CN108231157A - Animal behavior detection method and device - Google Patents
Animal behavior detection method and device Download PDFInfo
- Publication number
- CN108231157A CN108231157A CN201711402570.3A CN201711402570A CN108231157A CN 108231157 A CN108231157 A CN 108231157A CN 201711402570 A CN201711402570 A CN 201711402570A CN 108231157 A CN108231157 A CN 108231157A
- Authority
- CN
- China
- Prior art keywords
- action
- animal
- trend
- tendency
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
A kind of animal behavior detection method and device, are related to behavioral value technical field.Wherein animal behavior detection method includes：Acquire the exercise data of animal to be detected in real time by motion sensor；According to the exercise data of acquisition, the motion vector direction of animal to be detected and action tendency are analyzed；When the continuous consistent action tendency for analyzing animal to be detected reaches predetermined times and consistent corresponding motion vector direction, there is cyclical action trend in confirmation；The characteristic of cyclical action trend and the characteristic of preset action trend are compared, obtain the matching degree of cyclical action trend and preset action trend；If matching degree, within preset threshold range, the number of continuous action behavior generated within cyclical action trend duration to animal to be detected counts, continuous action behavior is the action tendency continuously generated.Above-mentioned animal behavior detection method and device are simple and practicable and widely used, it can be achieved that the analysis and detection of animal behavior.
Description
Technical field
The present invention relates to behavioral value technical field more particularly to a kind of animal behavior detection method and device.
Background technology
At present, the intelligent wearable devices such as most of intelligence meter step bracelets, intelligent wristwatch, pedometer have step function, can
It is detected with the walking to the mankind or running behavior.But existing step-recording method is only to mankind's walking or running
Behavioural analysis there is no method to be applied to the application of zoometer step and the behavioral value analysis field of animal.Therefore, how by simple
Certain behavioural analyses of easy method detection and analysis animal so that animal owner can it is more scientific and effective management and
Nutrition purposes, especially for feeding animals is that current industry is badly in need of a great problem solved.
Invention content
The embodiment of the present invention provides a kind of animal behavior detection method and device, is used to implement the detection of animal behavior and divides
Analysis.
First aspect of the embodiment of the present invention provides a kind of animal behavior detection method, including：
Acquire the exercise data of animal to be detected in real time by motion sensor；
According to the exercise data of acquisition, the motion vector direction of the animal to be detected and action tendency are analyzed；
When the continuous consistent action tendency for analyzing the animal to be detected reaches predetermined times and corresponding movement arrow
When amount direction is consistent, there is cyclical action trend in confirmation；
The characteristic of the cyclical action trend and the characteristic of preset action trend are compared, obtained
The matching degree of the cyclical action trend and the preset action trend；
If the matching degree is within preset threshold range, to the animal to be detected in the cyclical action trend
The number of the continuous action behavior generated in duration is counted, the continuous action behavior be continuously generate it is described dynamic
Make tendency.
Second aspect of the embodiment of the present invention provides a kind of animal behavior detection device, including：
Acquisition module, for passing through the exercise data that motion sensor acquires animal to be detected in real time；
Analysis module for the exercise data according to acquisition, is analyzed the motion vector direction of the animal to be detected and is moved
Make tendency, and when the continuous consistent action tendency for analyzing the animal to be detected reaches predetermined times and corresponding movement arrow
When amount direction is consistent, there is cyclical action trend in confirmation；
Matching module, for by the characteristic of the characteristic of the cyclical action trend and preset action trend
It is compared, obtains the matching degree of the cyclical action trend and the preset action trend；
Statistical module, if for the matching degree within preset threshold range, to the animal to be detected described
The number of the continuous action behavior generated in cyclical action trend duration is counted, and the continuous action behavior is connects
The continuous action tendency generated.
Action tendency of the animal under various different motion states is decomposed into multiple actions, and root by the various embodiments described above
According to each micromotion and different motion vector directions, analysis obtains action trend of the animal under various motion states, then lead to
The athletic posture of detection device matching action trend identification animal is crossed, method is simple, and due to not requiring type of animal, only
Wanting motion state is the method that is all suitable for of regular trend, therefore also has the characteristics that widely used.
