CN108664912A - A kind of information processing method, device, computer storage media and terminal - Google Patents
A kind of information processing method, device, computer storage media and terminal Download PDFInfo
- Publication number
- CN108664912A CN108664912A CN201810419877.2A CN201810419877A CN108664912A CN 108664912 A CN108664912 A CN 108664912A CN 201810419877 A CN201810419877 A CN 201810419877A CN 108664912 A CN108664912 A CN 108664912A
- Authority
- CN
- China
- Prior art keywords
- image
- target object
- active state
- information processing
- preset
- 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
-
- 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
- G06V20/47—Detecting features for summarising video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
A kind of information processing method, device, computer storage media and terminal, including：Obtain the action message of target in video image object；The action message that statistical analysis obtains, obtains the active state of target object.The embodiment of the present invention improves the efficiency that active state analysis is carried out to target object by the action message of the acquisition target object from video image.
Description
Technical field
Present document relates to but be not limited to image processing techniques, espespecially a kind of information processing method, device, computer storage media
And terminal.
Background technology
The active state of animal is analyzed, is the important foundation for carrying out analysis management to animal；Including：According to dynamic
The active state of object is analyzed, and is driven or is gone out except certain animal in some regions；Based on to the analysis of the active state of animal, formulating and
Adjust the cultivation planning of animal.
In catering trade, after technical staff obtains video data by pre-set image collecting device, to muroid activity
It is checked and is controlled；Such as obtain the video data of recording in real time by monitoring camera in kitchen of restaurant, relevant departments
Hygienic testing staff according to certain period it is artificial check video content, determining whether there is muroid in conjunction with rear kitchen scene lives
It is dynamic；When determining the muroid activity for existing and be easy to causeing health concerns, trap is captured by setting and carries out muroid removing.
Since murine subject is small, movable secret, hair is easy by the method for artificially checking video data combination site inspection
Raw omission, the especially muroid of small volume, there is a situation where omit to be more easy to occur；In addition, artificially checking the side of video data
Method checks that process is time-consuming and laborious due to video data redundancy.After still for kitchen：Store a large amount of five cereals, meat products, vegetables etc.
The region of food materials, muroid are not often just to carry out including creeping, smelling on kitchen tools, tableware and food materials in rear kitchen in staff
It is movable to visit and gnaw etc., causes health and the safety problem such as kitchen instrument and pollution food materials after damage.According to some cycles, by working
Personnel check the video data of recording, in conjunction with site inspection, it is likely that part muroid zone of action is determined, but
It determines that muroid zone of action is often not prompt enough, and needs to expend a large amount of manpower, check the work people of video data for a long time
Member is also easy to the problem of occurring to omit muroid zone of action, muroid inefficiency, food during long-term clear control
Safety problem cannot be controlled effectively.Cannot the action of permanently effective control mouse, in turn result in more serious food security accident.
To sum up, by staff by manpower mode, can not precise and high efficiency realization muroid active state analysis, influence
The movable control of muroid, influences food hygiene and safety.
Invention content
It is the general introduction of the theme to being described in detail herein below.This general introduction is not to limit the protection model of claim
It encloses.
The embodiment of the present invention provides a kind of information processing method, device, computer storage media and terminal, can be promoted pair
Target object carries out the efficiency of active state analysis.
An embodiment of the present invention provides a kind of information processing methods, including：
Obtain the action message of target in video image object；
The action message that statistical analysis obtains, obtains the active state of target object.
Optionally, the action message for obtaining target in video image object includes：
Determine whether each frame image that the video image includes includes the target object；
The image for including the target object to each frame marks the target object according to preset image identification；
To each frame image of label described image mark, the moving position of the target object is recorded frame by frame and corresponding to work
The activity time of dynamic position.
Optionally, before the action message for obtaining target in video image object, described information processing method includes：
According to preset monitoring cycle, it is determined whether receive the video image；
Wherein, the video image includes：It is more than first by the video data that preset image acquisition device arrives
When preset duration, the length that acquisition is split to the video data of acquisition is the video clip of the first preset duration.
Optionally, the active state of the statistical analysis target object includes：
A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition,
Obtain the active state corresponding to each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or behaviour area
Domain sizes threshold value.
Optionally, before the action message for obtaining target in video image object, described information processing method is also wrapped
It includes：
It receives in the second preset duration after the video image, according to each frame image for including in the video image
Time-sequencing sequence, compare adjacent two field pictures frame by frame；
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, really
It is initial pictures to be scheduled on a later frame image；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
Optionally, each frame image of the determination whether comprising the target object include：
The initial pictures and posterior adjacent image are compared, when the initial pictures and posterior adjacent image
Pixel difference percentage be more than preset second percentage threshold when, analyze and confirm posterior adjacent image whether include
The target object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than the preset 200th
When dividing than threshold value, determined in later group phase using the posterior adjacent image as in preceding image according to the clooating sequence of time
Adjacent image；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than the preset 200th
When dividing than threshold value, analyzes and confirm whether posterior adjacent image includes the target object；When the pixel difference of adjacent image
Percentage when being less than preset second percentage threshold, according to the clooating sequence of time, made with the posterior adjacent image
In preceding image, to determine in later group adjacent image, to continue whether to include the confirmation of the target object.
Optionally, described information processing method further includes：
To being counted respectively corresponding to the active state of each active state reference parameter, each active state pair is obtained
The activity frequency answered.
Optionally, the target object includes muroid, and the active state for obtaining target object includes：
According to the action message of acquisition, activity duration of the statistical analysis muroid in the zone of action of each size；
According to the statistic analysis result of activity duration of the muroid in the zone of action of each size, determine that muroid exists
Active state in the zone of action of each size.
On the other hand, the embodiment of the present invention also provides a kind of information processing unit, including：Acquiring unit and statistical analysis list
Member；Wherein,
Acquiring unit is used for：Obtain the action message of target in video image object；
Statistical analysis unit is used for：The action message that statistical analysis obtains, obtains the active state of target object.
Optionally, the acquiring unit is specifically used for：
Determine whether each frame image that the video image includes includes the target object；
The image for including the target object to each frame marks the target object according to preset image identification；
To each frame image of label described image mark, the moving position of the target object is recorded frame by frame and corresponding to work
The activity time of dynamic position.
Optionally, described information processing unit further includes monitoring unit, is used for：According to preset monitoring cycle, determination is
It is no to receive the video image；
Wherein, the video image includes：It is more than first by the video data that preset image acquisition device arrives
When preset duration, the length that acquisition is split to the video data of acquisition is the video clip of the first preset duration.
Optionally, the statistical analysis unit is specifically used for：
A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition,
Obtain the active state corresponding to each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or behaviour area
Domain sizes threshold value.
Optionally, described information processing unit further includes initial pictures determination unit, is used for：
It receives in the second preset duration after the video image, according to each frame image for including in the video image
Time-sequencing sequence, compare adjacent two field pictures frame by frame；
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, really
It is initial pictures to be scheduled on a later frame image；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
Optionally, the acquiring unit for determine each frame image whether comprising the target object include：
The initial pictures and posterior adjacent image are compared, when the initial pictures and posterior adjacent image
Pixel difference percentage be more than preset second percentage threshold when, analyze and confirm posterior adjacent image whether include
The target object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than the preset 200th
When dividing than threshold value, determined in later group phase using the posterior adjacent image as in preceding image according to the clooating sequence of time
Adjacent image；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than the preset 200th
When dividing than threshold value, analyzes and confirm whether posterior adjacent image includes the target object；When the pixel difference of adjacent image
Percentage when being less than preset second percentage threshold, according to the clooating sequence of time, made with the posterior adjacent image
In preceding image, to determine in later group adjacent image, to continue whether to include the confirmation of the target object.
Optionally, the statistical analysis unit is additionally operable to：
To being counted respectively corresponding to the active state of each active state reference parameter, each active state pair is obtained
The activity frequency answered.
Optionally, the target object includes muroid, and the statistical analysis unit is specifically used for：
According to the action message of acquisition, activity duration of the statistical analysis muroid in the zone of action of each size；
According to the statistic analysis result of activity duration of the muroid in the zone of action of each size, determine that muroid exists
Active state in the zone of action of each size.
In another aspect, the embodiment of the present invention also provides a kind of computer storage media, deposited in the computer storage media
Computer executable instructions are contained, the computer executable instructions are for executing above- mentioned information processing method.
Further aspect, the embodiment of the present invention also provide a kind of terminal, including：Memory and processor；Wherein,
Processor is configured as executing the program instruction in memory；
Program instruction reads in processor and executes following operation：
Obtain the action message of target in video image object；
The action message that statistical analysis obtains, obtains the active state of target object.
Compared with the relevant technologies, technical scheme includes：Obtain the action message of target in video image object；System
The action message that meter analysis obtains, obtains the active state of target object.The embodiment of the present invention from video image by obtaining
The action message of target object improves the efficiency that active state analysis is carried out to target object.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The purpose of the present invention and other advantages can be by specification, rights
Specifically noted structure is realized and is obtained in claim and attached drawing.
Description of the drawings
Attached drawing is used for providing further understanding technical solution of the present invention, and a part for constitution instruction, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is the flow chart of information processing method of the embodiment of the present invention；
Fig. 2 is the structure diagram of information processing unit of the embodiment of the present invention.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature mutually can arbitrarily combine.
Step shown in the flowchart of the accompanying drawings can be in the computer system of such as a group of computer-executable instructions
It executes.Also, although logical order is shown in flow charts, and it in some cases, can be with suitable different from herein
Sequence executes shown or described step.
Fig. 1 is the flow chart of information processing method of the embodiment of the present invention, as shown in Figure 1, including：
Step 101, the action message for obtaining target in video image object；
Optionally, the action message of acquisition of embodiment of the present invention target in video image object includes：
Determine whether each frame image that the video image includes includes the target object；
The image for including target object to each frame, according to preset image identification marking target body；
To each frame image of label described image mark, the moving position of the target object is recorded frame by frame and corresponding to work
The activity time of dynamic position.
It should be noted that the method for identification target object, can apply the spy of existing target object in the related technology
Sign data carry out analysis determination.
Optionally, before the action message for obtaining target in video image object, information processing method of the embodiment of the present invention
Including：According to preset monitoring cycle, it is determined whether receive the video image；
Wherein, video image includes：It is default to be more than first by the video data that preset image acquisition device arrives
When duration, the length that acquisition is split to the video data of acquisition is the video clip of the first preset duration.Here, first is pre-
If duration can carry out analysis by those skilled in the art and determine according to requirement of real-time；Such as the first preset duration of setting is
1 hour.
It is configured it should be noted that monitoring cycle is referred to requirement of real-time, such as setting monitoring cycle is 30
Second.
Optionally, before the action message for obtaining target in video image object, information processing method of the embodiment of the present invention
Further include：
It receives in the second preset duration after the video image, according to each frame image for including in the video image
Time-sequencing sequence, compare adjacent two field pictures frame by frame；
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, really
It is initial pictures to be scheduled on a later frame image；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
The action message that step 102, statistical analysis obtain, obtains the active state of target object.
Optionally, the active state of the embodiment of the present invention, statistical analysis target object includes：
A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition,
Obtain the active state corresponding to each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or behaviour area
Domain sizes threshold value.
Optionally, the embodiment of the present invention determine each frame image whether comprising the target object include：
The initial pictures and posterior adjacent image are compared, when the initial pictures and posterior adjacent image
Pixel difference percentage be more than preset second percentage threshold when, analyze and confirm posterior adjacent image whether include
The target object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than the preset 200th
When dividing than threshold value, determined in later group phase using the posterior adjacent image as in preceding image according to the clooating sequence of time
Adjacent image；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than the preset 200th
When dividing than threshold value, analyzes and confirm whether posterior adjacent image includes the target object；When the pixel difference of adjacent image
Percentage when being less than preset second percentage threshold, according to the clooating sequence of time, made with the posterior adjacent image
In preceding image, to determine in later group adjacent image, to continue whether to include the confirmation of the target object.
Optionally, after obtaining active state, information processing method of the embodiment of the present invention further includes：
To being counted respectively corresponding to the active state of each active state reference parameter, each active state pair is obtained
The activity frequency answered.
Optionally, target object of the embodiment of the present invention includes muroid, obtains active state and includes：
According to the action message of acquisition, activity duration of the statistical analysis muroid in the zone of action of each size；
According to the statistic analysis result of activity duration of the muroid in the zone of action of each size, determine that muroid exists
Active state in the zone of action of each size.
The embodiment of the present invention can be applied to the active state point of other animals of other influences human lives property health
Analysis can also be applied to the husbandry sector process of other animals, by the timely analysis of the active state of target object, can and
When determine the active state of target object, the efficient control process for realizing target object.
Compared with the relevant technologies, technical scheme includes：Obtain the action message of target in video image object；System
The action message that meter analysis obtains, obtains the active state of target object.The embodiment of the present invention from video image by obtaining
The action message of target object improves the efficiency that active state analysis is carried out to target object.
Fig. 2 is the structure diagram of information processing unit of the embodiment of the present invention, as shown in Fig. 2, including：Acquiring unit and statistics
Analytic unit；Wherein,
Acquiring unit is used for：Obtain the action message of target in video image object；
Optionally, acquiring unit of the embodiment of the present invention is specifically used for：
Determine whether each frame image that the video image includes includes the target object；
The image for including target object to each frame marks the target object according to preset image identification；
To each frame image of label described image mark, the moving position of the target object is recorded frame by frame and corresponding to work
The activity time of dynamic position.
Statistical analysis unit is used for：The action message that statistical analysis obtains, obtains the active state of target object.
Optionally, information processing unit of the embodiment of the present invention further includes monitoring unit, is used for：According to preset monitoring week
Phase, it is determined whether receive the video image；
Wherein, the video image includes：It is more than first by the video data that preset image acquisition device arrives
When preset duration, the length that acquisition is split to the video data of acquisition is the video clip of the first preset duration.It needs
Bright, monitoring cycle is referred to requirement of real-time and is configured, such as setting monitoring cycle is 30 seconds.
Optionally, statistical analysis unit of the embodiment of the present invention is specifically used for：
A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition,
Obtain the active state corresponding to each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or behaviour area
Domain sizes threshold value.
Optionally, information processing unit of the embodiment of the present invention further includes initial pictures determination unit, is used for：
It receives in the second preset duration after the video image, according to each frame image for including in the video image
Time-sequencing sequence, compare adjacent two field pictures frame by frame；
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, really
It is initial pictures to be scheduled on a later frame image；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
Optionally, acquiring unit of the embodiment of the present invention for determine each frame image whether comprising the target object include：
The initial pictures and posterior adjacent image are compared, when the initial pictures and posterior adjacent image
Pixel difference percentage be more than preset second percentage threshold when, analyze and confirm posterior adjacent image whether include
The target object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than the preset 200th
When dividing than threshold value, determined in later group phase using the posterior adjacent image as in preceding image according to the clooating sequence of time
Adjacent image；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than the preset 200th
When dividing than threshold value, analyzes and confirm whether posterior adjacent image includes the target object；When the pixel difference of adjacent image
Percentage when being less than preset second percentage threshold, according to the clooating sequence of time, made with the posterior adjacent image
In preceding image, to determine in later group adjacent image, to continue whether to include the confirmation of the target object.
Optionally, statistical analysis unit of the embodiment of the present invention is additionally operable to：
To being counted respectively corresponding to the active state of each active state reference parameter, each active state pair is obtained
The activity frequency answered.
Optionally, target object of the embodiment of the present invention includes muroid, and statistical analysis unit is specifically used for：
According to the action message of acquisition, activity duration of the statistical analysis muroid in the zone of action of each size；
According to the statistic analysis result of activity duration of the muroid in the zone of action of each size, determine that muroid exists
Active state in the zone of action of each size.
The embodiment of the present invention also provides a kind of computer storage media, and computer is stored in the computer storage media
Executable instruction, the computer executable instructions are for executing above- mentioned information processing method.
The embodiment of the present invention also provides a kind of terminal, including：Memory and processor；Wherein,
Processor is configured as executing the program instruction in memory；
Program instruction reads in processor and executes following operation：
Obtain the action message of target in video image object；
The action message that statistical analysis obtains, obtains the active state of target object.
Present invention method is carried out to understand detailed description below by way of using example, is only used for using example old
The present invention is stated, is not intended to limit the scope of protection of the present invention.
Using example
This application example is illustrated by taking the camera installed indoors as an example, and camera collects video data
When, video data will be collected using one hour as unit time, segmentation obtains the video that this application example carries out information processing
Image.The video image that cutting obtains can be stored according to pre-set store path.This application example, video image
Transmitted again after being handled by the modes such as encrypting, compress, video image can be carried out according to the relevant technologies backup and
Record.
After the cutting of this application example obtains video data, the video data that cutting obtains is sent to and carries out target object activity
The server or device of information analysis；The server or device of above-mentioned carry out target object action message analysis are according to preset prison
The period is surveyed, according to preset monitoring cycle, it is determined whether receive video image；Here, monitoring cycle can be according to living
The requirement of real-time of dynamic information analysis is set；Such as could be provided as 30 seconds, since information content is small, there is no need to consider
The occupancy of bandwidth resources；
Table 1 is that store video images record information signal, as shown in table 1, has recorded reference number of a document, the storage of video image
Path, initial time and termination time further include whether video image being sent to the clothes for carrying out target object action message analysis
The transmission state of business device or device.
| Reference number of a document | Store path | Initial time | End time | Transmission state |
| 207 | /data/207.avi | 2017-12-26 05:00:00 | 2017-12-26 05:59:59 | It is processed |
| 208 | /data/208.avi | 2017-12-26 06:00:00 | 2017-12-26 06:59:59 | It is untreated |
Table 1
It receives in the second preset duration after the video image, according to each frame image for including in the video image
Time-sequencing sequence, compare adjacent two field pictures frame by frame；Here, the second preset duration can be based on calculate analyze speed into
Row determines, needs to ensure that the video image of subsequent transmission can be handled timely, meanwhile, timely processing video image can
To obtain the action message of target object in real time.
This application example can also determine whether the processing for completing the action message of target object, table 2 by processing state
The example of operation state analysis is carried out for this application example, as shown in table 1, including：Reference number of a document, into operation Queue time,
Start operation time, terminate operation time and operation state；
Table 2
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, really
It is initial pictures to be scheduled on a later frame image；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
After determining initial pictures and carrying out coordinates modeling, whether comprising target object determination is identified to each frame image；
This application example determine each frame image whether comprising target object include：
Initial pictures and posterior adjacent image are compared, when the pixel difference of initial pictures and posterior adjacent image
When different percentage is more than preset second percentage threshold, analyzes and confirm whether posterior adjacent image includes the target
Object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than preset second percentage threshold
When, it is determined in later group adjacent image using posterior adjacent image as in preceding image according to the clooating sequence of time；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than the preset 200th
When dividing than threshold value, analyzes and confirm whether posterior adjacent image includes target object；When the hundred of the pixel difference of adjacent image
When dividing than less than preset second percentage threshold, according to the clooating sequence of time, using posterior adjacent image as in preceding figure
Picture is determined in later group adjacent image, to continue whether to include the confirmation of target object.
This application example to changing smaller picture frame without analysis, that is, passes through pixel by the percentage of pixel difference
The percentage of difference filters the small picture frame of information content；
After identifying target object, this application example includes each frame the image of target object, according to preset image mark
Know marking target body；
To each frame image of label described image mark, the moving position of target object is recorded frame by frame and corresponds to activity bit
The activity time set.
Table 3 is the signal that this application example carries out action message record, as shown in table 3, including：Coordinate number, file are compiled
Number, the coordinate of activity time and moving position；Wherein, coordinate label can be the position being arranged according to camera, by this field
Technical staff analyzes the number of setting.
| Coordinate is numbered | Reference number of a document | Activity time | Moving position |
| 102 | 207 | 2017-12-26 05:02:24 | 728,730,758,760 |
| 102 | 207 | 2017-12-26 05:02:25 | 748,736,770,758 |
| 102 | 207 | 2017-12-26 05:02:26 | 768,732,788,762 |
| 102 | 207 | 2017-12-26 05:02:27 | 750,716,774,738 |
| 102 | 207 | 2017-12-26 05:02:28 | 776,768,796,704 |
| 102 | 207 | 2017-12-26 05:02:29 | 796,656,822,690 |
| 102 | 207 | 2017-12-26 05:02:30 | 820,632,844,668 |
| 102 | 207 | 2017-12-26 05:02:31 | 816,608,842,626 |
| 102 | 207 | 2017-12-26 05:02:32 | 820,600,848,622 |
| 102 | 207 | 2017-12-26 05:02:33 | 820,582,856,616 |
| 102 | 207 | 2017-12-26 05:02:34 | 830,562,858,592 |
| 102 | 207 | 2017-12-26 05:02:35 | 868,554,898,584 |
| 102 | 207 | 2017-12-26 05:02:36 | 916,550,940,586 |
Table 3
After record obtains the activity time of target object, the active state of statistical analysis target object of the embodiment of the present invention；
Specifically, may include：A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition,
Obtain the active state corresponding to each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or behaviour area
Domain sizes threshold value.
The zone of action of this application example, target object includes：
It determines after there is target object in picture frame, target object is marked by pre-set image identification,
Record the moving position of target object frame by frame according to time-sequencing and corresponding to the activity time of moving position after, according to each activity
Time for moving position, it may be determined that the zone of action of target object；
This application example, it is assumed that two groups of active state reference parameters are provided with, including：First activity duration threshold value and
First zone of action size threshold；Second activity duration threshold value and the second zone of action size threshold；Then determine object
The active state of body may include：
In the first activity duration threshold value in setting, the current active region of target object is less than the first behaviour area
When domain sizes threshold value, determine that target object is in the first active state in current active region；
In the second activity duration threshold value in setting, the current active region of target object is less than the second behaviour area
When domain sizes threshold value, determine that target object is in the second active state in current active region；
It should be noted that zone of action size threshold needs the activity based on camera installation site and target object living
Jump degree and volume size etc. carry out analysis and determine and adjust；First activity duration threshold value can be based on zone of action size
The daily routines state of threshold value base target object carries out analysis determination.
By taking muroid as an example, it is assumed that the first activity duration threshold value is 5 seconds and the first zone of action size threshold is 3 to multiply 3
Pixel region；Second activity duration threshold value is 10 seconds and the second zone of action size threshold is 10 pixel regions for multiplying 10
Domain；If muroid is in current active region when determining first group of active state reference parameter of satisfaction based on related data gnaws shape
State, muroid is in thermal point structure state in current active region when meeting second group of active state reference parameter, it is determined that muroid
Active state may include：
In 5 seconds, the current active region of muroid is less than 3 pixel regions for multiplying 3, determines muroid in current active region
In the state of gnawing；
In 10 seconds, the current active region of muroid is less than 10 pixel regions for multiplying 10, determines muroid in current active
Region is in thermal point structure state.
Based on the action message of table 3, this application example can be inserted into the judging result of active state in table 3, to be formed
The content of table 4 in table 4, is illustrated using the state of gnawing and thermal point structure state as active state：
Table 4
This application example can carry out the frequency based on above-mentioned each zone of action and corresponding to the active state of zone of action
Statistics；After the completion of frequency statistics, display can be identified in the picture.This application example can also be arranged stays work to muroid
Move, track of creeping etc. carries out judging active state reference parameter, is arranged by above-mentioned parameter, can be to the progress more such as muroid subject to
True analysis.
This application example can be combined with the state of muroid site of activity, be adjusted to above-mentioned active state reference parameter
It is whole；
Illustrating based on muroid, can be applied to include the food storages such as fresh food supermarket, kitchen region, by upper
Active state analysis is stated, realizes the processing of the movable monitoring analysis of muroid and the follow-up prevention plague of rats；Avoid the muroid activity of gnawing right
The damage of instrument and the pollution of food materials.
This application example can timely realize the active state analysis of target object, be analyzed based on active state, can be with
Target object is carried out to include the control process such as preventing, driving.
The embodiment of the present invention can be applied to the active state point of other animals of other influences human lives property health
Analysis, by the timely analysis of the active state of target object, can determine the active state of target object in time, efficient to realize
The control process of target object.
One of ordinary skill in the art will appreciate that all or part of step in the above method can be instructed by program
Related hardware (such as processor) is completed, and described program can be stored in computer readable storage medium, as read-only memory,
Disk or CD etc..Optionally, all or part of step of above-described embodiment can also be come using one or more integrated circuits
It realizes.Correspondingly, the form realization of hardware may be used in each module/unit in above-described embodiment, such as passes through integrated electricity
Its corresponding function is realized on road, can also be realized in the form of software function module, such as is stored in by processor execution
Program/instruction in memory realizes its corresponding function.The present invention is not limited to the hardware and softwares of any particular form
In conjunction with.
Although disclosed herein embodiment it is as above, the content only for ease of understanding the present invention and use
Embodiment is not limited to the present invention.Technical staff in any fields of the present invention is taken off not departing from the present invention
Under the premise of the spirit and scope of dew, any modification and variation, but the present invention can be carried out in the form and details of implementation
Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.
Claims (18)
1. a kind of information processing method, which is characterized in that including：
Obtain the action message of target in video image object；
The action message that statistical analysis obtains, obtains the active state of target object.
2. information processing method according to claim 1, which is characterized in that the acquisition target in video image object
Action message includes：
Determine whether each frame image that the video image includes includes the target object；
The image for including the target object to each frame marks the target object according to preset image identification；
To each frame image of label described image mark, the moving position of the target object is recorded frame by frame and corresponds to activity bit
The activity time set.
3. information processing method according to claim 1 or 2, which is characterized in that the acquisition target in video image object
Before the action message of body, described information processing method includes：
According to preset monitoring cycle, it is determined whether receive the video image；
Wherein, the video image includes：It is default to be more than first by the video data that preset image acquisition device arrives
When duration, the length that acquisition is split to the video data of acquisition is the video clip of the first preset duration.
4. information processing method according to claim 1 or 2, which is characterized in that the work of the statistical analysis target object
Dynamic state includes：
A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition, it obtains
Corresponding to the active state of each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or zone of action ruler
Very little threshold value.
5. information processing method according to claim 2, which is characterized in that the acquisition target in video image object
Before action message, described information processing method further includes：
Receive in the second preset duration after the video image, according to each frame image for including in the video image when
Between clooating sequence, compare adjacent two field pictures frame by frame；
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, determine
A later frame image is initial pictures；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
6. information processing method according to claim 5, which is characterized in that whether each frame image of determination is comprising described
Target object includes：
The initial pictures and posterior adjacent image are compared, when the picture of the initial pictures and posterior adjacent image
When the percentage of plain difference is more than preset second percentage threshold, analyzes and confirm posterior adjacent image whether comprising described
Target object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than preset second percentage
When threshold value, determined in later group neighbor map using the posterior adjacent image as in preceding image according to the clooating sequence of time
Picture；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than preset second percentage
When threshold value, analyzes and confirm whether posterior adjacent image includes the target object；When the hundred of the pixel difference of adjacent image
When point than being less than preset second percentage threshold, according to the clooating sequence of time, using the posterior adjacent image as
Preceding image is determined in later group adjacent image, to continue whether to include the confirmation of the target object.
7. information processing method according to claim 4, which is characterized in that described information processing method further includes：
To being counted respectively corresponding to the active state of each active state reference parameter, it is corresponding to obtain each active state
The activity frequency.
8. according to the information processing method described in claim 1,2,5 or 6, which is characterized in that the target object includes muroid,
It is described obtain target object active state include：
According to the action message of acquisition, activity duration of the statistical analysis muroid in the zone of action of each size；
According to the statistic analysis result of activity duration of the muroid in the zone of action of each size, determine muroid in each ruler
Active state in very little zone of action.
9. a kind of information processing unit, which is characterized in that including：Acquiring unit and statistical analysis unit；Wherein,
Acquiring unit is used for：Obtain the action message of target in video image object；
Statistical analysis unit is used for：The action message that statistical analysis obtains, obtains the active state of target object.
10. information processing unit according to claim 9, which is characterized in that the acquiring unit is specifically used for：
Determine whether each frame image that the video image includes includes the target object；
The image for including the target object to each frame marks the target object according to preset image identification；
To each frame image of label described image mark, the moving position of the target object is recorded frame by frame and corresponds to activity bit
The activity time set.
11. information processing unit according to claim 9 or 10, which is characterized in that described information processing unit further includes
Monitoring unit is used for：According to preset monitoring cycle, it is determined whether receive the video image；
Wherein, the video image includes：It is default to be more than first by the video data that preset image acquisition device arrives
When duration, the length that acquisition is split to the video data of acquisition is the video clip of the first preset duration.
12. information processing unit according to claim 9 or 10, which is characterized in that the statistical analysis unit is specifically used
In：
A group or more of active state reference parameters are set；
Active state reference parameter described in each group according to setting, it is for statistical analysis to the action message of acquisition, it obtains
Corresponding to the active state of each active state reference parameter；
Wherein, active state reference parameter described in each group includes corresponding：Activity duration threshold value and/or zone of action ruler
Very little threshold value.
13. information processing unit according to claim 10, which is characterized in that described information processing unit further includes initial
Image determination unit is used for：
Receive in the second preset duration after the video image, according to each frame image for including in the video image when
Between clooating sequence, compare adjacent two field pictures frame by frame；
When determining that the percentage of pixel difference of adjacent two field pictures is less than preset first percentage threshold, determine
A later frame image is initial pictures；
Coordinates modeling is carried out according to determining initial pictures, to record the moving position according to coordinates modeling.
14. information processing unit according to claim 13, which is characterized in that the acquiring unit is for determining each frame figure
Seem no includes comprising the target object：
The initial pictures and posterior adjacent image are compared, when the picture of the initial pictures and posterior adjacent image
When the percentage of plain difference is more than preset second percentage threshold, analyzes and confirm posterior adjacent image whether comprising described
Target object；When the percentage of the initial pictures and the pixel difference of posterior adjacent image is less than preset second percentage
When threshold value, determined in later group neighbor map using the posterior adjacent image as in preceding image according to the clooating sequence of time
Picture；
To determining in later group adjacent image, when the percentage of the pixel difference of adjacent image is more than preset second percentage
When threshold value, analyzes and confirm whether posterior adjacent image includes the target object；When the hundred of the pixel difference of adjacent image
When point than being less than preset second percentage threshold, according to the clooating sequence of time, using the posterior adjacent image as
Preceding image is determined in later group adjacent image, to continue whether to include the confirmation of the target object.
15. information processing unit according to claim 12, which is characterized in that the statistical analysis unit is additionally operable to：
To being counted respectively corresponding to the active state of each active state reference parameter, it is corresponding to obtain each active state
The activity frequency.
16. according to the information processing unit described in claim 9,10,13 or 14, which is characterized in that the target object includes
Muroid, the statistical analysis unit are specifically used for：
According to the action message of acquisition, activity duration of the statistical analysis muroid in the zone of action of each size；
According to the statistic analysis result of activity duration of the muroid in the zone of action of each size, determine muroid in each ruler
Active state in very little zone of action.
17. a kind of computer storage media, computer executable instructions, the calculating are stored in the computer storage media
Machine executable instruction requires the information processing method described in any one of 1~8 for perform claim.
18. a kind of terminal, including：Memory and processor；Wherein,
Processor is configured as executing the program instruction in memory；
Program instruction reads in processor and executes following operation：
Obtain the action message of target in video image object；
The action message that statistical analysis obtains, obtains the active state of target object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810419877.2A CN108664912B (en) | 2018-05-04 | 2018-05-04 | Information processing method and device, computer storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810419877.2A CN108664912B (en) | 2018-05-04 | 2018-05-04 | Information processing method and device, computer storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108664912A true CN108664912A (en) | 2018-10-16 |
| CN108664912B CN108664912B (en) | 2022-12-20 |
Family
ID=63781845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810419877.2A Active CN108664912B (en) | 2018-05-04 | 2018-05-04 | Information processing method and device, computer storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108664912B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539974A (en) * | 2020-04-07 | 2020-08-14 | 北京明略软件系统有限公司 | Method and device for determining track, computer storage medium and terminal |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303726A (en) * | 2008-06-06 | 2008-11-12 | 重庆大学 | System for tracking infrared human body target based on corpuscle dynamic sampling model |
| CN101584585A (en) * | 2009-06-08 | 2009-11-25 | 浙江大学 | Experimental system for the determination of white rat behavior |
| US20100298658A1 (en) * | 2009-05-20 | 2010-11-25 | Triage Wireless, Inc. | Graphical 'mapping system' for continuously monitoring a patient's vital signs, motion, and location |
| CN102046076A (en) * | 2008-04-03 | 2011-05-04 | Kai医药公司 | Non-contact physiologic motion sensors and methods for use |
| CN102356753A (en) * | 2011-07-01 | 2012-02-22 | 浙江大学 | Infrared thermal image tracking-based measuring and experimental system for unbiased animal behaviors |
| WO2012057860A1 (en) * | 2010-10-28 | 2012-05-03 | Medtronic, Inc. | Heart failure monitoring and notification |
| CN103577832A (en) * | 2012-07-30 | 2014-02-12 | 华中科技大学 | People flow statistical method based on spatio-temporal context |
| CN104075731A (en) * | 2013-03-12 | 2014-10-01 | 阿迪达斯股份公司 | Methods Of Determining Performance Information For Individuals And Sports Objects |
| CN104504245A (en) * | 2014-12-04 | 2015-04-08 | 吉林大学 | Method of utilizing GPS trip survey data to identify trips and activities |
| CN104573706A (en) * | 2013-10-25 | 2015-04-29 | Tcl集团股份有限公司 | Object identification method and system thereof |
| CN106303225A (en) * | 2016-07-29 | 2017-01-04 | 努比亚技术有限公司 | A kind of image processing method and electronic equipment |
| CN106462027A (en) * | 2014-06-23 | 2017-02-22 | 本田技研工业株式会社 | System and method for responding to driver state |
| CN106686452A (en) * | 2016-12-29 | 2017-05-17 | 北京奇艺世纪科技有限公司 | Dynamic picture generation method and device |
| CN106845620A (en) * | 2016-12-19 | 2017-06-13 | 江苏慧眼数据科技股份有限公司 | A kind of passenger flow counting method based on quene state analysis |
| CN107157458A (en) * | 2017-05-25 | 2017-09-15 | 中国科学院合肥物质科学研究院 | The sensor-based system and method for a kind of animal individual feed intake and health monitoring |
| CN107172590A (en) * | 2017-06-30 | 2017-09-15 | 北京奇虎科技有限公司 | Moving state information processing method, device and mobile terminal based on mobile terminal |
| CN107197161A (en) * | 2017-06-30 | 2017-09-22 | 北京金山安全软件有限公司 | Image data processing method and device, electronic equipment and storage medium |
| CN107346415A (en) * | 2017-06-08 | 2017-11-14 | 小草数语（北京）科技有限公司 | Method of video image processing, device and monitoring device |
| CN107454395A (en) * | 2017-08-23 | 2017-12-08 | 上海安威士科技股份有限公司 | A kind of high-definition network camera and intelligent code stream control method |
| CN107564034A (en) * | 2017-07-27 | 2018-01-09 | 华南理工大学 | The pedestrian detection and tracking of multiple target in a kind of monitor video |
-
2018
- 2018-05-04 CN CN201810419877.2A patent/CN108664912B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102046076A (en) * | 2008-04-03 | 2011-05-04 | Kai医药公司 | Non-contact physiologic motion sensors and methods for use |
| CN101303726A (en) * | 2008-06-06 | 2008-11-12 | 重庆大学 | System for tracking infrared human body target based on corpuscle dynamic sampling model |
| US20100298658A1 (en) * | 2009-05-20 | 2010-11-25 | Triage Wireless, Inc. | Graphical 'mapping system' for continuously monitoring a patient's vital signs, motion, and location |
| CN101584585A (en) * | 2009-06-08 | 2009-11-25 | 浙江大学 | Experimental system for the determination of white rat behavior |
| WO2012057860A1 (en) * | 2010-10-28 | 2012-05-03 | Medtronic, Inc. | Heart failure monitoring and notification |
| CN102356753A (en) * | 2011-07-01 | 2012-02-22 | 浙江大学 | Infrared thermal image tracking-based measuring and experimental system for unbiased animal behaviors |
| CN103577832A (en) * | 2012-07-30 | 2014-02-12 | 华中科技大学 | People flow statistical method based on spatio-temporal context |
| CN104075731A (en) * | 2013-03-12 | 2014-10-01 | 阿迪达斯股份公司 | Methods Of Determining Performance Information For Individuals And Sports Objects |
| CN104573706A (en) * | 2013-10-25 | 2015-04-29 | Tcl集团股份有限公司 | Object identification method and system thereof |
| CN106462027A (en) * | 2014-06-23 | 2017-02-22 | 本田技研工业株式会社 | System and method for responding to driver state |
| CN104504245A (en) * | 2014-12-04 | 2015-04-08 | 吉林大学 | Method of utilizing GPS trip survey data to identify trips and activities |
| CN106303225A (en) * | 2016-07-29 | 2017-01-04 | 努比亚技术有限公司 | A kind of image processing method and electronic equipment |
| CN106845620A (en) * | 2016-12-19 | 2017-06-13 | 江苏慧眼数据科技股份有限公司 | A kind of passenger flow counting method based on quene state analysis |
| CN106686452A (en) * | 2016-12-29 | 2017-05-17 | 北京奇艺世纪科技有限公司 | Dynamic picture generation method and device |
| CN107157458A (en) * | 2017-05-25 | 2017-09-15 | 中国科学院合肥物质科学研究院 | The sensor-based system and method for a kind of animal individual feed intake and health monitoring |
| CN107346415A (en) * | 2017-06-08 | 2017-11-14 | 小草数语（北京）科技有限公司 | Method of video image processing, device and monitoring device |
| CN107172590A (en) * | 2017-06-30 | 2017-09-15 | 北京奇虎科技有限公司 | Moving state information processing method, device and mobile terminal based on mobile terminal |
| CN107197161A (en) * | 2017-06-30 | 2017-09-22 | 北京金山安全软件有限公司 | Image data processing method and device, electronic equipment and storage medium |
| CN107564034A (en) * | 2017-07-27 | 2018-01-09 | 华南理工大学 | The pedestrian detection and tracking of multiple target in a kind of monitor video |
| CN107454395A (en) * | 2017-08-23 | 2017-12-08 | 上海安威士科技股份有限公司 | A kind of high-definition network camera and intelligent code stream control method |
Non-Patent Citations (2)
| Title |
|---|
| 王艳英等: "香樟枝叶挥发物对小白鼠自发行为影响", 《生态环境学报》 * |
| 齐美彬等: "一种基于车辆遮挡模型的车流量统计算法", 《仪器仪表学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539974A (en) * | 2020-04-07 | 2020-08-14 | 北京明略软件系统有限公司 | Method and device for determining track, computer storage medium and terminal |
| CN111539974B (en) * | 2020-04-07 | 2022-11-11 | 北京明略软件系统有限公司 | Method and device for determining track, computer storage medium and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108664912B (en) | 2022-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ratnayake et al. | Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring | |
| Fernandes et al. | A novel automated system to acquire biometric and morphological measurements and predict body weight of pigs via 3D computer vision | |
| Redfern et al. | Biases in estimating population size from an aerial census: A case study in the Kruger National Park, South Africa: Starfield Festschrift | |
| TW201539357A (en) | Livestock identification system and method | |
| CN111294565A (en) | Intelligent pig raising monitoring method and management terminal | |
| CN107707875A (en) | Livestock monitoring method, computer program, storage medium and electronic equipment | |
| CN110059761A (en) | A kind of human body behavior prediction method and device | |
| KR102315991B1 (en) | Device and system for managing livestck remotly using artificial intelligence | |
| CN110830772A (en) | Kitchen video analysis resource scheduling method, device and system | |
| CN112580552A (en) | Method and device for analyzing behavior of rats | |
| CN107330403A (en) | A kind of yak method of counting based on video data | |
| CN109784239A (en) | The recognition methods of winged insect quantity and device | |
| CN110706219A (en) | Animal waste monitoring method, monitoring device, inspection equipment and inspection system | |
| US9839355B2 (en) | Method of processing information, and information processing apparatus | |
| CA3230401A1 (en) | Systems and methods for the automated monitoring of animal physiological conditions and for the prediction of animal phenotypes and health outcomes | |
| CN108470180A (en) | A kind of method and device for realizing information processing | |
| CN111797831A (en) | BIM and artificial intelligence based parallel abnormality detection method for poultry feeding | |
| CN108664912A (en) | A kind of information processing method, device, computer storage media and terminal | |
| Tangemann et al. | Measuring the importance of temporal features in video saliency | |
| Dennis et al. | Measuring excreta patch distribution in grazed pasture through low‐cost image analysis | |
| CN108062408B (en) | Data processing method and device | |
| EP3769036A1 (en) | Method and system for extraction of statistical sample of moving objects | |
| CN113516139A (en) | Data processing method, device, equipment and storage medium | |
| CN112150498A (en) | Method and device for determining posture information, storage medium and electronic device | |
| CN108960165A (en) | A kind of stadiums population surveillance method based on intelligent video identification technology |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100086 room 084, room 1704, 17 / F, Qingyun contemporary building, building 9, Manting Fangyuan community, Qingyun Li, Haidian District, Beijing Patentee after: Beijing minglue Zhaohui Technology Co.,Ltd. Address before: 100086 room 084, room 1704, 17 / F, Qingyun contemporary building, building 9, Manting Fangyuan community, Qingyun Li, Haidian District, Beijing Patentee before: BEIJING SUPERTOOL INTERNET TECHNOLOGY LTD. |
|
| CP01 | Change in the name or title of a patent holder | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230804 Address after: 200232 unit 5b06, floor 5, building 2, No. 277, Longlan Road, Xuhui District, Shanghai Patentee after: Shanghai Mingsheng Pinzhi Artificial Intelligence Technology Co.,Ltd. Address before: 100086 room 084, room 1704, 17 / F, Qingyun contemporary building, building 9, Manting Fangyuan community, Qingyun Li, Haidian District, Beijing Patentee before: Beijing minglue Zhaohui Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |