CN113836356A - Video retrieval method and device, electronic equipment and storage medium - Google Patents
Video retrieval method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113836356A CN113836356A CN202111390319.6A CN202111390319A CN113836356A CN 113836356 A CN113836356 A CN 113836356A CN 202111390319 A CN202111390319 A CN 202111390319A CN 113836356 A CN113836356 A CN 113836356A
- Authority
- CN
- China
- Prior art keywords
- video
- retrieval
- playing time
- retrieval object
- target video
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- 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
- G06F16/7844—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 original textual content or text extracted from visual content or transcript of audio data
-
- 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
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention provides a video retrieval method, a video retrieval device, electronic equipment and a storage medium, wherein the video retrieval method comprises the following steps: responding to an input retrieval object, and screening a video library to obtain a target video comprising the retrieval object; and determining the playing time of the retrieval object in the target video based on the timestamp, and displaying the playing time and the target video frame image corresponding to the playing time. By the video retrieval method provided by the invention, the input based on the retrieval object is realized, and the corresponding video clip or key frame image can be retrieved and displayed.
Description
Technical Field
The present invention relates to the field of video retrieval technologies, and in particular, to a video retrieval method and apparatus, an electronic device, and a storage medium.
Background
The information content of video data is obviously higher than that of single-dimensional data such as text, audio, image and the like, so that the video data has great value. The video data often contains a large amount of information with different dimensions, which is related to each other, such as geographical location information, objects, characters and other creatures, characters or symbols shot in the video, sound information, and various interaction information therebetween.
As known in the related art, the information in the video data is often extracted or retrieved by manually watching the information and then recording and summarizing the information in a text mode. The searched and extracted information cannot be related to a specific video segment or a specific position of a certain frame of image, and related segments or key image frames in the video need to be manually found during viewing, so that the operation is complicated and the efficiency of acquiring the information is low.
Disclosure of Invention
The invention provides a video retrieval method, a video retrieval device, electronic equipment and a storage medium, which are used for overcoming the defect of complicated operation of manually acquiring video clips or key frame images in the prior art and realizing the purpose that corresponding video clips or key frame images can be automatically retrieved and displayed through the input of a retrieval object.
The invention provides a video retrieval method, which is characterized by comprising the following steps: responding to an input retrieval object, and screening a video library to obtain a target video comprising the retrieval object; and determining the playing time of the retrieval object in the target video based on the timestamp, and displaying the playing time and the target video frame image corresponding to the playing time.
The video retrieval method provided by the invention is characterized in that the step of screening a target video including a retrieval object in a video library in response to the input of the retrieval object comprises the following steps: in response to inputting a retrieval object, determining a feature value of the retrieval object; and screening a target video comprising the retrieval object in a video library based on the characteristic value.
According to the video retrieval method provided by the invention, the retrieval object comprises a text retrieval object, and the target video comprising the retrieval object is screened in a video library in response to the input of the retrieval object, and the method comprises the following steps: in response to inputting the text retrieval object, determining a first feature value corresponding to the text retrieval object; performing dimension reduction processing on each video in the video library to obtain text information corresponding to the video, and determining a second characteristic value corresponding to the text information based on the text information; and comparing the first characteristic value with the second characteristic value, and screening in the video library based on a comparison result to obtain a target video comprising the text retrieval object.
The video retrieval method provided by the invention is characterized in that the video retrieval method further comprises a step of setting a display list, wherein the step of displaying the playing time and a target video frame image corresponding to the playing time comprises the following steps: and displaying the playing time and the target video frame image corresponding to the playing time based on the display list.
The video retrieval method provided by the invention is characterized in that after the displaying of the playing time and the video frame image corresponding to the playing time, the method further comprises the following steps: and responding to the user input playing operation, and playing the video clip comprising the target video frame image by the playing time.
The present invention also provides a video retrieval device, comprising: the screening module is used for responding to input retrieval objects and screening target videos comprising the retrieval objects in a video library; and the processing module is used for determining the playing time of the retrieval object in the target video based on the timestamp and displaying the playing time and the target video frame image corresponding to the playing time.
The video retrieval device provided by the invention is characterized in that the screening module screens a video library to obtain a target video comprising the retrieval object by adopting the following modes: in response to inputting a retrieval object, determining a feature value of the retrieval object; and screening a target video comprising the retrieval object in a video library based on the characteristic value.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the video retrieval methods described above when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the video retrieval method as described in any of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the video retrieval method as described in any one of the above.
According to the video retrieval method, the video retrieval device, the electronic equipment and the storage medium, the target video comprising the retrieval object is obtained by screening in the video library, and the playing time of the retrieval object in the target video is determined based on the timestamp so as to display the playing time and the target video frame image corresponding to the playing time. Therefore, the input based on the retrieval object is realized, and the corresponding video clip or key frame image can be automatically retrieved and displayed.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a video retrieval method according to the present invention;
FIG. 2 is a schematic flow chart of screening a video library to obtain a target video including a search object according to the present invention;
fig. 3 is a second schematic flowchart of the process of screening a video library to obtain a target video including a search object according to the present invention;
FIG. 4 is a second flowchart of a video retrieval method according to the present invention;
FIG. 5 is a schematic view of a scene to which the video retrieval method provided by the present invention is applied;
FIG. 6 is a schematic structural diagram of a video retrieval apparatus according to the present invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As known in the related art, the extraction or retrieval of information in video data usually depends on manual viewing, and then the summary is recorded in a text mode. The searched and extracted information cannot be related to a specific video segment or a specific position of a certain frame of image, and related segments or key image frames in the video need to be manually found during viewing, so that the operation is complicated and the efficiency of acquiring the information is low.
The video retrieval method provided by the invention can automatically retrieve and display the corresponding video clip or key frame image through the input of the retrieval object, and further can efficiently and accurately jump to the position of the corresponding key frame image to play the video.
The present invention will be described with reference to the following embodiments.
Fig. 1 is a schematic flow chart of a video retrieval method according to the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 1, the video retrieval method may include steps 110 and 120, which will be described separately below.
In step 110, in response to inputting the search object, a target video including the search object is screened in the video library.
In one embodiment, the retrieval object may be a search keyword, a picture or a voice segment, etc. input by the user. The search object may be information in a plurality of modal forms, and in the present embodiment, the type of the search object is not particularly limited, and the search object may be adjusted according to actual conditions.
In the application process, in response to inputting the retrieval object, the target video including the retrieval object can be screened in the video library. The number of target videos including the retrieval object screened in the video library may be one or more. The video library may be a collection of a plurality of videos stored in advance. In an example, videos stored in the video library may also be added and updated in real-time.
In an example, the input retrieval object may be a picture with an X feature. In the application process, a target video including a picture with X characteristics can be screened from a video library based on an image recognition algorithm, such as an Artificial Intelligence (AI) face recognition algorithm or an AI object recognition algorithm. It is understood that the target video may be one video clip or may be a plurality of video clips.
In step 120, based on the timestamp, the playing time of the retrieval object in the target video is determined, and the playing time and the target video frame image corresponding to the playing time are displayed.
A time stamp is typically a sequence of characters that uniquely identifies a time of a moment. In an example, the playing time of the retrieval object in the target video can be determined based on the timestamp, and the playing time and the target video frame image corresponding to the playing time can be displayed to the user.
The following description will take an example in which the search target is a picture having an X feature. In an example, if it is determined that a picture with an X feature appears at the 256 th second of the target video based on the time stamp, the 256 th second information of the target video and the 256 th corresponding target video frame image may be presented to the user. It is understood that the target video frame image includes a picture having an X feature. In yet another example, a pixel region where a picture with an X-feature appears in the target video frame image may be further determined, so that a specific position of the picture with the X-feature may be further located.
According to the video retrieval method, the video retrieval device, the electronic equipment and the storage medium, the target video comprising the retrieval object is obtained by screening in the video library, and the playing time of the retrieval object in the target video is determined based on the timestamp so as to display the playing time and the target video frame image corresponding to the playing time. Therefore, the input based on the retrieval object is realized, and the corresponding video clip or key frame image can be automatically retrieved and displayed.
The present invention will be described with reference to the following embodiments, in which a target video including a search object is screened from a video library in response to an input of the search object.
Fig. 2 is one of the flow diagrams of the present invention for obtaining a target video including a retrieval object by screening in a video library.
In an exemplary embodiment of the present invention, as shown in fig. 2, the step of screening the target video including the retrieval object in the video library may include steps 210 and 220, which will be described separately below.
In step 210, in response to inputting the search object, a feature value of the search object is determined.
The characteristic value may be a kind of flag characterizing information of different modalities. In one embodiment, in response to a user input to retrieve an object, a feature value regarding the retrieved object may be extracted based on an AI algorithm or the like. In an example, the retrieval object is a face image, and feature values about the face image may be extracted based on an AI face recognition algorithm. The retrieval object is a Speech segment, and feature values of the Speech segment can be extracted based on an Automatic Speech Recognition technology (also called ASR).
In step 220, a target video including the retrieval object is screened from the video library based on the feature value.
In an example, a target video including the retrieval object may be obtained through screening based on the extracted feature value of the retrieval object and the feature values of the videos in the video library. In an example, if the retrieval object is a face image, the features of the portrait appearing in the video may be extracted, and the target video including the retrieval object is obtained by screening based on the feature value of the retrieval object and the feature value of the portrait extracted from the video. Through the embodiment, when the target video frame image of the retrieval object needs to be searched, the playing time of the retrieval object in the target video can be automatically known only through program processing in a very short time without manually watching each video in the video library repeatedly, so that the labor, resource and money costs are reduced.
In the application process, the search object input by the user is mostly in a text form, for example, the search object is a text search object. The present invention will be described with reference to the following embodiments, in which when a search target is a text search target, a process of obtaining a target video including the search target by screening in a video library in response to inputting the search target is performed.
Fig. 3 is a second schematic flowchart of the process of screening a video library to obtain a target video including a search object according to the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 3, the step of screening the target video including the search object in the video library may include steps 310 to 330, which will be described separately below.
In step 310, in response to inputting a text search object, a first feature value corresponding to the text search object is determined.
In one embodiment, when it is detected that the user inputs a text retrieval object, for example, the user inputs a keyword regarding product model information, a first feature value corresponding to the keyword may be determined.
In step 320, performing dimension reduction processing on each video in the video library to obtain text information corresponding to the video, and determining a second feature value corresponding to the text information based on the text information.
In one embodiment, each video in the video library may be subjected to dimension reduction processing, that is, multi-modal information in the video, such as voice information, picture information, and the like, is reduced into text information, text information about the video is obtained, and a second feature value corresponding to the text information is determined based on the text information.
In step 330, the first feature value and the second feature value are compared, and a target video including the text retrieval object is screened from the video library based on the comparison result.
In one embodiment, a first characteristic value of a text retrieval object is compared with a second characteristic value of text information obtained after video dimension reduction processing to obtain a comparison result, and a target video comprising the text retrieval object input by a user is screened in a video library according to the comparison result. In this embodiment, the target video may also be obtained based on multi-modal retrieval. Wherein, the modality can refer to sense, and the multi-modality can be a fusion of multiple senses. Accordingly, multimodal retrieval may refer to retrieving data (text, pictures, audio, video, etc.) collected from more than one type of sensory collection to obtain a target video. Through the embodiment, the characteristic of large information amount of video data can be fully utilized, and the information required by the user can be quickly and accurately retrieved.
Further, the playing time of the text retrieval object in the target video can be determined based on the timestamp, and the playing time and the target video frame image corresponding to the playing time are displayed to the user. Through the embodiment, the video clip corresponding to the text retrieval object or the specific position of a certain image frame in the video clip can be accurately associated, and the playing time of the text retrieval object in the target video can be automatically obtained only through program processing in a very short time without manually watching each video in a video library repeatedly, so that the human, resource and money costs are reduced.
To further illustrate the video retrieval method provided by the present invention, the following embodiments will be described.
In one embodiment, in a remote video call scenario, both parties discuss information about product type X and record the video call. In the application process, if a user inputs a keyword of product X type information, the voice information in the video can be converted into character information based on an ASR voice-to-character processing technology. Further, based on the characteristics of the keywords input by the user and the characteristics of the converted text information, and the time stamp, the specific position of the keywords in the video can be determined. When the user clicks the keyword for searching the product X type information, the video can jump from the position where the product X type information appears for playing. Through the embodiment, the video does not need to be watched repeatedly by people to determine the dialogue about the product X type information in the video, and the playing time of the product X type information in the target video can be automatically obtained only through program processing in a very short time, so that the retrieval efficiency and the information utilization rate of video data are greatly improved, and the experience of a user is improved.
In another embodiment, when the user clicks a keyword for searching for the product X model information, the video may jump from a position where the product X model information appears, and a video duration for playing the video clip containing the product X model information may be defined. In one example, when the product X model information appears at 93 th to 160 th seconds of the target video, the 93 rd to 180 th seconds of the target video may be played during the playing. It is understood that, in the present invention, the playing time length is not specifically limited, as long as within the playing time length, the video segment includes the product X model information and the video time length that does not include the product X model information does not exceed the predetermined time length. By the method, the retrieval efficiency and the playing efficiency can be improved, the time of a user is saved, and the experience of the user is improved.
In one embodiment, the video retrieval method may further include setting a presentation list. The display of the playing time and the target video frame image corresponding to the playing time can be realized by the following modes:
and displaying the playing time and the target video frame image corresponding to the playing time based on the display list.
In one embodiment, when multiple target video segments are retrieved, multiple target video frame images may be derived based on the timestamps. The target video frame image may be a video frame image belonging to the same target video, or a video frame image not belonging to the same target video. In the application process, the plurality of target video frame images and the corresponding playing moments can be displayed in a display list mode, so that the user can watch the target video frame images conveniently, and the user can select the corresponding video clip containing the target video frame images conveniently to play.
To further describe the video retrieval method provided by the present invention, another video retrieval method will be described below with reference to the following embodiments.
Fig. 4 is a second flowchart of the video retrieval method according to the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 4, the video retrieval method may include steps 410 to 430, where steps 410 and 420 are the same as steps 110 and 120 described above, and specific embodiments and beneficial effects thereof may refer to the foregoing description, which is not repeated in this embodiment, and step 430 will be described in detail below.
In step 430, in response to the user input of the play operation, the video segment including the target video frame image is played by the play time.
In an embodiment, after determining the playing time of the retrieval object in the target video based on the timestamp and showing the playing time and the target video frame image corresponding to the playing time to the user, if the user inputs a video playing operation, a video clip including the target video frame image may be played at the playing time. The playing time length for playing the video clip can be adjusted according to the actual situation, as long as the video time length of the video clip including the retrieval object and not including the retrieval object does not exceed the preset time length within the playing time length. By the method, the retrieval efficiency and the playing efficiency can be improved, the time of a user is saved, and the experience of the user is improved.
To further describe the video retrieval method provided by the present invention, the following description will be made with reference to a scene to which the video retrieval method provided by the present invention is applied.
Fig. 5 is a schematic view of a scene to which the video retrieval method provided by the present invention is applied.
In one embodiment, as shown in FIG. 5, when the user inputs keywords of model 123, multimodal retrieval of the video is possible. For example, information such as the contents of a conversation appearing in a video, a video directory, characters appearing in a video, and characters is retrieved. In an example, speech information in a video may be converted to text information based on ASR speech-to-text processing techniques. Further, the specific position of the keyword in the video is determined based on the characteristics of the keyword input by the user, the characteristics of the converted text information and the time stamp. In an example, when the user clicks on a keyword searching for the model 123, the video may jump from a position where the keyword of the model 123 appears.
In another embodiment, when a plurality of video segments containing the keyword of the model 123 are retrieved, the plurality of video segments may be presented in the form of a presentation list, and corresponding information, for example, partial text information and information about the time when the keyword of the model 123 appears, may be marked in the presentation list. By the method, the user can conveniently and intuitively obtain the video clips and the related information about the keywords. Further, when the user clicks the corresponding video segment, the user can directly jump to the video segment to play, wherein the playing starting point of the video segment is the moment when the keyword of the model 123 appears.
According to the above description, the video retrieval method provided by the invention obtains the target video including the retrieval object by screening in the video library, and determines the playing time of the retrieval object in the target video based on the timestamp to display the playing time and the target video frame image corresponding to the playing time. Therefore, the input based on the retrieval object is realized, and the corresponding video clip or key frame image can be automatically retrieved and displayed.
Based on the same conception, the invention also provides a video retrieval device.
The following describes the video retrieval device provided by the present invention, and the video retrieval device described below and the video retrieval method described above may be referred to correspondingly.
Fig. 6 is a schematic structural diagram of a video retrieval apparatus provided in the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 6, the video retrieval apparatus may include a filtering module 610 and a processing module 620, which will be described separately below.
The screening module 610 may be configured to screen a target video including a search object in a video library in response to inputting the search object.
The processing module 620 may be configured to determine a playing time of the retrieval object in the target video based on the timestamp, and display the playing time and a target video frame image corresponding to the playing time.
In an exemplary embodiment of the present invention, the screening module 610 may screen the video library to obtain a target video including the search object by the following steps: in response to inputting a retrieval object, determining a characteristic value of the retrieval object; and screening the target video comprising the retrieval object in the video library based on the characteristic value.
In an exemplary embodiment of the present invention, the screening module 610 may screen the video library to obtain a target video including the search object by the following steps: in response to inputting a text retrieval object, determining a first feature value corresponding to the text retrieval object; performing dimensionality reduction processing on each video in a video library to obtain text information corresponding to the video, and determining a second characteristic value corresponding to the text information based on the text information; and comparing the first characteristic value with the second characteristic value, and screening in a video library based on a comparison result to obtain a target video comprising a text retrieval object.
In an exemplary embodiment of the present invention, the video retrieval apparatus may further include a setting module, wherein the setting module may be configured to set the presentation list; the processing module 620 may display the playing time and the target video frame image corresponding to the playing time in the following manner: and displaying the playing time and the target video frame image corresponding to the playing time based on the display list.
In an exemplary embodiment of the present invention, the video retrieval apparatus may further include a play module. Wherein the playing module may be configured to play the video clip including the target video frame image by the playing time in response to a user input playing operation.
Fig. 7 illustrates a physical structure diagram of an electronic device, and as shown in fig. 7, the electronic device may include: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform a video retrieval method, wherein the video retrieval method comprises: responding to the input of a retrieval object, and screening a video library to obtain a target video comprising the retrieval object; and determining the playing time of the retrieval object in the target video based on the timestamp, and displaying the playing time and the target video frame image corresponding to the playing time.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, a computer is capable of executing the video retrieval method provided by the above methods, the method comprising: responding to the input of a retrieval object, and screening a video library to obtain a target video comprising the retrieval object; and determining the playing time of the retrieval object in the target video based on the timestamp, and displaying the playing time and the target video frame image corresponding to the playing time.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the video retrieval method provided by the above methods, the method comprising: responding to the input of a retrieval object, and screening a video library to obtain a target video comprising the retrieval object; and determining the playing time of the retrieval object in the target video based on the timestamp, and displaying the playing time and the target video frame image corresponding to the playing time.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for video retrieval, the method comprising:
responding to an input retrieval object, and screening a video library to obtain a target video comprising the retrieval object;
and determining the playing time of the retrieval object in the target video based on the timestamp, and displaying the playing time and the target video frame image corresponding to the playing time.
2. The video retrieval method of claim 1, wherein the selecting a target video including a retrieval object in a video library in response to inputting the retrieval object comprises:
in response to inputting a retrieval object, determining a feature value of the retrieval object;
and screening a target video comprising the retrieval object in a video library based on the characteristic value.
3. The video retrieval method of claim 2, wherein the retrieval object comprises a text retrieval object, and the step of screening a video library for a target video comprising the retrieval object in response to inputting the retrieval object comprises:
in response to inputting the text retrieval object, determining a first feature value corresponding to the text retrieval object;
performing dimension reduction processing on each video in the video library to obtain text information corresponding to the video, and determining a second characteristic value corresponding to the text information based on the text information;
and comparing the first characteristic value with the second characteristic value, and screening in the video library based on a comparison result to obtain a target video comprising the text retrieval object.
4. The video retrieval method according to claim 1, wherein the video retrieval method further comprises setting a presentation list, and the presenting the playing time and the target video frame image corresponding to the playing time comprises:
and displaying the playing time and the target video frame image corresponding to the playing time based on the display list.
5. The video retrieval method according to claim 1 or 4, wherein after the displaying the playing time and the video frame image corresponding to the playing time, the method further comprises:
and responding to the user input playing operation, and playing the video clip comprising the target video frame image by the playing time.
6. A video retrieval apparatus, the apparatus comprising:
the screening module is used for responding to input retrieval objects and screening target videos comprising the retrieval objects in a video library;
and the processing module is used for determining the playing time of the retrieval object in the target video based on the timestamp and displaying the playing time and the target video frame image corresponding to the playing time.
7. The video retrieval device of claim 6, wherein the screening module screens a video library to obtain a target video including the retrieval object by:
in response to inputting a retrieval object, determining a feature value of the retrieval object;
and screening a target video comprising the retrieval object in a video library based on the characteristic value.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the video retrieval method according to any of claims 1 to 5 are implemented when the processor executes the program.
9. A non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the video retrieval method according to any one of claims 1 to 5.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the video retrieval method according to any one of claims 1 to 5 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111390319.6A CN113836356A (en) | 2021-11-23 | 2021-11-23 | Video retrieval method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111390319.6A CN113836356A (en) | 2021-11-23 | 2021-11-23 | Video retrieval method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113836356A true CN113836356A (en) | 2021-12-24 |
Family
ID=78971599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111390319.6A Pending CN113836356A (en) | 2021-11-23 | 2021-11-23 | Video retrieval method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113836356A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787062A (en) * | 2016-02-29 | 2016-07-20 | 北京时代云英科技有限公司 | Method and equipment for searching for target object based on video platform |
| WO2018062644A2 (en) * | 2016-09-30 | 2018-04-05 | 설영석 | Target retrieval system using object recognition |
| CN110851641A (en) * | 2018-08-01 | 2020-02-28 | 杭州海康威视数字技术股份有限公司 | Cross-modal retrieval method and device and readable storage medium |
| CN111131902A (en) * | 2019-12-13 | 2020-05-08 | 华为技术有限公司 | Method for determining target object information and video playing equipment |
| CN113434716A (en) * | 2021-07-02 | 2021-09-24 | 泰康保险集团股份有限公司 | Cross-modal information retrieval method and device |
-
2021
- 2021-11-23 CN CN202111390319.6A patent/CN113836356A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787062A (en) * | 2016-02-29 | 2016-07-20 | 北京时代云英科技有限公司 | Method and equipment for searching for target object based on video platform |
| WO2018062644A2 (en) * | 2016-09-30 | 2018-04-05 | 설영석 | Target retrieval system using object recognition |
| CN110851641A (en) * | 2018-08-01 | 2020-02-28 | 杭州海康威视数字技术股份有限公司 | Cross-modal retrieval method and device and readable storage medium |
| CN111131902A (en) * | 2019-12-13 | 2020-05-08 | 华为技术有限公司 | Method for determining target object information and video playing equipment |
| CN113434716A (en) * | 2021-07-02 | 2021-09-24 | 泰康保险集团股份有限公司 | Cross-modal information retrieval method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11317139B2 (en) | Control method and apparatus | |
| CN109803180B (en) | Video preview generation method and device, computer equipment and storage medium | |
| WO2023011094A1 (en) | Video editing method and apparatus, electronic device, and storage medium | |
| CN104216956B (en) | The searching method and device of a kind of pictorial information | |
| US11762905B2 (en) | Video quality evaluation method and apparatus, device, and storage medium | |
| CN109408672B (en) | Article generation method, article generation device, server and storage medium | |
| US20190364211A1 (en) | System and method for editing video contents automatically technical field | |
| CN112954450B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN103514248B (en) | video recording apparatus, information processing system, information processing method and recording medium | |
| US20150189384A1 (en) | Presenting information based on a video | |
| US10897658B1 (en) | Techniques for annotating media content | |
| CN111182359A (en) | Video preview method, video frame extraction method, video processing device and storage medium | |
| CN113542833A (en) | Video playing method, device and equipment based on face recognition and storage medium | |
| CN111401238A (en) | Method and device for detecting character close-up segments in video | |
| CN113709545A (en) | Video processing method and device, computer equipment and storage medium | |
| CN114339423A (en) | Short video generation method and device, computing equipment and computer readable storage medium | |
| KR20180017424A (en) | Display apparatus and controlling method thereof | |
| CN111881734A (en) | Method and device for automatically intercepting target video | |
| US20170139933A1 (en) | Electronic Device, And Computer-Readable Storage Medium For Quickly Searching Video Segments | |
| KR102534270B1 (en) | Apparatus and method for providing meta-data | |
| CN113836356A (en) | Video retrieval method and device, electronic equipment and storage medium | |
| CN112055258A (en) | Time delay testing method and device for loading live broadcast picture and electronic equipment | |
| CN115665508A (en) | Video abstract generation method and device, electronic equipment and storage medium | |
| CN113891136A (en) | Video playing method and device, electronic equipment and storage medium | |
| CN112165626A (en) | Image processing method, resource acquisition method, related device and medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211224 |