Description of the drawings
Fig. 1 is the realization flow diagram of animal behavior detection method that one embodiment of the invention provides；
Fig. 2 is the realization flow diagram of animal behavior detection method that another embodiment of the present invention provides；
Fig. 3 is the structure diagram of animal behavior detection device that one embodiment of the invention provides；
Fig. 4 is the structure diagram of animal behavior detection device that another embodiment of the present invention provides.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
The technical solution in the embodiment of the present invention is clearly and completely described in attached drawing in embodiment, it is clear that described reality
It is only part of the embodiment of the present invention to apply example, and not all embodiments.Based on the embodiments of the present invention, people in the art
Member's all other embodiments obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, for the realization flow diagram of a kind of animal behavior detection method that one embodiment of the invention provides,
With animal and the intelligent portable detection device of motion sensor is built-in with applied to wearable, such as：Pedometer, intelligent hand
Table etc..Motion sensor is the movement that 3-axis acceleration sensor or other and 3-axis acceleration sensor have identical function
Sensor, such as：Gravity sensor, gyroscope etc..For ease of understanding, following embodiment is by taking acceleration transducer as an example.Such as
Shown in Fig. 1, this method mainly includes the following steps that：
101st, the exercise data of animal to be detected is acquired in real time by motion sensor；
It is specifically, dynamic with intelligent portable detection device by the acquisition in real time of built-in 3-axis acceleration sensor
The exercise data of object.The exercise data is embodied in the X, Y, Z axis data of 3-axis acceleration sensor acquisition.In practical application
In, intelligent portable detection device periodically obtains the X, Y, Z axis data of 3-axis acceleration sensor acquisition and preserves, so as to
Subsequently analyzed.Obtaining the period can be by User Defined.
102nd, according to the exercise data of acquisition, the motion vector direction of animal to be detected and action tendency are analyzed；
Action tendency is the combination of actions with regularity being made of multiple micromotions, can be, but not limited to include：
It walks, run, remain where one is and jumps.By quadruped walk tendency for, which can be decomposed into
Lower 4 actions：1st, before left front foot is marched toward；2nd, right rear foot follow-up；3rd, before right front foot is marched toward；4th, left back heel into.
Motion vector direction refers to the direction of regular action behavior.For example continuously go ahead, then act direction vector just
It is forward.
Specifically, by the exercise data of acquisition, such as X, Y, Z axis data of multigroup 3-axis acceleration sensor acquisition are and pre-
If multiple operation direction vectors and the characteristic of various motion tendency matched, will be with X, Y, Z axis Data Matching degree most
High motion vector direction and action tendency are confirmed as the motion vector direction of animal to be detected and action tendency.Actually should
In, the group number for the X, Y, Z axis data of matching characteristic data can be adjusted by User Defined and at any time.
103rd, when the continuous consistent action tendency for analyzing animal to be detected reaches predetermined times and corresponding movement arrow
When amount direction is consistent, there is cyclical action trend in confirmation；
Action trend is made of, for example continuously go ahead the action tendency of multiple continuous regular repeatability, then for
Preceding action trend.It, can when continuously there is the same or similar action tendency of multiple same or similar motion vector directions
Think to form effective cyclical action trend.
104th, the characteristic of cyclical action trend and the characteristic of preset action trend are compared, obtained
The matching degree of cyclical action trend and preset action trend；
Specifically, the first motion vector direction for forming cyclical action trend, the first action tendency and first are moved
Make the tandem of tendency generation, act tendency with the second motion vector direction of the preset action trend of composition, second respectively
And second action tendency generate tandem matched, obtain of cyclical action trend and preset action trend
With degree (or, goodness of fit).
If the 105, matching degree is within preset threshold range, to animal to be detected in cyclical action trend duration
The number of the continuous action behavior of interior generation is counted.
Cyclical action trend and the matching degree of preset action trend are compared with preset threshold range, if matching
Degree then confirms generation action behavior, then animal to be detected is continued in cyclical action trend within preset threshold range
During the number of continuous action behavior that generates counted.The action that continuous action behavior refers to continuously repeat is walked
Gesture, the action tendency of the jump such as continuously generated.
It should be understood that the acquisition of exercise data and analyzing the action of animal to be detected according to the exercise data of acquisition and walking
Gesture and motion vector direction are to continue to carry out.There is cyclical action trend and action behavior and to animal to be detected in confirmation
It is that cycle carries out that the number of continuous action behavior generated within cyclical action trend duration, which carries out statistics,.At one
After cyclical action trend occurs, as long as the type of the new action tendency generated and motion vector direction do not change, it is considered as
The cyclical action trend still continues, and just statistics is gone down always, until the motion state of animal to be detected is changed,
That is, the type or motion vector direction of action tendency are changed, then it is assumed that this cyclical action trend terminates.Then,
Start to be confirmed whether next cycle sexual act trend and action occurred according to the action tendency and motion vector direction of analysis
Behavior, in the event of then starting the continuous action behavioral statistics of a new round, and so on, until terminating statistics task.
Animal behavior detection method provided in this embodiment, by action tendency point of the animal under various different motion states
It solves as multiple actions, and according to each micromotion and different motion vector directions, analysis obtains animal in various motion states
Under action trend, then the athletic posture that trend identifies animal is acted by detection device matching, method is simple, and due to dynamic
Species type does not require, as long as motion state is the method that is all suitable for of regular trend, therefore also has widely used
The characteristics of.
Referring to Fig. 2, a kind of realization flow of the animal behavior detection method signal provided for another embodiment of the present invention
Figure with animal and is built-in with the intelligent portable detection device of motion sensor, such as applied to wearable：Pedometer, intelligence
Energy wrist-watch etc..Motion sensor is 3-axis acceleration sensor or other have identical function with 3-axis acceleration sensor
Motion sensor, such as：Gravity sensor, gyroscope etc..For ease of understanding, following embodiment using acceleration transducer as
Example.As shown in Fig. 2, this method mainly includes the following steps that：
201st, the action tendency of multiple and different types by least one or a kind of animal under different motion state carries out
Movement decomposition；
202nd, the mathematical model of the action tendency of multiple and different types is established according to the action of decomposition；
203rd, according to mathematical model and multiple and different motion vector directions, analysis obtains corresponding multiple and different types
Action trend characteristic, and be preset in portable detector；
Action trend is made of, for example continuously go ahead the action tendency of multiple continuous regular repeatability, then for
Preceding action trend.It is the regular combination of actions being made of multiple micromotions to act tendency, can be, but not limited to wrap
It includes：It walks, run, remain where one is and jumps.By taking quadruped walks tendency as an example, which can be decomposed into
4 actions below：1st, before left front foot is marched toward；2nd, right rear foot follow-up；3rd, before right front foot is marched toward；4th, left back heel into.
Specifically, the various motion states of at least one or a kind of animal are collected, by different types of animal in various fortune
The action tendency of multiple and different types under dynamic state is decomposed, and obtains forming multiple decomposition of different types of action tendency
Action, the micromotion being then based on establish the mathematical model of the action tendency of multiple and different types in terminal device,
Later according to the mathematical model of foundation and multiple and different motion vector directions, the action that analysis obtains multiple and different types becomes
The characteristic of gesture, and be preset in intelligent portable detection device.
In practical applications, analyzing the characteristic of the action trend of multiple and different types can be detected by intelligent portable
It is realized in other-end equipment except device.That is, it analyzes to obtain the characteristic of action trend by mathematical modeling
It can be completed respectively by two different devices from detection animal behavior.
Optionally, the characteristic of the action trend of multiple and different types that analysis obtains is embedded in intelligent portable inspection
It surveys in the firmware of device.
204th, the exercise data of animal to be detected is acquired in real time by motion sensor；
It is specifically, dynamic with intelligent portable detection device by the acquisition in real time of built-in 3-axis acceleration sensor
The exercise data of object.The exercise data is embodied in the X, Y, Z axis data of 3-axis acceleration sensor acquisition.In practical application
In, intelligent portable detection device periodically obtains the X, Y, Z axis data of 3-axis acceleration sensor acquisition and preserves, so as to
Subsequently analyzed.Obtaining the period can be by User Defined.
205th, the motion vector direction of animal to be detected and action tendency are analyzed according to the exercise data of acquisition, and from point
In the action tendency of precipitation, frequency is filtered out except predeterminated frequency section and movement range is except predetermined amplitude section
Invalid action tendency；
Motion vector direction refers to the direction of regular action behavior.For example continuously go ahead, then act direction vector just
It is forward.
Specifically, by the exercise data of acquisition, such as X, Y, Z axis data of multigroup 3-axis acceleration sensor acquisition are and pre-
If multiple operation direction vectors and the characteristic of various motion tendency matched, will be with X, Y, Z axis Data Matching degree most
High motion vector direction and action tendency are confirmed as the motion vector direction of animal to be detected and action tendency.Actually should
In, the group number for the X, Y, Z axis data of matching characteristic data can be adjusted by User Defined and at any time.
