JP6648930B2 - Editing device, editing method and program - Google Patents

Description

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

  2. Description of the Related Art Conventionally, a technique is known in which a plurality of pieces of video data is divided into arbitrary sections, and partial video in each of the divided sections is combined or replaced to create new video data. Patent Literature 1 discloses a technique for creating a common story from a plurality of news videos explaining the same matter and generating a news video reconstructed along the story. Further, Patent Literature 2 discloses a technique of editing video data by exchanging contents so as to maintain the original intentions of the authors of the contents, that is, the identity of the contents to some extent. Further, Patent Literature 3 discloses a technique in which, when an error occurs during reception of broadcast content, correction is performed using content received from another device.

JP 2008-537627 A JP 2007-207405 A JP 2008-160698 A

  However, when creating a video for a specific purpose such as work education, there is a problem that it is difficult to select a video according to the purpose. For example, when a plurality of videos are edited to create a video for education of one work, there is a problem that an angle is not desirable and a partial video in which a work target is hidden behind a worker is employed. . In addition, there is a problem that, although there is another image whose work content is easy to understand, another partial image is adopted. In addition, there is also a problem that it is troublesome to manually edit such a video.

  The present invention has been made in view of such problems, and has as its object to perform appropriate editing of video data without requiring a complicated operation by a user.

  Therefore, the present invention is an editing apparatus for editing a work video, and extracts a partial video of each process from each of a plurality of work videos related to the same work based on a work time of each process included in the work. Selecting means for selecting a representative partial video of each step from a plurality of partial videos extracted from each of the plurality of work videos based on the extracting means, the work information indicating the work content, and the partial video And a reconstructing unit that connects the representative partial images of the respective steps selected by the selecting unit and generates an edited video.

  According to the present invention, it is possible to perform appropriate editing of video data without requiring a complicated operation by a user.

It is a figure showing a picture management system. FIG. 3 is a diagram illustrating a hardware configuration of an editing device. FIG. 3 is a diagram illustrating a software configuration of the editing device. FIG. 3 is a diagram illustrating an example of document data. It is a flowchart which shows the preparation process of an edit video. It is an explanatory view of a process. It is a flowchart which shows the update process of an edit video. It is a flow chart which shows a part of creation processing concerning a 2nd embodiment. It is an explanatory view of a process.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram illustrating a video management system according to the first embodiment. The video management system includes an editing device 100 for editing an image, and a plurality of cameras 110 connected to the editing device 100 via a network. Each camera 110 captures an image of a state 120 in which the worker is working, that is, a work image. The work video obtained by each camera 110 is recorded in the editing device 100. The editing apparatus 100 creates an edited video by dividing each of the working videos obtained by each camera 110 into a plurality of partial videos and performing an editing process of joining the partial videos. The editing device 100 according to the present embodiment generates an educational image for educating a worker in an article manufacturing factory by editing a work image. It should be noted that the camera 110 is not provided for the purpose of generating educational videos, but may be used for other purposes such as monitoring work.

  FIG. 2 is a diagram illustrating a hardware configuration of the editing device 100. The CPU 201 executes processing using computer programs and data stored in the RAM 206 and the ROM 207. In this way, the CPU 201 controls the operation of the entire editing apparatus 100 and executes each process described below as being performed by the editing apparatus 100. The input device 202 is a user interface such as a group of buttons, and can perform various inputs to the editing device 100 by operating the user. The output device 203 includes a liquid crystal screen, a speaker, and the like, and can display a processing result of the CPU 201 and output sound. The touch panel screen may be configured by combining the user interface function of the input device 202 and the display function of the output device 203.

  The communication device 204 includes an interface such as a USB port and a LAN port for receiving input / output of data from outside. The communication device 204 is connected to the camera 110, a medium on which a work video and a recorded video are recorded, and inputs and outputs processing target data.

  The storage device 205 includes a hard disk drive device, a flash memory, and the like. The storage device 205 stores an OS (Operating System) and computer programs and data for causing the CPU 201 to execute or control each process to be described later that the editing device 100 performs. In the following description, the storage destination of the video data used for the process and the newly created video data is the storage device 205. The computer programs and data stored in the storage device 205 are appropriately loaded into the RAM 206 under the control of the CPU 201 and are processed by the CPU 201.

  The RAM 206 has an area for storing computer programs and data loaded from the storage device 205. Further, the RAM 206 has a work area used when the CPU 201 executes various processes. As described above, the RAM 206 can appropriately provide various areas. The ROM 207 stores computer programs and data that do not need to be rewritten, such as setting data and a startup program of the editing apparatus 100. Note that the functions and processing of the editing device 100 described later are realized by the CPU 201 reading out a program stored in the ROM 207 or the storage device 205 and executing the program. The CPU 201, the input device 202, the output device 203, the communication device 204, the storage device 205, the RAM 206, and the ROM 207 are all connected to a bus (BUS) 208.

  FIG. 3 is a diagram illustrating a software configuration of the editing device 100. The document acquisition unit 300 acquires a document. Specifically, the document acquiring unit 300 acquires, as a document, an edited video to be created by the editing apparatus 100, that is, a process table of work to be educational contents in an educational video and a work standard. FIG. 4A is a diagram illustrating an example of a process chart. In the process table 401, a process number (No), work contents in the process, and a required time of the process are described. FIG. 4B is a diagram illustrating an example of a work standard document. The work standard document is data including a photograph, a drawing, and the like related to the process, in addition to a sentence indicating the work content for each process. The work standard book is a document read by a learner who is a viewer of an edited video to be edited by the editing apparatus 100 so as to learn a series of work. When each document is an electronic document, the document acquiring unit 300 may acquire the content as it is. When the document is a scanned document such as paper, the document acquiring unit 300 acquires the content by OCR character recognition. The work standard document is an example of work information indicating work contents.

  Returning to FIG. 3, the analysis unit 301 analyzes the content described in the document data acquired by the document acquisition unit 300. The analysis unit 301 determines, for example, a section for dividing the work video into the partial video corresponding to the process according to the process chart. The analysis unit 301 also determines conditions for determining whether or not the video is suitable for education in each section according to the work standard document. The change recognizing unit 302 recognizes whether or not there has been a change in the process chart or the work standard according to the analysis result of the document data acquired by the document acquiring unit 300. The image acquisition unit 303 acquires an image captured by each camera 110 in real time. As another example, the video acquisition unit 303 may acquire a video captured in the past from a medium or the like.

  The extracting unit 304 extracts a partial video in units of a section corresponding to one process included in the work from each work video based on the analysis result of the process table. The score calculation unit 305 calculates the score of each partial video obtained by the extraction unit 304. The selection unit 306 selects a representative partial image used for reconstruction as an image corresponding to each step included in the work. The reconstructing unit 307 generates an edited video for teaching work contents by joining the plurality of representative partial videos obtained by the selecting unit 306 in accordance with the execution order of the steps.

  FIG. 5 is a flowchart showing a process of creating an edited video by the editing apparatus 100. First, in S500, the document obtaining unit 300 obtains a process chart and interprets the description. Specifically, the document acquisition unit 300 specifies the number of steps included in the work to be imaged, the content of each step, and the time required for each step. Next, in S501, the analysis unit 301 selects one process. The following process is executed with the process selected in S501 as a process target. Next, in step S502, the analysis unit 301 acquires a work standard document, analyzes the contents of the work standard document, and specifies detailed work contents of the selected process. The analysis unit 301 specifies, for example, an object such as a part or a tool used in a selected process, an operation content of a worker performed in the selected process, a component movement, and the like.

  Next, in S503, the video acquisition unit 303 acquires one work video obtained by one camera 110. Then, the video acquisition unit 303 converts the acquired work video into a partial video corresponding to the selected process based on the process number and the required time of the currently selected process shown in the process table 401 acquired in S500. A margin is provided and a partial image is extracted. Then, the video acquisition unit 303 analyzes the content of the partial video including the margin. It should be noted that the difference between the required time of the selected process determined from the process chart and the actual work time is accumulated, and there is a possibility that a difference from the estimated time has occurred. Thus, the extraction unit 304 extracts a partial video with a certain time margin before and after the assumed period, and extracts the partial video as an analysis target.

  The video acquisition unit 303 specifies, for example, components used in the selected process, operations of the worker performed in the selected process, and the like. In the content analysis of the video in S503, the video acquisition unit 303 uses, for example, pattern matching, matching using a local feature amount, or the like. The motion to be recognized is a motion that can be recognized from the image, for example, a screw is fastened with a screwdriver.

  Next, in S504, the extraction unit 304 extracts a partial video obtained by removing the margin from the partial video provided with the margin obtained by the video acquisition unit 303. The reason for removing the margin in S504 is to obtain a partial video used for reconstruction (editing). If the margin is left, the content of the reconstructed image will be blurred at the joint of each procedure, making it difficult to see. To avoid this, margins will be removed.

  Further, the extraction unit 304 associates the contents described in the work standard 402 with the movement of the worker identified from the video in S503, the parts used in the process, etc. Specify the start position of the process. The extraction unit 304 may extract a partial video in response to a user operation when the automatic determination has failed, for example, when there is no recognizable large movement. The process of S504 is an example of an extraction process of extracting a partial video of each process from a work video.

  Next, in S505, the video acquisition unit 303 checks whether there is an unprocessed video, and if there is an unprocessed video (Yes in S505), the process proceeds to S503. In step S503, the video acquisition unit 303 acquires an unprocessed video, and the subsequent processing is continued. For example, when the images of the three cameras 110 are targeted, the processes of S503 and S504 are repeated for the images of the three cameras 110. When the processes of S503 and S504 are completed for all the videos (No in S505), the video acquisition unit 303 advances the process to S506.

  In S506, the score calculation unit 305 calculates the score of each partial video extracted from each video for the process being selected in S504. The score is an evaluation value as to whether each partial video is a video suitable for the purpose of work education of the edited video to be generated. The score calculation unit 305 calculates a score based on a recognition result indicating whether or not the article used in the process and the operation content of the worker, which are indicated in the work standard, are included in the partial video. Further, in the present embodiment, the score calculation unit 305 uses a time during which an image similar to the image shown in the work standard document 402 by a certain reference or more is displayed. This is because if the similar time is long, it is considered that there is a high possibility that the work target is displayed without occlusion by a worker or a tool or the like for a long time.

  Here, there are two points that need to be considered. The first point is that occlusion may occur due to the operator's hand or tags or instructions inserted in the image, and the second point is that similar scenes may exist in the worker image. is there. In order to correspond to the first point, the score calculation unit 305 sets a threshold value of the similarity that is determined to be the same at the time of recognition to be lower than a value used for another purpose, for example, personal authentication or the like.

  In addition, the score calculation unit 305 uses an image having a large difference as compared with an image corresponding to a process other than the process being selected, that is, a process to be processed, in order to correspond to the second point. Thereby, the probability of erroneous recognition can be reduced. Basically, the image of the work standard 402 corresponds to the content of the partial video. For this reason, if the image in the work standard document 402 has a large difference from the image in the other process, the difference from the partial image in the process other than the corresponding process is also considered to be large in the comparison with the partial video. Therefore, the above method can be adopted. Further, the image published in the work standard 402 may be an enlarged image of a part of the article. In this case, a part of the partial video may correspond to the enlarged image. Therefore, the score calculation unit 305 searches for a matching portion in the video using a matching method that is robust to a change in the size of the image, for example, using a local feature amount.

  Next, in S507, the selection unit 306 selects a representative partial video of the selected process from the plurality of partial videos extracted from each work video based on the score (selection process). In the present embodiment, the selection unit 306 selects a partial video having the highest score as a representative partial video. When there are a plurality of partial videos having the same score, the selection unit 306 narrows down the number of partial videos to one by a plurality of processes described below. That is, the selection unit 306 selects a partial video extracted from the working video including the partial video selected for the immediately preceding process from among the plurality of partial videos having the highest score. Next, the selection unit 306 suspends the determination of the selection of the partial video and selects the partial video extracted from the work video including the partial video selected for the next step. Next, the selection unit 306 selects a partial video extracted from a work video having a large number of times selected in a process before the process to be processed. Finally, the selection unit 306 selects a partial video at random or in response to a user operation.

  Next, in S508, the analysis unit 301 checks whether or not there is an unprocessed process. If there is an unprocessed process (Yes in S508), the process proceeds to S501. In S501, the analysis unit 301 selects one unselected step, and the subsequent processing is continued. For example, if the work includes four steps, the processes of S501 to S507 are performed for each of the four steps, and a representative partial image is selected for each step. When the processes for all the processes are completed (No in S508), the analysis unit 301 advances the process to S509.

  In step S <b> 509, the reconstructing unit 307 creates an edited video by linking the representative partial videos selected for each process. FIG. 6 is an explanatory diagram of the processing of S509. In step S506, a score is calculated for the partial video of each work video (candidate video A to X), and the partial video having the highest score is selected as a representative partial video. In FIG. 6, the representative partial video is indicated by a thick frame. The reconstructing unit 307 creates an edited video by joining the representative partial videos indicated by the thick frames. At this time, the reconstructing unit 307 also records which period corresponds to which process, for example, as metadata in the edited data.

  Referring back to FIG. 5, after the processing of S509, in S510, the reconstructing unit 307 divides the created edited video. This is for facilitating the handling of the video when the work included in the created edited video is performed by a plurality of persons. Specifically, the reconstructing unit 307 divides the edited video based on the assigned range of each worker described in the process chart 401. When one worker performs all the processes, the process of S510 is unnecessary. In addition, there is a case where the worker determines that there is no need to divide the image. Therefore, in such a case, the process of S510 is unnecessary. That is, the process of S510 can be omitted. Thus, the editing video creation processing ends.

  As described above, the editing device 100 divides each of the plurality of videos into specific sections, and selects a partial video determined to be most suitable for education in each section as a representative partial video. Then, the editing device 100 creates an edited video by joining the representative partial videos. Thereby, the work load on the video creator can be reduced.

  FIG. 7 is a flowchart showing the editing video update process. In a work in a factory or the like, the work content may frequently change due to a change in a product to be created. However, not all steps are changed. In this case, it is troublesome to recreate the educational video from scratch, so it is desirable to update only necessary parts. The update process is a process for updating this necessary part.

  In S700, the change recognition unit 302 recognizes whether the work standard document 402 has been updated. When the document acquiring unit 300 acquires the work standard 402, the change recognizing unit 302 determines whether there is an update (change) by obtaining a difference from the content of the previous work standard 402. This utilizes the fact that the work standard 402 is also changed whenever the work is changed. Of course, the process chart 401 is also updated and acquired. However, it is determined that it is easy to understand that the update has been performed due to the occurrence of the page replacement, and the work standard 402 is used as a trigger.

  If the change recognizing unit 302 recognizes that it has been updated (Yes in S700), the process proceeds to 701. In step S701, the extraction unit 304 selects one process corresponding to the update specified by the change recognition unit 302 in the edited video. Hereinafter, the process selected in S701 is referred to as an update target process. Next, in S702, the extraction unit 304 extracts a partial video corresponding to the update target process from the edited video. Next, in step S703, the CPU 201 selects a partial image by performing the same processing as the processing in steps S502 to S507. The partial video selected in S703 is used for updating the edited video. Hereinafter, the partial video selected in S703 is referred to as a substitute partial video.

  Next, in step S704, the CPU 201 checks whether or not there is an unprocessed process in which the processes of S702 and S703 are not performed among the processes corresponding to the update. (Yes in S704), the process proceeds to S701. If the processing has been completed for all the processes corresponding to the update (No in S704), the CPU 201 advances the processing to S705. In step S705, the reconstruction unit 307 creates a new edited video using the substitute partial video.

  The basic processing in S705 is the same as the processing in S509. However, the reconstructing unit 307 uses the original video as it is for the portion that is not updated, and uses the newly selected alternative partial video only for the updated portion. That is, the reconstruction unit 307 replaces the video in the section related to the update with the substitute partial video. In addition, since the period corresponding to each process may be changed, the reconfiguration unit 307 updates the recording period information of each process together. After that, in step S706, the reconstruction unit 307 performs a process of dividing the edited video. This processing is similar to the processing of S510. As described above, the editing apparatus 100 can update the edited video by replacing only a part of the edited video according to the update of the work by the update process. Thereby, the work load on the video creator can be reduced.

  As described above, the editing device 100 according to the first embodiment can perform appropriate editing of video data without requiring a complicated operation by a user.

(Second embodiment)
Next, a video management system according to a second embodiment will be described. Hereinafter, the differences between the video management system according to the second embodiment and the video management system according to the first embodiment will be described. FIG. 8 is a flowchart illustrating a part of the creation processing by the editing device 100 according to the second embodiment. The update process according to the second embodiment is a process that follows the processes of S500 to S506 illustrated in FIG. 5, continues to the processes of S800 to S806 illustrated in FIG. . Hereinafter, an update process performed by the editing device 100 according to the second embodiment will be described.

  After the processing in S506, the CPU 201 advances the processing to S800 in FIG. In S800, the CPU 201 determines whether or not the highest score is equal to or greater than a threshold. If the highest value is less than the threshold value (No in S800), CPU 201 advances the process to S508 in FIG. That is, the CPU 201 starts the processing from S501 for the next step without selecting a representative partial image for the section to be processed. On the other hand, if the highest value is equal to or larger than the threshold (Yes in S800), the CPU 201 advances the processing to S801.

  In S801, the selection unit 306 selects a partial video having the highest score as a representative partial video. This processing is similar to the processing of S507. Next, in S802, the score calculation unit 305 checks whether or not the representative partial video for the process immediately before the process to be processed has been selected. If the representative partial video of the immediately preceding process has been selected (Yes in S802), the score calculation unit 305 advances the process to S508. On the other hand, when the representative partial video of the immediately preceding process has not been selected (No in S802), the score calculation unit 305 advances the processing to S803.

  In step S <b> 803, the selection unit 306 sets the immediately preceding image as a processing target, and checks whether the representative images before and after the immediately preceding image are extracted from the same work image. If the representative partial video before and after the immediately preceding video is extracted from the same work video (Yes in S803), the selection unit 306 advances the process to S804. If the representative partial video before and after the immediately preceding video is not extracted from the same work video (No in S803), the selection unit 306 advances the process to S805.

  In S804, the selection unit 306 selects a partial video extracted from the working video corresponding to the representative partial video of the process before and after the immediately preceding process as a representative partial video for the immediately preceding process, and then proceeds to S508. On the other hand, in step S805, the selection unit 306 determines the score of the step before the immediately preceding step and the partial image of the step after the immediately preceding step in the work video having the highest score in the step before the immediately preceding step. The total value of the score and is calculated. Similarly, the selection unit 306 determines the sum of the score of the step after the immediately preceding step and the score of the step before the immediately preceding step in the work video having the highest score in the step after the immediately preceding step. Calculate the value. Next, in S806, the selection unit 306 selects the partial video extracted from the work video with the larger total value calculated in S805 as the representative partial video for the immediately preceding process, and then proceeds to S508.

  For example, as shown in FIG. 9A, the score 80 of the partial video of the work video “candidate video D” has the highest value in the previous process “process n−1” with respect to the immediately preceding process n, and It is assumed that the partial video of the video D is selected as the representative partial video. Also, in the subsequent step “step n + 1”, it is assumed that the partial image score 85 of the working video “candidate video D” has the highest value, and the partial video of the candidate video D is selected as the representative partial video. In this case, since the work images corresponding to the representative partial images of the preceding and succeeding processes are the same, the partial image of the candidate video D is also selected as the representative partial image for the immediately preceding process n.

  On the other hand, as shown in FIG. 9B, the score 80 of the partial video of the work video “candidate video F” has the highest value in the previous process “n−1” with respect to the immediately preceding process n, and It is assumed that the partial image of F is selected as the representative partial image. In the subsequent step “step n + 1”, it is assumed that the score 85 of the partial video of the working video “candidate video G” has the highest value, and the partial video of the candidate video G is selected as the representative partial video. In this case, since the work videos corresponding to the representative partial videos in the preceding and succeeding processes are different, the total score of the candidate videos F and G is calculated. Then, in the example of FIG. 9B, since the work video having the large total value is the candidate video F, the partial video of the candidate video F is selected as the representative partial video of the immediately preceding process n.

  Here, in S803, if the representative partial images before and after the immediately preceding image are not extracted from the same work image (No in S803), another example will be described. In this case, the selection unit 306 may select the partial video of the work video corresponding to the representative partial video of one of the preceding and following processes as the representative partial video for the immediately preceding process in accordance with the user operation. Good. Other configurations and processes of the video management system according to the second embodiment are the same as those of the video management system according to the first embodiment.

  In the present embodiment, the representative partial video of the process to be processed is selected based on the representative partial video of the process before and after the process to be processed (the immediately preceding process). It is not limited. As another example, among other processes other than the process to be processed, a process in which the representative partial video has already been selected may be referred to.

  As described in the first embodiment, the editing device 100 considers the occurrence of occlusion and the like when calculating the score. However, there is still a possibility that the scores of all the partial videos do not satisfy a certain standard. It is also conceivable that an image to be a reference is not included in the work standard 402 in the first place. On the other hand, the editing apparatus 100 according to the third embodiment includes a case where the same part as the image described in the work standard 402 is hardly reflected in the work video group, and an image corresponding to a certain process in the work standard 402 is included. If not, the representative video can be appropriately selected. That is, the editing apparatus 100 of the third embodiment can perform appropriate editing of video data even in such a case.

  As a modified example of the second embodiment, the case of selecting a representative partial image of a process to be processed by the processes of S803 to S806 is not limited to the embodiment. As another example, when the scores of the processes before and after the process to be processed have been determined, the representative portion of the process to be processed is calculated by the processes of S803 to S806 without calculating the score of the process to be processed. An image may be selected.

  As a modification of the first and second embodiments, the editing device 100 may add additional information to the edited video at the time of creating the edited video so that the viewer of the edited video can easily understand the edited video. . The editing apparatus 100 may, for example, display the text of the work standard 402 as a telop in the video, or display the work standard 402 itself as a part of the edited video. As a result, it is possible to perform reproduction while marking which part is explained. If the work standard 402 specifies an important work, the editing apparatus 100 may display the mark or change the color of the character to make it stand out. When the work standard 402 is photographed by a portable device, the video data corresponding to the page may be reproduced or superimposed.

  As described above, the preferred embodiments of the present invention have been described in detail, but the present invention is not limited to the specific embodiments, and various modifications may be made within the scope of the present invention described in the appended claims.・ Change is possible.

(Other Examples)
The present invention supplies a program for realizing one or more functions of the above-described embodiments to a system or an apparatus via a network or a storage medium, and one or more processors in a computer of the system or the apparatus read and execute the program. This processing can be realized. Further, it can be realized by a circuit (for example, an ASIC) that realizes one or more functions.

100 Editing device 300 Document acquisition unit 304 Extraction unit 306 Selection unit 307 Reconstruction unit

Claims (10)

An editing device for editing a work video,
Extracting means for extracting a partial video of each process from each of a plurality of work videos related to the same work, based on a work time of each process included in the work,
Work information indicating the work content, based on the partial video, from among the plurality of partial videos extracted from each of the plurality of work videos, selecting means for selecting a representative partial video of each step,
An editing apparatus comprising: a reconstructing unit that generates an edited video by connecting the representative partial video of each step selected by the selecting unit. The work information includes information indicating an object used for the work,
2. The editing apparatus according to claim 1, wherein the selection unit selects the representative partial image based on a recognition result of the object in the plurality of partial images. The work information includes an operation content of the worker,
2. The editing apparatus according to claim 1, wherein the selection unit selects the representative partial video based on a recognition result of the operation content in the plurality of partial videos. 3. The work information indicates work contents corresponding to each of a plurality of processes included in the work,
4. The method according to claim 1, wherein the selection unit selects the representative partial video of the process to be processed based on the work content of the process to be processed and the partial video. 5. An editing device according to item 1.   The method according to claim 1, wherein the selecting unit further selects the representative partial video of the process to be processed based on the work content of a process other than the process to be processed and the partial video. 5. The editing device according to 4.   The selecting means, based on the representative partial video of the other process, when the representative partial video is already selected for a process other than the process to be processed, which is included in the work, 6. The editing apparatus according to claim 1, wherein a representative partial image of a process to be processed is selected.   When the representative partial video has already been selected for a process before and after the process to be processed, the selecting unit performs the process to be processed based on the representative partial video of each of the processes before and after the process. 7. The editing apparatus according to claim 6, wherein a representative partial video is selected. The selecting means, when the work information is updated, select an alternative partial video of the process related to the update,
8. The method according to claim 1, wherein when the alternative partial image is selected, the reconstructing unit replaces an image in a section corresponding to a process related to updating the edited image with the alternative partial image. 9. 2. The editing device according to claim 1. An editing method performed by an editing device that edits a work video,
An extraction step of extracting a partial video of each process from each of a plurality of work videos related to the same work, based on a work time of each process included in the work,
Work information indicating the work content, based on the partial video, from among the plurality of partial videos extracted from each of the plurality of work videos, a selection step of selecting a representative partial video of each process,
A reconstructing step of connecting the representative partial images of the respective steps selected in the selecting step to generate an edited image. Computer
Extracting means for extracting a partial video of each process from each of a plurality of work videos related to the same work, based on a work time of each process included in the work,
Work information indicating the work content, based on the partial video, from among the plurality of partial videos extracted from each of the plurality of work videos, selecting means for selecting a representative partial video of each step,
A program for linking the representative partial images of the respective steps selected by the selection unit and functioning as a reconstructing unit that generates an edited video.

Images