CN108289201A - Video data handling procedure, device and electronic equipment - Google Patents
Video data handling procedure, device and electronic equipment Download PDFInfo
- Publication number
- CN108289201A CN108289201A CN201810067998.5A CN201810067998A CN108289201A CN 108289201 A CN108289201 A CN 108289201A CN 201810067998 A CN201810067998 A CN 201810067998A CN 108289201 A CN108289201 A CN 108289201A
- Authority
- CN
- China
- Prior art keywords
- video
- behavior
- video data
- handling procedure
- preassigned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/91—Television signal processing therefor
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
A kind of video data handling procedure is disclosed, including:Include the first video of object by the acquisition of the first image capture device, described first image collecting device has first resolution;The initial attitude of the object is detected from the initial video frame of first video;Determine whether the initial attitude of the object meets the first preassigned;And, meet first preassigned in response to the initial attitude of the object, triggering is by the second video that the acquisition of the second image capture device includes object, and second image capture device has second resolution, and the second resolution is higher than the first resolution.It is thereby achieved that the efficient process of video data.
Description
Technical field
This application involves video technique fields, and more particularly, to a kind of video data handling procedure, video data at
Manage device and electronic equipment.
Background technology
Image, video are the significant datas in people's life production, and video monitoring is important application therein.Video monitoring
Basic function be to provide real time video collection, and recorded a video to the picture of acquisition, transimission and storage, to confirm afterwards.
It is improved year by year with the extensive arrangement and resolution ratio of the camera for video monitoring, whole day, magnanimity is presented in data, accordingly
Data processing, storage, inquiry etc. all encounter new challenge.
Therefore, it is necessary to improved video data processing schemes.
Invention content
In order to solve the above-mentioned technical problem, it is proposed that the application.Embodiments herein provides at a kind of video data
The efficient process of video data may be implemented in reason method, video data processing apparatus and electronic equipment.
According to the one side of the application, a kind of video data handling procedure is provided, including:Pass through the first Image Acquisition
Equipment acquisition includes the first video of object, and described first image collecting device has first resolution;From first video
Initial video frame detect the initial attitude of the object;Determine whether the initial attitude of the object meets the first pre- calibration
It is accurate;And meeting first preassigned in response to the initial attitude of the object, triggering passes through the second image capture device
Acquisition includes the second video of object, and second image capture device has second resolution, and the second resolution is high
In the first resolution.
According to the another aspect of the application, a kind of video data processing apparatus is provided, including:Acquiring unit, for leading to
The first video that the acquisition of the first image capture device includes object is crossed, described first image collecting device has first resolution;
Detection unit, the initial attitude for detecting the object from the initial video frame of first video;Determination unit, for true
Whether the initial attitude of the fixed object meets the first preassigned;And control unit, in response to the first of the object
Beginning posture meets first preassigned, and triggering passes through the second video that the acquisition of the second image capture device includes object, institute
Stating the second image capture device has second resolution, and the second resolution is higher than the first resolution.
According to the another aspect of the application, a kind of electronic equipment is provided, including:Processor;And memory, in institute
It states and is stored with computer program instructions in memory, the computer program instructions make described when being run by the processor
Processor executes video data handling procedure as described above.
According to the another aspect of the application, a kind of computer readable storage medium is provided, is stored thereon with computer journey
Sequence instructs, and the computer program instructions make the processor execute video data as described above when being run by processor
Processing method.
Compared with prior art, using video data handling procedure, the video data processing dress according to the embodiment of the present application
Set and electronic equipment, can be obtained by the first image capture device include object the first video, described first image acquires
Equipment has first resolution;The initial attitude of the object is detected from the initial video frame of first video;Described in determination
Whether the initial attitude of object meets the first preassigned;And meet described first in response to the initial attitude of the object
Preassigned, triggering pass through the second video that the acquisition of the second image capture device includes object, second image capture device
With second resolution, and the second resolution is higher than the first resolution.Therefore, the gesture recognition of object can be passed through
The pith in video is determined, to correspondingly realize the efficient process of video data.
Description of the drawings
The embodiment of the present application is described in more detail in conjunction with the accompanying drawings, the above-mentioned and other purposes of the application,
Feature and advantage will be apparent.Attached drawing is used for providing further understanding the embodiment of the present application, and constitutes explanation
A part for book does not constitute the limitation to the application for explaining the application together with the embodiment of the present application.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 illustrates the schematic diagrames of the application scenarios handled according to the video data of the embodiment of the present application.
Fig. 2 illustrates the flow chart of the video data handling procedure according to the embodiment of the present application.
Fig. 3 illustrates the schematic diagram of the single frames estimation technique according to the human body attitude of the embodiment of the present application.
Fig. 4 illustrates the schematic diagram of the Activity recognition technology based on human body attitude according to the embodiment of the present application.
Fig. 5 illustrates the flow chart of the video data acquiring process according to the embodiment of the present application.
Fig. 6 illustrates the flow chart of the video data storing process according to the embodiment of the present application.
Fig. 7 illustrates the block diagram of the video data processing apparatus according to the embodiment of the present application.
Fig. 8 illustrates the block diagram of the electronic equipment according to the embodiment of the present application.
Specific implementation mode
In the following, example embodiment according to the application will be described in detail by referring to the drawings.Obviously, described embodiment is only
Only it is a part of the embodiment of the application, rather than the whole embodiments of the application, it should be appreciated that the application is not by described herein
The limitation of example embodiment.
Application is summarized
As described above, generating the video data of magnanimity in people’s lives production at present.But in these data videos
In, and the importance of not all frame is completely the same, this feature shows to be especially apparent in monitoring field.In general, camera shooting model
Sparsity is presented in the unusual behavior for enclosing interior personage, this part is just most important part in entire monitoring data.Therefore, by adopting
With human body attitude and Activity recognition technology, the key frame in video can be provided, to efficiently handle video data.
For the technical problem, the basic conception of the application is to propose a kind of video data handling procedure, at video data
Device and electronic equipment are managed, the pith in video can be determined by the gesture recognition of object, and in video
Pith and insignificant part carry out different processing, to realize the efficient process of video data.
It should be noted that the above-mentioned basic conception of the application can be applied not only to the gesture recognition of human body, it can also
Applied to other objects, for example, non-human moving object or anthropoid robot etc. gesture recognition.
After describing the basic principle of the application, carry out the specific various non-limits for introducing the application below with reference to the accompanying drawings
Property embodiment processed.
Exemplary system
Fig. 1 illustrates the schematic diagrames of the application scenarios handled according to the video data of the embodiment of the present application.
As shown in Figure 1, the application scenarios for video data processing include the first image capture device 110, the second image
Collecting device 120 and object 130.
First image capture device 110 can be any kind of image capture device, for example, camera etc..For example,
Camera institute the image collected data can be consecutive image frame sequence (that is, video flowing) or discrete picture frame sequence (that is,
In the image data set that predetermined sampling time point sampling arrives) etc..For example, the camera can be as monocular camera, binocular camera,
More mesh cameras etc. can also capture the cromogram with colouring information in addition, it can be used for capturing gray-scale map.Certainly, ability
The camera of any other type known and be likely to occur in the future can be applied to the application in domain, and the application catches it
The mode for catching image is not particularly limited, as long as the gray scale or colour information of input picture can be obtained.After reducing
Calculation amount in continuous operation can carry out cromogram at gray processing before being analyzed and being handled in one embodiment
Reason.Certainly, in order to retain the information content of bigger, in another embodiment, can also directly cromogram be analyzed and handled.
Second image capture device 120 can also be any kind of image capture device, can be with the first image
Collecting device 110 has different types, or has different imaging parameters from the first image capture device 110.
The object 130 can be any kind of imaging object.For example, the object 130 can be people or other movements
Object, including robot etc..
Illustrative methods
Fig. 2 illustrates the flow chart of the video data handling procedure according to the embodiment of the present application.
As shown in Fig. 2, the video data handling procedure according to the embodiment of the present application includes:S210 is adopted by the first image
Collection equipment acquisition includes the first video of object, and described first image collecting device has first resolution;S220, from described
The initial video frame of one video detects the initial attitude of the object;S230, determines whether the initial attitude of the object meets
First preassigned;And S240, meet first preassigned in response to the initial attitude of the object, triggering passes through the
The acquisition of two image capture devices includes the second video of object, and second image capture device has second resolution, and institute
It states second resolution and is higher than the first resolution.
In the following, will be described in detail each step.
In step S210, by the first image capture device 110, for example, first camera acquisition includes the first of object regarding
Frequently.Here, in order to reduce the operand and memory space of gesture recognition, described first image collecting device can have lower
First resolution.
In step S220, the initial attitude of the object is detected from the initial video frame of first video.
Fig. 3 illustrates the schematic diagram of the single frames estimation technique according to the human body attitude of the embodiment of the present application.
As shown in figure 3, the posture of human body can be detected from the single video frame in video.Specifically, can pass through
Emerging computer vision technique carries out the Attitude estimation of human body, face etc..For example, can be obtained from monocular or binocular camera
Image to the skeleton (head, shoulder, elbow, wrist, hip, knee, ankle etc.) and head pose (pitching or so and respective corners of human body
Degree) high-precision identification is carried out, and then estimate limbs correlation and fat or thin height.
In step S230, determine whether the initial attitude of the object meets the first preassigned.That is, by described in determination
Whether the initial attitude of object meets the first preassigned, it may be determined that whether the initial attitude of the object, which needs, is paid close attention to
Particular pose, for example, in the case where household guards scene, the lean forward posture or the posture that lies low etc. of human body.
Then, in step S240, in the case where the initial attitude of the object is the particular pose for needing to pay close attention to, triggering
Include the second video of object by the acquisition of the second image capture device 120.Here, in order to more obtain the concern figure being more clear
Picture, second image capture device can have higher resolution ratio.
Therefore, in the video data handling procedure according to the embodiment of the present application, the spy for detecting object is depended on whether
Determine posture, object is obtained by the first image capture device with different resolution and the second image capture device respectively
First video and the second video.In this way, can carry out including object by the second video with higher second resolution
The processing of the key frame of key poses, to improve the treatment effeciency of video data.
But in the case where the posture only for object is identified, it is understood that there may be can not clearly determine object
The case where behavior.For example, detect human body lean forward posture in the case of, can not accurately judge the follow-up behavior of human body, example
Such as, the follow-up behavior of human body can be the behavior of running of active, can also be passive to fall down behavior.
Therefore, in the video data handling procedure according to the embodiment of the present application, further according to the sequence of video frame, lead to
The gesture recognition of consecutive frame is crossed as a result, carrying out effectively identification (for example, the climbing of human body, sitting down, falling down) to behavior.
Fig. 4 illustrates the schematic diagram of the Activity recognition technology based on human body attitude according to the embodiment of the present application.Such as Fig. 4 institutes
Show, based on the human body attitude identified in continuous several frames, the behavior of human body can be gone out by posture recognition sequence.
For the identification of the behavior of object, the video data handling procedure according to the embodiment of the present application may include two and show
Example.
First, in the first example, can be in the case where confirmly detecting the specific behavior of object, just triggering passes through institute
It includes second video to state the acquisition of the second image capture device.In this way, can reduce with high-resolution second figure
As the probability of the error starting of collecting device.For example, first can be met determining the initial attitude detected from initial video frame
In the case of preassigned, after further determining that first detected in the first subsequent video frame after the initial video frame
Whether continuous posture also complies with first preassigned.Also, the specific appearance of user is detected in continuous multiple video frame
In the case of state, the behavior based on object described in posture recognition sequence.That is, in the video counts according to the embodiment of the present application
According in processing method, the first follow-up posture of initial attitude and first subsequent video frame based on the initial video frame is known
The behavior of the not described object.
Pass through the Activity recognition result of the object, it may be determined that the priority of the behavior of the object.That is, according to this
In the video data handling procedure for applying for embodiment, the object is determined according to the behavior classification information of the behavior of the object
Whether behavior is high priority behavior.Here, the high priority behavior refers to the behavior for the object for needing to pay close attention to, example
Such as, in the case where household guards scene, human body falls down behavior.Correspondingly, low priority behavior is the common behavior of the object, example
Such as, the behavior of walking about etc. of human body.
In this way, in the case where confirmly detecting the high priority behavior of the object, triggering passes through second image
Collecting device obtains second video, to ensure second image capture device not because unessential object behavior and
Error starting.
Therefore, in the video data handling procedure according to the embodiment of the present application, in response to the initial attitude of the object
Meet first preassigned, triggering can be wrapped by the second video S240 that the acquisition of the second image capture device includes object
It includes:Meet first preassigned in response to the initial attitude of the object, after first after the initial video frame
Continuous video frame detects the first follow-up posture of the object;Determine whether the first follow-up posture of the object meets described first
Preassigned;Meet first preassigned in response to the first follow-up posture of the object, determines the behavior of the object
It is the high priority behavior that priority is more than predetermined threshold;And in response to determining that the behavior of the object is the Gao You
First grade behavior, triggering pass through the second video that second image capture device acquisition includes object.
But in these cases, if the time span of the behavior of the object is longer, there are second images
The startup time of collecting device too late, to miss the possibility of key message.
Therefore, alternatively, in the second example, in the particular pose for detecting object, for example, the posture that leans forward of human body
In the case of, just triggering has the second video that high-resolution second image capture device obtains object.And subsequently, based on institute
The subsequent video frame for stating the first video determines whether to detect the high priority behavior of the object.It is described right confirmly detecting
In the case of the high priority behavior of elephant, keep obtaining second video by second image capture device.Also,
In the case of determining the high priority behavior that the object is not detected, that is, the initial attitude generation based on the object is accidentally opened
In the case of dynamic, stop obtaining second video by second image capture device.
Here, it will be understood by those skilled in the art that in the second example, based on the posture recognition sequence institute in video frame
The process for stating the high priority behavior of object is identical with the first example, here in order to avoid redundancy just repeats no more.
Therefore, it in the video data handling procedure according to the embodiment of the present application, may further include:From described initial
The first subsequent video frame after video frame detects the first follow-up posture of the object;Determine the first follow-up appearance of the object
Whether state meets first preassigned;Meet first preassigned in response to the first follow-up posture of the object,
Determine that the behavior of the object is the high priority behavior that priority is more than predetermined threshold;And it is described right in response to determining
The behavior of elephant is the high priority behavior, keeps through second image capture device acquisition including the second of object regarding
Frequently.
Also, it in above-mentioned video data handling procedure, can further include:After the first of the object
Continuous posture does not meet first preassigned, determines that the behavior of the object is not the high priority behavior;And response
It is not the high priority behavior in the behavior of the object, stops through second image capture device acquisition including object
The second video.
In the video data handling procedure according to the embodiment of the present application, pass through second image capture device in triggering
After obtaining second video, it can still maintain and first video is obtained by described first image collecting device.This
Sample can detect the posture of the object, so that it is determined that the behavior of the object from the video frame of first video.By institute
Stating the first video has low resolution, this can reduce time and resource consumption needed for gesture recognition.
While second image capture device obtains second video, after first subsequent video frame
The second subsequent video frame continue to detect the second follow-up posture of the object, and determine whether the second follow-up posture meets
Second preassigned.Here, the first above-mentioned preassigned is for judging whether the posture of the object needs to pay close attention to
The standard of particular pose, and the second preassigned here is for judging whether the posture of the object reflects the needs of object
The end of the high priority behavior of concern.Come for example, people regains one's feet after falling down, human body attitude experienced from the posture that leans forward
Revert to the process of midstance.Alternatively, people has stopped getting off after running, human body attitude also experienced from pose recovery of running
For the process of walk about posture or midstance.Therefore, whether meet second by the second follow-up posture of the determination object
Preassigned, it may be determined that whether the high priority behavior that the needs of the object are paid close attention to terminates.Also, in the height of the object
In the case that priority behavior terminates, stop passing through the second video that second image capture device acquisition includes object.
That is, in the video data handling procedure according to the embodiment of the present application, may further include:After described first
The second subsequent video frame after continuous video frame detects the second follow-up posture of the object;Determine the second follow-up of the object
Whether posture meets the second preassigned;Meet second preassigned in response to the second follow-up posture of the object, really
The high priority behavior of the fixed object terminates;And terminate in response to the high priority behavior of the object, stopping passes through institute
State the second video that the acquisition of the second image capture device includes object.
Here, it will be understood by those skilled in the art that it is described above based on being obtained with described first image collecting device
First video detects the beginning and end of the specific behavior of the object.But it is set triggering second Image Acquisition
It is standby obtain second video in the case of, the specific behavior of the object can be equally determined based on second video
Beginning and end.
First video is being obtained by described first image collecting device and passes through second image capture device
After obtaining second video, first video and second video can be further stored, is regarded for subsequent
Frequency handles and the operations such as inquiry.
In addition, as described above, if the first follow-up appearance detected in the first subsequent video frame of first video
State does not meet first preassigned, then illustrates that the behavior of the object is not the high priority behavior.In this way, due to not
The behavior for needing to pay special attention to the object stored in second video, can delete second video, be deposited with reducing
Store up the occupancy in space.
That is, in above-mentioned video data handling procedure, may further include:In response to the first follow-up appearance of the object
State does not meet first preassigned, determines that the behavior of the object is not the high priority behavior;And in response to institute
The behavior for stating object is not the high priority behavior, deletes second video.
Fig. 5 illustrates the flow chart of the video data acquiring process according to the embodiment of the present application.As shown in figure 5, in step
S310 starts low resolution camera.In step S320, low-resolution image is acquired with low resolution camera.In step
S330 obtains the posture information of object from the low-resolution image.In step S340, classified based on preset posture, behavior
Standard and the definition of the priority of behavior, by pattern-recognition and behavior grade separation, obtain the behavior class of the behavior of the object
Other information and precedence information.Next, in step S350, judge whether the behavior of the object is high priority behavior.
Step S360, the behavior in response to the object are high priority behaviors, start high-resolution camera.In step S370, with
High-resolution camera acquires high-definition picture.Finally, in step S380, high-definition picture is stored.In addition, equally in step
Rapid S280, the behavior in response to the object are not high priority behaviors, store low-resolution image.Also, in step S380
The behavior classification information and precedence information of the behavior for the object that step S340 before can also being stored in is obtained, this will
It is further illustrated below.
That is, during above-mentioned video data acquiring, using high-resolution and low resolution camera while work
Make, obtains image information.Wherein, low resolution camera is acquired and is stored image information in real time, is carried out at the same time object
The Activity recognition of gesture recognition and segment, and based on the given expression video frame of preset Anomaly standard (as lain down, falling down)
Critical precedence information, posture result, behavior label (that is, behavior classification information and/or precedence information) and described
The associated video segment information of behavior simultaneously stores.In addition, if it is high exception level, then high-resolution camera acquisition image is triggered
And store the label information of the behavior.
In addition, in the storing process of first video and second video, since second video includes closing
In the key message for the object behavior for needing to pay close attention to, and first video includes more general object behavior, therefore, with
Little compressible stores second video, while storing first video with high compression rate, to obtain better memory space
Utilization ratio.
It, can be according to the key of the video of acquisition when the capacity of storage device is by limited time that is, when video stores
Property distinguishing property of information compression.The video frame of low exception level is stored using high compression rate, and the video frame of high exception level is adopted
It is stored with little compressible.In this way, by storing compressed video, the capacity of storage device can be discharged.
Also, if the memory capacity of the storage device is less than predetermined threshold, it can preferentially retain second video,
And delete at least part of first video.
As described above, during storing first video and second video, in addition to storage described first regards
Other than the behavior classification information and precedence information of the object behavior of frequency and second video, described first can also be stored and regarded
The temporal information of frequency and second video.In this way, when deleting at least part of first video, can be based on described
The temporal information of first video deletes in first video time one or more video frame earlier, that is, have indicate compared with
One or more video frame of the temporal information of early time.
That is, when the memory capacity of storage device with high compression rate coding by that still cannot meet lasting recording
When demand, the deletion for carrying out storage content is needed to carry out Free up Memory.It is sorted according to the time order and function of video record, while to figure
As the priority of frame and video-frequency band is ranked up, retain the high video frame information of priority, at the same delete priority it is low and when
Between early video frame information, thus the memory capacity of storage device is discharged.
Fig. 6 illustrates the flow chart of the video data storing process according to the embodiment of the present application.As shown in fig. 6, first,
Step S410 obtains the precedence information of video and behavior.Then, in step S420, determine whether the behavior of object is Gao You
First grade behavior.If it is high priority behavior, then lossless or little compressible coding is carried out, and if not high priority row
For, then it is damaged or high compression rate encodes, and in step S430, the information after being encoded.Next, in step
S440 obtains the currently active memory space of storage device.Also, in step S450, whether judgement memory capacity is insufficient.In step
Rapid S460, if it is decided that lack of memory capacity then carries out time-sequencing according to the temporal information of video to video frame.Finally, exist
Step S470 deletes current earliest low priority video frame, while retaining high priority video frame, and return to step S440,
Obtain the currently active memory space of storage device.
Here, it will be understood by those skilled in the art that in the video data handling procedure according to the embodiment of the present application, and
It is not required the temporal information of storage first video and second video, or first video and institute must be stored
State the behavior classification information and precedence information of the behavior of the object in the second video.If at subsequent video data
Above- mentioned information need not be applied in reason, then need not store information above.For example, if the memory capacity of storage device is very big,
Erasing time video frame earlier is not needed, then need not then store the temporal information of video.
In addition, in the behavior classification information and precedence information of the behavior for storing first video and second video
In the case of, the behavior label of the behavior of the object can be generated based on described information, to which identification record has the object
Specific behavior second video.Also, the behavior label of the behavior based on the object can be generated further described
The breviary information of second video, for example, the thumbnail of second video.
Specifically, the behavior classification information of the behavior based on the object and the precedence information can select to remember
Record has in initial video frame or the first subsequent video frame in first video of the particular pose of the object at least
One, it is used as the breviary information of second video.
Therefore, in the video data handling procedure according to the embodiment of the present application, during checking video, Ke Yigen
The key label and posture, behavioural information stored while according to storage video, generates representative frame or representative segment, with
Convenient for fast browsing.
Also, when storing video, temporal information, behavior classification information and precedence information that can be based on the video
At least one of video is segmented.For example, video is divided into multiple video-frequency bands according to time order and function, wherein individually
Video-frequency band indicates the behavior of some classification, or the behavior with different priorities.For example, in people during falling down, according to
Temporal information, behavior classification information and precedence information, respectively storage table let others have a look at the regarding of the normal walking behavior before falling down
Frequently, the video (including people from the process got up on the ground) for falling down process of people and people continue normal walking after standing up
Video.
In this way, in subsequent video frequency searching, key label when being stored according to video and posture, behavioural information,
It can also object-based posture and behavior progress quick-searching.It specifically, can be based on the row of the behavior of the object
For classification information, retrieval indicates the specific behavior of object, for example, the video of people fallen down.Further, it is also possible to be based on the object
Behavior high priority message, retrieval includes the video of object behavior that needs are paid special attention to.Therefore, it is possible to reduce video is examined
The hand labor expended when rope.
That is, in the video data handling procedure according to the embodiment of the present application, may further include:Based on institute
State first video of at least one of temporal information, the behavior classification information and described precedence information retrieval storage
With second video.
For example, the video content to be retrieved or thumbnail image or video skimming can be checked according to time or period.
The video content to be retrieved or thumbnail image or video skimming can be checked according to the type of posture.It can also be according to behavior
Priority level comes the video content to be retrieved or thumbnail image or video skimming.
Therefore, according to the video data handling procedure of the embodiment of the present application, it can be based on object, such as the posture of human body is known
Not, Activity recognition detects crucial video frame either video clip also, key based on video frame or video clip,
Distinction acquisition, compression, storage, the capacity release of video are carried out, and quickly checks and retrieves.It is set in this way, improving storage
Standby effective storage capacity reduces the storage burden of storage device.Also, since the video clip of storage is convenient for inquiry and inspection
Rope, the user experience is improved.
Exemplary means
Fig. 7 illustrates the block diagram of the video data processing apparatus according to the embodiment of the present application.
As shown in fig. 7, the video data processing apparatus 500 according to the embodiment of the present application includes:Acquiring unit 510, is used for
Include the first video of object by the acquisition of the first image capture device, described first image collecting device has first to differentiate
Rate;The initial video frame of detection unit 520, the first video for being obtained from the acquiring unit 510 detects the object
Initial attitude;Determination unit 530, for determining whether the initial attitude of the object that the detection unit 520 is detected accords with
Close the first preassigned;And control unit 540, the initial appearance for determining the object in response to the determination unit 530
State meets first preassigned, triggering obtained by the second image capture device include object the second video, described the
Two image capture devices have second resolution, and the second resolution is higher than the first resolution.
In one example, in above-mentioned video data processing apparatus 500, the detection unit 520 is further used for ringing
The initial attitude of object described in Ying Yu meets first preassigned, from the first subsequent video after the initial video frame
Frame detects the first follow-up posture of the object;The determination unit 530 is further used for determining the first follow-up of the object
Whether posture meets first preassigned, and to meet described first predetermined in response to the first follow-up posture of the object
Standard determines that the behavior of the object is the high priority behavior that priority is more than predetermined threshold;And described control unit 540
For in response to determining that the behavior of the object is the high priority behavior, triggering to pass through second image capture device
Acquisition includes the second video of object.
In one example, in above-mentioned video data processing apparatus 500, the detection unit 520 be further used for from
The first subsequent video frame after the initial video frame detects the first follow-up posture of the object;The determination unit 530
It is further used for determining whether the first follow-up posture of the object meets first preassigned, and in response to described right
The first follow-up posture of elephant meets first preassigned, determines that the behavior of the object is that priority is more than predetermined threshold
High priority behavior;And described control unit 540 is used in response to determining that the behavior of the object is the high priority
Behavior keeps passing through the second video that second image capture device acquisition includes object.
In one example, in above-mentioned video data processing apparatus 500, the determination unit 530 is further used for ringing
First follow-up posture of object described in Ying Yu does not meet first preassigned, determines that the behavior of the object is not the height
Priority behavior;And behavior of the described control unit 540 in response to the object is not the high priority behavior, is stopped
It include only the second video of object by second image capture device acquisition.
In one example, in above-mentioned video data processing apparatus 500, the determination unit 530 is used for:Based on described
The behavior of object described in first follow-up gesture recognition of the initial attitude of initial video frame and first subsequent video frame;With
And determine that the behavior of the object is the high priority behavior based on the behavior classification information of the behavior of the object.
In one example, in above-mentioned video data processing apparatus 500, described control unit 540 is further used for
After triggering obtains second video by second image capture device, keep passing through described first image collecting device
Obtain first video.
In one example, in above-mentioned video data processing apparatus 500, the detection unit 520 be further used for from
The second subsequent video frame after first subsequent video frame detects the second follow-up posture of the object;The determination unit
530 are further used for determining whether the second follow-up posture of the object meets the second preassigned, and in response to described right
The second follow-up posture of elephant meets second preassigned, determines that the high priority behavior of the object terminates;And it is described
Control unit 540 is further used for terminating in response to the high priority behavior of the object, and stopping is adopted by second image
Collection equipment acquisition includes the second video of object.
In one example, in above-mentioned video data processing apparatus 500, further comprise storage unit, for storing
First video and second video.
In one example, in above-mentioned video data processing apparatus 500, the determination unit 530 is further used for ringing
First follow-up posture of object described in Ying Yu does not meet first preassigned, determines that the behavior of the object is not the height
Priority behavior;And behavior of the described control unit 540 in response to the object is not the high priority behavior, is deleted
Except second video.
In one example, in above-mentioned video data processing apparatus 500, the storage unit with high compression rate for being deposited
Store up first video;And second video is stored with little compressible.
In one example, in above-mentioned video data processing apparatus 500, the storage unit be further used for storage with
Under at least one:The temporal information of first video and second video;And first video and described
The behavior classification information and precedence information of the behavior of the object in second video.
In one example, in above-mentioned video data processing apparatus 500, further comprise breviary information generating unit,
Breviary information for generating second video based on the behavior classification information and the precedence information.
In one example, in above-mentioned video data processing apparatus 500, the breviary information generating unit is used for:Base
The initial video frame and the first subsequent video of first video are selected in the behavior classification information and the precedence information
Breviary information of at least one of the frame as second video.
In one example, in above-mentioned video data processing apparatus 500, the storage unit is further used for:It determines
Whether memory capacity is less than predetermined threshold;And it is less than predetermined threshold in response to the memory capacity, delete first video
At least part.
In one example, in above-mentioned video data processing apparatus 500, at least part of first video is institute
Stating has the one or more video frame for the temporal information for indicating earlier time in the first video.
In one example, in above-mentioned video data processing apparatus 500, further comprise retrieval unit, for being based on
Described the first of at least one of the temporal information, the behavior classification information and described precedence information retrieval storage regards
Frequency and second video.
The concrete function of each unit and module in above-mentioned video data processing apparatus 500 and operation have been described above ginseng
It examines and is discussed in detail in the video data handling procedure of Fig. 1 to Fig. 6 descriptions, and therefore, its repeated description will be omitted.
As described above, may be implemented in video data processing according to the video data processing apparatus 500 of the embodiment of the present application
In equipment, which can be that the first image capture device 110 and the second Image Acquisition as shown in Figure 1 are set
Standby any of 120 or both, can also be and their independent stand-alone devices.
In one example, a software mould can be used as according to the video data processing apparatus of the embodiment of the present application 500
Block and/or hardware module and be integrated into the video data processing device.For example, the video data processing apparatus 500 can be
A software module in the operating system of the video data processing device, or can be directed to video data processing to set
The standby application program developed;Certainly, which equally can be the video data processing device
One of numerous hardware modules.
Alternatively, in another example, which can also be with the video data processing device
Discrete equipment, and the video data processing apparatus 400 can be connected to the video data by wired and or wireless network
Processing equipment, and transmit interactive information according to the data format of agreement.
Example electronic device
In the following, being described with reference to Figure 8 the electronic equipment according to the embodiment of the present application.The electronic equipment can be integrated with first
It any of image capture device 110 and the second image capture device 120 or both or is set with their independent single machines
Standby, which can be communicated with the first image capture device and the second image capture device, to receive institute from them
Collected input signal.
Fig. 8 illustrates the block diagram of the electronic equipment according to the embodiment of the present application.
As shown in figure 8, electronic equipment 10 includes one or more processors 11 and memory 12.
Processor 8 can be central processing unit (CPU) or with data-handling capacity and/or instruction execution capability
The processing unit of other forms, and can be with the other assemblies in control electronics 10 to execute desired function.
Memory 12 may include one or more computer program products, and the computer program product may include each
The computer readable storage medium of kind form, such as volatile memory and/or nonvolatile memory.The volatile storage
Device is such as may include random access memory (RAM) and/or cache memory (cache).It is described non-volatile to deposit
Reservoir is such as may include read-only memory (ROM), hard disk, flash memory.It can be deposited on the computer readable storage medium
The one or more computer program instructions of storage, processor 11 can run described program instruction, to realize this Shen described above
The video data handling procedure of each embodiment please and/or other desired functions.In the computer-readable storage
It is each that behavior classification information, precedence information of the behavior of the first video, the second video, object etc. can also be stored in medium
Kind content.
In one example, electronic equipment 10 can also include:Input unit 13 and output device 14, these components pass through
Bindiny mechanism's (not shown) interconnection of bus system and/or other forms.
For example, when the electronic equipment is integrated with the first image capture device 110 and the second image capture device 120, it should
Input unit 13 can be the first image capture device 110 and the second image capture device 120, such as camera, for shooting
Video including object.When the electronic equipment is stand-alone device, which can be communication network connector, be used for
Acquired input signal is received from the first image capture device 110 and the second image capture device 120.
In addition, the input equipment 13 can also include such as keyboard, mouse etc..
The output device 14 can be output to the outside various information, including video data and object behavior information etc..
The output equipment 14 may include such as display, loud speaker, printer and communication network and its long-range output that is connected
Equipment etc..
Certainly, to put it more simply, illustrating only some in the electronic equipment 10 in component related with the application in Fig. 8,
The component of such as bus, input/output interface etc. is omitted.In addition to this, according to concrete application situation, electronic equipment 10 is also
It may include any other component appropriate.
Illustrative computer program product and computer readable storage medium
Other than the above method and equipment, embodiments herein can also be computer program product comprising meter
Calculation machine program instruction, it is above-mentioned that the computer program instructions make that the processor executes this specification when being run by processor
The step in the video data handling procedure according to the various embodiments of the application described in " illustrative methods " part.
The computer program product can be write with any combination of one or more programming languages for holding
The program code of row the embodiment of the present application operation, described program design language includes object oriented program language, such as
Java, C++ etc. further include conventional procedural programming language, such as " C " language or similar programming language.Journey
Sequence code can be executed fully, partly execute on a user device, is independent soft as one on the user computing device
Part packet executes, part executes or on a remote computing completely in remote computing device on the user computing device for part
Or it is executed on server.
In addition, embodiments herein can also be computer readable storage medium, it is stored thereon with computer program and refers to
It enables, the computer program instructions make the processor execute above-mentioned " the exemplary side of this specification when being run by processor
The step in the video data handling procedure according to the various embodiments of the application described in method " part.
The arbitrary combination of one or more readable mediums may be used in the computer readable storage medium.Readable medium can
To be readable signal medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can include but is not limited to electricity, magnetic, light, electricity
Magnetic, the system of infrared ray or semiconductor, device or device, or the arbitrary above combination.Readable storage medium storing program for executing it is more specific
Example (non exhaustive list) includes:Electrical connection, portable disc with one or more conducting wires, hard disk, random access memory
Device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The basic principle of the application is described above in association with specific embodiment, however, it is desirable to, it is noted that in this application
The advantages of referring to, advantage, effect etc. are only exemplary rather than limitation, must not believe that these advantages, advantage, effect etc. are the application
Each embodiment is prerequisite.In addition, detail disclosed above is merely to exemplary effect and the work being easy to understand
With, and it is unrestricted, it is that must be realized using above-mentioned concrete details that above-mentioned details, which is not intended to limit the application,.
The block diagram of device, device, equipment, system involved in the application only as illustrative example and is not intended to
It is required that or hint must be attached in such a way that box illustrates, arrange, configure.As those skilled in the art will appreciate that
, it can be connected by any way, arrange, configure these devices, device, equipment, system.Such as "include", "comprise", " tool
" etc. word be open vocabulary, refer to " including but not limited to ", and can be used interchangeably with it.Vocabulary used herein above
"or" and " and " refer to vocabulary "and/or", and can be used interchangeably with it, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be used interchangeably with it.
It may also be noted that in the device of the application, device and method, each component or each step are can to decompose
And/or reconfigure.These decompose and/or reconfigure the equivalent scheme that should be regarded as the application.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
Application.Various modifications in terms of these are readily apparent to those skilled in the art, and are defined herein
General Principle can be applied to other aspect without departing from scope of the present application.Therefore, the application is not intended to be limited to
Aspect shown in this, but according to the widest range consistent with principle disclosed herein and novel feature.
In order to which purpose of illustration and description has been presented for above description.In addition, this description is not intended to the reality of the application
It applies example and is restricted to form disclosed herein.Although already discussed above multiple exemplary aspects and embodiment, this field skill
Art personnel will be recognized that its certain modifications, modification, change, addition and sub-portfolio.
Claims (18)
1. a kind of video data handling procedure, including:
Include the first video of object by the acquisition of the first image capture device, described first image collecting device has first point
Resolution;
The initial attitude of the object is detected from the initial video frame of first video;
Determine whether the initial attitude of the object meets the first preassigned;And
Meet first preassigned in response to the initial attitude of the object, triggering is obtained by the second image capture device
The second video including object, second image capture device has second resolution, and the second resolution is higher than institute
State first resolution.
2. video data handling procedure as described in claim 1, wherein in response to the object initial attitude meet it is described
First preassigned, triggering include by the second video that the acquisition of the second image capture device includes object:
Meet first preassigned in response to the initial attitude of the object, after first after the initial video frame
Continuous video frame detects the first follow-up posture of the object;
Determine whether the first follow-up posture of the object meets first preassigned;
Meet first preassigned in response to the first follow-up posture of the object, determines that the behavior of the object is preferential
Grade is more than the high priority behavior of predetermined threshold;And
In response to determining that the behavior of the object is the high priority behavior, triggering passes through second image capture device
Acquisition includes the second video of object.
3. video data handling procedure as described in claim 1, further comprises:
The first follow-up posture of the object is detected from the first subsequent video frame after the initial video frame;
Determine whether the first follow-up posture of the object meets first preassigned;
Meet first preassigned in response to the first follow-up posture of the object, determines that the behavior of the object is preferential
Grade is more than the high priority behavior of predetermined threshold;And
In response to determining that the behavior of the object is the high priority behavior, keep passing through second image capture device
Acquisition includes the second video of object.
4. video data handling procedure as claimed in claim 3, further comprises:
First preassigned is not met in response to the first follow-up posture of the object, determines that the behavior of the object is not
The high priority behavior;And
Behavior in response to the object is not the high priority behavior, stops obtaining by second image capture device
The second video including object.
5. the video data handling procedure as described in claim 2 or 3, wherein determine that the behavior of the object is priority
High priority behavior more than predetermined threshold includes:
Initial attitude based on the initial video frame and described in the first follow-up gesture recognition of first subsequent video frame it is right
The behavior of elephant;And
Determine that the behavior of the object is the high priority behavior based on the behavior classification information of the behavior of the object.
6. the video data handling procedure as described in claim 2 or 3, further comprises:
After triggering through second image capture device acquisition, second video, holding is adopted by described first image
Collect equipment and obtains first video.
7. the video data handling procedure as described in claim 2 or 3, further comprises:
The second follow-up posture of the object is detected from the second subsequent video frame after first subsequent video frame;
Determine whether the second follow-up posture of the object meets the second preassigned;
Meet second preassigned in response to the second follow-up posture of the object, determines the high priority row of the object
To terminate;And
High priority behavior in response to the object terminates, and stops through second image capture device acquisition including object
The second video.
8. the video data handling procedure as described in claim 2 or 3, further comprises:
Store first video and second video.
9. video data handling procedure as claimed in claim 8, further comprises:
First preassigned is not met in response to the first follow-up posture of the object, determines that the behavior of the object is not
The high priority behavior;And
Behavior in response to the object is not the high priority behavior, deletes second video.
10. video data handling procedure as claimed in claim 8, wherein store first video and second video
Including:
First video is stored with high compression rate;And
Second video is stored with little compressible.
11. video data handling procedure as claimed in claim 8, wherein store first video and second video
Including store it is below at least one:
The temporal information of first video and second video;And
The behavior classification information and precedence information of the behavior of first video and the object in second video.
12. video data handling procedure as claimed in claim 11, further comprises:
The breviary information of second video is generated based on the behavior classification information and the precedence information.
13. video data handling procedure as claimed in claim 12, wherein based on the behavior classification information and described preferential
Grade information generates the breviary information of second video and includes:
After the initial video frame and first for selecting first video based on the behavior classification information and the precedence information
Breviary information of at least one of the continuous video frame as second video.
14. video data handling procedure as claimed in claim 11, further comprises:
Determine whether memory capacity is less than predetermined threshold;
It is less than predetermined threshold in response to the memory capacity, deletes at least part of first video.
15. video data handling procedure as claimed in claim 14, wherein at least part of first video is described
There are the one or more video frame for the temporal information for indicating earlier time in first video.
16. video data handling procedure as claimed in claim 10, further comprises:
Institute based on the retrieval storage of at least one of the temporal information, the behavior classification information and described precedence information
State the first video and second video.
17. a kind of video data processing apparatus, including:
Acquiring unit, for including the first video of object, described first image acquisition by the acquisition of the first image capture device
Equipment has first resolution;
Detection unit, the initial attitude for detecting the object from the initial video frame of first video;
Determination unit, for determining whether the initial attitude of the object meets the first preassigned;And
Control unit, for meeting first preassigned in response to the initial attitude of the object, triggering passes through the second figure
As collecting device obtain include object the second video, second image capture device is with second resolution, and described the
Two high resolutions are in the first resolution.
18. a kind of electronic equipment, including:
Processor;And
Memory is stored with computer program instructions in the memory, and the computer program instructions are by the processing
Device makes the processor execute the video data handling procedure as described in any one of claim 1-16 when running.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810067998.5A CN108289201B (en) | 2018-01-24 | 2018-01-24 | Video data processing method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810067998.5A CN108289201B (en) | 2018-01-24 | 2018-01-24 | Video data processing method and device and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108289201A true CN108289201A (en) | 2018-07-17 |
CN108289201B CN108289201B (en) | 2020-12-25 |
Family
ID=62835601
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810067998.5A Active CN108289201B (en) | 2018-01-24 | 2018-01-24 | Video data processing method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108289201B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109259726A (en) * | 2018-08-19 | 2019-01-25 | 天津大学 | A kind of automatic grasp shoot method of tongue picture based on bidirectional imaging |
CN110826506A (en) * | 2019-11-11 | 2020-02-21 | 上海秒针网络科技有限公司 | Target behavior identification method and device |
WO2020172809A1 (en) * | 2019-02-27 | 2020-09-03 | 深圳市大疆创新科技有限公司 | Method for video playback by photography apparatus and photography apparatus |
CN112514373A (en) * | 2018-08-14 | 2021-03-16 | 华为技术有限公司 | Image processing apparatus and method for feature extraction |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593268A (en) * | 2008-05-30 | 2009-12-02 | 深圳市普罗巴克科技股份有限公司 | A kind of multiresolution fingerprint identification method and multiresolution fingerprint recognition system |
CN202026403U (en) * | 2011-01-24 | 2011-11-02 | 南京壹进制信息技术有限公司 | Monitoring device capable of dynamically regulating resolution based on sensitive information |
CN102880854A (en) * | 2012-08-16 | 2013-01-16 | 北京理工大学 | Distributed processing and Hash mapping-based outdoor massive object identification method and system |
CN104394389A (en) * | 2014-12-15 | 2015-03-04 | 成都鼎智汇科技有限公司 | Intelligent distribution type video monitoring system |
CN104598897A (en) * | 2015-02-12 | 2015-05-06 | 杭州摩图科技有限公司 | Visual sensor, image processing method and device and visual interactive device |
US20150269731A1 (en) * | 2014-03-19 | 2015-09-24 | Vivotek Inc. | Device, method for image analysis and computer-readable medium |
CN105227929A (en) * | 2015-10-16 | 2016-01-06 | 中国民航科学技术研究院 | A kind of safety monitoring device for airport |
CN106303390A (en) * | 2015-06-02 | 2017-01-04 | 联想(北京)有限公司 | Image-pickup method and device thereof, image transfer method and device thereof |
CN107516074A (en) * | 2017-08-01 | 2017-12-26 | 广州杰赛科技股份有限公司 | A kind of certification recognition methods and system |
-
2018
- 2018-01-24 CN CN201810067998.5A patent/CN108289201B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593268A (en) * | 2008-05-30 | 2009-12-02 | 深圳市普罗巴克科技股份有限公司 | A kind of multiresolution fingerprint identification method and multiresolution fingerprint recognition system |
CN202026403U (en) * | 2011-01-24 | 2011-11-02 | 南京壹进制信息技术有限公司 | Monitoring device capable of dynamically regulating resolution based on sensitive information |
CN102880854A (en) * | 2012-08-16 | 2013-01-16 | 北京理工大学 | Distributed processing and Hash mapping-based outdoor massive object identification method and system |
US20150269731A1 (en) * | 2014-03-19 | 2015-09-24 | Vivotek Inc. | Device, method for image analysis and computer-readable medium |
CN104394389A (en) * | 2014-12-15 | 2015-03-04 | 成都鼎智汇科技有限公司 | Intelligent distribution type video monitoring system |
CN104598897A (en) * | 2015-02-12 | 2015-05-06 | 杭州摩图科技有限公司 | Visual sensor, image processing method and device and visual interactive device |
CN106303390A (en) * | 2015-06-02 | 2017-01-04 | 联想(北京)有限公司 | Image-pickup method and device thereof, image transfer method and device thereof |
CN105227929A (en) * | 2015-10-16 | 2016-01-06 | 中国民航科学技术研究院 | A kind of safety monitoring device for airport |
CN107516074A (en) * | 2017-08-01 | 2017-12-26 | 广州杰赛科技股份有限公司 | A kind of certification recognition methods and system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112514373A (en) * | 2018-08-14 | 2021-03-16 | 华为技术有限公司 | Image processing apparatus and method for feature extraction |
CN112514373B (en) * | 2018-08-14 | 2023-09-15 | 华为技术有限公司 | Image processing apparatus and method for feature extraction |
CN109259726A (en) * | 2018-08-19 | 2019-01-25 | 天津大学 | A kind of automatic grasp shoot method of tongue picture based on bidirectional imaging |
WO2020172809A1 (en) * | 2019-02-27 | 2020-09-03 | 深圳市大疆创新科技有限公司 | Method for video playback by photography apparatus and photography apparatus |
CN110826506A (en) * | 2019-11-11 | 2020-02-21 | 上海秒针网络科技有限公司 | Target behavior identification method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108289201B (en) | 2020-12-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11113587B2 (en) | System and method for appearance search | |
US9665777B2 (en) | System and method for object and event identification using multiple cameras | |
CN108289201A (en) | Video data handling procedure, device and electronic equipment | |
US8971585B2 (en) | Image processing apparatus for retrieving object from moving image and method thereof | |
US10380603B2 (en) | Assessing personality and mood characteristics of a customer to enhance customer satisfaction and improve chances of a sale | |
CN107590473B (en) | Human face living body detection method, medium and related device | |
CN105681749A (en) | Method, device and system for previewing videos and computer readable media | |
KR101996371B1 (en) | System and method for creating caption for image and computer program for the same | |
CN108229289B (en) | Target retrieval method and device and electronic equipment | |
CN109986553B (en) | Active interaction robot, system, method and storage device | |
US11157549B2 (en) | Emotional experience metadata on recorded images | |
JP5552946B2 (en) | Face image sample collection device, face image sample collection method, program | |
KR20210041856A (en) | Method and apparatus for generating learning data required to learn animation characters based on deep learning | |
CN115871679A (en) | Driver fatigue detection method, driver fatigue detection device, electronic device, and medium | |
CN114245232A (en) | Video abstract generation method and device, storage medium and electronic equipment | |
US10541006B2 (en) | Information processor, information processing method, and program | |
JP2018137639A (en) | Moving image processing system, encoder and program, decoder and program | |
JP4449483B2 (en) | Image analysis apparatus, image analysis method, and computer program | |
CN111209807A (en) | Yolov 3-based video structuring method and system | |
KR102589150B1 (en) | Long-distance object detection system using cumulative difference image | |
CN116433939B (en) | Sample image generation method, training method, recognition method and device | |
JP2009129006A (en) | Image analysis apparatus and image analysis system | |
CN112784634A (en) | Video information processing method, device and system | |
CN117079191A (en) | Rapid scoring method for intelligent experiment platform | |
DeCamp | Headlock: Wide-range head pose estimation for low resolution video |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |