CN110321796A - A kind of dog only instructs and guides method, apparatus, system and storage medium - Google Patents
A kind of dog only instructs and guides method, apparatus, system and storage medium Download PDFInfo
- Publication number
- CN110321796A CN110321796A CN201910463078.XA CN201910463078A CN110321796A CN 110321796 A CN110321796 A CN 110321796A CN 201910463078 A CN201910463078 A CN 201910463078A CN 110321796 A CN110321796 A CN 110321796A
- Authority
- CN
- China
- Prior art keywords
- dog
- toilet
- region
- goes
- behavior
- 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
- 238000000034 method Methods 0.000 title claims abstract description 94
- 230000005284 excitation Effects 0.000 claims abstract description 46
- 230000006399 behavior Effects 0.000 claims description 73
- 238000001514 detection method Methods 0.000 claims description 38
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 15
- 230000003542 behavioural effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 20
- 238000006467 substitution reaction Methods 0.000 abstract description 7
- 241000282472 Canis lupus familiaris Species 0.000 abstract 14
- 230000034002 defecation rhythm Effects 0.000 description 19
- 230000013872 defecation Effects 0.000 description 16
- 230000006870 function Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 10
- 230000009885 systemic effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 235000013305 food Nutrition 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K15/00—Devices for taming animals, e.g. nose-rings or hobbles; Devices for overturning animals in general; Training or exercising equipment; Covering boxes
- A01K15/02—Training or exercising equipment, e.g. mazes or labyrinths for animals ; Electric shock devices ; Toys specially adapted for animals
- A01K15/021—Electronic training devices specially adapted for dogs or cats
-
- 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
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- Animal Husbandry (AREA)
- Animal Behavior & Ethology (AREA)
- Zoology (AREA)
- Health & Medical Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Physical Education & Sports Medicine (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of dogs only to instruct and guide method, apparatus, system and storage medium, which comprises the image data of acquisition dog only；It detects dog described in described image data only, judges whether the dog is only located at the region that goes to the toilet；It identifies the behavior of dog described in described image data only, judges whether the behavior of the dog only early warning behavior occurs；Only whether be located at according to the dog it is described go to the toilet region and whether the dog only early warning behavior occurs, Xiang Suoshu dog only provides feedback excitation.According to the method for the present invention, device, system and storage medium, the position occurred by only carrying out Activity recognition and bonding behavior to dog, give dog only corresponding feedback excitation, realize that substitution manually only instructs and guides dog, the efficiency that dog is only instructed and guided is improved, human cost and economic cost that dog is only instructed and guided are greatly reduced.
Description
Technical field
The present invention relates to technical field of image processing, relate more specifically to the processing that dog is only instructed and guided.
Background technique
The a large amount of crowds of modern society select dog to bring company and happy to oneself and household as house pet, however dog is not
It is same as other pets (such as cat) of part and has the ability independently gone to toilet, the owner of dog is needed to go out to walk a dog or pass through daily
Long-term introduction makes its association's fixed point go to toilet, and otherwise may cause spot, peculiar smell and healthy hidden danger etc. one by random defecation at home
Serial adverse consequences.However it is a time-consuming and laborious job that one pet dog fixed point of church, which is gone to toilet, needs to monitor constantly and dote on
The state of object dog once finds that the omen movement of going to toilet of its area other than lavatory will be instructed and guided and refer to just until it is formed
Good habit, it is excessively high for time energy cost needed for current numerous Yang Chong family, if employing profession instruction dog Shi Jinhang training
It instructs its selling at exorbitant prices and has exceeded general family's ability to bear range.
Therefore, dog can only be instructed and guided by the way of manually instructing and guiding by, which existing in the prior art, only completes Go to lavatory, greatly
Dependence and artificial, cause dog owner to instruct and guide the time energy monetary cost of dog only excessively high.
Summary of the invention
The present invention is proposed in view of the above problem.The present invention provides a kind of dog only instruct and guide method, apparatus, system and
Computer storage medium, the position occurred by only carrying out Activity recognition and bonding behavior to dog, it is only corresponding anti-to give dog
Feedback excitation realizes that substitution manually only instructs and guides dog, improves the efficiency that dog is only instructed and guided, greatly reduce the people that dog is only instructed and guided
Power cost and economic cost.
According to the first aspect of the invention, it provides a kind of dog and only instructs and guides method, comprising:
Acquire the image data of dog only；
It detects dog described in described image data only, judges whether the dog is only located at the region that goes to the toilet；
It identifies the behavior of dog described in described image data only, judges whether the behavior of the dog only early warning behavior occurs；
Only whether be located at according to the dog it is described go to the toilet region and whether the dog early warning behavior only occurs, Xiang Suoshu dog is only
Feedback excitation is provided.
According to the second aspect of the invention, it provides a kind of dog and only instructs and guides device, comprising:
Image capture module, for acquiring the image data of dog only；
Dog detecting module judges whether the dog is only located at and goes to the toilet for detecting dog described in described image data only
Region；
Behavioural analysis module, for identification behavior of dog described in described image data only judge the behavior of the dog only
Whether early warning behavior is occurred；
Feedback excitation module, for only whether be located at according to the dog it is described go to the toilet region and the dog only whether occur it is pre-
Alert behavior, Xiang Suoshu dog only provide feedback excitation.
According to the third aspect of the invention we, it provides a kind of dog and only instructs and guides system, including memory, processor and be stored in
The computer program run on the memory and on the processor, which is characterized in that the processor executes the meter
The step of first aspect the method is realized when calculation machine program.
According to the fourth aspect of the invention, a kind of computer storage medium is provided, computer program is stored thereon with,
The step of being characterized in that, first aspect the method realized when the computer program is computer-executed.
Dog according to an embodiment of the present invention only instructs and guides method, apparatus, system and computer storage medium, by dog only into
Dog only corresponding feedback excitation is given in the position that row Activity recognition and bonding behavior occur, realize substitution manually to dog only into
Row instruction and guide, improve the efficiency that dog is only instructed and guided, greatly reduce human cost and economic cost that dog is only instructed and guided.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 is the signal that the exemplary electronic device of method and apparatus is only instructed and guided for realizing dog according to an embodiment of the present invention
Property block diagram；
Fig. 2 is the schematic flow chart that dog according to an embodiment of the present invention only instructs and guides method；
Fig. 3 is the schematic block diagram that dog according to an embodiment of the present invention only instructs and guides device；
Fig. 4 is the schematic block diagram that dog according to an embodiment of the present invention only instructs and guides system.
Specific embodiment
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
Firstly, being described with reference to Figure 1 the exemplary electron for only instructing and guiding method and apparatus for realizing the dog of the embodiment of the present invention
Equipment 100.
As shown in Figure 1, electronic equipment 100 include one or more processors 101, it is one or more storage device 102, defeated
Enter device 103, output device 104, imaging sensor 105, the connection machine that these components pass through bus system 106 or other forms
The interconnection of structure (not shown).It should be noted that the component and structure of electronic equipment 100 shown in FIG. 1 are only exemplary, rather than limit
Property, as needed, the electronic equipment also can have other assemblies and structure.
The processor 101 can be central processing unit (CPU) or have data-handling capacity or instruction execution energy
The processing unit of the other forms of power, and can control other components in the electronic equipment 100 to execute desired function
Energy.
The storage device 102 may include one or more computer program products, and the computer program product can
To include various forms of computer readable storage mediums, such as volatile memory or nonvolatile memory.It is described volatile
Property memory for example may include random access memory (RAM) or cache memory (cache) etc..It is described non-volatile
Memory for example may include read-only memory (ROM), hard disk, flash memory etc..It can be on the computer readable storage medium
One or more computer program instructions are stored, processor 102 can run described program instruction, to realize sheet described below
The client functionality (realized by processor) in inventive embodiments and/or other desired functions.The computer can
It reads that various application programs and various data can also be stored in storage medium, such as the application program is used or generated various
Data etc..
The input unit 103 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output device 104 can export various information (such as image or sound) to external (such as user), and
It may include one or more of display, loudspeaker etc..
Described image sensor 105 can be shot the desired image of user (such as photo, video etc.), and will be captured
Image be stored in the storage device 102 for other components use.
Illustratively, the exemplary electronic device for only instructing and guiding method and apparatus for realizing dog according to an embodiment of the present invention can
To be implemented as smart phone, tablet computer, Image Acquisition end etc..
Dog according to an embodiment of the present invention, which is described, next, with reference to Fig. 2 only instructs and guides method 200.As shown in Fig. 2, a kind of dog
Only instruction and guide method 200, comprising:
Firstly, in step S210, the image data of acquisition dog only；
In step S220, dog described in described image data is detected only, judge whether the dog is only located at the region that goes to the toilet；
In step S230, the behavior of dog described in described image data only is identified, judge whether the behavior of the dog only goes out
Existing early warning behavior；
Finally, in step S240, only whether be located at according to the dog it is described go to the toilet region and the dog only whether occur it is pre-
Alert behavior, Xiang Suoshu dog only provide feedback excitation.
It should be noted that above-mentioned steps sequence is only schematic, the application method 200 is not represented centainly according to above-mentioned
The sequence of step；Specifically, above-mentioned steps S230 is not limited to detect described in described image data in step S220
After dog, it can be before step S220 or occur simultaneously with step S220, herein with no restrictions.
Wherein, view-based access control model identification and machine learning techniques after the image data of acquisition dog, identify in image data
The dog only whether give corresponding feedback excitation in conjunction with the position of the dog prediction occurring behavior, draw by prediction occurring behavior
Dog is led only to go to the toilet in the region that goes to the toilet.Artificial real time monitoring dog is substituted by intelligent instruction and guide method so only, with machine learning
Method judges that dog only acts, and solves the problems, such as manually to cultivate dog and only pinpoints and goes to the toilet time-consuming and laborious, is suitble to be widely used in family,
The feeding dog place such as doghouse.
Illustratively, only the method for instructing and guiding can be in setting with memory and processor for dog according to an embodiment of the present invention
It is realized in standby, device or system.
Only the method for instructing and guiding can be deployed at Image Acquisition end or at personal terminal dog according to an embodiment of the present invention, example
Such as, the Image Acquisition end of doghouse, smart phone, tablet computer, personal computer etc. can be deployed in.For example, can be in image
The image data of dog only is acquired at collection terminal or personal terminal, and whether go to the toilet region and the dog are only located at according to the dog
Only whether there is early warning behavior, controls corresponding device and complete feedback excitation, to complete instruction and guide process；
Alternatively, dog according to an embodiment of the present invention only the method for instructing and guiding can also be deployed in being distributed Image Acquisition end and
People's terminal, smart phone, tablet computer, personal computer etc. at the personal terminal.For example, can be at Image Acquisition end
The image data of dog only is acquired, described image data are sent to the personal terminal, are according to the dog by personal terminal
It is no be located at it is described go to the toilet region and whether the dog only early warning behavior occurs, control corresponding device and complete feedback excitation, thus
Complete instruction and guide process；
Alternatively, only the method for instructing and guiding can also be deployed in server end (or cloud to dog according to an embodiment of the present invention with being distributed
End) and Image Acquisition end or personal terminal at.For example, the image of dog only can be acquired at Image Acquisition end or personal terminal
Described image data are passed to server end (or cloud) by data, and then server end (or cloud) is identified or judged
Afterwards, it controls corresponding device and completes feedback excitation, to complete instruction and guide process.
It will be appreciated that the device of above-mentioned completion feedback excitation can be independently of described image collection terminal or personal terminal, it can also
To be integrated in described image collection terminal or personal terminal, herein with no restrictions.
Dog according to an embodiment of the present invention only instructs and guides method, is occurred by only carrying out Activity recognition and bonding behavior to dog
Position, give dog only corresponding feedback excitation, realize that substitution manually only instructs and guides dog, improve the effect that dog is only instructed and guided
Rate greatly reduces human cost and economic cost that dog is only instructed and guided, ensure that the usage experience of user.
According to embodiments of the present invention, can further include in step S210: by least one image collecting device
Acquire the image data of the dog only.
Wherein, the image data of the dog only can derive from an image collecting device, can also derive from multiple figures
As acquisition device.By using multiple images acquisition device, the scope of activities of dog only can be covered comprehensively, and then is provided comprehensive
Dog behavior monitoring and instruction and guide data, can prevent in this way in single image acquisition device, can not obtain dog and be only positioned at image
Behavioral data except the coverage of acquisition device, to further increase the efficiency of instruction and guide.
According to embodiments of the present invention, can further include in step S220:
Go to the toilet the position in region described in the characteristic point position only of dog described in detection described image data and acquisition；
According to the position of the position of the characteristic point of the dog only and the region that goes to the toilet, judge whether the dog is only located at institute
State the region that goes to the toilet.
Illustratively, detecting the characteristic point of dog described in described image data only includes: only to carry out dog face based on the dog
Characteristic point detection and/or the detection of dog systemic features point, obtain the characteristic point position of the dog only.
In one embodiment, dog face characteristic point and/or the detection of dog systemic features point based on the dog, comprising:
Described image data are input to characteristic point detection model and obtain the characteristic point and its coordinate of the dog.Wherein, characteristic point is examined
Surveying model can be systemic features point detection model.
Illustratively, the region that goes to the toilet includes: the preassigned region of user.Wherein, the region that goes to the toilet can adopt
It is demarcated with color or optical markers.
Illustratively, the region that goes to the toilet is with color and/or shape attribute.It is possible to according to the region that goes to the toilet
Color or shape or optical markers detection described image data described in go to the toilet region and its coordinate.
Illustratively, the region that goes to the toilet includes round, oval, polygon or customized shape.Wherein, institute
Personalized customization can be carried out according to the hobby of user by stating the region that goes to the toilet, to increase the interest of instruction and guide process, while can be with
Meet the individual demand of user.
Illustratively, the region that goes to the toilet further includes multiple regions that go to the toilet.Wherein it is possible to be an image collecting device pair
Multiple regions that go to the toilet are answered, can also be that multiple images acquisition device corresponds to one or more and goes to the toilet region, this is not limited at this
System.
Illustratively, go to the toilet described in acquisition region position include: by object detection method detect described image data
Described in go to the toilet region, obtain the region that goes to the toilet position or user setting described in go to the toilet the position in region.
In one embodiment, described that the region that goes to the toilet described in described image data is detected by object detection method, it obtains
To the position in the region that goes to the toilet, comprising: using the region that goes to the toilet described in the object detection method detection based on deep learning, obtain
The position in the region that goes to the toilet and its coordinate.Wherein, the object detection method based on deep learning can be is nominated based on region
Method, such as Faster-RCNN and based on method, such as YOLO end to end, SSD etc..
In one embodiment, go to the toilet described in the user setting position in region includes: to go to the toilet region described in user's input
Position coordinates.
Illustratively, go to the toilet described in acquisition region position can also include: use described in go to the toilet the color or light in region
The region that goes to the toilet described in Mark Detection is learned, position and its coordinate in the region that goes to the toilet are obtained.
In one embodiment, go to the toilet described in the use region that goes to the toilet described in the color detection in region includes: using face
Go to the toilet region described in color characteristic HSV or RGB detection.Wherein, HSV (Hue, Saturation, Value) refers to hsv color model,
Including parametric tone (H), saturation degree (S), lightness (V)；RGB refers to rgb color mode, indicates the face in three channels of red, green, blue
Color.
Illustratively, go to the toilet described in acquisition region position can also include: from external data source obtain described in go to the toilet area
The position in domain and its coordinate.For example, data source (the i.e. external number that the position in the region that goes to the toilet and its coordinate pass through distinct device
According to source) setting or storage, can from the data source obtain described in go to the toilet region position and its coordinate.In this way, in the region that goes to the toilet
In the case where not changing, when the device of the method deployment cause to go to the toilet for some reason the information in region lose when, do not have to again into
Go to the toilet the information in region described in row identification or setting, can be obtained directly from Backup Data described in go to the toilet region position and its
Coordinate saves computing resource, further improves instruction and guide efficiency.
It should be appreciated that the present invention is not limited by the object detection method specifically used, either existing object detection method
Or the object detection method of exploitation in the future can be applied to dog according to an embodiment of the present invention only in instruction and guide method, and
It also should include within the scope of the present invention.
Illustratively, the position of the position and the region that goes to the toilet of the characteristic point according to the dog only judges the dog only
Whether the go to the toilet region is located at, comprising:
If the characteristic point positioned at rear leg section of at least described dog only is located at described go to the toilet in region, it is determined that the dog
It is only positioned at the region that goes to the toilet；And/or
If the characteristic point positioned at rear leg section of the dog only is not located at described go to the toilet in region, it is determined that the dog is only
It is not located at the region that goes to the toilet.
Wherein, only it can just guarantee that the dog is only going to the toilet when the rear leg section of the dog only is located at and goes to the toilet region
Go to lavatory is carried out in region, and the characteristic point of the rear leg section of dog only and other more characteristic points are located at described go to the toilet in region
When, the Go to lavatory of the dog only can also carry out in the region that goes to the toilet.So, it is only necessary to detect it is described after the characteristic point of leg section be
It is no to can determine whether the Go to lavatory of the dog only is located at the region that goes to the toilet in the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when the dog only after leg section all characteristic point coordinates in the boundary coordinate in the region that goes to the toilet or the model of boundary function
In enclosing, it is determined that the dog is only positioned at the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when the dog only after leg section at least one characteristic point coordinate not in the boundary coordinate or boundary letter in the region that goes to the toilet
In several ranges, it is determined that the dog is not only located at the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when be greater than or equal to preset ratio the dog only after leg section characteristic point coordinate the region that goes to the toilet boundary sit
In the range of mark or boundary function, it is determined that the dog is only positioned at the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when be less than the dog of preset ratio only after leg section boundary coordinate or side of the characteristic point coordinate in the region that goes to the toilet
In the range of bound function, it is determined that the dog is not only located at the region that goes to the toilet.
It will be appreciated that the preset ratio can according to need and be configured, herein with no restrictions.
According to embodiments of the present invention, in step S230, the early warning behavior can further include: defecation omen is dynamic
Make or defecation acts.
Illustratively, the defecation omen movement is squatted down including lifting a back leg or the bending of two back legs.
Illustratively, the defecation movement includes: the defecation omen movement, and discharge stool and/or urine.
Illustratively, identify that the behavior of dog described in described image data only includes: to identify institute by Activity recognition method
State the behavior of dog only.
Wherein, the Activity recognition method includes: iDT (improved dense trajectories) method, based on deep
Spend Two Stream Network (double-current CNN) and deriving method, C3D Network (3D convolution) method etc. of study.Ying Liao
The solution present invention is not limited by the Activity recognition method specifically used, either existing Activity recognition method or in the future exploitation
Activity recognition method, dog according to an embodiment of the present invention can be applied to only in instruction and guide method, and should also be included in this
In the protection scope of invention.
According to embodiments of the present invention, can further include in step S240:
When the dog is only positioned at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides positive incentive；With/
Or,
When the dog is only not at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides negative sense and swashs
It encourages.
Illustratively, can further include in step S240:
When the dog is only without appearance with early warning behavior, feedback excitation is not only provided to the dog.
Wherein, by only carrying out defecation behavior in the region that goes to the toilet to dog or attempting progress defecation behavior to give positive incentive,
And dog is not only carried out defecation behavior or attempt progress defecation behavior in the region that goes to the toilet to give negative incentive, from front and negative two
Dog is only strengthened in a direction, and guidance dog only will carry out defecation behavior in the region that goes to the toilet or attempt to carry out defecation behavior and forward direction
Excitation foundation contacts, and will not carry out defecation behavior in the region that goes to the toilet or attempt to carry out defecation behavior and negative incentive foundation connection
System, so that dog only for positive incentive is pursued, avoids negative incentive and learns to carry out defecation behavior or examination in the region that goes to the toilet
Figure carries out defecation behavior, to achieve the purpose that the instruction and guide dog only learns to pinpoint defecation.It is this that artificial realize is substituted by machine
The mode of dog only is instructed and guided, has been greatly saved artificial and economic cost, allowing user hardly to take energy can be solved the dog only row of fixed point
Just the problem of.
Illustratively, the positive incentive includes: that automatic feeder gives food and/or plays compliment voice.
Illustratively, the negative incentive includes: that voice or alarm song are reprimanded in broadcasting.
According to embodiments of the present invention, the method 200 further include:
The information of the behavior of the feedback excitation and its corresponding dog only is stored and/or analyzed, and is sent to user.
Illustratively, store and/or analyze the behavior of the feedback excitation and its corresponding dog only include: storage and/
Or in analysis all periods or the dog of predetermined amount of time behavioural information and corresponding feedback excitation only.
In one embodiment, it stores and analyzes in all periods or the dog of predetermined amount of time behavioural information only and right
After the feedback excitation answered, analysis report is generated, and the analysis report is sent to user.
Wherein, all behaviors of dog and its corresponding feedback excitation are recorded and is analyzed, and be sent to user, had
The progress and situation that dog only instructs and guides process are understood conducive to user, to decide whether to carry out manual intervention.When according to storage and/or point
The information for analysing the behavior of the feedback excitation and its corresponding dog only, when determining that the instruction and guide process make good progress, then user
Without intervening；Conversely, manual intervention can be then carried out, to improve the efficiency of instruction and guide.
According to embodiments of the present invention, the method 200 further include:
When the dog is only not at the region and when early warning behavior occur and continuing for the first predetermined time of going to the toilet, reminds and use
Family carries out human intervention；And/or
When the dog is only positioned at the region and when early warning behavior occur and continuing for the second predetermined time of going to the toilet, remind user complete
It is only instructed and guided at the dog.
In one embodiment, by the dog of the embodiment of the present invention only instruct and guide method distribution be deployed in Image Acquisition end and
For at personal terminal, method 200 is only instructed and guided to the dog and is further illustrated.The method 200 includes:
Firstly, opening dog on personal terminal only instructs and guides APP, Image Acquisition end acquires the image data of dog only, and will be described
Image data is sent at personal terminal；Described image data can be shown at personal terminal；
It is then detected that dog described in described image data only, judges whether the dog is only located at the region that goes to the toilet, and identification
The behavior of dog described in described image data only, judges whether the behavior of the dog only early warning behavior occurs；It specifically includes:
Identify whether the dog movement of defecation omen or defecation movement only occurs by Activity recognition method；And
The detection of dog systemic features point is only carried out to the dog in described image data, obtains the characteristic point of the dog only
Position, and the position in the region that goes to the toilet described in acquisition；Judge that whether being located at positioned at the characteristic point of rear leg section for the dog is described
It goes to the toilet in region, if the characteristic point positioned at rear leg section of at least described dog only is located at described go to the toilet in region, it is determined that institute
It states dog and is only positioned at the region that goes to the toilet；If the characteristic point positioned at rear leg section of the dog only is not located at the region that goes to the toilet
It is interior, it is determined that the dog is not only located at the region that goes to the toilet；
Then, only whether be located at according to the dog it is described go to the toilet region and whether the dog only early warning behavior occurs, to institute
It states dog and feedback excitation is only provided；It specifically includes:
When the dog is only positioned at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides positive incentive, such as
Personal terminal controls automatic feeder by sending corresponding control instruction and gives food and/or control playing device broadcasting
Praise voice；
When the dog is only not at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides negative sense and swashs
It encourages, as personal terminal reprimands voice or alarm song by sending corresponding control instruction control playing device broadcasting；
When the dog is only without appearance with early warning behavior, feedback excitation is not only provided to the dog；
Meanwhile it storing and analyzing in all periods or the dog of predetermined amount of time behavioural information only and corresponding feedback swash
It encourages, and is sent to user；
Finally, when the dog is only not at the region and when early warning behavior occur and continuing for the first predetermined time of going to the toilet,
User is reminded to carry out human intervention；Region and occur early warning behavior when the dog is only positioned at described go to the toilet and continued for the second predetermined time
When, it reminds user to complete the dog and only instructs and guides.
It follows that dog according to an embodiment of the present invention only instructs and guides method, by only carrying out Activity recognition and knot to dog
Dog only corresponding feedback excitation is given in the position that conjunction behavior occurs, and realizes that substitution manually only instructs and guides dog, improves dog only
The efficiency of instruction and guide greatly reduces human cost and economic cost that dog is only instructed and guided, ensure that the usage experience of user.
Fig. 3 shows the schematic block diagram that dog according to an embodiment of the present invention only instructs and guides device 300.As shown in figure 3, according to
The dog of the embodiment of the present invention only instructs and guides device 300
Image capture module 310, for acquiring the image data of dog only；
Dog detecting module 320 judges whether the dog is only located at such as detecting dog described in described image data only
Lavatory region；
Behavioural analysis module 330, for identification behavior of dog described in described image data only judge the row of the dog only
Whether to there is early warning behavior；
Feedback excitation module 340 described goes to the toilet region and whether the dog only goes out for only whether being located at according to the dog
Existing early warning behavior, Xiang Suoshu dog only provide feedback excitation.
Wherein, dog only instructs and guides device view-based access control model identification and machine learning techniques after the image data of acquisition dog, knows
Dog described in other image data only whether give corresponding in conjunction with the position of the dog prediction occurring behavior by prediction occurring behavior
Feedback excitation, guidance dog only go to the toilet in the region that goes to the toilet.Dog only instructs and guides device and is substituted by intelligent instruction and guide method manually in real time
It monitors dog only, judges that dog only acts in the method for machine learning, solve artificial culture dog and only pinpoint time-consuming and laborious ask that go to the toilet
Topic, is suitble to be widely used in family, the feeding dog place such as doghouse.
According to embodiments of the present invention, described image acquisition module 310 can further include: pass through at least one image
Acquisition module acquires the image data of the dog only.
Wherein, the image data of the dog only can derive from an image capture module, can also derive from multiple figures
As acquisition module.By using multiple images acquisition module, the scope of activities of dog only can be covered comprehensively, and then is provided comprehensive
Dog behavior monitoring and instruction and guide data, can prevent in this way in single image acquisition module, can not obtain dog and be only positioned at image
Behavioral data except the coverage of acquisition module, to further increase the efficiency of instruction and guide.
According to embodiments of the present invention, the dog detecting module 320 includes:
Dog position module 321, for detecting the characteristic point position of dog described in described image data only；
Regional location module 322, for obtaining the position in the region that goes to the toilet；
Position comparison module 323 is sentenced for the position of the characteristic point according to the dog only and the position in the region that goes to the toilet
Whether the dog of breaking only is located at the region that goes to the toilet.
Illustratively, dog position module 321 is also used to: only carrying out the detection of dog face characteristic point and/or dog based on the dog
The detection of systemic features point obtains the characteristic point position of the dog only.
In one embodiment, dog face characteristic point and/or dog whole body spy of the dog position module 321 based on the dog
Sign point detection, comprising: described image data are input to characteristic point detection model and obtain the characteristic point and its coordinate of the dog.
Wherein, characteristic point detection model can be systemic features point detection model.
Illustratively, the region that goes to the toilet includes: the preassigned region of user.Wherein, the region that goes to the toilet can adopt
It is demarcated with color or optical markers.
Illustratively, the region that goes to the toilet is with color and/or shape attribute.It is possible to according to the region that goes to the toilet
Color or shape or optical markers detection described image data described in go to the toilet region and its coordinate.
Illustratively, the region that goes to the toilet includes round, oval, polygon or customized shape.Wherein, institute
Personalized customization can be carried out according to the hobby of user by stating the region that goes to the toilet, to increase the interest of instruction and guide process, while can be with
Meet the individual demand of user.
Illustratively, the region that goes to the toilet further includes multiple regions that go to the toilet.Wherein it is possible to be an image collecting device pair
Multiple regions that go to the toilet are answered, can also be that multiple images acquisition device corresponds to one or more and goes to the toilet region, this is not limited at this
System.
Illustratively, regional location module 322 is also used to: being detected described in described image data by object detection method
Go to the toilet region, obtain the region that goes to the toilet position or user setting described in go to the toilet the position in region.
In one embodiment, it is detected in described image data described in regional location module 322 by object detection method
The region that goes to the toilet, obtains the position in the region that goes to the toilet, comprising: detects institute using the object detection method based on deep learning
The region that goes to the toilet is stated, position and its coordinate in the region that goes to the toilet are obtained.Wherein, the object detection method based on deep learning can be with
It is the method based on region nomination, such as Faster-RCNN and based on method, such as YOLO end to end, SSD etc..
In one embodiment, go to the toilet described in the user setting position in region includes: to go to the toilet region described in user's input
Position coordinates.
Illustratively, regional location module 322 can be also used for: color or the optical markers inspection in the region that goes to the toilet described in use
Go to the toilet region described in survey, obtains position and its coordinate in the region that goes to the toilet.
In one embodiment, it goes to the toilet described in the use of regional location module 322 and goes to the toilet described in the color detection in region
Region includes: using the region that goes to the toilet described in color characteristic HSV or RGB detection.Wherein, HSV (Hue, Saturation, Value)
Refer to hsv color model, including parametric tone (H), saturation degree (S), lightness (V)；RGB refers to rgb color mode, indicate it is red,
The color in green, blue three channels.
Illustratively, the position that the regional location module 322 obtains the region that goes to the toilet can also include: from external number
According to source obtain described in go to the toilet region position and its coordinate.For example, the position in the region that goes to the toilet and its coordinate are set by difference
Standby data source (i.e. external data source) setting or storage, can be obtained from the data source described in go to the toilet region position and its seat
Mark.In this way, in the case where the region that goes to the toilet does not change, when the device of the method deployment causes to go to the toilet for some reason the information in region
When loss, without re-starting the information in region of going to the toilet described in identification or setting, can be obtained directly from Backup Data described in
Go to the toilet region position and its coordinate, save computing resource, further improve instruction and guide efficiency.
It should be appreciated that the present invention is not limited by the object detection method specifically used, either existing object detection method
Or the object detection method of exploitation in the future can be applied to dog according to an embodiment of the present invention only in instruction and guide method, and
It also should include within the scope of the present invention.
Illustratively, the position comparison module 323 is also used to:
If the characteristic point positioned at rear leg section of at least described dog only is located at described go to the toilet in region, it is determined that the dog
It is only positioned at the region that goes to the toilet；And/or
If the characteristic point positioned at rear leg section of the dog only is not located at described go to the toilet in region, it is determined that the dog is only
It is not located at the region that goes to the toilet.
Wherein, only it can just guarantee that the dog is only going to the toilet when the rear leg section of the dog only is located at and goes to the toilet region
Go to lavatory is carried out in region, and the characteristic point of the rear leg section of dog only and other more characteristic points are located at described go to the toilet in region
When, the Go to lavatory of the dog only can also carry out in the region that goes to the toilet.So, it is only necessary to detect it is described after the characteristic point of leg section be
It is no to can determine whether the Go to lavatory of the dog only is located at the region that goes to the toilet in the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when the dog only after leg section all characteristic point coordinates in the boundary coordinate in the region that goes to the toilet or the model of boundary function
In enclosing, then the position comparison module 323 determines that the dog is only positioned at the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when the dog only after leg section at least one characteristic point coordinate not in the boundary coordinate or boundary letter in the region that goes to the toilet
In several ranges, then the position comparison module 323 determines that the dog is not only located at the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when be greater than or equal to preset ratio the dog only after leg section characteristic point coordinate the region that goes to the toilet boundary sit
In the range of mark or boundary function, then the position comparison module 323 determines that the dog is only positioned at the region that goes to the toilet.
In one embodiment, the position in the region that goes to the toilet includes the boundary coordinate or boundary letter in the region that goes to the toilet
Number, when be less than the dog of preset ratio only after leg section boundary coordinate or side of the characteristic point coordinate in the region that goes to the toilet
In the range of bound function, then the position comparison module 323 determines that the dog is not only located at the region that goes to the toilet.
It will be appreciated that the preset ratio can according to need and be configured, herein with no restrictions.
According to embodiments of the present invention, the early warning behavior can further include: the movement of defecation omen or defecation movement.
Illustratively, the defecation omen movement is squatted down including lifting a back leg or the bending of two back legs.
Illustratively, the defecation movement includes: the defecation omen movement, and discharge stool and/or urine.
Illustratively, the behavioural analysis module 330 is also used to: identifying the row of the dog only by Activity recognition method
For.
Wherein, the Activity recognition method includes: iDT (improved dense trajectories) method, based on deep
Spend Two Stream Network (double-current CNN) and deriving method, C3D Network (3D convolution) method etc. of study.Ying Liao
The solution present invention is not limited by the Activity recognition method specifically used, either existing Activity recognition method or in the future exploitation
Activity recognition method, dog according to an embodiment of the present invention can be applied to only in instruction and guide method, and should also be included in this
In the protection scope of invention.
According to embodiments of the present invention, the feedback excitation module 340 is also used to:
When the dog is only positioned at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides positive incentive；With/
Or,
When the dog is only not at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides negative sense and swashs
It encourages.
Illustratively, the feedback excitation module 340 is also used to:
When the dog is only without appearance with early warning behavior, feedback excitation is not only provided to the dog.
Wherein, the feedback excitation module 340 is by only carrying out defecation behavior in the region that goes to the toilet to dog or attempting to arrange
Just positive incentive is given in behavior, and does not only carry out defecation behavior in the region that goes to the toilet to dog or attempt progress defecation behavior to give negative sense
Excitation only strengthens dog from front and negative both direction, and guidance dog only will carry out defecation behavior or examination in the region that goes to the toilet
Figure carries out defecation behavior and contacts with positive incentive foundation, and will not carry out defecation behavior in the region that goes to the toilet or attempt to carry out defecation
Behavior is contacted with negative incentive foundation, so that dog avoids negative incentive and learn going to the toilet only for positive incentive is pursued
Region carries out defecation behavior or attempts to carry out defecation behavior, to achieve the purpose that the instruction and guide dog only learns to pinpoint defecation.It is this
In such a way that machine substitutes artificial realization instruction and guide dog only, it is greatly saved artificial and economic cost, user is allowed hardly to take essence
The problem of dog only pinpoints defecation can be solved in power.
Illustratively, the positive incentive includes: that automatic feeder gives food and/or plays compliment voice.
Illustratively, the negative incentive includes: that voice or alarm song are reprimanded in broadcasting.
According to embodiments of the present invention, described device 300 further include:
Information stores analysis module 350, for storing and/or analyzing the row of the feedback excitation and its corresponding dog only
For information, and be sent to user.
Illustratively, the information storage analysis module 350 is also used to: being stored and/or is analyzed and is in all periods or pre-
The behavioural information and corresponding feedback excitation of the dog for section of fixing time only.
In one embodiment, it the storage of information storage analysis module 350 and analyzes in all periods or pre- timing
Between section dog behavioural information and corresponding feedback excitation only after, generate analysis report, and the analysis report be sent to use
Family.
Wherein, the information storage analysis module 350 remembers all behaviors of dog and its corresponding feedback excitation
Record and analysis, and it is sent to user, be conducive to user and understand progress and situation that dog only instructs and guides process, to decide whether to carry out people
Work intervention.When determining the instruction according to the information for storing and/or analyzing the behavior of the feedback excitation and its corresponding dog only
When the process of leading make good progress, then user is without intervening；Conversely, manual intervention can be then carried out, to improve the efficiency of instruction and guide.
According to embodiments of the present invention, described device 300 further include:
Reminding module 360, for region and occurring early warning behavior when the dog is only not at described go to the toilet and continuing first
When the predetermined time, user is reminded to carry out human intervention；And/or
When the dog is only positioned at the region and when early warning behavior occur and continuing for the second predetermined time of going to the toilet, remind user complete
It is only instructed and guided at the dog.
It follows that dog according to an embodiment of the present invention only instructs and guides device, by only carrying out Activity recognition and knot to dog
Dog only corresponding feedback excitation is given in the position that conjunction behavior occurs, and realizes that substitution manually only instructs and guides dog, improves dog only
The efficiency of instruction and guide greatly reduces human cost and economic cost that dog is only instructed and guided, ensure that the usage experience of user.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
Fig. 4 shows the schematic block diagram that dog according to an embodiment of the present invention only instructs and guides system 400.Dog only instructs and guides system
400 include imaging sensor 410, storage device 420 and processor 430.
Imaging sensor 410 is for acquiring image data.
The storage of storage device 420 is for realizing the corresponding steps in dog according to an embodiment of the present invention only instruction and guide method
Program code.
The processor 430 is for running the program code stored in the storage device 420, to execute according to the present invention
The dog of embodiment only instructs and guides the corresponding steps of method, and only instructs and guides in device for realizing dog according to an embodiment of the present invention
Image capture module 310, dog detecting module 320, behavioural analysis module 330 and feedback excitation module 340.
In addition, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage
Instruction only instructs and guides method for executing the dog of the embodiment of the present invention when described program instruction is run by computer or processor
Corresponding steps, and only instruct and guide for realizing dog according to an embodiment of the present invention corresponding module in device.The storage medium
It such as may include the storage card of smart phone, the storage unit of tablet computer, the hard disk of personal computer, read-only memory
(ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB storage,
Or any combination of above-mentioned storage medium.The computer readable storage medium can be one or more computer-readable deposit
Any combination of storage media, such as a computer readable storage medium include by being randomly generated based on action command sequence
The readable program code of calculation machine, another computer readable storage medium include for carry out dog only instruct and guide it is computer-readable
Program code.
In one embodiment, the computer program instructions may be implemented real according to the present invention when being run by computer
The dog for applying example only instructs and guides each functional module of device, and/or can execute dog according to an embodiment of the present invention and only instruct and guide
Method.
Each module of the dog according to an embodiment of the present invention only in instruction and guide system can pass through dog according to an embodiment of the present invention
Only the processor computer program instructions that store in memory of operation of the electronic equipment of instruction and guide are realized, or can be in root
The computer instruction stored in computer readable storage medium according to the computer program product of the embodiment of the present invention is by computer
It is realized when operation.
Dog according to an embodiment of the present invention only instructs and guides method, apparatus, system and storage medium, by only going to dog
For the position that identification and bonding behavior occur, dog only corresponding feedback excitation is given, realizes that substitution manually only instructs dog
It leads, improves the efficiency that dog is only instructed and guided, greatly reduce human cost and economic cost that dog is only instructed and guided, ensure that user's
Usage experience.
Although describing example embodiment by reference to attached drawing here, it should be understood that above example embodiment are only exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects,
To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the invention should not be construed to reflect an intention that i.e. claimed
The present invention claims features more more than feature expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used
Sign is to solve corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in this specific
Embodiment, wherein each, the claims themselves are regarded as separate embodiments of the invention.
It will be understood to those skilled in the art that any combination pair can be used other than mutually exclusive between feature
All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method
Or all process or units of equipment are combined.Unless expressly stated otherwise, this specification (is wanted including adjoint right
Ask, make a summary and attached drawing) disclosed in each feature can be replaced with an alternative feature that provides the same, equivalent, or similar purpose.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any
Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize some moulds in article analytical equipment according to an embodiment of the present invention
The some or all functions of block.The present invention is also implemented as a part or complete for executing method as described herein
The program of device (for example, computer program and computer program product) in portion.It is such to realize that program of the invention can store
On a computer-readable medium, it or may be in the form of one or more signals.Such signal can be from internet
Downloading obtains on website, is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
The above description is merely a specific embodiment or to the explanation of specific embodiment, protection of the invention
Range is not limited thereto, and anyone skilled in the art in the technical scope disclosed by the present invention, can be easily
Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim
Subject to protection scope.
Claims (10)
1. a kind of dog only instructs and guides method, which is characterized in that the described method includes:
Acquire the image data of dog only；
It detects dog described in described image data only, judges whether the dog is only located at the region that goes to the toilet；
It identifies the behavior of dog described in described image data only, judges whether the behavior of the dog only early warning behavior occurs；
Only whether be located at according to the dog it is described go to the toilet region and whether the dog only early warning behavior occurs, Xiang Suoshu dog only provides
Feedback excitation.
2. the method as described in claim 1, which is characterized in that only whether be located at the region and described of going to the toilet according to the dog
Whether dog only there is early warning behavior, and Xiang Suoshu dog only provides feedback excitation, comprising:
When the dog is only positioned at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides positive incentive；And/or
When the dog is only not at the region and when there is early warning behavior of going to the toilet, Xiang Suoshu dog only provides negative incentive.
3. the method as described in claim 1, which is characterized in that dog described in detection described image data only, judges the dog
Only whether it is located at the region that goes to the toilet, comprising:
Go to the toilet the position in region described in the characteristic point position only of dog described in detection described image data and acquisition；
According to the position of the position of the characteristic point of the dog only and the region that goes to the toilet, judge the dog only whether be located at it is described such as
Lavatory region.
4. method as claimed in claim 3, which is characterized in that according to the position and the area that goes to the toilet of the characteristic point of the dog only
The position in domain, judges whether the dog is only located at the region that goes to the toilet, comprising:
If the characteristic point positioned at rear leg section of at least described dog only is located at described go to the toilet in region, it is determined that the dog position
In the region that goes to the toilet；And/or
If the characteristic point positioned at rear leg section of the dog only is not located at described go to the toilet in region, it is determined that the dog not position
In the region that goes to the toilet.
5. method as claimed in claim 3, which is characterized in that the position in the region that goes to the toilet described in acquisition includes: to be examined by target
Go to the toilet region described in survey method detection described image data, obtain the region that goes to the toilet position or user setting described in such as
The position in lavatory region.
6. the method as described in claim 1, which is characterized in that the method also includes:
When the dog is only not at the region and when early warning behavior occur and continuing for the first predetermined time of going to the toilet, remind user into
Row human intervention；And/or
When the dog is only positioned at the region and when early warning behavior occur and continuing for the second predetermined time of going to the toilet, user is reminded to complete institute
Dog is stated only to instruct and guide.
7. the method as described in claim 1, which is characterized in that the early warning behavior includes:
The information of the behavior of the feedback excitation and its corresponding dog only is stored and/or analyzed, and is sent to user.
8. a kind of dog only instructs and guides device, which is characterized in that described device includes:
Image capture module, for acquiring the image data of dog only；
Dog detecting module judges whether the dog is only located at the region that goes to the toilet for detecting dog described in described image data only；
Whether behavioural analysis module, for identification behavior of dog described in described image data only judge the behavior of the dog only
There is early warning behavior；
Feedback excitation module described goes to the toilet region and whether the dog early warning row only occurs for only whether being located at according to the dog
For Xiang Suoshu dog only provides feedback excitation.
9. a kind of dog only instructs and guides system, including memory, processor and it is stored on the memory and on the processor
The computer program of operation, which is characterized in that the processor is realized in claim 1 to 7 when executing the computer program
The step of any one the method.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is counted
The step of calculation machine realizes any one of claims 1 to 7 the method when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463078.XA CN110321796A (en) | 2019-05-30 | 2019-05-30 | A kind of dog only instructs and guides method, apparatus, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463078.XA CN110321796A (en) | 2019-05-30 | 2019-05-30 | A kind of dog only instructs and guides method, apparatus, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110321796A true CN110321796A (en) | 2019-10-11 |
Family
ID=68119282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910463078.XA Pending CN110321796A (en) | 2019-05-30 | 2019-05-30 | A kind of dog only instructs and guides method, apparatus, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321796A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111406669A (en) * | 2020-05-06 | 2020-07-14 | 江苏农牧科技职业学院 | Method for adjusting human-trapping behavior of household pet dog |
| CN114128671A (en) * | 2021-11-26 | 2022-03-04 | 广州鼎飞航空科技有限公司 | Animal training method and control device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150128878A1 (en) * | 2013-11-12 | 2015-05-14 | E-Collar Technologies, Inc. | System and method for preventing animals from approaching certain areas using image recognition |
| US20160316716A1 (en) * | 2015-04-30 | 2016-11-03 | Kevin Hanson | Methods and device for pet enrichment |
| CN106455523A (en) * | 2014-10-31 | 2017-02-22 | 深圳市大疆创新科技有限公司 | Systems and methods for walking pets |
| CN107466205A (en) * | 2016-05-08 | 2017-12-12 | 深圳市欸阿技术有限公司 | Method and system, wearing terminal, induction terminal, the dispensing terminal of defecation supervision |
| CN109582810A (en) * | 2018-12-03 | 2019-04-05 | 泰芯科技（杭州）有限公司 | A kind of dog dog management system and its implementation based on deep learning |
-
2019
- 2019-05-30 CN CN201910463078.XA patent/CN110321796A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150128878A1 (en) * | 2013-11-12 | 2015-05-14 | E-Collar Technologies, Inc. | System and method for preventing animals from approaching certain areas using image recognition |
| CN106455523A (en) * | 2014-10-31 | 2017-02-22 | 深圳市大疆创新科技有限公司 | Systems and methods for walking pets |
| US20160316716A1 (en) * | 2015-04-30 | 2016-11-03 | Kevin Hanson | Methods and device for pet enrichment |
| CN107466205A (en) * | 2016-05-08 | 2017-12-12 | 深圳市欸阿技术有限公司 | Method and system, wearing terminal, induction terminal, the dispensing terminal of defecation supervision |
| CN109582810A (en) * | 2018-12-03 | 2019-04-05 | 泰芯科技（杭州）有限公司 | A kind of dog dog management system and its implementation based on deep learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111406669A (en) * | 2020-05-06 | 2020-07-14 | 江苏农牧科技职业学院 | Method for adjusting human-trapping behavior of household pet dog |
| CN114128671A (en) * | 2021-11-26 | 2022-03-04 | 广州鼎飞航空科技有限公司 | Animal training method and control device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Norton et al. | Precision livestock farming: Building ‘digital representations’ to bring the animals closer to the farmer | |
| Macé et al. | The time-course of visual categorizations: you spot the animal faster than the bird | |
| Orquin et al. | Attention and choice: A review on eye movements in decision making | |
| JP5156030B2 (en) | Activity monitoring and display | |
| CN111275911B (en) | Danger prompting method, equipment and computer readable storage medium | |
| CN105260731A (en) | Human face living body detection system and method based on optical pulses | |
| CN109817312A (en) | A kind of medical bootstrap technique and computer equipment | |
| CN110008859A (en) | The dog of view-based access control model only recognition methods and device again | |
| CN110321796A (en) | A kind of dog only instructs and guides method, apparatus, system and storage medium | |
| CN107133629B (en) | Picture classification method and device and mobile terminal | |
| CN109169365A (en) | The guidance system of pet behavior | |
| CN109086696B (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
| CN105844106A (en) | Health prompting method and device | |
| AU2020222048A1 (en) | Methods and apparatus for livestock rearing | |
| Marin-Cudraz et al. | Acoustic monitoring of rock ptarmigan: A multi-year comparison with point-count protocol | |
| Campbell | A new spatial framework incorporating uncertain stock and fleet dynamics for estimating fish abundance | |
| CN109522858A (en) | Plant disease detection method, device and terminal device | |
| CN109709546B (en) | Pet state monitoring method and device | |
| CN108710820A (en) | Infantile state recognition methods, device and server based on recognition of face | |
| CN104519143A (en) | Method and system for improving work and rest health of old people on basis of intelligent terminal | |
| Bernos et al. | What can be learned from fishers’ perceptions for fishery management planning? Case study insights from Sainte-Marie, Madagascar | |
| JP2017223812A (en) | Apparatus control system, apparatus control method and control program | |
| Doornweerd et al. | Passive radio frequency identification and video tracking for the determination of location and movement of broilers | |
| CN112489815A (en) | Depression emotion monitoring method and device and readable storage medium | |
| Aodha et al. | Towards a general approach for bat echolocation detection and classification |
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 |
Application publication date: 20191011 |
|
| RJ01 | Rejection of invention patent application after publication |