JP3831180B2 - Video information printing apparatus, video information summarizing method, and computer-readable recording medium storing a program for causing a computer to execute the method - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a video information printing apparatus, a video information summarizing method, and a computer-readable recording medium recording a program for causing a computer to execute the method.
[0002]
[Prior art]
For example, a recording medium (video recording medium) capable of recording information such as a video tape and a DVD (Digital Versatile Disc) as a video is widely used. Such a video recording medium is generally provided with an index that allows the contents of the recorded video to be understood at a glance, and is used for organizing and managing the video recording medium.
[0003]
Currently, as a configuration for easily creating an index, the invention described in JP-A-6-245179, the invention described in JP-A-8-294080, the invention described in JP-A-9-93527 are disclosed. is there. Of these, the invention described in Japanese Patent Laid-Open No. 6-245179 stores a video signal in a memory by pressing a freeze button, and prints a still image represented by the stored video signal.
[0004]
In the invention described in Japanese Patent Laid-Open No. 8-294080, an index area is provided on a video recording medium, and index data is created by recording a representative screen of the video data, a shooting date, a shooting location, and the like in the index area. . The representative screen recorded as index data can be displayed on the display screen or output on paper. At this time, the shooting date / time and shooting location can be displayed or output on paper in correspondence with the representative screen.
[0005]
The invention described in Japanese Patent Laid-Open No. 9-93527 extracts (basically) a representative image based on a scene change in a reproduced video, and stores the extracted representative image to create an index. To do. This index is a list of representative images, and can be displayed on the display unit or printed. According to the invention described in JP-A-6-245179, the invention described in JP-A-8-294080, and the invention described in JP-A-9-93527, all are included in the video. Images can be printed on paper and output. The output printed matter can be used as an index of the video recording medium.
[0006]
[Problems to be solved by the invention]
However, all of the above-described conventional inventions mainly use an image included in a video as an index. An index mainly composed of images is effective for understanding the content of video to some extent, but there is a possibility that information essential for understanding may be lost or unnecessary information may be mixed.
[0007]
In addition, although the conventional invention adds simple information such as the shooting date and time and the shooting location to compensate for the lack of information or manually replaces the representative image determined based on the scene change, the content of the video is sufficient. There is still room for improvement in creating an easily understandable index.
[0008]
Further, when organizing video recording media using an index, for example, it is conceivable that the index is directly attached to the case of the video recording medium, or only the index is filed. However, the above-described conventional invention cannot change the print layout for printing the created data index in accordance with the index usage method. For this reason, the user needs to process the printed index according to the usage method.
[0009]
By the way, at present, a video structuring apparatus for structuring a video to facilitate editing and processing of the video has been proposed. Video structuring refers to a process of dividing a video by detecting a change point of an image constituting the video and making it possible to search the video for each divided group.
[0010]
Known examples of video structuring apparatuses for structuring video include, for example, Japanese Patent Application Laid-Open Nos. 8-339379 and 10-13773, and Japanese Patent Application No. 11-277361 as a tree structure. A video structuring apparatus to be managed has been filed. Information indicating the contents of each divided group is added to the structured video, but a technique for printing this information and using it as an index of a video recording medium has not yet been completed.
[0011]
The present invention has been made to solve the above-mentioned problems, and its first object is to add information sufficient to understand the content of the video to the paper output index of the video recording medium. To provide a video information printing apparatus capable of easily and reliably creating an index for understanding video content, a video information summarizing method, and a computer-readable recording medium storing a program for causing a computer to execute the method With the goal.
[0012]
The second purpose is to determine the layout of the index according to the user's request, and to create an optimal index for a usage method such as sticking to a video recording medium case or filing, and video information It is an object of the present invention to provide a computer-readable recording medium recording a summarizing method and a program for causing a computer to execute the method.
[0013]
[Means for Solving the Problems]
In order to solve the above-described problems and achieve the object, the video information printing apparatus according to the first aspect of the present invention is a video information printing apparatus that summarizes information about videos and prints the summarized information, Condition setting means for setting a summary condition that is a condition at the time of information summarization and a print format for printing summary information, a video structure index that represents the structure of the video in a tree structure, and information on the video based on the summary condition Summarizing video information summarizing means, print information shaping means for shaping the information summarized by the video information summarizing means based on the print format, summarizing by the video information summarizing means, and by the print information shaping means Printing output means for outputting the shaped information as a printed matter.
[0014]
According to the first aspect of the present invention, it is possible to summarize information related to video according to the summarizing condition by using the video structure index having a tree structure. In addition, the summarized information can be printed according to the print format.
[0015]
In the video information printing apparatus according to claim 2, the summary condition is Extraction conditions for extracting a reference frame in which each representative frame is aggregated from a representative frame group representing a frame image of each segment constituting the video defined by the video structure index It is characterized by including.
[0016]
According to the invention described in claim 2, Video information is efficiently searched by extracting images (representative frame groups) representing video using the video structure index from the video information, and reference frames are extracted from the representative frame groups according to the extraction conditions. can do.
[0017]
The video information printing apparatus according to claim 3, wherein the summary condition and the print format And It is characterized by comprising registration means for registering.
[0018]
According to the third aspect of the present invention, it is possible to register the summary condition and the print format, and it is possible to eliminate the need to input the summary condition and the print format each time video information is printed. Further, the operator can store new summary conditions and print formats in the video information printing apparatus.
[0019]
According to a fourth aspect of the present invention, in the video information printing apparatus, the video information summarizing unit includes a feature amount acquiring unit that acquires a feature amount of an image extracted from the video, and the feature amount acquiring unit between the images. A feature quantity difference obtaining unit that obtains a difference between the obtained feature quantities, and a plurality of images in which the feature quantity difference obtained by the feature quantity difference obtaining unit is equal to or less than a predetermined value is represented by one image. It is characterized by that.
[0020]
According to the fourth aspect of the present invention, the extracted image can be represented by one image. In addition, by representing an image with a small difference in feature amount as a single image, it is possible to suppress a decrease in the amount of information included in the entire extracted image.
[0021]
According to a fifth aspect of the present invention, in the video information printing apparatus, the print information shaping unit includes a layout storage unit that stores a plurality of layouts at the time of printing, and uses the layout stored in the layout storage unit. Then, the information summarized by the video information summarizing means is shaped.
[0022]
According to the fifth aspect of the present invention, the layout at the time of printing can be stored in advance, and it is not necessary to input the layout every time printing is performed. Also, the operator can store a new layout in the video information printing apparatus.
[0023]
A video information printing apparatus according to a sixth aspect of the invention is characterized in that the layout storage unit stores a layout for an identification label of a video medium.
[0024]
According to the sixth aspect of the present invention, it is possible to print information relating to the summarized video with an optimum layout on the identification label of the video media.
[0025]
According to a seventh aspect of the present invention, the video information printing apparatus further comprises position information adding means for attaching video position information relating to a position in an image of an image included in the information shaped by the print information shaping means to the print information. The print output means outputs the video position information together with the print information as a printed matter.
[0026]
According to the seventh aspect of the present invention, information relating to the position of the image in the video can be added to the printed matter.
[0027]
A video information summarizing method according to an eighth aspect of the present invention is a video information summarizing method for summarizing information related to video and shaping the information into a printable format. A condition setting step for setting a print format at the time of printing, a video information summarizing step for summarizing information about the video based on a video structure index representing the structure of the video in a tree structure and the summarizing condition, and the information summarizing step A printing information shaping step for shaping the information summarized in (1) based on the printing format.
[0028]
According to the eighth aspect of the present invention, it is possible to summarize the information about the video according to the summarizing condition by using the video structure index having a tree structure.
[0029]
The video information summarizing method according to the invention of claim 9 is characterized in that the summarizing condition is: Extraction conditions for extracting a reference frame in which each representative frame is aggregated from a representative frame group representing a frame image of each segment constituting the video defined by the video structure index It is characterized by including.
[0030]
According to the invention of claim 9, Video information is efficiently searched by extracting images (representative frame groups) representing video using the video structure index from the video information, and reference frames are extracted from the representative frame groups according to the extraction conditions. can do.
[0031]
In the video information summarizing method according to claim 10, the information summarizing step acquires the feature amount of the image extracted from the video and the feature amount acquisition step between the images. A feature amount difference obtaining step for obtaining a difference between the feature amounts, and representing a plurality of images in which the difference between the feature amounts obtained in the feature amount difference obtaining step is a predetermined value or less as one image It is characterized by.
[0032]
According to the tenth aspect of the present invention, the extracted image can be represented by one image. In addition, by representing an image with a small difference in feature amount as a single image, it is possible to suppress a decrease in the amount of information included in the entire extracted image.
[0033]
A recording medium according to an eleventh aspect of the invention can record a program that causes a computer to execute any one of the video information summarizing methods according to the eighth to tenth aspects.
[0034]
DETAILED DESCRIPTION OF THE INVENTION
Exemplary embodiments of a video information printing apparatus according to the present invention will be explained below in detail with reference to the accompanying drawings. The video summarization referred to in the embodiment of the present specification refers to a process of extracting a frame image included in a video together with a document added to the frame image based on the structured video. .
[0035]
FIG. 1 is a block diagram for explaining a video information printing apparatus according to the present embodiment. The video information printing apparatus according to the present embodiment is a video information printing apparatus that summarizes video (video information 102), creates summary information, and prints the created summary information.
[0036]
The illustrated video information printing apparatus includes a video structure interpretation unit 103, an input unit 104, a video summary generation unit 105 including a registration unit 111, a print shaping unit 106, a print language generation unit 107, a video reference frame extraction unit 109, a barcode. An adding unit 110 and a printing unit 108 are provided. The video processed by the video information printing apparatus of this embodiment is based on the video information (video main body) 102 and the video structure index 101 attached to the video information 102 and representing the video structure in a tree structure. It has become.
[0037]
FIG. 2 is a diagram for explaining the video structure index 101 used in the video information printing apparatus according to the present embodiment. The video structure index 101 is configured as a hierarchical tree structure. The hierarchy of the tree structure is divided according to the degree of detail of information, and the lower hierarchy holds detailed information about the video. The tree structure shown represents video management data having one root directory 201 for the entire recording medium.
[0038]
The video structure index 101 is data representing the video information 102 in a structured manner. The structuring of the video information 102 refers to a process of capturing the video represented by the video information as a continuous frame image (an image created by dividing a moving image) and grouping the frame images into a predetermined unit. A group of a plurality of frame images grouped by structuring is called a segment. According to the video structure index 101, it is possible to obtain information indicating what sort of image each segment is.
[0039]
In the present embodiment, a segment is created for each shooting, and the segments grouped for each shooting are further grouped for each cut / shot change point. Cut-shot change point is a recording time calculated from the start of video recording, or frame images arranged based on the number of recorded images. It is provided between large frame images. Note that the feature amounts include, for example, the following.
・ Color histogram
・ Spatial color distribution
・ Spatial edge distribution
・ Spatial texture distribution
・ Object shape
[0040]
In FIG. 2, X represents environment information, Y represents camera information, and Z represents a still image feature amount of a representative frame. The environment information X is information related to the external environment at the time of shooting, and includes information related to date and time, position (latitude and longitude), altitude, temperature, and humidity. Note that the video structuring apparatus that creates the video structure index 101 includes a clock (standard for GMT time), a GPS (Global Positioning System), a barometric sensor, a temperature sensor, and a humidity sensor for acquiring such information. I have.
