CN108268847A - A kind of method and system of film montage language analysis - Google Patents

A kind of method and system of film montage language analysis Download PDF

Info

Publication number
CN108268847A
CN108268847A CN201810048953.3A CN201810048953A CN108268847A CN 108268847 A CN108268847 A CN 108268847A CN 201810048953 A CN201810048953 A CN 201810048953A CN 108268847 A CN108268847 A CN 108268847A
Authority
CN
China
Prior art keywords
frame picture
point
characteristic point
picture
feature point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201810048953.3A
Other languages
Chinese (zh)
Other versions
CN108268847B (en
Inventor
逄泽沐风
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Pang Zewenyue
Original Assignee
逄泽沐风
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 逄泽沐风 filed Critical 逄泽沐风
Priority to CN201810048953.3A priority Critical patent/CN108268847B/en
Publication of CN108268847A publication Critical patent/CN108268847A/en
Application granted granted Critical
Publication of CN108268847B publication Critical patent/CN108268847B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames

Abstract

This application discloses a kind of method and system of film montage language analysis, including：It is loaded into video information；Video information is cut according to camera lens to obtain at least one video clip；Video clip according to playing sequence is arranged and assigns number；Obtain the number and playing duration of video clip；The scape for obtaining video clip is other, obtains the shooting skill of video clip, the montage language that the number of summary video segment, playing duration, scape are other and shooting gimmick is as video information.A kind of method and system of film montage language analysis provided by the present invention does not have the requirement that any step has personnel film working experience in entire method and system, solves the problems, such as in the past low with efficiency for personnel's skill requirement is high, time-consuming.

Description

A kind of method and system of film montage language analysis
Technical field
The present invention relates to film analysis field, more particularly, to a kind of method of film montage language analysis with being System.
Background technology
As the gradually development of society and the promotion of levels of substance, people gradually increase the consumption of film and TV, see The activity videos such as TV of watching movie have become entertainment way important in people's daily life.
Montage language be according to specific creation purpose and follow a series of art rules to camera lens and camera lens, picture and Sound carries out the basic means of organic assembling, by this means, creates the integrality, uniformly of cinematographic work room and time Property, complete the narration to personage, environment and event, thought and emotion of the expression with internal logic, create harmonious rhythm and Style, montage language are more than a kind of editing rule, while are also in a kind of method of thinking and creative method actual life, excellent A variety of different montage language have often been used in the activity videos such as elegant film and television, have passed through shadow movable to film and television etc. As in montage language analyzed and learnt, can keep film practitioner learn director shooting skill when and performance Method, so as to improve the ability level of film practitioner, in the prior art, film practitioner is mainly by floor The shooting gimmick and skill for watching director are learnt, but it is possible to carry out the chance of viewing study in floor and its have Limit, therefore, when more, film practitioner is the activity videos such as the film and television shot by watching director, and is analyzed Montage language therein, time-consuming for this method, efficiency is low, and everyone for film montage language understanding often It is deviated, easily malfunctions.
Therefore it provides a kind of method and system of film montage language analysis, is this field urgent problem to be solved.
Invention content
In view of this, the present invention provides a kind of method and system of film montage language analysis, to solve existing skill And error-prone problem low to film montage language identification efficiency in art.
In order to solve the above-mentioned technical problem, the application proposes a kind of method of film montage language analysis, including：
It is loaded into video information；
The video information is cut according to camera lens to obtain at least one video clip；
The video clip according to playing sequence is arranged and assigns number；
Obtain the number and playing duration of the video clip；
The scape for obtaining the video clip is other, further for:
The frame picture of the video clip is obtained, takes the sampled point on the frame picture, by the sampled point and people Body sample characteristics library is matched, and obtains the sampling point value to match, by the sampling point value to match with predefining Matching threshold compare,
When the sampling point value to match is less than the predefined matching threshold, the frame picture does not include people The frame of object and personage's close up fragmentary, the scape of the frame picture not Wei distant view,
When the sampling point value to match is greater than or equal to the predefined matching threshold, the frame picture packet Frame containing personage or personage's close up fragmentary obtains the ratio of the head area of human body and display screen area in the frame picture,
When human body head area accounts for screen proportion more than or equal to 1/6 in the frame picture, the scape of the frame picture is other For feature,
When in the shot information human body head area account for screen proportion less than 1/6 and more than or equal to 1/48 when, it is described The scape of frame picture not Wei close shot,
When in the shot information human body head area account for screen proportion less than 1/48 and more than or equal to 1/85 when, it is described The scape of frame picture not Wei middle scape,
When human body head area accounts for screen proportion less than 1/85 in the shot information, the scape of the frame picture is not complete Scape,
It obtains in the video clip, the scape of the frame picture is other, and the scape as the video clip is other；
Obtain the shooting skill of the video clip, further for：
The characteristic point on the frame picture of the video clip is obtained, wherein, the spy on any frame picture The number of sign point is fixed value,
Coordinate system is established in the plane where the frame picture, wherein, the coordinate system, including：Transverse coordinate axis and Longitudinal coordinate axle, the origin of the coordinate system are located at the geometric center of the frame picture, and the positive direction of the transverse coordinate axis is The frame picture either direction planar, the positive direction of the longitudinal coordinate axle, the pros with the transverse coordinate axis To intersecting,
Coordinate value of the characteristic point in the coordinate system is calculated, wherein, the coordinate value, including：Abscissa and vertical Coordinate,
Any frame picture is obtained in the video clip as target frame picture,
Obtain the comparison frame picture of the target frame picture, the number of the comparison frame picture, more than the target The number of frame picture,
The target frame picture and the characteristic point that shares of comparison frame picture are obtained, as common characteristic point,
With coordinate value of the common characteristic point in the comparison frame picture, the common characteristic point is subtracted in the mesh The coordinate value in frame picture is marked, obtains the coordinate difference of the common characteristic point, wherein, the coordinate difference includes：Abscissa Difference and ordinate difference,
It is obtained from the common characteristic point, the abscissa difference is more than zero and the spy of the ordinate difference more than zero Point is levied, as fisrt feature point,
It is obtained from the common characteristic point, the abscissa difference is less than zero and the spy of the ordinate difference more than zero Point is levied, as second feature point,
It is obtained from the common characteristic point, the abscissa difference is less than zero and the minus spy of ordinate difference Point is levied, as third feature point,
It is obtained from the common characteristic point, the abscissa difference is more than zero and the minus spy of ordinate difference Point is levied, as fourth feature point,
When the number of the fisrt feature point, second feature point, third feature point and fourth feature point All not less than zero, and the abscissa of fisrt feature point and fourth feature point in the comparison frame picture, it is more than During abscissa in the comparison frame picture of the second feature point and third feature point, the target frame picture and described right The shooting skill used than frame picture to push away,
When the number of the fisrt feature point, second feature point, third feature point and fourth feature point All not less than zero, and the abscissa of second feature point and third feature point in the comparison frame picture, it is more than During abscissa in the comparison frame picture of the fisrt feature point and fourth feature point, the target frame picture and described right Than the shooting skill that frame picture uses to draw,
The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than Zero, and the abscissa difference of common characteristic point and the ordinate difference, with the common characteristic point described When not having monotonicity between the exhausted angle value of the abscissa in target frame picture and the absolute value of the ordinate, the mesh Mark frame picture and the shooting skill that uses of comparison frame picture for shifting,
The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than Zero, and the abscissa difference of common characteristic point or the ordinate difference, with the common characteristic point described When not having monotonicity between the absolute value of the abscissa in target frame picture or the absolute value of the ordinate, the mesh Mark frame picture and the shooting skill that uses of comparison frame picture to shake,
It obtains in the common characteristic point, the abscissa difference and the ordinate difference are equal to zero feature Point is as static feature point, when the number of the static feature point is more than first threshold, the target frame picture and described right The shooting skill used than frame picture for establishing shot, wherein, the first threshold, described in any frame picture The ratio of the number of characteristic point, more than 10%,
It obtains in the video clip, the shooting skill that the target frame picture and the comparison frame picture use, The shooting skill as the video clip；
Summarize the other and described shooting gimmick of the number, the playing duration, the scape of the video clip as institute State the montage language of video information.
Optionally, the video information is cut to obtain at least one video clip according to camera lens, further for：
Any frame picture is obtained from the video information as present frame picture,
The a later frame picture adjacent with the present frame picture is obtained from the video information,
The characteristic point of the present frame picture and a later frame picture is obtained,
The number of the characteristic point that the present frame picture and a later frame picture share is calculated as continuation degree,
When the continuation degree is greater than or equal to second threshold, the present frame picture and a later frame picture belong to same One video clip, wherein：The second threshold, the ratio with the number of the characteristic point of any frame picture, greatly In 50%,
When the continuation degree is less than second threshold, the present frame picture is not belonging to same institute with a later frame picture Video clip is stated, is cut between the present frame picture and a later frame picture.
Optionally, the comparison frame picture belongs to the same video clip with the target frame picture；
The comparison frame picture and the target frame picture are adjacent in the video clip.
Optionally, the coordinate system is rectangular coordinate system, and the transverse coordinate axis and the longitudinal coordinate axle are mutually perpendicular to.
Optionally, obtain the characteristic point on the frame picture, further for：
Static scenes are obtained from the frame picture, at least two characteristic points are set in the static scenes.
Optionally, including：The other acquisition module of video read module, scape, shooting skill acquisition module and computing module；
The video read module, acquisition module other with the scape and the computing module are connected, for being loaded into video Information is cut according to camera lens the video information to obtain at least one video clip, to the video clip according to broadcasting Sequence is arranged and assigns number, obtains the number and playing duration of the video clip；
The other acquisition module of the scape, with the video read module, the shooting skill acquisition module and the calculating mould Block is connected, other for obtaining the scape of the video clip, wherein, the scape for obtaining the video clip is other, further for:
The frame picture of the video clip is obtained, takes the sampled point on the frame picture, by the sampled point and people Body sample characteristics library is matched, and obtains the sampling point value to match, by the sampling point value to match with predefining Matching threshold compare,
When the sampling point value to match is less than the predefined matching threshold, the frame picture does not include people Object frame, the scape of the frame picture not Wei distant view,
When the sampling point value to match is greater than or equal to the predefined matching threshold, the frame picture packet Frame containing personage and personage's close up fragmentary obtains the ratio of the head area of human body and display screen area in the frame picture,
When human body head area accounts for screen proportion more than or equal to 1/6 in the frame picture, the scape of the frame picture is other For feature,
When in the shot information human body head area account for screen proportion less than 1/6 and more than or equal to 1/48 when, it is described The scape of frame picture not Wei close shot,
When in the shot information human body head area account for screen proportion less than 1/48 and more than or equal to 1/85 when, it is described The scape of frame picture not Wei middle scape,
When human body head area accounts for screen proportion less than 1/85 in the shot information, the scape of the frame picture is not complete Scape,
It obtains in the video clip, the scape of the frame picture is other, and the scape as the video clip is other；
The shooting skill acquisition module, acquisition module other with the scape and the computing module are connected, for obtaining The shooting skill of the video clip, wherein, obtain the shooting skill of the video clip, further for：
The characteristic point on the frame picture of the video clip is obtained, wherein：The spy on any frame picture The number of sign point is fixed value,
Coordinate system is established in the plane where the frame picture, wherein, the coordinate system, including：Transverse coordinate axis and Longitudinal coordinate axle, the origin of the coordinate system are located at the geometric center of the frame picture, and the positive direction of the transverse coordinate axis is The frame picture either direction planar, the positive direction of the longitudinal coordinate axle, the pros with the transverse coordinate axis To intersecting,
Coordinate value of the characteristic point in the coordinate system is calculated, wherein, the coordinate value, including：Abscissa and vertical Coordinate,
Any frame picture is obtained in the video clip as target frame picture,
Obtain the comparison frame picture of the target frame picture, the number of the comparison frame picture, more than the target The number of frame picture,
The target frame picture and the characteristic point that shares of comparison frame picture are obtained, as common characteristic point,
With coordinate value of the common characteristic point in the comparison frame picture, the common characteristic point is subtracted in the mesh The coordinate value in frame picture is marked, obtains the coordinate difference of the common characteristic point, wherein, the coordinate difference includes：Abscissa Difference and ordinate difference,
It is obtained from the common characteristic point, the abscissa difference is more than zero and the spy of the ordinate difference more than zero Point is levied, as fisrt feature point,
It is obtained from the common characteristic point, the abscissa difference is less than zero and the spy of the ordinate difference more than zero Point is levied, as second feature point,
It is obtained from the common characteristic point, the abscissa difference is less than zero and the minus spy of ordinate difference Point is levied, as third feature point,
It is obtained from the common characteristic point, the abscissa difference is more than zero and the minus spy of ordinate difference Point is levied, as fourth feature point,
When the number of the fisrt feature point, second feature point, third feature point and fourth feature point All not less than zero, and the abscissa of fisrt feature point and fourth feature point in the comparison frame picture, it is more than During abscissa in the comparison frame picture of the second feature point and third feature point, the target frame picture and described right The shooting skill used than frame picture to push away,
When the number of the fisrt feature point, second feature point, third feature point and fourth feature point All not less than zero, and the abscissa of second feature point and third feature point in the comparison frame picture, it is more than During abscissa in the comparison frame picture of the fisrt feature point and fourth feature point, the target frame picture and described right Than the shooting skill that frame picture uses to draw,
The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than Zero, and the abscissa difference of common characteristic point and the ordinate difference, with the common characteristic point described When not having monotonicity between the exhausted angle value of the abscissa in target frame picture and the absolute value of the ordinate, the mesh Mark frame picture and the shooting skill that uses of comparison frame picture for shifting,
The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than Zero, and the abscissa difference of common characteristic point or the ordinate difference, with the common characteristic point described When not having monotonicity between the absolute value of the abscissa in target frame picture or the absolute value of the ordinate, the mesh Mark frame picture and the shooting skill that uses of comparison frame picture to shake,
It obtains in the common characteristic point, the abscissa difference and the ordinate difference are equal to zero feature Point is as static feature point, when the number of the static feature point is more than first threshold, the target frame picture and described right The shooting skill used than frame picture for establishing shot, wherein, the first threshold and the institute with any frame picture The ratio for stating feature point number is more than 10%,
It obtains in the video clip, the target frame picture and the comparison frame draw the shooting skill used, make The shooting skill for the video clip；
The computing module obtains respectively with the video read module, the other acquisition module of the scape and the shooting skill Modulus block is connected, for summarizing the other and described shooting hand of the number of the video clip, the playing duration, the scape Montage language of the method as the video information.
Optionally, the video read module, including：Video cutter unit, the video cutter unit, is used for：
Any frame picture is obtained from the video information as present frame picture,
The a later frame picture adjacent with the present frame picture is obtained from the video information,
The characteristic point of the present frame picture and a later frame picture is obtained,
The number of the characteristic point that the present frame picture and a later frame picture share is calculated as continuation degree,
When the continuation degree is greater than or equal to second threshold, the present frame picture and a later frame picture belong to same One video clip, wherein：The second threshold and the ratio of the number of the characteristic point of any frame picture are more than 50%,
When the continuation degree is less than second threshold, the present frame picture is not belonging to same institute with a later frame picture Video clip is stated, is cut between the present frame picture and a later frame picture.
Compared with prior art, the method and system of a kind of film montage language analysis provided by the invention, realizes Following advantageous effect：
1) method and system of a kind of film montage language analysis provided by the present invention, it is not any in entire method Step has personnel the requirement of film working experience, solves in the past low with efficiency for personnel's skill requirement is high, time-consuming The problem of；
2) method and system of a kind of film montage language analysis provided by the present invention, reduce to it is artificial according to Rely, can quickly identify the montage language in the activity videos such as film and television, learn film shooting skill for film practitioner Ingeniously provide abundant data.
Description of the drawings
It is combined in the description and the attached drawing of a part for constitution instruction shows the embodiment of the present invention, and even With its explanation together principle for explaining the present invention.
Fig. 1 is a kind of flow chart of the method for film montage language analysis in the present invention；
Fig. 2 is a kind of flow chart for the scape method for distinguishing for obtaining video clip in the present invention；
Fig. 3 is a kind of flow chart of the method for the shooting skill for obtaining video clip in the present invention；
Fig. 4 is a kind of system of film montage language analysis in the present invention.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should be noted that：Unless in addition have Body illustrates that the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally The range of invention.
It is illustrative to the description only actually of at least one exemplary embodiment below, is never used as to the present invention And its application or any restrictions that use.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable In the case of, the technology, method and apparatus should be considered as part of specification.
In shown here and discussion all examples, any occurrence should be construed as merely illustrative, without It is as limitation.Therefore, other examples of exemplary embodiment can have different values.It should be noted that：Once a certain item exists It is defined in one attached drawing, then in subsequent attached drawing does not need to that it is further discussed.
Fig. 1 is a kind of flow chart of the method for film montage language analysis in the present invention, as shown in Figure 1, the present invention carries A kind of method of the film montage language analysis supplied, including：
S101：Video information is loaded into, video information is cut according to camera lens to obtain at least one video clip, to regarding Frequency segment is arranged according to playing sequence and assigns number.
Specifically, when video information is played out according to the broadcasting speed of general video, playing duration should not be too short, one As should be more than 10 seconds, the video information of reading can be the video informations such as the film and television of black and white or colour, film and television etc. Video information can include image and audio, and it is by a series of frame pictures that can also there was only the video informations such as image, film and television Composition includes 24 width frame pictures in usual one second, when broadcasting, because previous width frame picture has image residue on human eye, and institute Go out the interval of two width frame pictures with human eye None- identified, when obtaining the frame picture in video information, whole frames can be obtained and drawn Face can also be spaced a certain number of frame pictures, a width frame picture be extracted, because the variation between adjacent two width frame picture is past It is past smaller, it is difficult to the distinctive points between two width frame pictures are found out, be easy to cause the problem of identification is difficult, therefore, optionally, for The video informations such as general film and television, one width frame picture of middle extraction per second, i.e., extract a width frame picture every 23 width frame pictures, The frame picture of all extractions is summarized, assigns and numbering according to playing sequence, number since 1, according to natural number sequentially Arrangement, then the frame picture summarized is cut according to camera lens, then according to the position of cutting, correspondence is found out in video information Cutting position, cut video information in the position, obtain each video clip.
S102：Obtain the number and playing duration of video clip.
Specifically, video clip is arranged, and obtain each video clip respectively according to the sequence of number from small to large Playing duration.
S103：The scape for obtaining video clip is other.
Fig. 2 is a kind of flow chart for the scape method for distinguishing for obtaining video clip in the present invention, as shown in Fig. 2, obtaining video The scape of segment does not further comprise：S1031-S1038.
S1031：The frame picture of video clip is obtained, the sampled point on frame picture is taken, by sampled point and human sample Feature database is matched, and obtains the sampling point value to match, by the sampling point value to match and predefined matching threshold It compares.
S1032：When the sampling point value to match is less than predefined matching threshold, frame picture does not include personage and people The frame of object close up fragmentary, the scape of frame picture Wei not distant view.
Specifically, when containing character image in frame picture, then the sampling point value to match should be greater than or equal to predefined Matching threshold, when not containing character image in shot information, then the sampling point value to match should be less than predefined It is distant view when not containing character image with threshold value.
S1033：When the sampling point value to match is greater than or equal to predefined matching threshold, frame picture includes personage Or the frame of personage's close up fragmentary, the ratio of the head area of human body and display screen area in getting frame picture.
Specifically, scape can not be divided into feature, close shot, middle scape, distant view and panorama, the not middle character image of different scapes is stood Ratio it is different, the head of usual people accounts for the 1/8 of Human Height, and human body head width accounts for the 1/2 of human body shoulder breadth.Human body is in camera lens The range occurred in information is different, and the ratio for causing human body head shared in shot information is different.Therefore according to the head of human body The area ratio of portion's area and display screen, as the differentiation other foundation of camera lens scape.
S1034：When human body head area accounts for screen proportion more than or equal to 1/6 in frame picture, the scape of frame picture Wei not be special It writes.
S1035：When in shot information human body head area account for screen proportion less than 1/6 and more than or equal to 1/48 when, frame The scape of picture Wei not close shot.
S1036：When in shot information human body head area account for screen proportion less than 1/48 and more than or equal to 1/85 when, frame The scape of picture Wei not middle scape.
S1037：When human body head area accounts for screen proportion less than 1/85 in shot information, the scape of frame picture is not complete Scape.
S1038：It obtains in video clip, the scape of frame picture is other, and the scape as video clip is other.
Specifically, for any video clip, the scape for needing to obtain each frame picture in the video clip is other, when the video Existing in segment and use the other frame picture of different scapes, then the scape of video clip is not that all types of scapes are other, such as：One video It is made of in segment the other frame picture of scape scape in using the other frame picture of close shot scape and using, then the scape of the video clip is not Close shot and middle scape.
S104：Obtain the shooting skill of video clip.
Fig. 3 is a kind of method flow diagram for the shooting skill for obtaining video clip in the present invention, is regarded as shown in figure 3, obtaining The shooting skill of frequency segment, including：S1041-S1049.
S1041：Characteristic point on getting frame picture cuts according to camera lens video information to obtain video clip, Coordinate system is established in plane where frame picture, calculates the coordinate value of characteristic point in a coordinate system.
Specifically, the number of the characteristic point on any one frame picture is fixed value, i.e. characteristic point on any frame picture Number, it is equal with the number of the characteristic point on another frame picture, further, in some optional embodiments, getting frame Characteristic point on picture, further for：Static scenes are obtained from frame picture, at least two features are set in static scenes Point.After video information is cut according to camera lens, the whole frame picture in any one video clip is carried out using a camera lens Shooting, the origin of coordinate system are located at the geometric center of frame picture, and coordinate system includes：Transverse coordinate axis and longitudinal coordinate axle, laterally The positive direction of reference axis, be frame picture either direction planar, the positive direction of longitudinal coordinate axle, with transverse coordinate axis Positive direction intersects, and there are one intersection point, non-overlapping copies, angular relationships each other not to do for transverse coordinate axis and longitudinal coordinate axle Any restriction, further, in some optional embodiments, coordinate system is rectangular coordinate system, lateral coordinates and longitudinal coordinate It is mutually perpendicular to, optionally, frame picture is rectangle, and lateral coordinates and longitudinal coordinate are respectively parallel to the horizontal edge and longitudinal edge of frame picture. In other situations, according to specific condition and requirement, non-orthogonal coordinate system can also be established.Coordinate value in coordinate system, packet It includes：Abscissa and ordinate.
S1042：Obtaining any frame picture in video clip, as target frame picture, the comparison frame for obtaining target frame picture is drawn Face obtains target frame picture and compares the characteristic point that frame picture shares, as common characteristic point.
Specifically, it is generally obtained, then obtain it since the first width frame picture of video clip when obtaining target frame picture Corresponding target frame picture, the frame picture after then obtaining successively obtain corresponding target frame and draw as target frame picture Face compares the number of frame picture, more than the number of target frame picture.The common characteristic point of acquisition, refers to existing simultaneously in mesh It marks frame picture and compares the characteristic point in frame picture, the position relation between these characteristic points will not change, for example, in mesh It marks in frame picture, characteristic point A and characteristic point B are located at the left and right sides of characteristic point C, then in frame picture is compared, characteristic point A and spy Sign point B is still located at the both sides of characteristic point C, and still, distance relation each other can change, i.e. between two characteristic points Distance can change.
S1043：With coordinate value of the common characteristic point in frame picture is compared, common characteristic point is subtracted in target frame picture Coordinate value, obtain the coordinate difference of common characteristic point, wherein, coordinate difference includes：Abscissa difference and ordinate difference, from Fisrt feature point, second feature point, third feature point and fourth feature point are obtained in common characteristic point.
Specifically, the size of comparison frame picture should be identical with the size of target frame picture, the coordinate system of foundation is same Kind coordinate system, and establish at same position, at this moment difference operation could be carried out to coordinate value, carry out the rule of difference operation It is that the abscissa subtracted in target frame picture with the abscissa in common characteristic point comparison frame picture obtains abscissa difference, The ordinate subtracted in target frame picture with the ordinate in common characteristic point comparison frame picture obtains ordinate difference.
Specifically, being obtained from common characteristic point, abscissa difference is more than zero and feature of the ordinate difference more than zero Point, as fisrt feature point；It is obtained from common characteristic point, abscissa difference is less than zero and feature of the ordinate difference more than zero Point, as second feature point；It is obtained from common characteristic point, abscissa difference is less than zero and the minus feature of ordinate difference Point, as third feature point；It is obtained from common characteristic point, abscissa difference is more than zero and the minus feature of ordinate difference Point, as fourth feature point；When the coordinate system of foundation is Descartes's rectangular coordinate system, the pros of abscissa are represented with right direction To upper direction represents the positive direction of ordinate, and fisrt feature point refers to the characteristic point moved to upper right, second feature point The characteristic point of upper left movement is directed to, third feature point is directed to the characteristic point of lower left movement, and fourth feature point is It is directed toward the characteristic point of lower right movement.
S1044：When the number of fisrt feature point, second feature point, third feature point and fourth feature point is all not less than zero, And the abscissa of fisrt feature point and fourth feature point in frame picture is compared, exists more than second feature point and third feature point When comparing the abscissa in frame picture, the shooting skill that target frame picture and comparison frame picture use is pushes away.
S1045：When the number of fisrt feature point, second feature point, third feature point and fourth feature point is all not less than zero, And the abscissa of second feature point and third feature point in frame picture is compared, exists more than fisrt feature point and fourth feature point When comparing the abscissa in frame picture, the shooting skill that target frame picture and comparison frame picture use is draws；.
Specifically, by the coordinate system of foundation for for Descartes's rectangular coordinate system, the pros of abscissa are represented with right direction Represent the positive direction of ordinate to, upper direction, fisrt feature point, second feature point, third feature point and fourth feature point Number represents that comparison frame picture is pushed or pulled on relative to target frame picture all not less than zero, and in frame picture is compared, first The abscissa of characteristic point and fourth feature point during more than the abscissa of second feature point and third feature point, represents to be located at right side Characteristic point move to the right, the characteristic point positioned at left side moves to the left, i.e., the local content of target frame picture comparison frame It is amplified in picture, at this point, the ordinate of fisrt feature point and second feature point in frame picture is compared, more than third feature point With ordinate of the fourth feature point in frame picture is compared.Similarly, in frame picture is compared, second feature point and third feature point Abscissa, during more than the abscissa of fisrt feature point and fourth feature point, represent characteristic point positioned at right side to sitting side movement, Characteristic point positioned at left side moves to the right, i.e., target frame picture in frame picture is compared be reduced, at this point, fisrt feature point and Ordinate of the second feature point in frame picture is compared, it is vertical in frame picture is compared less than third feature point and fourth feature point Coordinate.
S1046：When the abscissa difference of common characteristic point or ordinate difference, both greater than zero or both less than zero, and The abscissa difference of common characteristic point and ordinate difference, the absolute value with abscissa of the shared characteristic point in target frame picture When not having monotonicity between the absolute value of ordinate, the shooting skill that target frame picture and comparison frame picture use is moves.
Specifically, when the abscissa difference of common characteristic point or ordinate difference, when both greater than zero or both less than zero, table Bright video camera for shooting is not moved forward and backward in movement, i.e., without along being moved perpendicular to the direction of camera lens, sharing spy The abscissa difference of point and ordinate difference are levied, absolute value and vertical seat with abscissa of the shared characteristic point in target frame picture Do not have monotonicity between target absolute value, the distance for showing each common characteristic point movement and the position in its again target frame picture It puts unrelated, i.e., is non-translation in the front-back direction at this time, i.e., using shifting.
S1047：When the abscissa difference of common characteristic point or ordinate difference, both greater than zero or both less than zero, and The abscissa difference of common characteristic point or ordinate difference, the absolute value with abscissa of the shared characteristic point in target frame picture Or when not having monotonicity between the absolute value of ordinate, the shooting skill that target frame picture and comparison frame picture use is shakes.
Specifically, when the abscissa difference of common characteristic point or ordinate difference, when both greater than zero or both less than zero, table Bright video camera for shooting is not moved forward and backward in movement, the abscissa difference of common characteristic point or ordinate difference, Between the absolute value of abscissa of the shared characteristic point in target frame picture or the absolute value of ordinate there is monotonicity, show The distance of each common characteristic point movement is related with the position in its again target frame picture, i.e., using shifting, this is because adopting When with shaking, angle change has occurred, different angle measure two characteristic points between apart from when be different, so When using shaking, the coordinate difference of common characteristic point is related with the position where it.
S1048：It obtains in common characteristic point, abscissa difference and ordinate difference are equal to zero characteristic point as static Characteristic point, when the number of static feature point is more than first threshold, the shooting skill of target frame picture and the picture use of comparison frame For establishing shot.
Specifically, first threshold is with the ratio of the feature point number of any frame picture with being more than 10%, during establishing shot, take the photograph Camera is fixed, so the significant scenery such as building will not be good in target frame picture and compares and change position in frame picture, There is common characteristic point of multiple coordinate values without variation, still, it is contemplated that vibrations, light refraction etc. in practical photographic process Influence factor is shown as mobile during the original object without movement is possible, and the object moved originally may also be shown as static, Therefore it needs to set first threshold, only when the number of static feature point is more than first threshold, can just think the shooting used Skill is establishing shot, and first threshold with the ratio of the feature point number of any frame picture with being more than 10%.
S1049：It obtains in video clip, target frame picture and comparison frame draw the shooting skill used, as video clip Shooting skill.
S105：The montage language that the number of summary video segment, playing duration, scape are other and shooting gimmick is as video information Speech.
Specifically, obtained montage language includes each video clip, video clip coding and playing duration, each regards Scape employed in frequency segment and used by shooting the video clip does not shoot gimmick.
Further, it in some optional embodiments, video information is cut to obtain at least one according to camera lens is regarded Frequency segment, further to obtain any frame picture from video information as present frame picture, being obtained from video information any Frame picture obtains a later frame picture adjacent with present frame picture from video information, obtains present frame as present frame picture The characteristic point of picture and a later frame picture calculates the number for the characteristic point that present frame picture and a later frame picture share as continuous Degree, when continuation degree is greater than or equal to second threshold, present frame picture and a later frame picture belong to same video clip, wherein： Second threshold and the ratio of the number of the characteristic point of any frame picture are more than 50%, when continuation degree is less than second threshold, currently Frame picture is not belonging to same video clip with a later frame picture, is cut between present frame picture and a later frame picture.
Specifically, the number of characteristic point is identical possessed by each frame picture, i.e., feature point number possessed by frame picture It is fixed value, when distinguishing whether present frame picture belongs to unified video clip with a later frame picture, this two width frame picture is total to With the number of characteristic point possessed, as continuation degree, to the foundation as judgement, because of the frame picture shot with unified camera lens There should be more same characteristic features point, so, when continuation degree is greater than or equal to second threshold, and second threshold and any frame The ratio of the number of the characteristic point of picture is more than 50%.
Further, in some optional embodiments, comparison frame picture belongs to same video clip with target frame picture； It compares frame picture and target frame picture is adjacent in video clip；The number of frame picture is compared, more than the number of target frame picture, I.e. comparison frame picture is the latter width frame picture close to target frame picture.
The present invention provides a kind of methods of film montage language analysis, can directly acquire the activities such as film and television and regard Montage language in frequency including obtaining the scape of each video clip not and shooting gimmick, does not have any step in entire method There is working experience requirement to film practitioner, reduce identification cost, improve recognition efficiency, can be that film and television are obtained employment Personnel provide the data and guiding opinion of study, are conducive to improve the shooting skill of film practitioner.
The present invention also provides a kind of system of film montage language analysis, Fig. 4 is a kind of film montage in the present invention The system of language analysis, as shown in figure 4, the system includes：The other acquisition module 202 of video read module 201, scape, shooting skill Acquisition module 203 and computing module 204；
Video read module 201, acquisition module other with scape and computing module are connected, for being loaded into video information, will regard Frequency information is cut to obtain at least one video clip according to camera lens, and video clip is arranged and assigned according to playing sequence Number is given, obtains the number and playing duration of video clip.
Specifically, the video information read can be the activity videos such as the film and television of black and white or colour, film and television etc. Activity video can include image and audio, and it is by a series of frame pictures that can also there was only the activity videos such as image, film and television Composition includes 24 width frame pictures in usual one second, when obtaining the frame picture in video information, can obtain whole frame pictures, Can be spaced a certain number of frame pictures, extract a width frame picture because the variation between adjacent two width frame picture often compared with It is small, it is difficult to find out the distinctive points between two width frame pictures, be easy to cause the problem of identification is difficult, the frame picture of all extractions is converged Always, it assigns and numbering according to playing sequence, number since 1, according to the sequentially arrangement of natural number, then the frame picture that will summarize It is cut according to camera lens, then according to the position of cutting, correspondence is found out the corresponding position in video information, cut in the position Video information is cut, obtains at least one video clip, then calculates the playing duration of each video clip, and by each video clip Number and playing duration send computing module 204 to.
Further, at some optionally and in embodiment, video read module 201, including：Video cutter unit, depending on Frequency cutter unit, is used for：Any frame picture is obtained from video information as present frame picture, obtains and works as from video information The adjacent a later frame picture of previous frame picture obtains the characteristic point of present frame picture and a later frame picture, calculate present frame picture and The number for the characteristic point that a later frame picture shares is as continuation degree, and when continuation degree is greater than or equal to second threshold, present frame is drawn Face and a later frame picture belong to same video clip, wherein：Second threshold and the ratio of the number of the characteristic point of any frame picture More than 50%, when continuation degree is less than second threshold, present frame picture is not belonging to same video clip with a later frame picture, is working as It is cut between previous frame picture and a later frame picture.
Specifically, the number of characteristic point is identical possessed by each frame picture, i.e., characteristic point possessed by any frame picture Number is fixed value, when distinguishing whether present frame picture belongs to unified video clip with a later frame picture, this two width frame picture The number of co-owned characteristic point, as continuation degree, to the foundation as judgement, because of the frame shot with same camera lens Picture should have more same characteristic features point, so, when continuation degree is greater than or equal to second threshold, and second threshold is with appointing The ratio of the number of the characteristic point of one frame picture is more than 50%.
The other acquisition module 202 of scape, with 204 phase of video read module 201, shooting skill acquisition module 203 and computing module Connection, the scape of video clip is other for obtaining, and after video read module 201 handles the video information of reading, will cut The each video clip obtained afterwards sends the other acquisition module 202 of scape to.
The scape that the other acquisition module 202 of scape obtains video clip is other, further for:The frame picture of video clip is obtained, is obtained The sampled point on frame picture is taken, sampled point with human sample feature database is matched, obtains the sampling point value to match, it will The sampling point value to match is compared with predefined matching threshold, when the sampling point value to match is less than predefined During with threshold value, frame picture does not include the frame of personage and personage's close up fragmentary, the scape of frame picture not Wei distant view, when the sampling to match When point value is greater than or equal to predefined matching threshold, frame picture includes the frame of personage's frame or personage's close up fragmentary, getting frame The ratio of the head area of human body and display screen area in picture, when human body head area accounts for screen proportion and is more than in frame picture Or during equal to 1/6, the scape of frame picture not Wei feature, when to account for screen proportion less than 1/6 and big for human body head area in shot information When 1/48, the scape of frame picture not Wei close shot, when human body head area accounts for screen proportion less than 1/48 in shot information And during more than or equal to 1/85, the scape of frame picture not Wei middle scape, when human body head area accounts for screen proportion and is less than in shot information When 1/85, the scape of frame picture not Wei panorama, obtain in video clip, the scape of frame picture is other, and the scape as video clip is other.
Specifically, the other acquisition module 202 of scape get each video clip scape it is other after, the scape of acquisition is not and corresponding Video number be sent to computing module 204, computing module 204 stores the data of acquisition.
Shooting skill acquisition module 203, acquisition module 202 other with scape and computing module 204 are connected, for obtaining video The shooting skill of segment, in some optional embodiments, shooting skill acquisition module can be connected with video read module 201 It connects, the copy of the video clip after such video read module 201 is processed can be transmitted directly to shooting skill acquisition module 203, video clip is handled so as to synchronous with the other acquisition module 202 of scape.
Shooting skill acquisition module 203 obtain video clip shooting skill, further for：The frame for obtaining video clip is drawn Characteristic point on face, wherein：The number of the characteristic point of arbitrary two width frame picture is identical, establishes and sits in the plane where frame picture Mark system, wherein, coordinate system, including：Transverse coordinate axis and longitudinal coordinate axle, the origin of coordinate system are located in the geometry of frame picture The heart, the positive direction of transverse coordinate axis, be frame picture either direction planar, the positive direction of longitudinal coordinate axle, with transverse direction The positive direction of reference axis intersects, and calculates the coordinate value of characteristic point in a coordinate system, wherein, coordinate value, including：Abscissa and vertical seat Mark obtains any frame picture in video clip and, as target frame picture, obtains the comparison frame picture of target frame picture, comparison frame is drawn The number in face more than the number of target frame picture, obtains target frame picture and compares the characteristic point that frame picture shares, as shared Characteristic point with coordinate value of the common characteristic point in frame picture is compared, subtracts coordinate of the common characteristic point in target frame picture Value, obtains the coordinate difference of common characteristic point, wherein, coordinate difference includes：Abscissa difference and ordinate difference, from shared spy It is obtained in sign point, abscissa difference is more than zero and characteristic point of the ordinate difference more than zero, as fisrt feature point, from shared spy It is obtained in sign point, abscissa difference is less than zero and characteristic point of the ordinate difference more than zero, as second feature point, from shared spy It is obtained in sign point, abscissa difference is less than zero and the minus characteristic point of ordinate difference, as third feature point, from shared spy It is obtained in sign point, abscissa difference is more than zero and the minus characteristic point of ordinate difference, as fourth feature point, as the first spy The number of point, second feature point, third feature point and fourth feature point is levied all not less than zero, and fisrt feature point and the 4th spy Abscissa of the sign point in frame picture is compared, more than the abscissa of second feature point and third feature point in frame picture is compared When, the shooting skill that target frame picture and comparison frame picture use is pushes away, when fisrt feature point, second feature point, third feature The number of point and fourth feature point is all not less than zero, and the horizontal seat of second feature point and third feature point in frame picture is compared Mark, more than fisrt feature point and fourth feature point in the abscissa in comparing frame picture, target frame picture and comparison frame picture The shooting skill used is draws, when the abscissa difference of common characteristic point or ordinate difference, both greater than zero or both less than zero, And the abscissa difference of common characteristic point and ordinate difference, it is exhausted with abscissa of the shared characteristic point in target frame picture When not having monotonicity between angle value and the absolute value of ordinate, target frame picture and the shooting skill that uses of comparison frame picture for It moves, when the abscissa difference of common characteristic point or ordinate difference, both greater than zero or both less than zero, and common characteristic point Abscissa difference or ordinate difference, it is exhausted with the absolute value of abscissa of the shared characteristic point in target frame picture or ordinate When not having monotonicity between value, the shooting skill that target frame picture and comparison frame picture use obtains common characteristic to shake In point, abscissa difference and ordinate difference are equal to zero characteristic point as static feature point, when the number of static feature point During more than first threshold, target frame picture and the shooting skill that uses of comparison frame picture for establishing shot, wherein, first threshold and It is more than 10% with the ratio of the feature point number of any frame picture, obtains in video clip, target frame picture and comparison frame picture is adopted Shooting skill, the shooting skill as video clip.
Specifically, shooting skill is divided into and pushes away, draws, shaking, moving and establishing shot, in a video clip, using a mirror Head is shot, but can simultaneously using one or more shooting skills and video clip shooting skill can with more than one, Can simultaneously include it is a variety of, obtain shooting skill when, can only count the shooting skill used, can also count simultaneously use this The duration of shooting skill, the duration used so as to calculate each shooting skill account for the percentage of the video clip playing duration, So as to learn each shooting skill is occupied in the video clip ratio, such as：In one video clip in 30% time Using pushing away, 70% time uses establishing shot.The video judges the establishing shot pushed away with 70% that shooting skill includes 30%.
Computing module 304, respectively with video read module 301, the other acquisition module 302 of scape, shooting skill acquisition module 303 It is connected, the montage language that the number, playing duration, scape for summary video segment are other and shooting gimmick is as video information Speech.
1) method and system of a kind of film montage language analysis provided by the present invention, it is not any in entire method Step has personnel the requirement of film working experience, solves in the past low with efficiency for personnel's skill requirement is high, time-consuming The problem of；
2) method and system of a kind of film montage language analysis provided by the present invention, reduce to it is artificial according to Rely, can quickly identify the montage language in the activity videos such as film and television, learn film shooting skill for film practitioner Ingeniously provide abundant data.
Although some specific embodiments of the present invention are described in detail by example, the skill of this field Art personnel it should be understood that example above merely to illustrating, the range being not intended to be limiting of the invention.The skill of this field Art personnel are it should be understood that can without departing from the scope and spirit of the present invention modify to above example.This hair Bright range is defined by the following claims.

Claims (7)

  1. A kind of 1. method of film montage language analysis, which is characterized in that including：
    It is loaded into video information；
    The video information is cut according to camera lens to obtain at least one video clip；
    The video clip according to playing sequence is arranged and assigns number；
    Obtain the number and playing duration of the video clip；
    The scape for obtaining the video clip is other, further for:
    The frame picture of the video clip is obtained, takes the sampled point on the frame picture, by the sampled point and human body sample Eigen library is matched, and obtains the sampling point value to match, by the sampling point value to match and predefined It compares with threshold value,
    When the sampling point value to match be less than the predefined matching threshold when, the frame picture do not include personage and The frame of personage's close up fragmentary, the scape of the frame picture not Wei distant view,
    When the sampling point value to match is greater than or equal to the predefined matching threshold, the frame picture includes people The frame of object or personage's close up fragmentary obtains the ratio of the head area of human body and display screen area in the frame picture,
    When human body head area accounts for screen proportion more than or equal to 1/6 in the frame picture, the scape of the frame picture Wei not be special It writes,
    When human body head area accounts for screen proportion less than 1/6 and during more than or equal to 1/48 in the shot information, the frame is drawn The scape in face not Wei close shot,
    When human body head area accounts for screen proportion less than 1/48 and during more than or equal to 1/85 in the shot information, the frame is drawn The scape in face not Wei middle scape,
    When human body head area accounts for screen proportion less than 1/85 in the shot information, the scape of the frame picture not Wei panorama,
    It obtains in the video clip, the scape of the frame picture is other, and the scape as the video clip is other；
    Obtain the shooting skill of the video clip, further for：
    The characteristic point on the frame picture of the video clip is obtained, wherein, the characteristic point on any frame picture Number for fixed value,
    Coordinate system is established in the plane where the frame picture, wherein, the coordinate system, including：Transverse coordinate axis and longitudinal direction Reference axis, the origin of the coordinate system are located at the geometric center of the frame picture, and the positive direction of the transverse coordinate axis is described Frame picture either direction planar, the positive direction of the longitudinal coordinate axle, the positive direction phase with the transverse coordinate axis It hands over,
    Coordinate value of the characteristic point in the coordinate system is calculated, wherein, the coordinate value, including：Abscissa and ordinate,
    Any frame picture is obtained in the video clip as target frame picture,
    The comparison frame picture of the target frame picture is obtained, the number of the comparison frame picture is drawn more than the target frame The number in face,
    The target frame picture and the characteristic point that shares of comparison frame picture are obtained, as common characteristic point,
    With coordinate value of the common characteristic point in the comparison frame picture, the common characteristic point is subtracted in the target frame Coordinate value in picture obtains the coordinate difference of the common characteristic point, wherein, the coordinate difference includes：Abscissa difference With ordinate difference,
    It is obtained from the common characteristic point, the abscissa difference is more than zero and the feature of the ordinate difference more than zero Point, as fisrt feature point,
    It is obtained from the common characteristic point, the abscissa difference is less than zero and the feature of the ordinate difference more than zero Point, as second feature point,
    It is obtained from the common characteristic point, the abscissa difference is less than zero and the minus feature of ordinate difference Point, as third feature point,
    It is obtained from the common characteristic point, the abscissa difference is more than zero and the minus feature of ordinate difference Point, as fourth feature point,
    When the fisrt feature point, second feature point, third feature point and fourth feature point number not Less than zero, and the abscissa of fisrt feature point and fourth feature point in the comparison frame picture, more than described During abscissa in the comparison frame picture of second feature point and third feature point, the target frame picture and the comparison frame The shooting skill that picture uses to push away,
    When the fisrt feature point, second feature point, third feature point and fourth feature point number not Less than zero, and the abscissa of second feature point and third feature point in the comparison frame picture, more than described During abscissa in the comparison frame picture of fisrt feature point and fourth feature point, the target frame picture and the comparison frame The shooting skill that picture uses for draw,
    The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than zero, and And the abscissa difference and the ordinate difference of the common characteristic point, with the common characteristic point in the target frame When not having monotonicity between the exhausted angle value of the abscissa in picture and the absolute value of the ordinate, the target frame is drawn Face and the shooting skill that uses of comparison frame picture for shifting,
    The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than zero, and And the abscissa difference or the ordinate difference of the common characteristic point, with the common characteristic point in the target frame When not having monotonicity between the absolute value of the abscissa in picture or the absolute value of the ordinate, the target frame is drawn Face and the shooting skill that uses of comparison frame picture to shake,
    It obtains in the common characteristic point, the characteristic point that the abscissa difference and the ordinate difference are equal to zero is made For static feature point, when the number of the static feature point is more than first threshold, the target frame picture and the comparison frame The shooting skill that picture uses for establishing shot, wherein, the first threshold, the feature with any frame picture The ratio of the number of point, more than 10%,
    It obtains in the video clip, the shooting skill that the target frame picture and the comparison frame picture use, as The shooting skill of the video clip；
    Summarize and regarded described in the other and described shooting gimmick conduct of the number, the playing duration, the scape of the video clip The montage language of frequency information.
  2. 2. a kind of method of film montage language analysis as described in claim 1, which is characterized in that by the video information Cut to obtain at least one video clip according to camera lens, further for：
    Any frame picture is obtained from the video information as present frame picture,
    The a later frame picture adjacent with the present frame picture is obtained from the video information,
    The characteristic point of the present frame picture and a later frame picture is obtained,
    The number of the characteristic point that the present frame picture and a later frame picture share is calculated as continuation degree,
    When the continuation degree is greater than or equal to second threshold, the present frame picture and a later frame picture belong to same institute Video clip is stated, wherein：The second threshold, the ratio with the number of the characteristic point of any frame picture, is more than 50%,
    When the continuation degree is less than second threshold, the present frame picture and a later frame picture be not belonging to it is same described in regard Frequency segment is cut between the present frame picture and a later frame picture.
  3. 3. a kind of method of film montage language analysis as claimed in claim 2, which is characterized in that
    The comparison frame picture belongs to the same video clip with the target frame picture；
    The comparison frame picture and the target frame picture are adjacent in the video clip.
  4. 4. a kind of method of film montage language analysis as described in claim 1, which is characterized in that the coordinate system is straight Angular coordinate system, the transverse coordinate axis and the longitudinal coordinate axle are mutually perpendicular to.
  5. 5. a kind of method of film montage language analysis as described in claim 1, which is characterized in that obtain the frame picture On characteristic point, further for：
    Static scenes are obtained from the frame picture, at least two characteristic points are set in the static scenes.
  6. 6. a kind of system of film montage language analysis, which is characterized in that including：The other acquisition module of video read module, scape, Shooting skill acquisition module and computing module；
    The video read module, acquisition module other with the scape and the computing module are connected, for being loaded into video information, The video information is cut according to camera lens to obtain at least one video clip, to the video clip according to playing sequence It is arranged and assigns number, obtain the number and playing duration of the video clip；
    The other acquisition module of the scape, with the video read module, the shooting skill acquisition module and the computing module phase Connection, it is other for obtaining the scape of the video clip, wherein, the scape for obtaining the video clip is other, further for:
    The frame picture of the video clip is obtained, takes the sampled point on the frame picture, by the sampled point and human body sample Eigen library is matched, and obtains the sampling point value to match, by the sampling point value to match and predefined It compares with threshold value,
    When the sampling point value to match is less than the predefined matching threshold, the frame picture does not include personage Frame, the scape of the frame picture not Wei distant view,
    When the sampling point value to match is greater than or equal to the predefined matching threshold, the frame picture includes people The frame of object and personage's close up fragmentary obtains the ratio of the head area of human body and display screen area in the frame picture,
    When human body head area accounts for screen proportion more than or equal to 1/6 in the frame picture, the scape of the frame picture Wei not be special It writes,
    When human body head area accounts for screen proportion less than 1/6 and during more than or equal to 1/48 in the shot information, the frame is drawn The scape in face not Wei close shot,
    When human body head area accounts for screen proportion less than 1/48 and during more than or equal to 1/85 in the shot information, the frame is drawn The scape in face not Wei middle scape,
    When human body head area accounts for screen proportion less than 1/85 in the shot information, the scape of the frame picture not Wei panorama,
    It obtains in the video clip, the scape of the frame picture is other, and the scape as the video clip is other；
    The shooting skill acquisition module, acquisition module other with the scape and the computing module are connected, described for obtaining The shooting skill of video clip, wherein, obtain the shooting skill of the video clip, further for：
    The characteristic point on the frame picture of the video clip is obtained, wherein：The characteristic point on any frame picture Number for fixed value,
    Coordinate system is established in the plane where the frame picture, wherein, the coordinate system, including：Transverse coordinate axis and longitudinal direction Reference axis, the origin of the coordinate system are located at the geometric center of the frame picture, and the positive direction of the transverse coordinate axis is described Frame picture either direction planar, the positive direction of the longitudinal coordinate axle, the positive direction phase with the transverse coordinate axis It hands over,
    Coordinate value of the characteristic point in the coordinate system is calculated, wherein, the coordinate value, including：Abscissa and ordinate,
    Any frame picture is obtained in the video clip as target frame picture,
    The comparison frame picture of the target frame picture is obtained, the number of the comparison frame picture is drawn more than the target frame The number in face,
    The target frame picture and the characteristic point that shares of comparison frame picture are obtained, as common characteristic point,
    With coordinate value of the common characteristic point in the comparison frame picture, the common characteristic point is subtracted in the target frame Coordinate value in picture obtains the coordinate difference of the common characteristic point, wherein, the coordinate difference includes：Abscissa difference With ordinate difference,
    It is obtained from the common characteristic point, the abscissa difference is more than zero and the feature of the ordinate difference more than zero Point, as fisrt feature point,
    It is obtained from the common characteristic point, the abscissa difference is less than zero and the feature of the ordinate difference more than zero Point, as second feature point,
    It is obtained from the common characteristic point, the abscissa difference is less than zero and the minus feature of ordinate difference Point, as third feature point,
    It is obtained from the common characteristic point, the abscissa difference is more than zero and the minus feature of ordinate difference Point, as fourth feature point,
    When the fisrt feature point, second feature point, third feature point and fourth feature point number not Less than zero, and the abscissa of fisrt feature point and fourth feature point in the comparison frame picture, more than described During abscissa in the comparison frame picture of second feature point and third feature point, the target frame picture and the comparison frame The shooting skill that picture uses to push away,
    When the fisrt feature point, second feature point, third feature point and fourth feature point number not Less than zero, and the abscissa of second feature point and third feature point in the comparison frame picture, more than described During abscissa in the comparison frame picture of fisrt feature point and fourth feature point, the target frame picture and the comparison frame The shooting skill that picture uses is draws, the abscissa difference or the ordinate difference when the common characteristic point, Both greater than zero or both less than zero, and the abscissa difference of common characteristic point and the ordinate difference, with institute It states between the exhausted angle value of the abscissa of the common characteristic point in the target frame picture and the absolute value of the ordinate not During with monotonicity, the target frame picture and the shooting skill that uses of comparison frame picture for shifting,
    The abscissa difference or the ordinate difference when the common characteristic point, both greater than zero or both less than zero, and And the abscissa difference or the ordinate difference of the common characteristic point, with the common characteristic point in the target frame When not having monotonicity between the absolute value of the abscissa in picture or the absolute value of the ordinate, the target frame is drawn Face and the shooting skill that uses of comparison frame picture to shake,
    It obtains in the common characteristic point, the characteristic point that the abscissa difference and the ordinate difference are equal to zero is made For static feature point, when the number of the static feature point is more than first threshold, the target frame picture and the comparison frame The shooting skill that picture uses for establishing shot, wherein, the first threshold and the spy with any frame picture The ratio of sign point number is more than 10%,
    It obtains in the video clip, the target frame picture and the comparison frame draw the shooting skill used, as institute State the shooting skill of video clip；
    The computing module obtains mould with the video read module, the other acquisition module of the scape and the shooting skill respectively Block is connected, and makees for summarizing the other and described shooting gimmick of the number of the video clip, the playing duration, the scape Montage language for the video information.
  7. 7. a kind of system of film montage language analysis as claimed in claim 6, which is characterized in that the video reads mould Block, including：Video cutter unit, the video cutter unit, is used for：
    Any frame picture is obtained from the video information as present frame picture,
    The a later frame picture adjacent with the present frame picture is obtained from the video information,
    The characteristic point of the present frame picture and a later frame picture is obtained,
    The number of the characteristic point that the present frame picture and a later frame picture share is calculated as continuation degree,
    When the continuation degree is greater than or equal to second threshold, the present frame picture and a later frame picture belong to same institute Video clip is stated, wherein：The second threshold and the ratio of the number of the characteristic point of any frame picture are more than 50%,
    When the continuation degree is less than second threshold, the present frame picture and a later frame picture be not belonging to it is same described in regard Frequency segment is cut between the present frame picture and a later frame picture.
CN201810048953.3A 2018-01-18 2018-01-18 Method and system for analyzing movie montage language Active CN108268847B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810048953.3A CN108268847B (en) 2018-01-18 2018-01-18 Method and system for analyzing movie montage language

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810048953.3A CN108268847B (en) 2018-01-18 2018-01-18 Method and system for analyzing movie montage language

Publications (2)

Publication Number Publication Date
CN108268847A true CN108268847A (en) 2018-07-10
CN108268847B CN108268847B (en) 2020-04-21

Family

ID=62776021

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810048953.3A Active CN108268847B (en) 2018-01-18 2018-01-18 Method and system for analyzing movie montage language

Country Status (1)

Country Link
CN (1) CN108268847B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109165557A (en) * 2018-07-25 2019-01-08 曹清 Scape does not judge system and the other judgment method of scape
CN109508668A (en) * 2018-11-09 2019-03-22 北京奇艺世纪科技有限公司 A kind of lens type information identifying method and device
CN113347082A (en) * 2021-08-06 2021-09-03 深圳康易世佳科技有限公司 Method and device for intelligently displaying shared messages containing short videos

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004297297A (en) * 2003-03-26 2004-10-21 Fuji Photo Film Co Ltd Digital camera
CN101771815A (en) * 2008-12-30 2010-07-07 华晶科技股份有限公司 Digital image shooting method
US20100232681A1 (en) * 2009-03-12 2010-09-16 Omron Corporation Three-dimensional vision sensor
CN103246440A (en) * 2012-02-03 2013-08-14 瀚宇彩晶股份有限公司 Method for rotating picture through coordinate axis proportion and difference
CN106162158A (en) * 2015-04-02 2016-11-23 无锡天脉聚源传媒科技有限公司 A kind of method and device identifying lens shooting mode
CN106713726A (en) * 2015-07-14 2017-05-24 无锡天脉聚源传媒科技有限公司 Method and apparatus for recognizing photographing way
CN107437076A (en) * 2017-08-02 2017-12-05 陈雷 The method and system that scape based on video analysis does not divide

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004297297A (en) * 2003-03-26 2004-10-21 Fuji Photo Film Co Ltd Digital camera
CN101771815A (en) * 2008-12-30 2010-07-07 华晶科技股份有限公司 Digital image shooting method
US20100232681A1 (en) * 2009-03-12 2010-09-16 Omron Corporation Three-dimensional vision sensor
CN103246440A (en) * 2012-02-03 2013-08-14 瀚宇彩晶股份有限公司 Method for rotating picture through coordinate axis proportion and difference
CN106162158A (en) * 2015-04-02 2016-11-23 无锡天脉聚源传媒科技有限公司 A kind of method and device identifying lens shooting mode
CN106713726A (en) * 2015-07-14 2017-05-24 无锡天脉聚源传媒科技有限公司 Method and apparatus for recognizing photographing way
CN107437076A (en) * 2017-08-02 2017-12-05 陈雷 The method and system that scape based on video analysis does not divide

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李弟平: "基于视频的人体姿态检测与运动识别方法", 《CNKI中国学术文献网络出版总库》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109165557A (en) * 2018-07-25 2019-01-08 曹清 Scape does not judge system and the other judgment method of scape
CN109508668A (en) * 2018-11-09 2019-03-22 北京奇艺世纪科技有限公司 A kind of lens type information identifying method and device
CN113347082A (en) * 2021-08-06 2021-09-03 深圳康易世佳科技有限公司 Method and device for intelligently displaying shared messages containing short videos

Also Published As

Publication number Publication date
CN108268847B (en) 2020-04-21

Similar Documents

Publication Publication Date Title
WO2019223463A1 (en) Image processing method and apparatus, storage medium, and computer device
US10089769B2 (en) Augmented display of information in a device view of a display screen
CN106664376B (en) Augmented reality device and method
EP1057169A1 (en) Method and apparatus for processing, displaying and communicating images
CN107231531A (en) A kind of networks VR technology and real scene shooting combination production of film and TV system
CN108268847A (en) A kind of method and system of film montage language analysis
EP1843298A2 (en) Image blending system and method
EP4111677B1 (en) Multi-source image data synchronization
CN102799868A (en) Method for identifying key facial expressions of human faces
CN110401810A (en) Processing method, device, system, electronic equipment and the storage medium of virtual screen
CN115442542B (en) Method and device for splitting mirror
CN108289247A (en) A kind of automatic identifying method of the video pictures shooting skill based on video analysis
CN112827172B (en) Shooting method, shooting device, electronic equipment and storage medium
Schneider Expanded visions: rethinking anthropological research and representation through experimental film
Du et al. Application and research of VR virtual technology in film and television art
CN106210701A (en) A kind of mobile terminal for shooting VR image and VR image capturing apparatus thereof
WO2018124794A1 (en) Camerawork-based image synthesis system and image synthesis method
US11399166B2 (en) Relationship preserving projection of digital objects
JP4395082B2 (en) Video generation apparatus and program
Braester Photography at Tiananmen: Pictorial Frames, Spatial Borders, and Ideological Matrixes
Friedland et al. Anthropocentric video segmentation for lecture webcasts
Rubin Constraint-based cinematic editing
Maddock What Is Cinematography in the Age of Virtual Film Production? Posing a New Definition for the Practice of Cinematography
WO2023236656A1 (en) Method and apparatus for rendering interactive picture, and device, storage medium and program product
Geuens Through the Looking Glasses: From the Camera Obscura to Video Assist

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20220223

Address after: 100102 Room 303, unit 5, building 210, Huigu sunshine, Wangjing garden, Chaoyang District, Beijing

Patentee after: Pang Zewenyue

Address before: Room 308, building 3, courtyard 4, Chegongzhuang street, Xicheng District, Beijing 100044

Patentee before: Pang Zemufeng