images received from users. Here, FIG. 6 shows an example of the weight information storage unit 123 according to the embodiment. In the example shown in FIG. 6, the weight information storage unit 123 has items such as "weight ID", "video ID", "time", and "weight".

"Weight ID" is an identifier for identifying a weight. “Movie ID” is an identifier for identifying a movie received from the user. "Time" is information about the time in the moving image. “Weight” is information about the weight added so as to be accumulated for each frame of the moving image MO1. For example, in FIG. 6, "W1" identified by the weight ID has a time "T1" corresponding to "M1" identified by the moving image ID, and the weight is "0".

(Regarding the control unit 130)
The control unit 130 is a controller, and for example, various programs (an example of a generation program) stored in a storage device inside the generation device 100 are controlled by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. equivalent) is implemented by executing the RAM as a work area. Also, the control unit 130 is a controller, and is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3 , the control unit 130 includes a reception unit 131, a classification unit 132, an addition unit 133, a selection unit 134, a generation unit 135, and a provision unit 136, and includes information described below. Realize or perform the function or action of a process. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it performs information processing described later. Moreover, the connection relationship between the processing units of the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

(Regarding the reception unit 131)
The reception unit 131 receives information about moving images from the terminal device 10 used by the user. For example, the reception unit 131 receives information about moving images from the user via an application provided to the user. Then, the reception unit 131 stores information about the moving image in the moving image information storage unit 121 .

(Regarding the classification unit 132)
The classification unit 132 classifies objects displayed in the moving image received by the reception unit 131 into humans and non-human objects. Specifically, the classification unit 132 classifies the objects displayed in the moving image into humans and non-human objects by conventional techniques such as machine learning. For example, assume that an object other than a person is food. In this case, the classification unit 132 outputs a result of classifying the objects displayed in the moving image into the human and the food by inputting the moving image to the learning model that has learned the person and the food.

(Regarding the adder 133)

The addition unit 133 adds weights indicating the importance of a plurality of scenes that constitute the moving image and are scenes corresponding to the object when the object displayed in the moving image satisfies a predetermined condition. Specifically, the adding unit 133 adds the weight of the first scene in which the object displayed in the moving image satisfies a predetermined condition to the weight of the second scene in which the object displayed in the moving image satisfies the predetermined condition. are cumulatively added. More specifically, the addition unit 133 refers to the dictionary information storage unit 122 that stores information in which objects such as humans and objects other than humans are associated with weights, and adds weights to scenes forming a moving image. The scene weight is added by calculating the weight of the displayed object.

For example, it is assumed that the moving image MO1 is a moving image in which people and food are displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight of food is "+5" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight corresponding to the object stored in the dictionary information storage unit is "-5" when the person is not displayed in the moving image. In this case, the addition unit 133 adds “+5” as the weight when the first scene is a scene in which food is displayed. As a result, the accumulated weight becomes "+5" by adding "+5" to the initial weight "0".

Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+12" by adding "+7" to "+5". Then, the addition unit 133 adds “−5” as the weight when the next scene is a scene in which no person is displayed. As a result, the accumulated weight becomes "+7" by adding "-5" to "+12". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". In this way, the addition unit 133 accumulates the weights for each frame of the moving image MO1, thereby calculating the accumulated weight corresponding to the time of the moving image MO1. Then, the addition unit 133 stores the weight of the moving image in the weight information storage unit 123 in a format corresponding to the time of the moving image.

Also, for example, it is assumed that the moving image MO1 is a moving image in which a plurality of people are displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight of a predetermined number of people is "0" as the weight corresponding to the object stored in the dictionary information storage unit. In this case, the addition unit 133 adds “+7” as the weight when the first scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+7" by adding "+7" to the initial weight "0".

Then, the addition unit 133 adds “0” as the weight when the next scene is a scene in which a predetermined number of people are displayed. As a result, the accumulated weight becomes "+7" by adding "0" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". In this way, the addition unit 133 accumulates the weights for each frame of the moving image MO1, thereby calculating the accumulated weight corresponding to the time of the moving image MO1. Then, the addition unit 133 stores the weight of the moving image in the weight information storage unit 123 in a format corresponding to the time of the moving image.

Also, for example, it is assumed that the moving image MO1 is a moving image in which a person is displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. Also, if a scene in which the coordinates of a person do not change continues three times in a row, the weight is further increased by "+10". In this case, the addition unit 133 adds “+7” as the weight when the first scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+7" by adding "+7" to the initial weight "0".

Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. Thus, the accumulated weight becomes "+28" by adding "+7" to "+21". In addition, the adding unit 133 further adds the weight “+10” when scenes in which the coordinates of the person do not change continue three times. As a result, the accumulated weight becomes "+38" by adding "+10" to "+28". In this way, the addition unit 133 accumulates the weights for each frame of the moving image MO1, thereby calculating the accumulated weight corresponding to the time of the moving image MO1. Then, the addition unit 133 stores the weight of the moving image in the weight information storage unit 123 in a format corresponding to the time of the moving image.

(Regarding the selection unit 134)
The selection unit 134 selects a predetermined number of scenes from the plurality of scenes based on the weights added by the addition unit 133 . Specifically, the selection unit 134 selects a predetermined number of scenes from a plurality of scenes when the weight added by the addition unit 133 is equal to or greater than a predetermined threshold. For example, the selection unit 134 selects scenes whose weights stored in the weight information storage unit 123 are equal to or greater than a predetermined threshold. For example, the selection unit 134 assumes that the weight threshold is "70". In this case, the selection unit 134 selects a plurality of scenes whose weight is equal to or greater than the threshold value from the moving image.

(Regarding the generation unit 135)
The generation unit 135 generates an edited moving image composed of the predetermined number of scenes selected by the selection unit 134 . For example, the generation unit 135 generates an edited moving image based on multiple scenes selected by the selection unit 134 .

(Regarding the providing unit 136)
The providing unit 136 provides the user with information on the edited moving image as an edited moving image corresponding to the moving image. For example, the providing unit 136 refers to the weight information storage unit 123 and provides the user with information about the edited moving image as an edited moving image corresponding to the moving image.

[3. Flowchart of generation processing]
Next, with reference to FIG. 7, a procedure of generation processing executed by the generation device 100 according to the embodiment will be described. FIG. 7 is a flowchart illustrating an example of the flow of generation processing executed by the generation device according to the embodiment.

As shown in FIG. 7, the reception unit 131 receives information about the moving image MO1 from the user U1 (step S101). Then, if the accepting unit 131 has not accepted the moving image MO1 from the user U1 (step S101; No), the classifying unit 132 waits until accepting the moving image MO1 from the user U1.

On the other hand, when the receiving unit 131 receives the moving image MO1 from the user U1 (step S101; Yes), the classifying unit 132 classifies the objects displayed in the moving image MO1 into people and objects other than people (step S102). . For example, assume that an object other than a person is food. In this case, the classification unit 132 outputs a result of classifying the objects displayed in the moving image into the human and the food by inputting the moving image to the learning model that has learned the person and the food.

The addition unit 133 then refers to the dictionary information storage unit 122 and adds the weights of the scenes forming the moving image MO1 (step S103). For example, it is assumed that the moving image MO1 is a moving image in which people and food are displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight of food is "+5" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight corresponding to the object stored in the dictionary information storage unit is "-5" when the person is not displayed in the moving image. In this case, the addition unit 133 adds “+5” as the weight when the first scene is a scene in which food is displayed. As a result, the accumulated weight becomes "+5" by adding "+5" to the initial weight "0".

Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+12" by adding "+7" to "+5". Then, the addition unit 133 adds “−5” as the weight when the next scene is a scene in which no person is displayed. As a result, the accumulated weight becomes "+7" by adding "-5" to "+12". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". In this way, the addition unit 133 accumulates the weights for each frame of the moving image MO1, thereby calculating the accumulated weight corresponding to the time of the moving image MO1. Then, the addition unit 133 stores the weight of the moving image in the weight information storage unit 123 in a format corresponding to the time of the moving image.

Also, for example, it is assumed that the moving image MO1 is a moving image in which a plurality of people are displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. It is also assumed that the weight of a predetermined number of people is "0" as the weight corresponding to the object stored in the dictionary information storage unit. In this case, the addition unit 133 adds “+7” as the weight when the first scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+7" by adding "+7" to the initial weight "0".

Then, the addition unit 133 adds “0” as the weight when the next scene is a scene in which a predetermined number of people are displayed. As a result, the accumulated weight becomes "+7" by adding "0" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". In this way, the addition unit 133 accumulates the weights for each frame of the moving image MO1, thereby calculating the accumulated weight corresponding to the time of the moving image MO1. Then, the addition unit 133 stores the weight of the moving image in the weight information storage unit 123 in a format corresponding to the time of the moving image.

Also, for example, it is assumed that the moving image MO1 is a moving image in which a person is displayed. It is also assumed that the human weight is "+7" as the weight corresponding to the object stored in the dictionary information storage unit. Also, if a scene in which the coordinates of a person do not change continues three times in a row, the weight is further increased by "+10". In this case, the addition unit 133 adds “+7” as the weight when the first scene is a scene in which a person is displayed. As a result, the accumulated weight becomes "+7" by adding "+7" to the initial weight "0".

Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. As a result, the accumulated weight becomes "+14" by adding "+7" to "+7". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. Thus, the accumulated weight becomes "+21" by adding "+7" to "+14". Then, the addition unit 133 adds “+7” as the weight when the next scene is a scene in which a person is displayed and the coordinates of the person do not change from the previous scene. Thus, the accumulated weight becomes "+28" by adding "+7" to "+21". In addition, the adding unit 133 further adds the weight “+10” when scenes in which the coordinates of the person do not change continue three times. As a result, the accumulated weight becomes "+38" by adding "+10" to "+28". In this way, the addition unit 133 accumulates the weights for each frame of the moving image MO1, thereby calculating the accumulated weight corresponding to the time of the moving image MO1. Then, the addition unit 133 stores the weight of the moving image in the weight information storage unit 123 in a format corresponding to the time of the moving image.

Then, the selection unit 134 selects a scene based on the weight of each scene added by the addition unit 133 (step S104). For example, the selection unit 134 selects scenes whose weights stored in the weight information storage unit 123 are equal to or greater than a predetermined threshold. For example, the selection unit 134 assumes that the weight threshold is "70". In this case, the selection unit 134 selects a plurality of scenes whose weight is equal to or greater than the threshold value from the moving image. Then, the generation unit 135 generates an edited moving image EM1 composed of a plurality of scenes selected by the selection unit 134 (step S105).

[4. Modification]
The generating device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the generation device 100 will be described below.

[4-1. Object〕
In the above embodiment, an example was described in which information in which objects such as humans and objects other than humans are associated with weights is stored in the dictionary information storage unit 122 of the generation device 100. The weights stored in 122 may not be limited to objects only. For example, the dictionary information storage unit 122 may store information about the weight corresponding to the voice of a person who is not the object.

[4-2. Addition processing Change the weight according to the purpose]
In the above-described embodiment, the addition unit 133 of the generation device 100 constructs a moving image by referring to the dictionary information storage unit 122 that stores information in which objects such as humans and objects other than humans are associated with weights. An example of addition processing for adding the weight of a scene by calculating the weight of an object displayed in the scene has been described. Weights may be added with reference to weights that vary according to . Specifically, the adding unit 133 may accumulate the weight of each frame of the moving image based on the weight that varies according to the provider of the edited moving image. For example, it is assumed that the user has registered with SNS (Social Networking Service). It is also assumed that videos of food are frequently posted on SNSs used by users. In this case, the addition unit 133 refers to the dictionary information storage unit 122 that stores weights that are uniformly increased by “+5” to the food weights corresponding to the SNS, and accumulates the weights for each frame of the moving image. may be added.

As a result, the addition unit 133 of the generation device 100 according to the embodiment can perform addition so as to accumulate the weight for each frame of the video based on the weight optimized for each SNS posted by the user. A weight suitable for the mode in which the edited moving image is posted by the user can be added.

[4-3. Selection processing (1) Double speed when scenes of a specific object continue]
In the above-described embodiment, an example of selection processing in which the selection unit 134 of the generation device 100 selects a predetermined number of scenes from a plurality of scenes when the weight added by the addition unit 133 is equal to or greater than a predetermined threshold has been described. , when the weight added by the addition unit 133 does not change between the scenes before and after the moving image, a predetermined number of scenes including a scene in which the moving image display speed is increased with respect to the scene are selected from a plurality of scenes. good too. For example, the selection unit 134 selects a predetermined number of scenes including a scene whose moving image display speed is doubled with respect to scenes whose weights stored in the weight information storage unit 123 do not change.

As a result, the selection unit 134 of the generation device 100 according to the embodiment selects a predetermined number of scenes from a plurality of scenes, including a scene whose moving image display speed is doubled with respect to the scene before and after the scene does not change. Since it can be selected, redundant scenes can be removed from the edited video.

[4-4. Selection processing (2) Selection of video time]
In the above-described embodiment, an example of selection processing in which the selection unit 134 of the generation device 100 selects a predetermined number of scenes from a plurality of scenes when the weight added by the addition unit 133 is equal to or greater than a predetermined threshold has been described. , based on the weights added by the addition unit 133, a predetermined number of scenes corresponding to the time of the moving image may be selected from a plurality of scenes. For example, it is assumed that the total duration of the moving image received from the user is "5 minutes". It is also assumed that the user has designated the total time of the moving image to be "3 minutes". In this case, the selection unit 134 selects a predetermined number of scenes by excluding scenes whose weights stored in the weight information storage unit 123 do not change, so that an edited video with a total video time of “3 minutes” can be generated. select.

As a result, the selection unit 134 of the generation device 100 according to the embodiment can select a predetermined number of scenes corresponding to the time of the moving image from a plurality of scenes, so redundant scenes can be removed from the edited moving image.

[4-5. Selection processing (3) Selection when weight is added]
In the above-described embodiment, an example of selection processing in which the selection unit 134 of the generation device 100 selects a predetermined number of scenes from a plurality of scenes when the weight added by the addition unit 133 is equal to or greater than a predetermined threshold has been described. , a predetermined number of scenes corresponding to the weights added by the adder 133 may be selected from a plurality of scenes.

Here, a method for generating the edited moving image EM21 will be described with reference to FIG. FIG. 8 is a diagram showing an example of the process of the edited moving image generation method executed by the generation device 100 according to the modification. As shown in FIG. 8, FIG. FG21 shows changes in weight corresponding to time of the moving image MO1. The vertical axis of FIG. FG21 indicates the added weight value. The horizontal axis of FIG. FG21 indicates the time in the moving image MO1. FIG. FG21 includes a representation of a predetermined weight threshold. For example, in FIG. FG21, a plurality of scenes SE1, SE2, and SE3 within a predetermined range are scenes having a predetermined weight threshold or more.

Also, as shown in FIG. 8, FIG. FG22 shows a moving image including a plurality of scenes SE21, SE22, and SE23 within a predetermined range that are equal to or greater than a predetermined weight threshold. That is, this moving image corresponds to the edited moving image EM1.

For example, the selection unit 134 assumes that the weight threshold is "70". In this case, the selection unit 134 selects a plurality of scenes SE21, SE22, and SE23 within a predetermined range that is equal to or greater than the weight threshold from the moving image MO1.

As a result, the selection unit 134 of the generation device 100 according to the embodiment can select a plurality of scenes showing weights equal to or greater than a predetermined threshold and within a range in which the weights increase. In addition to preventing jumpy scenes in the edited moving image, it is also possible to eliminate long and redundant scenes.

[4-6. weight〕
In the above embodiment, an example has been described in which the dictionary information storage unit 122 of the generation device 100 stores information about “−5” as a weight for scenes in which there is no person. The weights to be used need not be limited to the above. For example, the dictionary information storage unit 122 may store information about "0" as a weight for a scene without people.

[4-7. movie〕
In the above-described embodiment, an example of the processing in which the reception unit 131 of the generation device 100 receives a video shot by the user with the terminal device 10 has been described. It is not limited and may be any moving image.

[5. Hardware configuration]
Also, the terminal device 10 and the generating device 100 according to the above-described embodiments are implemented by a computer 1000 configured as shown in FIG. 9, for example. The generation device 100 will be described below as an example. FIG. 9 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the generating device 100. As shown in FIG. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, a HDD (Hard Disk Drive) 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F). ) 1700.

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400 and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via network N, sends the data to CPU 1100, and transmits data generated by CPU 1100 via network N to other devices.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . Also, CPU 1100 outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the generation device 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control unit 130 by executing programs loaded on the RAM 1200 . In addition, data in storage unit 120 is stored in HDD 1400 . The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired via the network N from another device.

[6. others〕
Further, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or described as being performed manually. All or part of the processing can also be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing content.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the generating unit can be read as generating means or a generating circuit.

[7. effect〕
As described above, the generating device 100 according to the embodiment has the adding section 133 and the generating section 135 . The addition unit 133 adds weights indicating the degrees of importance of a plurality of scenes forming a moving image when an object displayed in the moving image satisfies a predetermined condition. The generation unit 135 generates an edited moving image composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit 133 .

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

In addition, in the generation device 100 according to the embodiment, the adding unit 133 adds the weight of the first scene where the object displayed in the moving image satisfies a predetermined condition to the weight of the first scene, and the object displayed in the moving image satisfies the predetermined condition. A selection unit 134 that adds the weights of the second scenes and selects a predetermined number of scenes from a plurality of scenes based on the weights added by the addition unit 133 . An edited moving image is generated from a predetermined number of scenes.

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

Further, in the generation device 100 according to the embodiment, the selection unit 134 selects a predetermined number of scenes from a plurality of scenes when the weight added by the addition unit 133 is equal to or greater than a predetermined threshold.

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

In addition, in the generation device 100 according to the embodiment, the selection unit 134 selects a predetermined number of scenes corresponding to the weights added by the addition unit 133 from a plurality of scenes.

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

In addition, in the generation device 100 according to the embodiment, when the weight added by the addition unit 133 does not change between the scenes before and after the moving image, the selection unit 134 selects a predetermined number of scenes that do not include the scene as a plurality of scenes. Select from scenes.

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

In addition, in the generation device 100 according to the embodiment, the selection unit 134 selects a predetermined number of scenes corresponding to the time of the moving image from a plurality of scenes based on the weights added by the addition unit 133 .

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

In addition, in the generation device 100 according to the embodiment, the addition unit 133 includes a storage unit that stores information in which objects and weights are associated with each other when objects displayed in a moving image satisfy predetermined conditions. Look up and add weights.

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image by focusing on the weight corresponding to the specific object, and thus can provide the user with an appropriately edited moving image. can.

In addition, in the generation device 100 according to the embodiment, the addition unit 133 is a weight stored in the storage unit when the object displayed in the moving image satisfies a predetermined condition, and is a weight according to the provider of the edited moving image. The weights are added with reference to the weights that are varied by

As a result, the generation device 100 according to the embodiment can select an appropriate scene from the moving image according to the destination of the edited moving image, and thus can provide the user with an appropriately edited moving image.

In addition, in the generation device 100 according to the embodiment, the adding unit 133 may set, as a predetermined condition, when an object displayed in a moving image is a person, a human voice, an animal, a creature, a moving object, food, or a toy. , add the weights.

As a result, the generating apparatus 100 according to the embodiment can select appropriate scenes from the moving image by focusing on the weights corresponding to various objects, thereby providing the user with an appropriately edited moving image. can.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

1 generation system 10 terminal device 100 generation device 110 communication unit 120 storage unit 121 moving image information storage unit 122 dictionary information storage unit 123 weight information storage unit 130 control unit 131 reception unit 132 classification unit 133 addition unit 134 selection unit 135 generation unit 136 provided Department

Claims (17)

an addition unit for adding a weight indicating the importance of a scene corresponding to each frame of a moving image when an object displayed in the moving image satisfies a predetermined condition;
a generating unit that generates an edited moving image composed of a predetermined number of scenes among a plurality of scenes that constitute the moving image based on the weights added by the adding unit;
with
The addition unit
When an object displayed in the moving image satisfies a predetermined condition, the weight associated with the object is obtained by referring to the storage unit that stores information in which the object and the weight are associated with each other. add as weights,
A generating device characterized by: The weight of a first scene in which an object displayed in the moving image satisfies a predetermined condition is added so as to accumulate the weight of a second scene in which an object displayed in the moving image satisfies a predetermined condition. death,
a selection unit that selects a predetermined number of scenes, which is less than the number of all scenes showing the moving image, from among a plurality of scenes corresponding to weights equal to or greater than a predetermined threshold among the weights added by the addition unit; further prepared,
The generating unit
generating the edited video composed of a predetermined number of scenes selected by the selection unit;
The generation device according to claim 1, characterized in that: The selection unit
selecting the predetermined number of scenes from the plurality of scenes when the weight added by the adding unit is equal to or greater than a predetermined threshold;
3. The generator according to claim 2, characterized by: The selection unit
selecting the predetermined number of scenes corresponding to the weights added by the adding unit from the plurality of scenes;
4. The generator according to claim 2 or 3, characterized in that: The selection unit
selecting from the plurality of scenes the predetermined number of scenes including the scene in which the display speed of the moving image is increased when the weight added by the adding unit does not change between the scenes before and after the moving image;
The generator according to any one of claims 2 to 4, characterized in that: The selection unit
Selecting the predetermined number of scenes corresponding to the time of the moving image from the plurality of scenes based on the weights added by the adding unit;
The generator according to any one of claims 2 to 5, characterized in that: The addition unit
When the object displayed in the moving image satisfies a predetermined condition, the weight stored in the storage unit and changed according to the provider of the edited moving image is referenced, and the weight is calculated by referring to the weight stored in the storage unit. to add,
The generation device according to claim 1 , characterized in that: The addition unit
As the predetermined condition, the weight is added when the object displayed in the moving image is a person, a human voice, an animal, a creature, a moving object, food, or a toy.
The generator according to any one of claims 1 to 7 , characterized in that: an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The weight of a first scene in which an object displayed in the moving image satisfies a predetermined condition is added so as to accumulate the weight of a second scene in which an object displayed in the moving image satisfies a predetermined condition. death,
a selection unit that selects a predetermined number of scenes, which is less than the number of all scenes showing the moving image, from among a plurality of scenes corresponding to weights equal to or greater than a predetermined threshold among the weights added by the addition unit; further prepared,
The generating unit
A generation device that generates the edited moving image composed of a predetermined number of scenes selected by the selection unit. an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The weight of a first scene in which an object displayed in the moving image satisfies a predetermined condition is added so as to accumulate the weight of a second scene in which an object displayed in the moving image satisfies a predetermined condition. death,
a selection unit that selects a predetermined number of scenes, which is less than the number of all scenes showing the moving image, from among a plurality of scenes corresponding to weights equal to or greater than a predetermined threshold among the weights added by the addition unit; further prepared,
The generating unit
generating the edited video composed of a predetermined number of scenes selected by the selection unit;
The selection unit
The generation device, wherein the predetermined number of scenes are selected from the plurality of scenes when the weight added by the addition unit is equal to or greater than a predetermined threshold. an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The weight of a first scene in which an object displayed in the moving image satisfies a predetermined condition is added so as to accumulate the weight of a second scene in which an object displayed in the moving image satisfies a predetermined condition. death,
a selection unit that selects a predetermined number of scenes, which is less than the number of all scenes showing the moving image, from among a plurality of scenes corresponding to weights equal to or greater than a predetermined threshold among the weights added by the addition unit; further prepared,
The generating unit
generating the edited video composed of a predetermined number of scenes selected by the selection unit;
The selection unit
The generation device, wherein the predetermined number of scenes corresponding to the weights added by the addition unit are selected from the plurality of scenes. an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The weight of a first scene in which an object displayed in the moving image satisfies a predetermined condition is added so as to accumulate the weight of a second scene in which an object displayed in the moving image satisfies a predetermined condition. death,
a selection unit that selects a predetermined number of scenes, which is less than the number of all scenes showing the moving image, from among a plurality of scenes corresponding to weights equal to or greater than a predetermined threshold among the weights added by the addition unit; further prepared,
The generating unit
generating the edited video composed of a predetermined number of scenes selected by the selection unit;
The selection unit
When the weight added by the addition unit does not change between the scenes before and after the moving image, the predetermined number of scenes including the scene whose moving image display speed is increased are selected from the plurality of scenes. generator. an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The weight of a first scene in which an object displayed in the moving image satisfies a predetermined condition is added so as to accumulate the weight of a second scene in which an object displayed in the moving image satisfies a predetermined condition. death,
a selection unit that selects a predetermined number of scenes, which is less than the number of all scenes showing the moving image, from among a plurality of scenes corresponding to weights equal to or greater than a predetermined threshold among the weights added by the addition unit; further prepared,
The generating unit
generating the edited video composed of a predetermined number of scenes selected by the selection unit;
The selection unit
The generation device, wherein the predetermined number of scenes corresponding to the time of the moving image are selected from the plurality of scenes based on the weights added by the addition unit. an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The addition unit
When an object displayed in the moving image satisfies a predetermined condition, the weight associated with the object is obtained by referring to the storage unit that stores information in which the object and the weight are associated with each other. Add as a weight,
The addition unit
When the object displayed in the moving image satisfies a predetermined condition, the weight stored in the storage unit and changed according to the provider of the edited moving image is referenced, and the weight is calculated by referring to the weight stored in the storage unit. A generating device characterized by adding. an addition unit that adds weights indicating the importance of a plurality of scenes that constitute a moving image and are scenes corresponding to the target object displayed in the moving image when the target object satisfies a predetermined condition;
a generation unit that generates an edited video composed of a predetermined number of scenes among the plurality of scenes based on the weights added by the addition unit;
with
The addition unit
When an object displayed in the moving image satisfies a predetermined condition, the weight associated with the object is obtained by referring to the storage unit that stores information in which the object and the weight are associated with each other. Add as a weight,
The addition unit
The generating device adds the weight when the object displayed in the moving image is a person, a human voice, an animal, a creature, a mobile object, food, or a toy as the predetermined condition. A computer implemented method of generation comprising:
an addition step of, when an object displayed in a moving image satisfies a predetermined condition, adding a weight indicating the importance of a scene corresponding to the object in each frame of the moving image;
a generating step of generating an edited moving image composed of a predetermined number of scenes among a plurality of scenes constituting the moving image based on the weights added in the adding step;
including
The addition step includes
When an object displayed in the moving image satisfies a predetermined condition, the weight associated with the object is obtained by referring to the storage unit that stores information in which the object and the weight are associated with each other. add as weights,
A generation method characterized by: an adding step of adding a weight indicating the importance of a scene corresponding to each frame of a moving image when an object displayed in the moving image satisfies a predetermined condition;
a generating procedure for generating an edited moving image composed of a predetermined number of scenes among a plurality of scenes constituting the moving image based on the weights added by the adding procedure;
on the computer, and
The addition procedure includes:
When an object displayed in the moving image satisfies a predetermined condition, the weight associated with the object is obtained by referring to the storage unit that stores information in which the object and the weight are associated with each other. add as weights,
A generating program characterized by:

Images