[0041]
The camera information Y includes information such as a focal length, an aperture value, a shutter speed, and a focusing distance when a frame image (an image created by dividing a moving image) included in a certain segment is captured. Yes. Among such information, it is possible to infer from the information about the focal length whether the object to be captured of the frame image is a landscape, an object such as a person or an object, wide-angle shooting, or telephoto shooting. Further, from the information about the aperture value, in addition to determining whether the object to be photographed is a landscape or an object, it is also possible to infer the brightness of the photographing location.
[0042]
Further, from the information about the shutter speed, it is possible to infer whether the subject to be photographed is stationary or moving, and the brightness of the photographing location. From the information on the focus distance, the distance between the camera portion of the video recording apparatus and the object to be photographed can be roughly estimated. By interpreting the above information in a complex manner, for example, if the aperture value is low regardless of the shutter speed, the focus distance is close, and the focal distance is long, the possibility that the object has been shot is high. You can guess.
[0043]
Furthermore, the still image feature amount Z is information representing the feature amount when the frame image is viewed as a still image.
[0044]
The cut / shot control information 202A and the cut / shot information 203A located immediately below the root directory 201 are information common to all the video information 102. Further, the cut / shot control information 202B is general information on the cut / shot change point of the segment managed by the cut / shot information 203A.
[0045]
In the tree structure shown in FIG. 2, there are two segments for each photographing created as the photographing progresses, and the cut / shot information 203B and 203C are attached to the two segments, respectively. Camera information Y is added to both of the two segments.
[0046]
Further, four cut / shot segments included in each segment are arranged below the segment to which the cut / shot information 203B and 2203C are added. The four segments are created by dividing the segment to which the cut / shot information 203B is added at the cut / shot change point. Cut shot information 203D, 203E, 203F, and 203G is arranged in each of the four cut shot segments. Cut shot information 203H, 203L, 203J, and 203K are added to the four segments arranged below the segment to which the cut shot information 203C is added. Camera information Y is added to each of the cut / shot information 203D to G and the cut / shot information 203H to K.
[0047]
Further, the cut shot information 203D to G and the cut shot information 203H to K include information on a representative frame (also referred to as key frame) image representing a frame image included in the segment to which each cut shot information is added ( (Representative frame information) 204A, 204B, 204C, 204D and representative frame information 204E, 204F, 204G, 204H are respectively added. Further, the still image feature value Z of each representative frame is added to the representative frame information 204A to 204D and the representative frame information 204E to 204H.
[0048]
The representative frame information 204A to D and the representative frame information 204E to H include a document describing each representative frame in addition to the still image feature amount Z of each representative frame. The document describing the representative frame is a document created by the operator when creating the video structure index 101 or a sample document automatically added according to the feature amount. In the video structure index 101, representative frame information 204A to D and representative frame information 204E to H including a document describing each representative frame are printable information.
[0049]
The input unit 104 of the video information printing apparatus according to the present embodiment is used for summarizing conditions (referred to as condition A in the figure) that are conditions used for summarization by the video summarization generation unit 105 and information shaping by the print shaping unit 106. Enter the print format (referred to as condition B in the figure). The input summary conditions and print format are set in the video information printing apparatus. The video structure interpretation unit 103 interprets the structure of the video structure index 101. The video summary generation unit 105 and the video reference frame extraction unit summarize the video information 102 based on the video structure index 101 interpreted by the video structure interpretation unit 103 and the summary condition. The print shaping unit 106 converts the information (video summary) generated by the video summary generation unit 105 and the video reference frame extraction unit 109 by summarizing the video information 102 into a printable format based on the print format (shaping).
[0050]
In the present embodiment, as the summarization conditions, the ratio of the image and the ratio of characters in the video summary, the accuracy at the time of summarization, and the reference frame (frame image to be printed) performed in the video reference frame extraction unit 109 are described. Set the extraction conditions and the number of reference frames to be extracted. Also, the layout at the time of printing is set as the print format. The summary conditions and the print format can be input from the input unit 104 or registered in advance in the registration unit 111 of the video summary generation unit 105.
[0051]
Among the above-described summarization conditions, the accuracy at the time of summarization is set by designating a tree structure hierarchy. The reference frame extraction condition is set by a keyword or image input by the operator to the input unit 104 or a keyword or image registered in the registration unit 111.
[0052]
The set keyword and image are input to the video reference frame extraction unit 109 via the video summary generation unit 105. The video reference frame extraction unit 109 searches for a frame image (in this embodiment, the target is a representative frame) based on the keyword, and extracts the corresponding representative frame. Alternatively, an image similar to the image set as the extraction condition is extracted. If the number of extracted images is larger than the number of summary condition reference frames, the video reference frame extraction unit 109 narrows down the representative frames by the method shown in FIG.
[0053]
That is, according to FIG. 3, when seven representative frames a, b, c, d, e, f, and g are extracted at the initial stage of extraction, the similarity between the representative frames a to g is determined. Compare. This similarity may be determined by, for example, a feature amount. As a result of the comparison of similarities, when it is determined that the representative frame a and the representative frame e are similar (for example, the difference in feature amount is smaller than a preset standard), the video reference frame extraction unit 109 Only one of frame a or representative frame e is left. The remaining representative frame a or e becomes a representative frame h. That is, the representative frame h represents the representative frames a and e. Similarly, when it is determined that the representative frame c and the representative frame f are similar, the representative frame c and the representative frame f are represented by the representative frame j by leaving only the representative frame c or the representative frame f. With the above processing, the seven representative frames a to g are narrowed down to five representative frames h, i, j, k, and l.
[0054]
Further, the video reference frame extraction unit 109 performs the same processing as the narrowing-down process performed on the representative frames a to g on the five representative frames h to l to obtain the five representative frames h to l. Narrow down to three representative frames m, n, and o. When the numerical value of 3 matches the number of reference frames to be extracted set as the summary condition, the video reference frame extraction unit 109 displays information that the representative frames m to o have been extracted as the video summary generation unit 105 and the print shaping unit. It outputs to 106.
[0055]
The video summary generation unit 105 compares the amounts of the representative frames m to o and the documents attached to the representative frames m to o with the ratio of the image set as the summary condition and the ratio of the characters. The amounts of the representative frames m to o and the documents attached to the representative frames m to o are obtained, for example, by calculating the area ratio occupied by the reference frame extracted in the printed image and the area ratio occupied by characters. It may be. At this time, the ratio occupied by the image and the ratio occupied by the characters set as the summary conditions are set by the area ratio occupied by the image and the area ratio occupied by the characters in the printed image.
[0056]
Then, the video summary generation unit 105 determines the ratio of the reference frame when the ratio of the representative frame extracted as the reference frame (hereinafter referred to as the reference frame) and the ratio of the character do not match the summary conditions. Adjust the proportion of characters to match the summary conditions. This adjustment is performed, for example, by a method of deleting the extracted reference frame and assigning the space to characters, or deleting information represented by characters. In addition, when deleting character information, the video | video summary production | generation part 105 extracts an important phrase for character information, for example. Then, it may be determined that a document including a lot of important words / phrases has a higher importance and a document having a smaller importance has a lower importance, and a document determined to have a lower importance is preferentially deleted.
[0057]
Further, the video summary generation unit 105 outputs information on the reference frame and the document whose ratios are adjusted as described above to the print shaping unit 106. The print shaping unit 106 arranges the reference frame and the document according to the layout set as the print format, and outputs the frame to the print language generation unit 107. At this time, the print shaping unit 106 outputs the position of the reference frame in the video from the information about the reference frame to the barcode adding unit 110. The bar code adding unit 110 converts the position of the reference frame in the video into information represented by a bar code, and outputs the information to the print language generating unit 107. Note that the position of the reference frame in the video indicates how many times the reference frame is positioned in the frame image constituting the video, or how many hours (minutes, seconds) the reference frame is played back from the start of video playback. It may be a temporal position.
[0058]
4A, 4B, and 4C are diagrams illustrating layouts set as print formats. FIG. 4A shows an image main layout mainly composed of images. (B) is an image / character mixed layout in which images and documents are distributed at a relatively close ratio. (C) is a character-based layout mainly composed of documents.
[0059]
The video information printing apparatus according to the present embodiment stores a plurality of layouts including the layout illustrated in FIG. At this time, in the present embodiment, it is assumed that a layout for an identification label (sticky note) of a video medium such as a video tape or DVD is also stored in the print shaping unit 106. When inputting the print format, a list of layouts is displayed on a display unit (not shown), and the operator designates an arbitrary layout. Further, the layout is not limited to the one stored in advance, and the operator can also register in the registration unit 111.
[0060]
The reference form and the document printed and shaped according to the layout are output from the print shaping unit 106 to the print language generation unit 107. Further, the barcode adding unit 110 outputs the position in the video of the reference frame converted into the barcode to the print language generating unit 107. The print language generation unit 107 converts the printed and formatted reference form, document, and barcode into the print language used by the print unit 108 and outputs the converted print language to the print unit 108. The printing unit 108 prints and outputs the reference form, the document, and the barcode on the same sheet. At this time, an area dedicated to barcodes may be provided in the layout.
[0061]
Next, processing performed by the video information printing apparatus described above will be described with reference to the flowchart shown in FIG. The process shown in FIG. 5 includes the video information summarizing method according to the embodiment of the present invention. As shown in FIG. 5, the video information printing apparatus according to the present embodiment inputs a summary condition and a print format by displaying a screen for inputting a summary condition and a print format on a display unit (not shown) (step S501). ).
[0062]
At this time, the video information printing apparatus determines whether or not the operator has specified a summary condition (such as a keyword) or a print format (such as a layout) registered in the registration unit 111 (step S502), and registration data is specified. In the case of registration (step S502: Yes), the registration data is read from the registration unit 111 (step S510). If the registered data is not designated (step S502: No), the video structure represented by the video information 102 is interpreted based on the video structure index 101 (step S503).
[0063]
Next, the video information printing apparatus executes a video summary creation subroutine (step S504). The video summary creation subroutine is processing performed in the video summary generation unit 105 and the video reference frame extraction unit 109. The process includes a process of extracting a reference frame in accordance with the summary condition, a process of adjusting the ratio of the document added to the extracted reference frame and the reference frame, and a process of specifying the position of the reference frame in the video.
[0064]
Next, the video information printing apparatus arranges the reference frame and the document obtained by the processing of the video summarizing subroutine in the layout based on the print format, and shapes the reference frame and the document into a printing format (step S505). In addition, the bar code adding unit 110 converts the information related to the position of the reference frame into a bar code and adds it to the reference frame and the document (step S506). Then, the reference frame, the document, and the barcode that are formatted in the printing format are converted into a language used by the printing unit 108 to generate a printing language (step S507), and the printing unit 108 prints it (step S508). ).
[0065]
Further, the video information printing apparatus according to the present embodiment determines whether or not the operator registers the summarization conditions and the print format used this time (step S509), and in the case of registration (step S509: Yes), the summarization is performed. The conditions and the print format are registered in the registration unit 111 (step S511). If not registered (step S509: No), the process is terminated without performing registration.
[0066]
Note that the video information summarization method described in this embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. This program is a hard disk, flexible The program is recorded on a computer-readable recording medium such as a disk, CD-ROM, MO, and DVD, and is executed by being read from the recording medium by the computer. The program can be distributed as a transmission medium or via the recording medium via a network such as the Internet.
[0067]
The video information printing apparatus according to the present embodiment described above efficiently searches video information and extracts a reference frame by extracting an image and a document representing the video from the video information using the video structure index. Can do. Also, a document for explaining the reference frame can be acquired relatively easily.
[0068]
Also, by summarizing the video according to the summarizing conditions set by the operator and printing it according to the print format set by the operator, the user's purpose and preference can be reflected in the selection of the reference frame and the document. In addition, the user's purpose and preference can be reflected in the layout when the reference frame and the document are printed. Furthermore, the operator registers the summary condition and the print format, so that the reference frame and the document extracted by the arbitrary summary condition can be printed with an arbitrary layout. If the printed material is used as an index of a video recording medium, an original index can be created for each user.
[0069]
Further, the video information printing apparatus according to the present embodiment can browse the video information on paper by outputting information summarizing the video information on paper. In addition, since the summary information of the video can be stored and managed on paper, it is convenient when, for example, cooking recipes are stored in a cooking program.
[0070]
【The invention's effect】
As described above, since the invention according to claim 1 summarizes the information about the video using the tree-structured video structure index, the video can be obtained with sufficient information to understand the content of the video. An information printing apparatus can be provided. In addition, since the information about the video can be summarized according to the summarization condition, it is possible to provide a video information printing apparatus that can obtain the summary information of the content according to the purpose. Furthermore, since the summary information can be printed according to the print format, it is possible to provide a video information printing apparatus capable of outputting information sufficient for understanding the content of the video on paper. Furthermore, it is possible to provide a video information printing apparatus capable of determining an index layout according to a user's request and creating an optimal index for a usage method such as sticking to a video recording medium case or filing. In addition, the invention described in the first embodiment is a special device such as a playback device that can list information including video summaries on paper, and can use the convenience of paper for processing video information (which can be viewed regardless of location). It is possible to provide a video information printing apparatus that can make use of (such as browsing without being). Also, it is possible to provide a video information printing apparatus capable of converting video into a document.
[0071]
The invention described in claim 2 Video information is efficiently searched by extracting images (representative frame groups) representing video using the video structure index from the video information, and reference frames are extracted from the representative frame groups according to the extraction conditions. It is possible to provide a video information printing apparatus capable of doing so.
[0072]
According to the third aspect of the present invention, since the summarization condition and the print format can be registered, there is no need to input the summarization condition and the print format every time the video information is printed, and a video information printing apparatus with high operability is provided. can do. In addition, it is possible to provide a video information printing apparatus capable of obtaining an index reflecting the user's preference by registering the summary condition and the print format reflecting the user's preference by the operator.
[0073]
According to the fourth aspect of the present invention, the extracted images can be represented by one image, and the extracted images can be narrowed down according to the number of necessary images. Therefore, it is possible to provide a video information printing apparatus that can extract an arbitrary number of images from information representing video.
[0074]
According to the fifth aspect of the present invention, it is possible to provide a video information printing apparatus with high operability that does not require a layout to be input every time printing is performed. In addition, it is possible to provide a video information printing apparatus in which an operator can obtain an index printed with a layout reflecting the user's preference by registering the layout reflecting the user's preference.
[0075]
According to the sixth aspect of the present invention, a video information printing apparatus capable of printing the information related to the summarized video in an optimal layout for the identification label of the video media, and obtaining an optimal printed matter for the identification label of the video media. Can be provided.
[0076]
According to the seventh aspect of the present invention, information regarding the position of the image in the video can be added to the printed matter, and the contents indicated by the image can be easily retrieved from the video. Therefore, it is possible to provide a video information printing apparatus capable of obtaining an index convenient for video processing and editing.
[0077]
The invention according to claim 8 provides a video information summarizing method capable of obtaining information sufficient for understanding the content of the video because the video related index is summarized using the video structure index of the tree structure. be able to. In addition, since the information about the video can be summarized according to the summarization condition, it is possible to provide a video information summarizing method capable of obtaining the summary information of the content according to the purpose.
[0078]
The invention according to claim 9 is: Video information is efficiently retrieved by extracting images (representative frame groups) representing the video from the video information using the video structure index, and reference frames are extracted from the representative frame groups according to the extraction conditions. It is possible to provide a video information summarization method.
[0079]
According to the tenth aspect of the present invention, the extracted images can be represented by one image, and the extracted images can be narrowed down according to the number of necessary images. Therefore, it is possible to provide a video information summarizing method that can extract an arbitrary number of images from information representing video.
[0080]
Since the recording medium concerning invention of Claim 11 can record the program which makes a computer perform any one of the video information summarizing methods of the said Claims 8-10, the said Claims 8 ~ 10. Any one of the video information summarizing methods described in 10 can be executed by a computer.
[Brief description of the drawings]
FIG. 1 is a block diagram for explaining a video information printing apparatus according to an embodiment of the present invention.
FIG. 2 is a diagram for explaining a video structure index used in the video information printing apparatus according to the embodiment of the present invention.
FIG. 3 is a diagram for explaining narrowing down of a reference frame.
FIG. 4 is a diagram illustrating a layout set as a print format in one embodiment of the present invention.
FIG. 5 is a diagram for explaining a video information summarizing method according to the present invention;
[Explanation of symbols]
101 Video structure index
102 Video information
103 Image structure interpretation part
104 Input section
105 Video summary generator
106 Print shaping unit
107 Print language generator
108 Printing department
109 Video reference frame extraction unit
110 Barcode addition part
111 Registration Department

Claims (11)

A video information printing apparatus that summarizes information about video and prints the summarized information,
Condition setting means for setting a summary condition that is a condition for information summarization and a print format for printing summary information;
Video information summarizing means for summarizing information about the video based on a video structure index representing the structure of the video in a tree structure and the summary condition;
Print information shaping means for shaping the information summarized by the video information summarizing means based on the print format;
Print output means for outputting the information summarized by the video information summarizing means and shaped by the print information shaping means as a printed matter;
A video information printing apparatus comprising: The summary condition includes an extraction condition for extracting a reference frame in which the representative frames are aggregated from a representative frame group representing a frame image of each segment constituting the video defined by the video structure index. The video information printing apparatus according to claim 1, wherein: The video information printing apparatus according to claim 1, further comprising registration means for registering the summary condition and the print format.   The video information summarizing unit includes a feature amount acquisition unit that acquires a feature amount of an image extracted from a video, and a feature amount difference acquisition unit that acquires a difference between the feature amounts acquired by the feature amount acquisition unit between images. A plurality of images in which a difference in feature amounts acquired by the feature amount difference acquisition unit is equal to or less than a predetermined value is represented by one image. The video information printing device described in 1.   The print information shaping means has layout storage means for storing a plurality of layouts at the time of printing, and uses the layout stored in the layout storage means to shape the information summarized by the video information summarization means. The video information printing apparatus according to claim 1, wherein:   The video information printing apparatus according to claim 5, wherein the layout storage unit stores a layout for an identification label of the video media.   Further, the image processing apparatus further comprises position information adding means for attaching to the print information video position information relating to a position in an image of an image included in the information shaped by the print information shaping means, and the print output means includes the video position together with the print information. The video information printing apparatus according to claim 1, wherein the information is output as a printed matter. A video information summarization method for summarizing information about video and shaping it into a printable format,
A condition setting step for setting a summary condition that is a condition for summarizing information and a print format for printing summary information;
A video information summarizing step for summarizing information about the video based on a video structure index representing the structure of the video in a tree structure and the summary condition;
A print information shaping step for shaping the information summarized in the information summarization step based on the print format;
A video information summarizing method comprising: The summary condition includes an extraction condition for extracting a reference frame in which the representative frames are aggregated from a representative frame group representing a frame image of each segment constituting the video defined by the video structure index. The video information summarizing method according to claim 8.   The information summarization step includes a feature amount acquisition step of acquiring a feature amount of an image extracted from a video, and a feature amount difference acquisition step of acquiring a difference between the feature amounts acquired in the feature amount acquisition step between images. 10. The video information summary according to claim 8, wherein a plurality of images in which the difference between the feature amounts acquired in the feature amount difference acquisition step is equal to or less than a predetermined value are represented by one image. Method.   A computer-readable recording medium having recorded thereon a program for causing a computer to execute any one of the video information summarizing methods according to claim 8.

Images