CN104754267A - Video clip marking method, device and terminal - Google Patents

Video clip marking method, device and terminal Download PDF

Info

Publication number
CN104754267A
CN104754267A CN201510119575.XA CN201510119575A CN104754267A CN 104754267 A CN104754267 A CN 104754267A CN 201510119575 A CN201510119575 A CN 201510119575A CN 104754267 A CN104754267 A CN 104754267A
Authority
CN
China
Prior art keywords
target
video segment
video
guarded region
arbitrary target
Prior art date
Application number
CN201510119575.XA
Other languages
Chinese (zh)
Inventor
吴小勇
刘洁
王维
Original Assignee
小米科技有限责任公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 小米科技有限责任公司 filed Critical 小米科技有限责任公司
Priority to CN201510119575.XA priority Critical patent/CN104754267A/en
Publication of CN104754267A publication Critical patent/CN104754267A/en

Links

Abstract

The invention provides a video clip marking method, device and terminal, and belongs to the technical field of data processing. The method comprises the steps of detecting whether a target enters a monitoring area during recording a video; recognizing the target when the target enters a monitoring area so as to obtain the recognizing result; marking the content of the video clip with the target according to the recognizing result so as to obtain marking keyboards of a plurality of video clips; storing the correspondence relationship between the marking keywords and the video clips. According to the method, the content marking is performed for the video clips according to the target recognizing result; in addition, the contents of the video clips can be accurately reflected through the marking keywords; therefore, a user can quickly find out or position the target video clips, and the operation is intelligent.

Description

Video segment mask method, device and terminal

Technical field

The disclosure relates to technical field of data processing, particularly a kind of video segment mask method, device and terminal.

Background technology

Along with the develop rapidly of information technology, watch-dog is sustainable recording long period video after unlatching.Such as, video camera popular at present, after the external storage card of insertion, can record the video of tens days.Under the state of video camera networking, the video pictures of the current recording of the equipment such as smart mobile phone or panel computer real time inspection video camera can also be passed through, or the video segment recorded before carrying out drag-and-drop operation to watch.

But, owing to continuing the video that recorded the long period, so user wants that the video segment finding oneself to want in one section of so long video just becomes very difficult.In correlation technique, if guarded region there occurs special circumstances at a certain concrete time point, if then user is for checking the video segment that video camera is recorded at this concrete time point, then only by ceaselessly drag operation realization.Therefore, in order to promote video retrieval speed and the accuracy of user, a kind of video segment mask method is needed badly.

Summary of the invention

For overcoming Problems existing in correlation technique, the disclosure provides a kind of video segment mask method, device and terminal.

According to the first aspect of disclosure embodiment, provide a kind of video segment mask method, described method comprises:

In video record process, detect and whether have arbitrary target to enter guarded region;

When there being arbitrary target to enter described guarded region, described arbitrary target being identified, obtains recognition result;

Carry out content mark according to the video segment of described recognition result to described arbitrary target place, obtain the mark keyword of multiple video segment;

The corresponding relation of mark keyword and video segment is stored.

Alternatively, described mark keyword and the corresponding relation of video segment are stored after, described method also comprises:

Obtain the nominal key of input;

In the multiple mark keywords stored, determine the specific mark keyword comprising described nominal key;

Video segment corresponding for described specific mark keyword is defined as described target video fragment, described target video fragment is shown.

Alternatively, describedly carry out content mark according to the video segment of described recognition result to described arbitrary target place, comprising:

Record the second time that described arbitrary target enters the very first time of described guarded region, described arbitrary target leaves described guarded region;

According to described recognition result, content mark is carried out to the video segment between the described very first time and described second time.

Alternatively, whether described detection has arbitrary target to enter guarded region, comprising:

Obtain the background frame of described guarded region;

Obtain the current picture of described guarded region;

Described current picture and described background frame are compared;

If the diversity factor between described current picture and described background frame is greater than predetermined threshold value, then defines target and enter described guarded region.

Alternatively, described video segment corresponding for described specific mark keyword is defined as described target video fragment, described target video fragment is shown, comprising:

Search in the corresponding relation of described mark keyword and video segment according to described specific mark keyword, obtain at least one the target video fragment matched with described specific mark keyword;

At least one target video fragment described is presented in specified page.

Alternatively, described at least one target video fragment described is presented in specified page after, described method also comprises:

When after the clicking operation arbitrary target video fragment being detected, play described arbitrary target video fragment.

According to the second aspect of disclosure embodiment, provide a kind of video segment annotation equipment, described device comprises:

Whether module of target detection, in video record process, detect and have arbitrary target to enter guarded region;

Target identification module, for when there being arbitrary target to enter described guarded region, identifying described arbitrary target, obtaining recognition result;

Content labeling module, for carrying out content mark according to the video segment of described recognition result to described arbitrary target place, obtains the mark keyword of multiple video segment;

Corresponding relation memory module, for storing the corresponding relation of mark keyword and video segment.

Alternatively, described device also comprises:

Keyword acquisition module, for obtaining the nominal key of input;

Keyword determination module, in the multiple mark keywords stored, determines the specific mark keyword comprising described nominal key;

Video segment display module, for video segment corresponding for described specific mark keyword is defined as described target video fragment, shows described target video fragment.

Alternatively, described content labeling module, enters the very first time of described guarded region, the second time that described arbitrary target leaves described guarded region for recording described arbitrary target; According to described recognition result, content mark is carried out to the video segment between the described very first time and described second time.

Alternatively, described module of target detection, for obtaining the background frame of described guarded region; Obtain the current picture of described guarded region; Described current picture and described background frame are compared; If the diversity factor between described current picture and described background frame is greater than predetermined threshold value, then defines target and enter described guarded region.

Alternatively, described video segment display module, for searching in the corresponding relation of described mark keyword and video segment according to described specific mark keyword, obtains at least one the target video fragment matched with described specific mark keyword; At least one target video fragment described is presented in specified page.

Alternatively, described device also comprises:

Video segment playing module, for when after the clicking operation arbitrary target video fragment being detected, plays described arbitrary target video fragment.

According to the third aspect of disclosure embodiment, provide a kind of terminal, it is characterized in that, described terminal comprises:

Processor;

For the memory of storage of processor executable instruction;

Whether wherein, described processor is configured to: in video record process, detect and have arbitrary target to enter guarded region; When there being arbitrary target to enter described guarded region, described arbitrary target being identified, obtains recognition result; Carry out content mark according to the video segment of described recognition result to described arbitrary target place, obtain the mark keyword of multiple video segment; The corresponding relation of mark keyword and video segment is stored.

The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:

In video record process, when detecting that arbitrary target enters guarded region, arbitrary target is identified, and carry out content mark according to the video segment of recognition result to arbitrary target place, because the recognition result of based target has carried out content mark to video segment, and mark keyword can the content of accurate reflecting video fragment, so this kind of video segment notation methods can help user's fast finding or localizing objects video segment, comparatively intelligence.

Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.

Accompanying drawing explanation

Accompanying drawing to be herein merged in specification and to form the part of this specification, shows embodiment according to the invention, and is used from specification one and explains principle of the present invention.

Fig. 1 is the flow chart of a kind of video segment mask method according to an exemplary embodiment.

Fig. 2 is the flow chart of a kind of video segment mask method according to an exemplary embodiment.

Fig. 3 is the block diagram of the first the video segment annotation equipment according to an exemplary embodiment.

Fig. 4 is the block diagram of the second video segment annotation equipment according to an exemplary embodiment.

Fig. 5 is the block diagram of the third video segment annotation equipment according to an exemplary embodiment.

Fig. 6 is the block diagram of a kind of terminal according to an exemplary embodiment.

Embodiment

Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Execution mode described in following exemplary embodiment does not represent all execution modes consistent with the present invention.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present invention are consistent.

Before in detail explanation is explained to video segment mask method, first terminal structure composition is once simply introduced.In the disclosed embodiments, terminal refers to the watch-dogs such as video camera.Wherein, terminal comprises intrusion detecting unit, pattern recognition unit and content mark unit.Wherein, whether terminal is detected by intrusion detecting unit has new target to enter guarded region; Pattern recognition unit, for identifying the target entering guarded region, obtains recognition result.Content mark unit, for marking video segment according to recognition result.Thus the video segment after content-based mark, just can fast finding and the target video fragment of consumer positioning for watching.

Fig. 1 is the flow chart of a kind of video segment mask method according to an exemplary embodiment, and as shown in Figure 1, this video segment mask method is used for, in terminal, comprising the following steps.

In a step 101, in video record process, detect and whether have arbitrary target to enter guarded region.

In a step 102, when there being arbitrary target to enter guarded region, arbitrary target being identified, obtains recognition result.

In step 103, carry out content mark according to the video segment of recognition result to arbitrary target place, obtain the mark keyword of multiple video segment.

At step 104, the corresponding relation of mark keyword and video segment is stored.

The method that disclosure embodiment provides, in video record process, when detecting that arbitrary target enters guarded region, arbitrary target is identified, and carry out content mark according to the video segment of recognition result to arbitrary target place, because the recognition result of based target has carried out content mark to video segment, and mark keyword can the content of accurate reflecting video fragment, so this kind of video segment notation methods can help user's fast finding or localizing objects video segment, comparatively intelligence.

Alternatively, after being stored by the corresponding relation marking keyword and video segment, the method also comprises:

Obtain the nominal key of input;

In the multiple mark keywords stored, determine the specific mark keyword comprising nominal key;

Video segment corresponding for specific mark keyword is defined as target video fragment, target video fragment is shown.

Alternatively, carry out content mark according to according to the video segment of recognition result to arbitrary target place, comprising:

Record the second time that arbitrary target enters the very first time of guarded region, arbitrary target leaves guarded region;

According to recognition result, content mark is carried out to the video segment between the very first time and the second time.

Alternatively, detect and whether have arbitrary target to enter guarded region, comprising:

Obtain the background frame of guarded region;

Obtain the current picture of guarded region;

Current picture and background frame are compared;

If the diversity factor between current picture and background frame is greater than predetermined threshold value, then defines target and enter guarded region.

Alternatively, video segment corresponding for specific mark keyword is defined as target video fragment, target video fragment is shown, comprising:

Search in the corresponding relation marking keyword and video segment according to specific mark keyword, obtain at least one the target video fragment matched with specific mark keyword;

At least one target video fragment is presented in specified page.

Alternatively, after being presented in specified page by least one target video fragment, the method also comprises:

When after the clicking operation arbitrary target video fragment being detected, play arbitrary target video fragment.

Above-mentioned all alternatives, can adopt and combine arbitrarily formation optional embodiment of the present invention, this is no longer going to repeat them.

Fig. 2 is the flow chart of a kind of video segment mask method according to an exemplary embodiment, and as shown in Figure 2, this video segment mask method is used for, in terminal, comprising the following steps.

In step 201, in video record process, detect and whether have arbitrary target to enter guarded region; When there being arbitrary target to enter guarded region, perform following step 202.

Wherein, terminal is often referred to for watch-dog, such as has the video camera of taking pictures with camera function.Certainly, also can refer to the smart mobile phone or panel computer etc. with camera function, disclosure embodiment does not specifically limit this.Arbitrary target can refer to any object entered in the guarded region of watch-dog, the article etc. in such as people, animal or motion.

In the disclosed embodiments, when whether detection has arbitrary target to enter guarded region, following manner can be taked to realize:

Obtain the background frame of guarded region; Obtain the current picture of guarded region; Current picture and background frame are compared; If the diversity factor between current picture and background frame is greater than predetermined threshold value, then defines target and enter guarded region.

Wherein, the background frame of guarded region refers to tableaux, is also the picture initially photographed after watch-dog is opened.Such as, this background frame can be tableaux, the community background tableaux etc. downstairs in family parlor.The guarded region picture that the watch-dog current shooting that refers to current picture arrives.Predetermined threshold value can be 20% or 50% etc., and disclosure embodiment does not specifically limit this.Certainly, carry out except taking aforesaid way, except target detection, also can taking other modes, disclosure embodiment does not specifically limit this.

In step 202., when there being arbitrary target to enter guarded region, according to arbitrary target, content mark being carried out to video segment, obtaining the mark keyword of each video segment.

Wherein, content mark is carried out to video segment, be video segment and play title.When there being target to enter guarded region, target residence just has relation with this target at the mark keyword (i.e. video segment title) that the time period of guarded region is corresponding.Wherein, mark keyword can shape as " cat occur ", " man appears at family " etc.

In the disclosed embodiments, when carrying out content mark according to arbitrary target to video segment, following manner can be taked to realize:

Arbitrary target is identified, obtains recognition result; Record the second time that arbitrary target enters the very first time of guarded region, arbitrary target leaves guarded region; According to recognition result, content mark is carried out to the video segment between the very first time and the second time.

Wherein, when identifying arbitrary target, existing recognition technology can be taked to realize, no longer repeat herein.The very first time refers to the initial time that target enters guarded region, and the second time referred to the time that target leaves guarded region, so the very first time will early than the second time.When supposing that the very first time is 16 days 16 March in 2015 23 points 56 seconds, when second time was 16 days 16 March in 2015 25 points 34 seconds, guarded region is the parlor of family is example, if then within this period, the cat of family appears in video pictures, then terminal is identifying after target is the cat of family, according to recognition result to 16 time 23 points 56 seconds to 16 time 25 points of 34 seconds these durations be that the video segment of 98 seconds marks, be such as labeled as " cat of family occurs ".

After obtaining mark keyword corresponding to each video segment, the corresponding relation of mark keyword and video segment is stored.Such as, be stored in the storage medium such as internal memory or hard disk, disclosure embodiment does not specifically limit this.

It should be noted that, just can complete the mark to video segment by above-mentioned steps 201 and step 202, so the video segment after content-based mark, just can search rapidly or the target video fragment of consumer positioning and viewing.Certainly, both can search by the video segment carried out based on marked content after marking video segment, also can carry out video segment in the process marked some video segment and search, disclosure embodiment does not specifically limit this.Detailed search procedure see following step 203 to step 205.In addition, annotation process and search procedure can all be completed by watch-dog.Certainly, annotation process also can be completed by watch-dog, and search procedure is completed by panel computer, PC or the smart mobile phone connected with watch-dog, and disclosure embodiment does not specifically limit equally to this.When being completed mark and search procedure by two equipment, panel computer, PC or smart mobile phone etc. store the video segment that watch-dog has been recorded.

In step 203, the nominal key of input is obtained.

In the disclosed embodiments, if user wants to search a certain target video fragment, then the video search frame provided by terminal demonstration interface is searched.When the search content of this input during inputted search content, is just defined as the nominal key inputted by user in video search frame.Wherein, nominal key can be object names etc.Such as cat, people, automobile etc., disclosure embodiment does not specifically limit this.

In step 204, in the multiple mark keywords stored, the specific mark keyword comprising nominal key is determined.

In the disclosed embodiments, all corresponding video segment of each mark keyword.After getting the nominal key of input, just multiple mark keywords of nominal key and storage can be compared; If nominal key is included in an arbitrary mark keyword, then corresponding with this mark keyword video segment, just as alternative, it can be used as the target video fragment of a candidate.In this step, specific mark keyword can be one or more, and nominal key can all be included in specific mark keyword.Such as, nominal key is cat, and special key words is " cat of family occurs ", " cat enters picture " etc.Certainly, nominal key also can partly be included in specific mark keyword, but the proportion that nominal key appears in specific mark keyword is larger.Such as, in nominal key, the word of more than 50% or 80% all appears in specific mark keyword.Such as, nominal key is cat and people, and special key words is " cat of family occurs ", " cat enters picture " etc.Disclosure embodiment is to determining that the mode of specific mark keyword does not specifically limit.

In step 205, target video fragment corresponding for specific mark keyword is shown.

In the disclosed embodiments, after finding the target video fragment corresponding with specific mark keyword, target video fragment corresponding for specific mark keyword is shown, selects for user.Wherein, when target video fragment corresponding for specific mark keyword being shown, following manner can be taked to realize:

Search in the corresponding relation marking keyword and video segment according to specific mark keyword, obtain at least one the target video fragment matched with specific mark keyword; At least one target video fragment is presented in specified page.

Wherein, specified page refers to the new page that is exclusively used in display-object video segment.User, after seeing multiple target video fragments of display, can choose arbitrary target video fragment based on manual clicking operation and play.Such as, after terminal detects the clicking operation of arbitrary target video fragment, directly call video player and play this arbitrary target video fragment.

The method that disclosure embodiment provides, in video record process, when detecting that arbitrary target enters guarded region, arbitrary target is identified, and carry out content mark according to the video segment of recognition result to arbitrary target place, because the recognition result of based target has carried out content mark to video segment, and mark keyword can the content of accurate reflecting video fragment, so this kind of video segment notation methods can help user's fast finding or localizing objects video segment, comparatively intelligence.

Fig. 3 is the block diagram of a kind of video segment annotation equipment according to an exemplary embodiment.With reference to Fig. 3, this device comprises module of target detection 301, target identification module 302, content labeling module 303 and corresponding relation memory module 304.

Whether wherein, module of target detection 301 is connected with target identification module 302, in video record process, detect and have arbitrary target to enter guarded region; Target identification module 302 is connected with content labeling module 303, for when there being arbitrary target to enter guarded region, identifying, obtain recognition result to arbitrary target; Content labeling module 303 is connected with corresponding relation memory module 304, for carrying out content mark according to the video segment of recognition result to arbitrary target place, obtains the mark keyword of multiple video segment; Corresponding relation memory module 304, for storing the corresponding relation of mark keyword and video segment.

See Fig. 4, this device also comprises:

Keyword acquisition module 305, for obtaining the nominal key of input;

Keyword determination module 306, in the multiple mark keywords stored, determines the specific mark keyword comprising nominal key;

Video segment display module 307, for video segment corresponding for specific mark keyword is defined as target video fragment, shows target video fragment.

Alternatively, content labeling module, enters the very first time of guarded region, the second time that arbitrary target leaves guarded region for recording arbitrary target; According to recognition result, content mark is carried out to the video segment between the very first time and the second time.

Alternatively, module of target detection, for obtaining the background frame of guarded region; Obtain the current picture of guarded region; Current picture and background frame are compared; If the diversity factor between current picture and background frame is greater than predetermined threshold value, then defines target and enter guarded region.

Alternatively, video segment display module, for searching in the corresponding relation marking keyword and video segment according to specific mark keyword, obtains at least one the target video fragment matched with specific mark keyword; At least one target video fragment is presented in specified page.

See Fig. 5, this device also comprises:

Video segment playing module 308, for when after the clicking operation arbitrary target video fragment being detected, plays arbitrary target video fragment.

The device that disclosure embodiment provides, in video record process, when detecting that arbitrary target enters guarded region, arbitrary target is identified, and carry out content mark according to the video segment of recognition result to arbitrary target place, because the recognition result of based target has carried out content mark to video segment, and mark keyword can the content of accurate reflecting video fragment, so this kind of video segment notation methods can help user's fast finding or localizing objects video segment, comparatively intelligence.

About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.

Fig. 6 is the block diagram of a kind of terminal 600 for video segment mark according to an exemplary embodiment.Such as, terminal 600 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, flat-panel devices, Medical Devices, body-building equipment, personal digital assistant etc.

With reference to Fig. 6, terminal 600 can comprise following one or more assembly: processing components 602, memory 604, power supply module 606, multimedia groupware 608, audio-frequency assembly 610, I/O (Input/Output, I/O) interface 612, sensor cluster 614, and communications component 616.

The integrated operation of the usual control terminal 600 of processing components 602, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 602 can comprise one or more processor 630 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 602 can comprise one or more module, and what be convenient between processing components 602 and other assemblies is mutual.Such as, processing components 602 can comprise multi-media module, mutual with what facilitate between multimedia groupware 608 and processing components 602.

Memory 604 is configured to store various types of data to be supported in the operation of terminal 600.The example of these data comprises for any application program of operation in terminal 600 or the instruction of method, contact data, telephone book data, message, picture, video etc.Memory 604 can be realized by the volatibility of any type or non-volatile memory device or their combination, as SRAM (Static Random AccessMemory, static RAM), EEPROM (Electrically-Erasable ProgrammableRead-Only Memory, Electrically Erasable Read Only Memory), EPROM (ErasableProgrammable Read Only Memory, Erasable Programmable Read Only Memory EPROM), PROM (Programmable Read-Only Memory, programmable read only memory), ROM (Read-OnlyMemory, read-only memory), magnetic memory, flash memory, disk or CD.

The various assemblies that power supply module 606 is terminal 600 provide electric power.Power supply module 606 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for terminal 600 and be associated.

Multimedia groupware 608 is included in the screen providing an output interface between described terminal 600 and user.In certain embodiments, screen can comprise LCD (Liquid Crystal Display, liquid crystal display) and TP (Touch Panel, touch panel).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 608 comprises a front-facing camera and/or post-positioned pick-up head.When terminal 600 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.

Audio-frequency assembly 610 is configured to export and/or input audio signal.Such as, audio-frequency assembly 610 comprises a MIC (Microphone, microphone), and when terminal 600 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The audio signal received can be stored in memory 604 further or be sent via communications component 616.In certain embodiments, audio-frequency assembly 610 also comprises a loud speaker, for output audio signal.

I/O interface 612 is for providing interface between processing components 602 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.

Sensor cluster 614 comprises one or more transducer, for providing the state estimation of various aspects for terminal 600.Such as, sensor cluster 614 can detect the opening/closing state of equipment 600, the relative positioning of assembly, such as assembly is display and the keypad of terminal 600, the position of all right sense terminals 600 of sensor cluster 614 or terminal 600 1 assemblies changes, the presence or absence that user contacts with terminal 600, the variations in temperature of terminal 600 orientation or acceleration/deceleration and terminal 600.Sensor cluster 614 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor cluster 614 can also comprise optical sensor, as CMOS (Complementary Metal OxideSemiconductor, CMOS (Complementary Metal Oxide Semiconductor)) or CCD (Charge-coupled Device, charge coupled cell) imageing sensor, for using in imaging applications.In certain embodiments, this sensor cluster 614 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.

Communications component 616 is configured to the communication being convenient to wired or wireless mode between terminal 600 and other equipment.Terminal 600 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 616 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communications component 616 also comprises NFC (Near Field Communication, near-field communication) module, to promote junction service.Such as, can based on RFID (Radio Frequency Identification in NFC module, radio-frequency (RF) identification) technology, IrDA (Infra-red Data Association, Infrared Data Association) technology, UWB (Ultra Wideband, ultra broadband) technology, BT (Bluetooth, bluetooth) technology and other technologies realize.

In the exemplary embodiment, terminal 600 can by one or more ASIC (Application SpecificIntegrated Circuit, application specific integrated circuit), DSP (Digital signal Processor, digital signal processor), DSPD (Digital signal Processor Device, digital signal processing appts), PLD (Programmable Logic Device, programmable logic device), FPGA) (Field ProgrammableGate Array, field programmable gate array), controller, microcontroller, microprocessor or other electronic components realize, for performing said method.

In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the memory 604 of instruction, above-mentioned instruction can perform said method by the processor 630 of terminal 600.Such as, described non-transitory computer-readable recording medium can be ROM, RAM (Random Access Memory, random access memory), CD-ROM (Compact Disc Read-OnlyMemory, compact disc read-only memory), tape, floppy disk and optical data storage devices etc.

A kind of non-transitory computer-readable recording medium, when the instruction in storage medium is performed by the processor of mobile terminal, make mobile terminal can perform a kind of video segment mask method, the method comprises:

In video record process, detect and whether have arbitrary target to enter guarded region;

When there being arbitrary target to enter guarded region, arbitrary target being identified, obtains recognition result;

Carry out content mark according to the video segment of recognition result to arbitrary target place, obtain the mark keyword of multiple video segment;

The corresponding relation of mark keyword and video segment is stored.

Alternatively, after being stored by the corresponding relation marking keyword and video segment, the method also comprises:

Obtain the nominal key of input;

In the multiple mark keywords stored, determine the specific mark keyword comprising nominal key;

Video segment corresponding for specific mark keyword is defined as target video fragment, target video fragment is shown.

Alternatively, carry out content mark according to the video segment of recognition result to arbitrary target place, comprising:

Record the second time that arbitrary target enters the very first time of guarded region, arbitrary target leaves guarded region;

According to recognition result, content mark is carried out to the video segment between the very first time and the second time.

Alternatively, detect and whether have arbitrary target to enter guarded region, comprising:

Obtain the background frame of guarded region;

Obtain the current picture of guarded region;

Current picture and background frame are compared;

If the diversity factor between current picture and background frame is greater than predetermined threshold value, then defines target and enter guarded region.

Alternatively, video segment corresponding for specific mark keyword is defined as target video fragment, target video fragment is shown, comprising:

Search in the corresponding relation marking keyword and video segment according to specific mark keyword, obtain at least one the target video fragment matched with specific mark keyword;

At least one target video fragment is presented in specified page.

Alternatively, after being presented in specified page by least one target video fragment, the method also comprises:

When after the clicking operation arbitrary target video fragment being detected, play arbitrary target video fragment.

The non-transitory computer-readable recording medium that disclosure embodiment provides, in video record process, when detecting that arbitrary target enters guarded region, arbitrary target is identified, and carry out content mark according to the video segment of recognition result to arbitrary target place, because the recognition result of based target has carried out content mark to video segment, and mark keyword can the content of accurate reflecting video fragment, so this kind of video segment notation methods can help user's fast finding or localizing objects video segment, comparatively intelligence.

Those skilled in the art, at consideration specification and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Specification and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.

Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.

Claims (13)

1. a video segment mask method, is characterized in that, described method comprises:
In video record process, detect and whether have arbitrary target to enter guarded region;
When there being arbitrary target to enter described guarded region, described arbitrary target being identified, obtains recognition result;
Carry out content mark according to the video segment of described recognition result to described arbitrary target place, obtain the mark keyword of multiple video segment;
The corresponding relation of mark keyword and video segment is stored.
2. method according to claim 1, is characterized in that, described mark keyword and the corresponding relation of video segment are stored after, described method also comprises:
Obtain the nominal key of input;
In the multiple mark keywords stored, determine the specific mark keyword comprising described nominal key;
Video segment corresponding for described specific mark keyword is defined as described target video fragment, described target video fragment is shown.
3. method according to claim 1, is characterized in that, describedly carries out content mark according to the video segment of described recognition result to described arbitrary target place, comprising:
Record the second time that described arbitrary target enters the very first time of described guarded region, described arbitrary target leaves described guarded region;
According to described recognition result, content mark is carried out to the video segment between the described very first time and described second time.
4. method according to claim 1, is characterized in that, whether described detection has arbitrary target to enter guarded region, comprising:
Obtain the background frame of described guarded region;
Obtain the current picture of described guarded region;
Described current picture and described background frame are compared;
If the diversity factor between described current picture and described background frame is greater than predetermined threshold value, then defines target and enter described guarded region.
5. method according to claim 2, is characterized in that, described video segment corresponding for described specific mark keyword is defined as described target video fragment, described target video fragment is shown, comprising:
Search in the corresponding relation of described mark keyword and video segment according to described specific mark keyword, obtain at least one the target video fragment matched with described specific mark keyword;
At least one target video fragment described is presented in specified page.
6. method according to claim 5, is characterized in that, described at least one target video fragment described is presented in specified page after, described method also comprises:
When after the clicking operation arbitrary target video fragment being detected, play described arbitrary target video fragment.
7. a video segment annotation equipment, is characterized in that, described device comprises:
Whether module of target detection, in video record process, detect and have arbitrary target to enter guarded region;
Target identification module, for when there being arbitrary target to enter described guarded region, identifying described arbitrary target, obtaining recognition result;
Content labeling module, for carrying out content mark according to the video segment of described recognition result to described arbitrary target place, obtains the mark keyword of multiple video segment;
Corresponding relation memory module, for storing the corresponding relation of mark keyword and video segment.
8. device according to claim 7, is characterized in that, described device also comprises:
Keyword acquisition module, for obtaining the nominal key of input;
Keyword determination module, in the multiple mark keywords stored, determines the specific mark keyword comprising described nominal key;
Video segment display module, for video segment corresponding for described specific mark keyword is defined as described target video fragment, shows described target video fragment.
9. device according to claim 7, is characterized in that, described content labeling module, enters the very first time of described guarded region, the second time that described arbitrary target leaves described guarded region for recording described arbitrary target; According to described recognition result, content mark is carried out to the video segment between the described very first time and described second time.
10. device according to claim 7, is characterized in that, described module of target detection, for obtaining the background frame of described guarded region; Obtain the current picture of described guarded region; Described current picture and described background frame are compared; If the diversity factor between described current picture and described background frame is greater than predetermined threshold value, then defines target and enter described guarded region.
11. devices according to claim 8, it is characterized in that, described video segment display module, for searching in the corresponding relation of described mark keyword and video segment according to described specific mark keyword, obtain at least one the target video fragment matched with described specific mark keyword; At least one target video fragment described is presented in specified page.
12. devices according to claim 11, is characterized in that, described device also comprises:
Video segment playing module, for when after the clicking operation arbitrary target video fragment being detected, plays described arbitrary target video fragment.
13. 1 kinds of terminals, is characterized in that, described terminal comprises:
Processor;
For the memory of storage of processor executable instruction;
Whether wherein, described processor is configured to: in video record process, detect and have arbitrary target to enter guarded region; When there being arbitrary target to enter described guarded region, described arbitrary target being identified, obtains recognition result; Carry out content mark according to the video segment of described recognition result to described arbitrary target place, obtain the mark keyword of multiple video segment; The corresponding relation of mark keyword and video segment is stored.
CN201510119575.XA 2015-03-18 2015-03-18 Video clip marking method, device and terminal CN104754267A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510119575.XA CN104754267A (en) 2015-03-18 2015-03-18 Video clip marking method, device and terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510119575.XA CN104754267A (en) 2015-03-18 2015-03-18 Video clip marking method, device and terminal

Publications (1)

Publication Number Publication Date
CN104754267A true CN104754267A (en) 2015-07-01

Family

ID=53593303

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510119575.XA CN104754267A (en) 2015-03-18 2015-03-18 Video clip marking method, device and terminal

Country Status (1)

Country Link
CN (1) CN104754267A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105141915A (en) * 2015-08-26 2015-12-09 广东创我科技发展有限公司 Video searching method and video searching system
CN105357475A (en) * 2015-10-28 2016-02-24 小米科技有限责任公司 Video playing method and device
CN105704457A (en) * 2016-03-09 2016-06-22 国网浙江省电力公司湖州供电公司 Target state identification and online monitoring equipment for important channel scene during extra-high-voltage power transmission process
CN106411927A (en) * 2016-10-28 2017-02-15 北京奇虎科技有限公司 Monitoring video recording method and device
CN107333189A (en) * 2017-07-31 2017-11-07 深圳回收宝科技有限公司 A kind of segmentation method, equipment and storage medium for detecting video
CN107734303A (en) * 2017-10-30 2018-02-23 北京小米移动软件有限公司 Video labeling method and device
CN107948585A (en) * 2017-11-13 2018-04-20 西安艾润物联网技术服务有限责任公司 Video recording labeling method, device and computer-readable recording medium
CN105142111B (en) * 2015-09-17 2018-12-28 中国有色金属长沙勘察设计研究院有限公司 A kind of identities match method and identities match device based on real time position

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101300578A (en) * 2005-11-03 2008-11-05 皇家飞利浦电子股份有限公司 Real-time information management method and apparatus based on object
CN102708685A (en) * 2012-04-27 2012-10-03 南京航空航天大学 Device and method for detecting and snapshotting violation vehicles
CN103004188A (en) * 2010-07-19 2013-03-27 爱普索科技有限公司 Apparatus, system and method
CN103927364A (en) * 2014-04-18 2014-07-16 苏州科达科技股份有限公司 Storage method and system and display system for video abstract data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101300578A (en) * 2005-11-03 2008-11-05 皇家飞利浦电子股份有限公司 Real-time information management method and apparatus based on object
CN103004188A (en) * 2010-07-19 2013-03-27 爱普索科技有限公司 Apparatus, system and method
CN102708685A (en) * 2012-04-27 2012-10-03 南京航空航天大学 Device and method for detecting and snapshotting violation vehicles
CN103927364A (en) * 2014-04-18 2014-07-16 苏州科达科技股份有限公司 Storage method and system and display system for video abstract data

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105141915A (en) * 2015-08-26 2015-12-09 广东创我科技发展有限公司 Video searching method and video searching system
CN105142111B (en) * 2015-09-17 2018-12-28 中国有色金属长沙勘察设计研究院有限公司 A kind of identities match method and identities match device based on real time position
CN105357475A (en) * 2015-10-28 2016-02-24 小米科技有限责任公司 Video playing method and device
WO2017071086A1 (en) * 2015-10-28 2017-05-04 小米科技有限责任公司 Method and device used for video playback
CN105704457A (en) * 2016-03-09 2016-06-22 国网浙江省电力公司湖州供电公司 Target state identification and online monitoring equipment for important channel scene during extra-high-voltage power transmission process
CN106411927A (en) * 2016-10-28 2017-02-15 北京奇虎科技有限公司 Monitoring video recording method and device
CN106411927B (en) * 2016-10-28 2019-06-04 北京奇虎科技有限公司 A kind of video monitoring method and device
CN107333189A (en) * 2017-07-31 2017-11-07 深圳回收宝科技有限公司 A kind of segmentation method, equipment and storage medium for detecting video
CN107734303A (en) * 2017-10-30 2018-02-23 北京小米移动软件有限公司 Video labeling method and device
CN107948585A (en) * 2017-11-13 2018-04-20 西安艾润物联网技术服务有限责任公司 Video recording labeling method, device and computer-readable recording medium

Similar Documents

Publication Publication Date Title
CN104991789B (en) Application program open method and device
CN104092808B (en) Number mark method, device and terminal
CN104038263A (en) Method and device for establishing Bluetooth connection
CN104159275B (en) Method for connecting network and device
CN105488112B (en) Information-pushing method and device
CN104615769A (en) Image classification method and device
CN104793739A (en) Play control method and device
CN104239566B (en) The method and device of video search
CN105279898A (en) Alarm method and device
CN104796781A (en) Video clip extraction method and device
CN103916711A (en) Method and device for playing video signals
CN104540184A (en) Equipment networking method and device
CN104008635A (en) Equipment control method and device
CN104834665A (en) Target picture acquiring method and device
CN105224349A (en) The deletion reminding method of application program and device
CN105306931A (en) Smart TV anomaly detection method and device
CN105657537A (en) Video editing method and device
CN104301532A (en) Communication message identification method and device
CN104793846A (en) Displaying method and device for interface of application program
CN105469056A (en) Face image processing method and device
CN104123093A (en) Information processing method and device
CN105549849A (en) Method and device for processing misoperation instruction
CN104105169B (en) From method and the device of the WLAN (wireless local area network) that is dynamically connected
CN105426152A (en) Bullet screen display method and device
CN105120191A (en) Video recording method and device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into 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: 20150701