During analysis, using preset frequency separation and amplitude section to the motion vector direction that analyzes and dynamic
It is filtered as tendency.Wherein, frequency is that the micromotion occurred repeatedly according to each group that forms an action tendency combines
The time completed together is calculated, such as：Complete how long an action tendency to remain where one is averagely has needs altogether.Have
The frequency of the action tendency of effect must be within preset frequency separation, less than the minimum threshold frequency of the frequency separation or big
It is judged as invalid action tendency in the action tendency of the maximum frequency threshold value of the frequency separation, need to filters out.
Movement range refers to single step amplitude of fluctuation.The amplitude of effective action tendency must be within predetermined amplitude section.
When amplitude peak threshold value of the amplitude more than the predetermined amplitude section for acting tendency, alternatively, less than the predetermined amplitude section most
By a small margin during threshold value, it is judged as invalid action tendency, need to filters out.
It should be understood that in order to avoid interference of the invalid corresponding motion vector direction of action tendency to judging result,
Also the invalid corresponding motion vector direction of action tendency can together be filtered out while invalid action tendency is filtered.
206th, when the continuous consistent action tendency for analyzing animal to be detected reaches predetermined times and corresponding movement arrow
When amount direction is consistent, there is cyclical action trend in confirmation；
When continuously there is the same or similar action tendency of multiple same or similar motion vector directions, it is believed that shape
Trend is acted into efficient periodic.
It should be understood that minimum threshold frequency, maximum frequency threshold value, minimum radius threshold value, amplitude peak threshold value and company
The predetermined times of continuous tendency are one group of threshold values, can be periodically or non-periodically adjusted by multiple actual test.It such as jogs and soon
The threshold range of race is different, respectively obtains corresponding sets of threshold values of jogging and hurry up by actual test, and constantly into
Row adjustment.
207th, the characteristic of cyclical action trend and the characteristic of preset action trend are compared, obtained
The matching degree of cyclical action trend and preset action trend；
Specifically, the first motion vector direction for forming cyclical action trend, the first action tendency and first are moved
Make the tandem of tendency generation, act tendency with the second motion vector direction of the preset action trend of composition, second respectively
And second action tendency generate tandem matched, obtain of cyclical action trend and preset action trend
With degree (or, goodness of fit).
If the 208, matching degree is within preset threshold range, generation action behavior is confirmed, to animal to be detected in the period
The number of the continuous action behavior generated in sexual act trend duration is counted, and according to cyclical action trend not
Together, the historical data of the quantity of the continuous action behavior of each cyclical action trend of statistics is classified and preserved；
Specifically, first, by the matching degree of cyclical action trend and preset action trend and preset threshold range into
Row compares, if matching degree within preset threshold range, confirms generation action behavior, then to animal to be detected in periodicity
The number of the continuous action behavior generated in action trend duration is counted.Continuous action behavior refers to continuously repeat
The action tendency of progress, the action tendency of the jump such as continuously generated.That is, become to animal to be detected in cyclical action
The number of action tendency continuously generated in gesture duration is counted.
It should be understood that is counted here is that this whole cycle sexual act becomes from cyclical action trend start to finish
The number of the action tendency generated in gesture duration, that is, cover and confirm that occur generating during cyclical action trend moves
Make tendency.As an example it is assumed that cyclical action trend is the action trend to remain where one is, then when action behavior occurs for confirmation
When, if having occurred that 10 action tendencies to remain where one is before confirming, after generation action behavior is confirmed, and recur
One-off tendency will then count on the basis of 10 and add 1, as 11 again.
Then, according to the difference of cyclical action trend, by the continuous action behavior of each cyclical action trend of statistics
Quantity historical data classification preserve, such as：All corresponding step numbers of action trend to remain where one is are merged
A numerical value is saved as, all corresponding step numbers of action trend run forward are merged and save as a numerical value, by institute
The corresponding step number of action trend for having jump, which merges, saves as a number.
It further, can be dynamic by the generation of each cyclical action trend and end time and the periodicity respectively
The number for making the line action behavior generated in trend duration is recorded as a corresponding daily record, and according to the output of triggering
Instruction, the report of summary information of the generation comprising all daily records, then according to the preset way of output, by the report output of generation
To user, the mailbox or exported in a manner of instant messaging for being either output to that user reserves such as are exported on a display screen
Onto intelligent mobile terminals such as user's mobile phone currently in use, smartwatch, tablet computers.
Further, can also be according to the difference of cyclical action trend, the number of continuous action behavior that will be counted
Classification output in real time；Alternatively, by the continuous action behavior generated in each cyclical action trend duration counted
After number summarizes, export in real time.For example, export animal jump to be detected in real time respectively on the screen of intelligent portable detection device
Number, the number that remains where one is, the number run forward carries out altogether alternatively, only exporting animal to be detected in real time on the screen
How many times action behavior.
Further, if the intelligent mobile terminals such as intelligent portable detection device and mobile phone, smartwatch, tablet computer
Data connection is established, then the classification action behavior of statistics is generated by number data and/or total time by the data connection of foundation
In number real-time data transmission to intelligent mobile terminal, so that user can understand animal to be detected by intelligent mobile terminal at any time
Motion state.
209th, it during the number of statistics continuous action behavior, when the exercise data according to acquisition, analyzes to be detected dynamic
The motion vector direction of object it is inconsistent or action tendency it is inconsistent when, then confirm that cyclical action trend terminates, preserve statistics knot
Fruit.
Specifically, the exercise data of motion sensor continuous collecting animal to be detected, will not because performing statistical operation and
It interrupts.And during the number of statistics continuous action behavior, it is still desirable to according to the exercise data of acquisition, analyze to be detected dynamic
The motion vector direction of object and action tendency, and judge the motion vector direction of the animal to be detected newly analyzed and action tendency
It is whether consistent with the motion vector direction and action tendency of the preceding animal to be detected once analyzed.It should be understood that analyzing
In the process, it is also desirable to which invalid action tendency and its corresponding motion vector direction are filtered.
If the motion vector direction of the animal to be detected newly analyzed and the preceding movement of animal to be detected once analyzed
Direction vector is inconsistent, alternatively, the action tendency of the animal to be detected newly analyzed and the preceding animal to be detected once analyzed
Action tendency it is inconsistent, then illustrate that the motion state of animal to be detected is changed, confirm this cyclical action trend
Terminate, preserve statistical result and simultaneously return and perform step 205 and subsequent step, so as to when confirm generate new action behavior when,
The number of continuous action behavior generated in new action behavior corresponding cyclical action trend duration is counted,
Until intelligent portable detection device is stopped or stops statistical operation in response to the halt instruction of reception.
It should be understood that " consistent " involved in the above is including identical or approximate.
Animal behavior detection method provided in this embodiment, by action tendency point of the animal under various different motion states
It solves as multiple actions, and according to each micromotion and different motion vector directions, analysis obtains animal in various motion states
Under action trend, then the athletic posture that trend identifies animal is acted by detection device matching, method is simple, and due to dynamic
Species type does not require, as long as motion state is the method that is all suitable for of regular trend, therefore also has widely used
The characteristics of.
Referring to Fig. 3, the structure diagram of animal behavior detection device provided for one embodiment of the invention.The device can
It is used to implement the animal behavior detection method that above-mentioned embodiment illustrated in fig. 1 provides.As shown in figure 3, the device mainly includes：
Acquisition module 301, for passing through the exercise data that motion sensor acquires animal to be detected in real time；
Analysis module 302 for the exercise data according to acquisition, is analyzed the motion vector direction of the animal to be detected and is moved
Make tendency, and when the continuous consistent action tendency for analyzing the animal to be detected reaches predetermined times and corresponding motion vector
When direction is consistent, there is cyclical action trend in confirmation；
Matching module 303, for by the characteristic of the characteristic of the cyclical action trend and preset action trend
According to being compared, the matching degree of the cyclical action trend and the preset action trend is obtained；
Statistical module 304, if for the matching degree within preset threshold range, to the animal to be detected in the period
The number of the continuous action behavior generated in sexual act trend duration is counted, and the continuous action behavior is continuously generates
The action tendency.
It should be noted that in the embodiment of the exemplary device of figure 3 above, the division of each function module is only to illustrate
It is bright, can be as needed in practical application, such as the convenient of realization of the configuration requirement or software of corresponding hardware considers, and incite somebody to action
Above-mentioned function distribution is completed by different function modules, i.e., the internal structure of animal behavior detection device is divided into different work(
Energy module, to complete all or part of function described above.Moreover, in practical applications, it is corresponding in the present embodiment
Function module can be by corresponding hardware realization, can also perform corresponding software by corresponding hardware and complete.This specification
The each embodiment provided can all apply foregoing description principle, repeat no more below.
The detailed process of the respective function of each Implement of Function Module, please join in animal behavior detection device provided in this embodiment
See the particular content described in above-mentioned embodiment illustrated in fig. 1, details are not described herein again.
Animal behavior detection device provided in this embodiment, by action tendency point of the animal under various different motion states
It solves as multiple actions, and according to each micromotion and different motion vector directions, analysis obtains animal in various motion states
Under action trend, then the athletic posture that trend identifies animal is acted by detection device matching, method is simple, and due to dynamic
Species type does not require, as long as motion state is the method that is all suitable for of regular trend, therefore also has widely used
The characteristics of.
Referring to Fig. 4, the structure diagram of animal behavior detection device provided for another embodiment of the present invention.The animal
Behavioral value device can be used for realizing above-mentioned Fig. 1 and the animal behavior detection method that embodiment illustrated in fig. 2 provides.Shown in Fig. 3
Animal behavior detection device unlike, in this present embodiment,
Further, which further includes：
Modeling module 401, for multiple and different types by least one or a kind of animal under different motion state
It acts tendency and carries out movement decomposition, and the mathematical model of multiple different types of action tendencies is established according to the action of decomposition；
Data analysis module 402, for being obtained according to the mathematical model and multiple and different motion vector directions, analysis
The characteristic of the action trend of corresponding multiple and different types；
Presetting module 403 is preset in portable inspectiont dress for data analysis module 402 to be analyzed obtained characteristic
In putting.
Further, which further includes：
Filtering module 404, in the exercise data according to acquisition, analyze the motion vector direction of the animal to be detected and
When acting tendency, from the action tendency analyzed, frequency is filtered out except predeterminated frequency section and movement range is pre-
If the invalid action tendency except amplitude section.
Further, which further includes：
Preserving module 405, for according to the difference of the cyclical action trend, by respectively cyclical action trend of statistics
Continuous behavior quantity historical data classification preserve.
Further, analysis module 302 are additionally operable to during the number for counting the continuous action behavior, when according to acquisition
Exercise data, analyze the animal to be detected motion vector direction it is inconsistent or action tendency it is inconsistent when, then confirm should
Cyclical action trend terminates, and preserves statistical result.
Further, which may also include：Output module, for according to the difference of the cyclical action trend, will unite
Respectively cyclical action trend duration that the number classification for the continuous action behavior counted out is exported and will be counted in real time
After the number of the continuous action behavior of interior generation summarizes, export in real time.
The detailed process of the respective function of each Implement of Function Module, please join in animal behavior detection device provided in this embodiment
See the particular content described in above-mentioned Fig. 1 to embodiment illustrated in fig. 3, details are not described herein again.
Animal behavior detection device provided in this embodiment, by action tendency point of the animal under various different motion states
It solves as multiple actions, and according to each micromotion and different motion vector directions, analysis obtains animal in various motion states
Under action trend, then the athletic posture that trend identifies animal is acted by detection device matching, method is simple, and due to dynamic
Species type does not require, as long as motion state is the method that is all suitable for of regular trend, therefore also has widely used
The characteristics of.
In several embodiments provided herein, it should be understood that disclosed method and apparatus can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the module, only
Only a kind of division of logic function can have other dividing mode in actual implementation, such as multiple module or components can be tied
It closes or is desirably integrated into another system or some features can be ignored or does not perform.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be the INDIRECT COUPLING or logical by some interfaces, device or module
Letter connection can be electrical, machinery or other forms.
The module illustrated as separating component may or may not be physically separate, be shown as module
The component shown may or may not be physical module, you can be located at a place or can also be distributed to multiple
On network module.Some or all of module therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each function module in each embodiment of the present invention can be integrated in a processing module, it can also
That modules are individually physically present, can also two or more modules be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.
If the integrated module is realized in the form of software function module and is independent product sale or uses
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme of the present invention is substantially
The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products
It embodies, which is stored in a readable storage medium storing program for executing, is used including some instructions so that a meter
It calculates machine equipment (can be personal computer, server or the network equipment etc.) and performs each embodiment the method for the present invention
All or part of step.And aforementioned readable storage medium storing program for executing includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with
Store the medium of program code.
It should be noted that for aforementioned each method embodiment, describe, therefore it is all expressed as a series of for simplicity
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, certain steps may be used other sequences or be carried out at the same time.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to preferred embodiment, and involved action and module might not all be this hairs
Necessary to bright.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiments.
It is to a kind of description of animal behavior detection method and device provided by the present invention, for the skill of this field above
The thought of art personnel, according to the present invention embodiment, there will be changes in specific embodiments and applications, to sum up,
The content of the present specification should not be construed as limiting the invention.
Claims (10)
1. a kind of animal behavior detection method, which is characterized in that the method includes：
Acquire the exercise data of animal to be detected in real time by motion sensor；
According to the exercise data of acquisition, the motion vector direction of the animal to be detected and action tendency are analyzed；
When the continuous consistent action tendency for analyzing the animal to be detected reaches predetermined times and corresponding motion vector side
To it is consistent when, confirmation there is cyclical action trend；
The characteristic of the cyclical action trend and the characteristic of preset action trend are compared, obtained described
The matching degree of cyclical action trend and the preset action trend；
If the matching degree continues within preset threshold range, to the animal to be detected in the cyclical action trend
During the number of continuous action behavior that generates counted, the continuous action behavior is that the action continuously generated is walked
Gesture.
2. the method as described in claim 1, which is characterized in that described to acquire animal to be detected in real time by motion sensor
Before exercise data, including：
The action tendency of multiple and different types of at least one or a kind of animal under different motion state is subjected to movement decomposition；
The mathematical model of multiple different types of action tendencies is established according to the action of decomposition；
According to the mathematical model and multiple and different motion vector directions, analysis obtains the dynamic of corresponding multiple and different types
Make the characteristic of trend, and be preset in portable detector.
3. the method as described in claim 1, which is characterized in that the method further includes：
In the exercise data according to acquisition, the motion vector direction of the analysis animal to be detected and action tendency, from analysis
In the action tendency gone out, the nothing that frequency is except predeterminated frequency section and movement range is except predetermined amplitude section is filtered out
Effect acts tendency.
4. the method as described in claim 1, which is characterized in that if the matching degree within preset threshold range,
The number of continuous action behavior generated within the cyclical action trend duration to the animal to be detected is united
After meter, including：
According to the difference of the cyclical action trend, by the quantity of the Continuous behavior of each cyclical action trend of statistics
Historical data classification preserve.
5. the method as described in claim 1, which is characterized in that the method further includes：
During the number for counting the continuous action behavior, when the exercise data according to acquisition, analyze described to be detected dynamic
The motion vector direction of object it is inconsistent or action tendency it is inconsistent when, then confirm that the cyclical action trend terminates, preserve system
Meter as a result, and perform the exercise data according to acquisition, the motion vector direction and action for analyzing the animal to be detected are walked
The step of gesture.
6. a kind of animal behavior detection device, which is characterized in that described device includes：
Acquisition module, for passing through the exercise data that motion sensor acquires animal to be detected in real time；
Analysis module, for the exercise data according to acquisition, the motion vector direction and action for analyzing the animal to be detected are walked
Gesture, and when the continuous consistent action tendency for analyzing the animal to be detected reaches predetermined times and corresponding motion vector side
To it is consistent when, confirmation there is cyclical action trend；
Matching module, for the characteristic of the characteristic of the cyclical action trend and preset action trend to be carried out
Compare, obtain the matching degree of the cyclical action trend and the preset action trend；
Statistical module, if for the matching degree within preset threshold range, to the animal to be detected in the period
The number of the continuous action behavior generated in sexual act trend duration is counted, and the continuous action behavior is continuous production
The raw action tendency.
7. device as claimed in claim 6, which is characterized in that described device further includes：
Modeling module, for the action tendency of multiple and different types by least one or a kind of animal under different motion state
Movement decomposition is carried out, and the mathematical model of multiple different types of action tendencies is established according to the action of decomposition；
Data analysis module, for according to the mathematical model and multiple and different motion vector directions, analysis to be corresponded to
Multiple and different types action trend characteristic；
Presetting module, the characteristic for the data analysis module to be analyzed are preset in portable detector.
8. device as claimed in claim 6, which is characterized in that described device further includes：
Filtering module, in the exercise data according to acquisition, the motion vector direction of the analysis animal to be detected and action
During tendency, from the action tendency analyzed, frequency is filtered out except predeterminated frequency section and movement range is in default width
Spend the invalid action tendency except section.
9. device as claimed in claim 6, which is characterized in that described device further includes：
Preserving module, for according to the difference of the cyclical action trend, by each cyclical action trend of statistics
The historical data classification of the quantity of Continuous behavior preserves.
10. device as claimed in claim 6, which is characterized in that
The analysis module is additionally operable to during the number for counting the continuous action behavior, when the exercise data according to acquisition,
Analyze the animal to be detected motion vector direction it is inconsistent or action tendency it is inconsistent when, then confirm that the periodicity is moved
Terminate as trend, preserve statistical result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711402570.3A CN108231157A (en) | 2017-12-22 | 2017-12-22 | Animal behavior detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711402570.3A CN108231157A (en) | 2017-12-22 | 2017-12-22 | Animal behavior detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108231157A true CN108231157A (en) | 2018-06-29 |
Family
ID=62648627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711402570.3A Pending CN108231157A (en) | 2017-12-22 | 2017-12-22 | Animal behavior detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108231157A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339838A (en) * | 2020-02-10 | 2020-06-26 | 中国农业科学院农业信息研究所 | Pig behavior identification method and system based on information fusion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101543400A (en) * | 2009-04-23 | 2009-09-30 | 深圳先进技术研究院 | Aanimal behavior detection and automatic analysis system and animal behavior analysis methods |
| CN102509305A (en) * | 2011-09-26 | 2012-06-20 | 浙江工业大学 | Animal behavior detection device based on omnidirectional vision |
| CN103519823A (en) * | 2013-10-17 | 2014-01-22 | 天津闪联科技有限公司 | Monitoring method for animal cultivation |
| CN106376482A (en) * | 2016-08-29 | 2017-02-08 | 深圳市沃特沃德股份有限公司 | Animal micro-action determining method, apparatus and micro-action indicating device |
-
2017
- 2017-12-22 CN CN201711402570.3A patent/CN108231157A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101543400A (en) * | 2009-04-23 | 2009-09-30 | 深圳先进技术研究院 | Aanimal behavior detection and automatic analysis system and animal behavior analysis methods |
| CN102509305A (en) * | 2011-09-26 | 2012-06-20 | 浙江工业大学 | Animal behavior detection device based on omnidirectional vision |
| CN103519823A (en) * | 2013-10-17 | 2014-01-22 | 天津闪联科技有限公司 | Monitoring method for animal cultivation |
| CN106376482A (en) * | 2016-08-29 | 2017-02-08 | 深圳市沃特沃德股份有限公司 | Animal micro-action determining method, apparatus and micro-action indicating device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339838A (en) * | 2020-02-10 | 2020-06-26 | 中国农业科学院农业信息研究所 | Pig behavior identification method and system based on information fusion |
| CN111339838B (en) * | 2020-02-10 | 2023-06-20 | 中国农业科学院农业信息研究所 | Pig behavior recognition method and system based on information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104197952B (en) | A kind of user's walking step-recording method, device and mobile terminal | |
| CN104780217B (en) | Detect method, system and the client of user job efficiency | |
| CN105902257A (en) | Sleep state analysis method and device and intelligent wearable equipment | |
| CN104699241B (en) | It is determined that the method and apparatus at action and/or action position | |
| CN104699242B (en) | It is determined that the method and apparatus at action and/or action position | |
| CN105167761A (en) | Wearing state detecting method and device for intelligent wearable equipment | |
| TWI617993B (en) | Recognition system and recognition method | |
| CN105943013A (en) | Heart rate detection method and device, and intelligent wearable device | |
| CN103646425A (en) | A method and a system for body feeling interaction | |
| CN104656895B (en) | It is determined that the method and apparatus of input information | |
| CN104809637A (en) | Commodity recommending method and system realized by computer | |
| CN104490401A (en) | Method for intelligent terminal for automatically recognizing human behaviors based on acceleration data | |
| CN106537415A (en) | Fingerprint-based pressure detection method and apparatus | |
| CN103517118B (en) | The action identification method of a kind of remote controller and system | |
| CN110363143A (en) | Monitoring method, device and system | |
| CN104157168A (en) | Intelligent database application system applied to artificial intelligent robot and interaction method | |
| CN108231157A (en) | Animal behavior detection method and device | |
| CN111723662A (en) | Human body posture recognition method based on convolutional neural network | |
| Sun et al. | Effective dimensionality reduction for visualizing neural dynamics by laplacian eigenmaps | |
| CN108089693A (en) | Gesture identification method and device, intelligence wearing terminal and server | |
| CN109199325B (en) | Sleep monitoring method and device | |
| CN110046585A (en) | A kind of gesture identification method based on environment light | |
| CN108170850A (en) | A kind of mobile data analysis mining method | |
| Ghorbel et al. | A fast and accurate motion descriptor for human action recognition applications | |
| CN107463689A (en) | Generation method, moving state identification method and the terminal in motion characteristic data storehouse |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |