CN115706852A

CN115706852A - Picture viewing method, system, storage medium and computer equipment for video

Info

Publication number: CN115706852A
Application number: CN202110916213.9A
Authority: CN
Inventors: 黄立军
Original assignee: Beijing Anyun Century Technology Co Ltd
Current assignee: Beijing Anyun Century Technology Co Ltd
Priority date: 2021-08-10
Filing date: 2021-08-10
Publication date: 2023-02-17

Abstract

The invention provides a picture viewing method of a video, which comprises the following steps: detecting whether a preset target object exists in a video picture of a video in a video recording process; if the target object exists, shooting the target object to obtain a picture; generating an object marker associated with the picture on a video picture of the video on which the target object is recorded; and receiving a viewing instruction triggered based on the object mark, and displaying the picture in a preset picture. A picture viewing system for a video recording, a storage medium for storing a computer program for executing the method, and a computer apparatus are also provided. Therefore, the method and the device can shoot the interested object in the video recording process, so that the detailed picture of the corresponding target can be observed conveniently in the subsequent video viewing process, and the problem that the video cannot clearly record the detailed picture in the prior art is solved.

Description

Picture viewing method, system, storage medium and computer equipment for video

Technical Field

The invention relates to the technical field of video processing, in particular to a picture viewing method, a picture viewing system, a storage medium and computer equipment for video.

Background

With the popularization of mobile phone photographing and video recording, most people take pictures and record videos through mobile phones. The photographing pixels of most of the existing mobile phones are very high, and the number of mobile phone cameras can reach one hundred million pixels; therefore, through the photos taken by the mobile phone, much detail content can be viewed through zooming.

However, the video resolution is far from this level, and currently only 4K resolution (an ultra high definition resolution) is the highest; due to the difference of the resolution of the video recording and the photographing, the video recording cannot be used for looking at the detail content at a distance through zooming, but the photographing is possible. Therefore, when some detailed pictures such as characters and figures appear in the video recording process, people must manually take pictures to complete the recording of the details. Is relatively cumbersome. And if the picture is not taken at the moment, certain details cannot be seen clearly when the video is viewed at the later stage. Therefore, when the remote detail content needs to be looked up, the remote detail content needs to be looked up by photographing, and the remote detail content cannot be looked up in the video.

As can be seen, the conventional method has many problems in practical use, and therefore, needs to be improved.

Disclosure of Invention

In view of the above-mentioned drawbacks, an object of the present invention is to provide a method, a system, a storage medium and a computer device for checking a picture of a video, which can take a picture of an object of interest during a video recording process, thereby facilitating observation of a detail picture of a corresponding target during subsequent video checking, so as to solve the problem in the prior art that a video cannot clearly record a detail picture.

In order to achieve the above object, the present invention provides a method for viewing a picture of a video, comprising the steps of:

detecting whether a preset target object exists in a video picture of a video in a video recording process;

if the target object exists, shooting the target object to obtain a picture;

generating an object mark associated with the picture on a video picture of the video on which the target object is recorded;

and receiving a viewing instruction triggered based on the object mark, and displaying the picture in a preset picture.

Optionally, the step of detecting whether a preset target object exists in a video recording picture of the video in the video recording process specifically includes:

acquiring the video frame image of the video at a preset time interval in the video recording process;

and identifying whether the preset target object exists in the video frame image.

On one hand, if the target object exists, the target object is shot, and the step of obtaining the picture comprises the following steps:

if a first target object in the current video frame image is identified, comparing the first target object with a second target object in an adjacent frame image; wherein the adjacent frame image is a previous frame image relative to the video frame image;

if the contrast difference value between the first target object and the second target object exceeds a preset threshold value, shooting the first target object to obtain the picture corresponding to the first target object.

On the other hand, if the target object exists, the step of shooting the target object and obtaining the picture further includes:

and if the contrast difference value between the first target object and the second target object does not exceed the preset threshold value, binding and associating the first target object with a historical picture shot based on the second target object.

Optionally, if the target object exists, the target object is photographed, and the step of obtaining the picture includes:

detecting whether the video equipment has an idle camera or not;

if the idle camera exists, the idle camera is called to shoot the target object;

and locally storing the shot picture.

Optionally, after the step of detecting whether the video recording device has an idle camera, the method further includes:

and if the idle camera does not exist, calling the camera for recording the video to shoot the target object.

Optionally, the step of generating an object marker associated with the picture when the target object is recorded on the video frame of the video includes:

generating the object mark at the position of the video picture of the video corresponding to the target object;

and establishing an incidence relation between the object mark and the corresponding picture.

Optionally, after the step of generating the object mark associated with the picture by recording the target object on the video frame of the video, the method further includes:

hiding the object mark when the video is played;

and if the target object exists on the pause picture of the video, displaying the corresponding object mark on the current picture.

Optionally, the step of receiving a viewing instruction triggered based on the object marker and displaying the picture in a preset picture specifically includes:

when monitoring that preset operation is executed on the object mark on the video picture, generating the viewing instruction;

and acquiring the picture associated with the object mark according to the viewing instruction, and displaying the picture on a current picture.

Still provide the picture viewing system of a video, including:

the detection unit is used for detecting whether a preset target object exists in a video picture of a video in the video recording process;

the shooting unit is used for shooting the target object to obtain a picture if the target object exists;

a marking unit, configured to generate an object mark associated with the picture when the target object is recorded on a video screen of the video;

and the display unit is used for receiving a viewing instruction triggered based on the object mark and displaying the picture in a preset picture.

In addition, a storage medium for storing a computer program for executing the above-described picture viewing method for a video recording video and a computer apparatus are also provided.

The computer device comprises a storage medium, a processor and a computer program which is stored on the storage medium and can run on the processor, wherein the processor executes the computer program to realize the picture viewing method of the video.

The picture viewing method and the system of the video recording video detect whether the video recording picture of the video in the video recording process has a preset target object, if so, the target object is shot to obtain a corresponding picture; further generating an object mark associated with the picture on a video picture of the video on which the target object is recorded; and monitoring whether a checking instruction triggered based on the object mark is received, and if the checking instruction is received, displaying the picture in a preset picture. Therefore, the method and the device can shoot the interested object in the video recording process, so that the detailed picture of the corresponding target can be observed conveniently in the subsequent video viewing process, and the problem that the video cannot clearly record the detailed picture in the prior art is solved.

Drawings

Fig. 1 is a flowchart illustrating steps of a method for viewing a picture of a video according to an embodiment of the present invention;

fig. 2 is a flowchart illustrating optional steps of the method for viewing a picture of a video according to an embodiment of the present invention, which are used to detect the target object;

fig. 3 is a flowchart illustrating optional steps of the picture viewing method for a video recording according to an embodiment of the present invention for capturing the picture;

fig. 4 is a flowchart illustrating optional steps of the method for viewing a picture of a video according to an embodiment of the present invention to generate the object tag;

FIG. 5 is a flowchart illustrating optional steps of a method for viewing a video frame of a video recording according to an embodiment of the present invention, for processing the object tag in the video frame;

fig. 6 is a flowchart illustrating steps that can be selected when the picture viewing method for the recorded video is used to display the picture according to an embodiment of the present invention;

FIG. 7 is a block diagram illustrating a structure of the system for viewing pictures of recorded videos according to an embodiment of the present invention;

FIG. 8 is a schematic block diagram illustrating an alternative structure of the detecting unit of the video frame viewing system according to an embodiment of the present invention;

fig. 9 is a schematic block diagram of an alternative structure of the shooting unit of the picture viewing system for recorded videos according to an embodiment of the present invention;

FIG. 10 is a schematic block diagram illustrating an alternative structure of the markup element of the video-recording frame viewing system according to an embodiment of the present invention;

fig. 11 is a schematic block diagram of an alternative structure of the display unit of the picture viewing system for videos according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

It should be noted that references in the specification to "one embodiment," "an example embodiment," etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not intended to refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

Moreover, where certain terms are used throughout the description and following claims to refer to particular components or features, those skilled in the art will understand that manufacturers may refer to a component or feature by different names or terms. This specification and the claims that follow do not intend to distinguish between components or features that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. In addition, the term "connected" as used herein includes any direct and indirect electrical connection. Indirect electrical connection means include connection by other means.

Fig. 1 illustrates a picture viewing method for a video recording according to an embodiment of the present invention, where the method is applicable to an intelligent terminal with a photographing and recording function, such as a smart phone, a tablet computer, a camera, and other devices; the method comprises the following steps:

s101: and detecting whether a preset target object exists in a video recording picture of the video in the video recording process. Wherein, the target object can be preset by a user or automatically configured by a system, and the target object comprises but is not limited to characters, animals and signboard; in daily photo taking or video recording, the contents that a user needs to magnify and view details are mainly as follows: characters, animals, nameplates and the like, like other scenes such as pictures of scenery, forests, sky and the like, are generally viewed without being enlarged by a user. Therefore, the embodiment records the corresponding scene first according to the requirement of looking up the details only in certain specific scenes. For example, scene pictures such as characters, animals and nameplates are identified as target objects by default, and the scene is a scene needing to view detail pictures. The video recording picture is a preview picture taken by the video in the real-time video recording process, and the target object detected by the embodiment is at least one area image mapped in the preview picture.

Referring to fig. 2, in an alternative embodiment,

step S101 specifically includes:

s1011: and acquiring the video frame image of the video at a preset time interval in the video recording process. In specific implementation, the preset time interval may be set to 0.5 second, that is, in this embodiment, the video frame image in the video recording process is acquired every 0.5 second; taking a mobile phone terminal as an example, in the process of recording a video through a mobile phone camera, a video frame image of the video in the recording process is captured at the frequency of every 0.5 second through a mobile phone background program, and the captured video frame image is a video image corresponding to the 0.5 th second, 1 st second and 1.5 th second time nodes of the video; of course, the specific parameter configuration of the preset time interval may depend on the software and hardware performance of the actual application terminal.

S1012: and identifying whether the preset target object exists in the video frame image. In the embodiment, the captured video frame image is used for identifying whether a preset target object such as a person or an animal exists in the picture or not by an image identification technology; in specific implementation, the identification of the relevant target object can be realized by adopting the identification model finished by pre-training.

The embodiment can be applied to the simultaneous recognition of a plurality of target objects in the video frame image, and can also be applied to the simultaneous recognition of a plurality of different target objects in the video frame image.

S102: and if the target object exists, shooting the target object to obtain a picture. When detecting and determining that at least one target object exists in the video frame image, shooting a corresponding target object; if only one target object exists, shooting a corresponding picture for the target object; if a plurality of target objects exist, shooting is carried out on the plurality of target objects respectively so as to obtain a plurality of one-to-one corresponding pictures.

S103: and generating an object mark associated with the picture on the video picture of the video recorded by the target object. That is, the object markers of this embodiment are attached to corresponding video frames of the video, and if a plurality of target objects exist in a certain video frame of the video, a plurality of corresponding object markers exist on the video frame, and the object markers correspond to pictures of the target objects one to one.

S104: and receiving a viewing instruction triggered based on the object mark, and displaying the picture in a preset picture. In specific implementation, a user can trigger a viewing instruction through an object mark displayed on a video picture, wherein the viewing instruction is a control instruction for viewing a picture corresponding to the object mark; and if the viewing instruction is received, displaying the corresponding picture in a preset picture according to the viewing instruction, wherein the preset picture comprises a full-screen display picture of the terminal equipment and a local display picture of the terminal equipment.

The invention can automatically take pictures in the video recording process according to the content of the video picture, and helps a user to clearly check certain detailed content when checking the video.

In one embodiment, the step S102 specifically includes:

detecting whether the video equipment has an idle camera or not; if the idle camera exists, the idle camera is called to shoot the target object; and locally storing the shot picture. Taking a mobile phone as a video recording device as an example, along with the continuous optimization of the functions of the smart phone, a smart phone with multiple cameras such as a dual camera, a three camera, a four camera and the like already exists in the market; when the smart phone is used for video recording, only one camera is often used; therefore, in this embodiment, when it is determined that a target object to be shot exists in a video picture of a video, whether an unoccupied idle camera exists in the video device, that is, a smartphone, is further detected, and if an idle camera exists, the idle camera is called to shoot the target object; when the idle camera takes photos, the target area needing to be shot can be locked according to the relative position of the target object in the video picture. The photographed picture is stored in a preset storage location, such as a specific gallery in a mobile phone system.

For example, when a mobile phone is kept still to shoot a video, a target object (such as a person) is detected to exist in a video picture, and the person is identified to be mapped to the upper left corner of the video picture, the called idle camera takes a camera recorded by the video as a reference, and an upper left corner area is locked for shooting; if the mobile phone shoots a video under the condition of moving, the called idle camera determines the specific position of the target object to be shot according to the camera for recording the video and the position change area detected by the gyroscope and/or the level meter, and then shoots the target object.

If there are multiple idle cameras, it may be preferable to use a telephoto lens to photograph the target object.

Optionally, after the step of detecting whether the video recording device has an idle camera, the method further includes: and if the idle camera does not exist, the camera for recording the video is taken to shoot the target object. If the video recording equipment is single-camera equipment, such as an intelligent camera or a single-camera mobile phone, when a target object exists in a video frame image, converting a camera currently in video recording into a shooting function to shoot a corresponding picture, and automatically switching to an original video recording state after shooting is finished; in the embodiment, the existing smart phone is optimized through software, hardware and/or an algorithm, so that the camera video recording process can be quickly switched to a shooting function for shooting, and the shooting process needs shorter time, so that excessive influence on video recording cannot be caused.

Referring to fig. 4, in an alternative embodiment, the step S103 includes:

s1031: and generating the object mark at the position of the video picture of the video corresponding to the target object. In particular, the object marker can be suspended on the top layer of the video picture and is close to the target object; the object markers may be more visually apparent markers based on the characteristics of the corresponding target object.

S1032: and establishing an incidence relation between the object mark and the corresponding picture. In specific implementation, after the video recording is completed, if the picture shot in the recording process exists, an association relation table is automatically generated so as to record the association relation of one-to-one mapping between the picture and the corresponding object mark on the association relation table. Therefore, when the user searches for the corresponding picture according to the object mark, the object mark and the corresponding picture can be matched and determined according to the incidence relation recorded on the incidence relation table.

Referring to fig. 5, in an alternative embodiment, after step S103, the method further includes:

s111: and hiding the object mark when the video is played. And if the video is detected to be played, hiding all object marks on the video frame picture so as to avoid disturbing the user experience in the video playing process.

S112: and if the target object exists on the pause picture of the video, displaying the corresponding object mark on the current picture. When a user pauses the video on a certain video picture, detecting and determining whether a target object exists on the corresponding paused picture, if so, presenting an object mark of the target object on the current picture, so that the user triggers and generates a viewing instruction through the preset operation of the object mark corresponding to the target object, and further presenting a picture shot correspondingly by the target object based on the viewing instruction.

One specific application scenario is as follows: a user records a video by using a mobile phone terminal, and when the user notices a certain interested target (namely a preset target object) during playing the video, the user generally pauses the video and wants to further view details; the system detects whether a target object exists in the current pause picture, if so, the object mark of the target object is presented in the current picture, the corresponding mark displayed in the pause picture indicates that the current picture has a related detail content photo, and a user can check the detail photo content only by clicking the related mark; and detecting whether the user clicks the object mark, if so, triggering to generate a viewing instruction, finding the matched picture from a system preset picture library according to the viewing instruction, and displaying the picture on the current display picture.

Referring to fig. 6, in an alternative embodiment, step S104 specifically includes:

s1041: and when monitoring that preset operation is executed on the object mark on the video picture, generating the viewing instruction. In specific implementation, the preset operation includes but is not limited to a click operation, a long press operation or a sliding operation; the user can trigger and generate a corresponding viewing instruction by preset operation aiming at the object mark, and the viewing instruction is sent to the corresponding processing unit.

S1042: and acquiring a picture associated with the object mark according to the viewing instruction, and displaying the picture on the current picture. In practical application, after the viewing instruction is received, searching a picture matched with the object mark according to the viewing instruction, and displaying the obtained picture in a current picture; and the current picture is a screen picture for displaying the video, such as a mobile phone screen.

Referring to fig. 3, optionally, step S102 includes:

s1021: if a first target object in the current video frame image is identified, comparing the first target object with a second target object in an adjacent frame image; wherein the adjacent frame image is a previous frame image relative to the video frame image. Since the embodiment identifies the video pictures in the video recording process at time intervals of every half second, it is inevitable to continuously identify the same target object, and if the target object is continuously identified and continuously shot, the system is likely to have a heavy operation burden, and the actual experience of the user is not facilitated. Therefore, in the embodiment, when the first target object exists on the video picture, the first target object is compared with the second target object in the previous frame of image, so as to determine whether the comparison difference value between the first target object and the second target object meets the requirement of re-shooting the first target object. For example, taking a video frame acquired every half second as an example, a first target object is derived from a video frame image at 1 st second of the video, a second target object is derived from a video frame image at 0.5 th second of the video, and both the first target object and the second target object represent the same target, such as both being a human object or both being an animal.

S1022: if the contrast difference value between the first target object and the second target object exceeds a preset threshold value, shooting the first target object to obtain a picture corresponding to the first target object. Wherein, the contrast difference value represents the difference of the contour shape, the image brightness, the image pixel and the like between the first target object and the second target object; if the contrast difference value of the contrast between the first target object and the second target object exceeds a preset threshold value, determining that the first target object has changed greatly relative to the second target object, for example, the first target object is closer to a lens relative to the second target object, and the size of an image shot by the first target object is larger than that of the second target object, so that when the outline size of the contrast between the first target object and the second target object is changed greatly, shooting the first target object; on the contrary, when the contrast difference between the first target object and the second target object does not exceed the preset threshold, it represents that the variation between the first target object and the second target object is not large, and at this time, the first target object does not need to be photographed again.

For example, a face is identified in the current video recording process, and after a video picture is captured for the first time, a person is identified, and at this time, the mobile phone can automatically photograph the current scene. After the picture is shot for the second time, the recognized face is the same as the face shot for the first time, but the face is closer to the shot, although the face is the same person, the face is closer to the shot, the detail checking effect after the picture is shot is better than that of the first time, and the picture is also shot automatically at the moment. Comparing the currently acquired video picture with the previous video picture, checking whether the difference between the two video pictures is smaller than a certain value, if so, representing that the two pictures are similar, and then, not needing to shoot the scene picture again, and if the difference is larger than the certain value, still needing to shoot the picture automatically.

Optionally, step S102 further includes:

s1023: and if the contrast difference value between the first target object and the second target object does not exceed the preset threshold value, binding and associating the first target object with a historical picture shot based on the second target object. And if the change between the first target object and the second target object is not large, namely the contrast difference value does not exceed a preset threshold value, binding and associating the historical picture shot based on the second target object with the first target object. When the user wants to view the first target object, the picture corresponding to the second target object can be called to be provided for the user to view. In practical application, an object marker corresponding to the first target object may be generated, and the object marker may be bound and associated with a picture of the second target object.

Fig. 7 illustrates a video image viewing system 100 according to an embodiment of the present invention, where the system 100 is applicable to an intelligent terminal with a photographing and recording function, such as a smart phone, a tablet computer, a video camera, and the like; the device comprises a detection unit 10, a shooting unit 20, a marking unit 30 and a display unit 40, wherein:

the detection unit 10 is configured to detect whether a preset target object exists in a video recording picture of a video in a video recording process; the shooting unit 20 is configured to shoot the target object to obtain a picture if the target object exists; the marking unit 30 is configured to generate an object mark associated with the picture when the target object is recorded on a video screen of the video; the display unit 40 is configured to receive a viewing instruction triggered based on the object marker, and display the picture in a preset screen.

Referring to fig. 8, in an alternative embodiment, the detecting unit 10 specifically includes an image acquiring subunit 11 and an image identifying subunit 12, where:

the image obtaining subunit 11 is configured to obtain the video frame image at a preset time interval in the video recording process of the video; the image recognition subunit 12 is configured to recognize whether a preset target object exists in the video frame image.

Referring to fig. 9, in an alternative embodiment, the photographing unit 20 includes a contrast subunit 21 and a photographing subunit 22, wherein:

the comparison subunit 21 is configured to compare, if a first target object in the current video frame image is identified, the first target object with a second target object in an adjacent frame image; wherein the adjacent frame image is a previous frame image relative to the video frame image; the shooting subunit 22 is configured to shoot the first target object if a contrast difference value between the first target object and the second target object exceeds a preset threshold, and obtain the picture corresponding to the first target object.

Optionally, the shooting unit 20 further includes a binding subunit 23, configured to bind and associate the first target object with a history picture shot based on the second target object if the contrast difference value between the first target object and the second target object does not exceed the preset threshold.

In one embodiment, the capturing unit 20 includes an image capturing detection subunit, a first retrieval capturing subunit, and a saving unit, wherein:

the camera detection subunit is used for detecting whether the video recording equipment has an idle camera or not; the first calling shooting subunit is used for calling the idle camera to shoot the target object if the idle camera exists; and the storage subunit is used for locally storing the shot picture.

Optionally, the shooting unit further includes a second shooting transferring subunit, configured to, if the idle camera does not exist, transfer the camera that records the video to shoot the target object.

Referring to fig. 10, optionally, the marking unit 30 includes a mark generation subunit 31 and a mark binding subunit 32, wherein:

the mark generating subunit 31 is configured to generate the object mark at a video frame position of the video corresponding to the target object; the mark binding subunit 32 is configured to establish an association relationship between the object mark and the corresponding picture.

In one embodiment, the system further comprises a mark hiding unit and a mark presenting unit, wherein: the mark hiding unit is used for hiding the object mark when the video is played; and the mark presenting unit is used for displaying the corresponding object mark on the current picture if the target object is monitored to exist on the pause picture of the video.

Referring to fig. 11, optionally, the display unit 40 specifically includes an instruction generation subunit 41 and a picture display subunit 42, where:

the instruction generating subunit 41 is configured to generate the viewing instruction when monitoring that a preset operation is performed on the object marker on the video picture; the picture display sub-unit 42 is configured to obtain the picture associated with the object marker according to the viewing instruction, and display the picture on the current screen.

The present invention also provides a storage medium for storing a computer program of the picture viewing method for the video recording described in fig. 1 to 6. Such as computer program instructions, which when executed by a computer, may invoke or otherwise provide methods and/or techniques in accordance with the present application through the operation of the computer. Program instructions which invoke the methods of the present application may be stored on fixed or removable storage media and/or transmitted via a data stream over a broadcast or other signal-bearing medium and/or stored on a storage medium of a computer device operating in accordance with the program instructions. Herein, an embodiment according to the present application includes a computer device of a picture viewing system for video recording as shown in fig. 7, the computer device preferably includes a storage medium for storing a computer program and a processor for executing the computer program, wherein when the computer program is executed by the processor, the computer device is triggered to execute the method and/or the technical solution according to the foregoing embodiments.

It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, as an Application Specific Integrated Circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software programs of the present application may be executed by a processor to implement the above steps or functions. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

The method according to the invention can be implemented on a computer as a computer-implemented method, or in dedicated hardware, or in a combination of both. Executable code for the method according to the invention or parts thereof may be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, and so forth. Preferably, the computer program product comprises non-transitory program code means stored on a computer readable medium for performing the method according to the invention when said program product is executed on a computer.

In a preferred embodiment, the computer program comprises computer program code means adapted to perform all the steps of the method according to the invention when the computer program is run on a computer. Preferably, the computer program is embodied on a computer readable medium.

In summary, the method and the system for checking the picture of the video recording according to the present invention detect whether a preset target object exists in the video recording picture of the video in the video recording process, and if the preset target object exists in the video recording picture of the video, shoot the target object to obtain a corresponding picture; further generating an object mark associated with the picture on a video picture of the video on which the target object is recorded; and monitoring whether a checking instruction triggered based on the object mark is received, and if the checking instruction is received, displaying the picture in a preset picture. Therefore, the method and the device can shoot the interested object in the video recording process, so that the detailed picture of the corresponding target can be observed conveniently in the subsequent video viewing process, and the problem that the video cannot clearly record the detailed picture in the prior art is solved.

The present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof, and it should be understood that various changes and modifications can be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.

A1, a picture viewing method of the video is also provided, which comprises the following steps:

if the target object exists, shooting the target object to obtain a picture;

A2, according to the picture viewing method for the video recording of the A1, the step of detecting whether a preset target object exists in the video recording picture of the video in the video recording process specifically comprises the following steps:

A3, according to the picture viewing method for the video, according to the A2, if the target object exists, shooting the target object, and obtaining the picture comprises the following steps:

A4, according to the picture viewing method for the video, described in the above A3, if the target object exists, the step of shooting the target object and obtaining the picture further includes:

A5, according to the picture viewing method for the video, described in the above A1, if the target object exists, the step of shooting the target object to obtain the picture includes:

detecting whether the video equipment has an idle camera or not;

and locally storing the shot picture.

A6, according to the picture viewing method for the video recording video in A5, after the step of detecting whether the video recording device has an idle camera, the method further comprises:

A7, according to the picture viewing method for a video recording described in A1, the step of generating an object marker associated with the picture on the video picture of the video on which the target object is recorded includes:

and establishing an association relation between the object mark and the corresponding picture.

A8, according to the picture viewing method for a video recording described in A1, after the step of generating the object marker associated with the picture when the target object is recorded on the video picture of the video, the method further includes:

when the video is played, hiding the object mark;

A9, according to the picture viewing method for a video recording of the above A1, the step of receiving a viewing instruction triggered based on the object marker and displaying the picture on a preset picture specifically includes:

B10, a picture viewing system for video recording is also provided, comprising:

B11, according to the picture viewing system for the video recording described in B10, the detecting unit specifically includes:

the image acquisition subunit is used for acquiring the video frame images at preset time intervals in the video recording process of the video;

and the image identification subunit is used for identifying whether the preset target object exists in the video frame image.

B12, according to the picture viewing system of the recorded video of B11, the shooting unit comprises:

the comparison subunit is configured to compare, if a first target object in the current video frame image is identified, the first target object with a second target object in an adjacent frame image; wherein the adjacent frame image is a previous frame image relative to the video frame image;

and the shooting subunit is configured to shoot the first target object to obtain the picture corresponding to the first target object if the contrast difference value between the first target object and the second target object exceeds a preset threshold.

B13, according to the picture viewing system of the recorded video of B12, the shooting unit further comprises:

and the binding subunit is configured to, if the contrast difference value between the first target object and the second target object does not exceed the preset threshold, bind and associate the first target object with a history picture taken based on the second target object.

B14, the picture viewing system for a video according to B10, wherein the capturing unit includes:

the camera detection subunit is used for detecting whether the video equipment has an idle camera or not;

the first transferring and shooting subunit is used for transferring the idle camera to shoot the target object if the idle camera exists;

and the storage subunit is used for locally storing the shot picture.

B15, according to the picture viewing system for the video recording described in B14, the shooting unit further includes:

and the second transferring shooting subunit is used for transferring the camera for recording the video to shoot the target object if the idle camera does not exist.

B16, the picture viewing system for a video according to B10, wherein the marking unit includes:

a marker generating subunit, configured to generate the object marker at a video screen position of the video corresponding to the target object;

and the mark binding subunit is used for establishing the association relationship between the object mark and the corresponding picture.

B17, the picture viewing system for a video according to B10, further comprising:

a mark hiding unit, configured to hide the object mark during playing of the video;

and the mark presenting unit is used for displaying the corresponding object mark on the current picture if the target object is monitored to exist on the pause picture of the video.

B18, according to the picture viewing method for a video according to B10, the display unit specifically includes:

the instruction generating subunit is configured to generate the viewing instruction when monitoring that a preset operation is performed on the object marker on the video picture;

and the picture display subunit is used for acquiring the picture associated with the object mark according to the viewing instruction and displaying the picture on the current picture.

C19, a storage medium storing a computer program for executing the picture viewing method of the video recording video of any one of A1 to A9 is also provided.

The D20 and the computer equipment comprise a storage medium, a processor and a computer program which is stored on the storage medium and can run on the processor, wherein the processor executes the computer program to realize the picture viewing method of the video recording video of any one of the A1-A9.

Claims

1. A picture viewing method of a video is characterized by comprising the following steps:

if the target object exists, shooting the target object to obtain a picture;

2. The method for checking the picture of the recorded video according to claim 1, wherein the step of detecting whether the recorded picture of the video has the preset target object in the recording process specifically comprises:

3. The method of claim 2, wherein the step of capturing the target object if the target object exists comprises:

4. The method of claim 3, wherein the step of capturing the picture of the target object if the target object exists further comprises:

5. The method of claim 1, wherein the step of capturing the target object and obtaining the picture includes:

detecting whether the video equipment has an idle camera or not;

and locally storing the shot picture.

6. The method of claim 5, wherein the step of detecting whether there is an idle camera in the video recording device further comprises:

7. The method of claim 1, wherein said step of generating an object tag associated with said picture on a video frame of said video on which said target object is recorded comprises:

8. A picture viewing system for video recording, comprising:

9. A storage medium storing a computer program for executing the picture viewing method for a video recording according to any one of claims 1 to 7.

10. A computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the picture viewing method for a video recording according to any one of claims 1 to 7 when executing the computer program.