CN106815569A - The method and apparatus of repeatedly contrast identification is carried out for destination object - Google Patents
The method and apparatus of repeatedly contrast identification is carried out for destination object Download PDFInfo
- Publication number
- CN106815569A CN106815569A CN201611262770.9A CN201611262770A CN106815569A CN 106815569 A CN106815569 A CN 106815569A CN 201611262770 A CN201611262770 A CN 201611262770A CN 106815569 A CN106815569 A CN 106815569A
- Authority
- CN
- China
- Prior art keywords
- face
- information
- identification information
- basis
- basis identification
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of method and apparatus that repeatedly contrast identification is carried out for destination object, and the method includes：Obtain the first face basis identification information of destination object；First face basis identification information is contrasted with face standard logo information；If the first face basis identification information and face's standard logo information match, send lock instruction lock onto target object；If mismatching, judge whether the first face basis identification information is destination object by face's basis identification information for being obtained after lift face；If so, then reducing the second face basis identification information before basis identification information to the destination object lift face of the first face；Second face basis identification information is contrasted with face standard logo information；If matching, send lock instruction and lock the destination object.The method and apparatus that the application is provided solves unmanned plane of the prior art during being identified to destination object, there is the inaccurate technical problem of identification information.
Description
Technical field
The present invention relates to unmanned air vehicle technique field, more particularly to a kind of side that repeatedly contrast identification is carried out for destination object
Method and equipment.
Background technology
Unmanned plane (English:Aircraft), refer to obtain air force by the relative motion of fuselage and air to go up to the air
The machine of flight.Including gyroplane, helicopter, fixed-wing etc..
At present, by synchronously having carried out the technologies such as information gathering, target identification tracking in unmanned plane in the air flight course
Gradually form one trend.
However, continuing to develop with shaping technique, and shaping trend rapidly spreads in recent years, and big people from portion is particularly
Purposive related personnel such as crime one's share of expenses for a joint undertaking, information spy etc., it will usually unmanned plane shooting is escaped by face's shaping and is known
The image information collecting of other system and identification, to cause unmanned plane accurately to obtain and recognize the identification information of destination object,
Then great obstacle is caused to the technology for being identified tracking to destination object by unmanned plane.
It can be seen that, there is identification information and forbidden in unmanned plane of the prior art during being identified to destination object
True technical problem.
The content of the invention
The present invention provides a kind of method and apparatus that repeatedly contrast identification is carried out for destination object, is used to solve existing skill
There is the inaccurate technical problem of identification information during being identified to destination object in the unmanned plane in art.
In a first aspect, the embodiment of the present application provides one kind carries out repeatedly contrast knowledge method for distinguishing for destination object, should
For unmanned plane, methods described includes：Obtain the first anticipation positional information of destination object；Believe according to the first anticipation position
Breath obtains the first face basis identification information of the destination object；By first face basis identification information and structure in advance
Standard database in face's standard logo information contrasted；If the first face basis identification information and the face
Standard logo information match, then send lock instruction and lock the destination object；If the first face basis identification information
Mismatched with face's standard logo information, then judge whether the first face basis identification information is the destination object
By the face's basis identification information obtained after lift face；If so, then reducing first face basis identification information to described
The second face basis identification information before destination object lift face；By second face basis identification information and face's standard
Identification information is contrasted；If the second face basis identification information and face's standard logo information match, send out
Lock instruction is sent to lock the destination object.
Optionally, it is described that first face basis identification information is marked with the face in the advance standard database for building
Quasi- identification information carries out contrast to be included：First face basis identification information is carried out into priority classification, described the after classification
One face basis identification information includes the first priority match information, the second priority match information and third priority matching letter
Breath；First face basis identification information is contrasted according to priority orders with face's standard logo information；Institute
Stating priority orders includes：It is excellent to the described 3rd from the first priority match information, the second priority match information
The order of first level match information；If the first face basis identification information and face's standard logo information match
Including：If the first priority match information and face's standard logo information match, judge first face
Basic identification information and face's standard logo information match；Or, if the second priority match information and described
Third priority match information with face's standard logo information match, then judge first face basis mark letter
Breath and face's standard logo information match.
Optionally, the first face basis identification information includes：First cheekbone basis identification information, the first eye basis
Identification information, the first nose basis identification information, the first supercilium basis identification information, the first ear basis identification information, first
Tooth portion identification information；Wherein, the first cheekbone basis identification information is the first priority match information；The first eye base
Plinth identification information, first nose basis identification information and first supercilium basis identification information are the second priority match
Information；The first ear basis identification information and the first tooth portion identification information are third priority match information；It is described
Face's standard logo information includes：Cheekbone standard logo information, eye standard logo information, nose standard logo information, supercilium
Standard logo information, ear standard logo information, tooth ministerial standard identification information.
Optionally, it is described to judge whether first face basis identification information is the destination object by institute after lift face
Face's basis identification information of acquisition includes：Build the adjusting range region of the standard logo information；Obtain first face
Comparison difference information of portion's basis identification information relative to face's standard logo information；Judging the comparison difference information is
It is no between the adjusting range region；If so, then the first face basis identification information is the destination object by whole
The face's basis identification information obtained after appearance.
Optionally, the second face before the reduction the first face basis identification information to destination object lift face
Basic identification information includes：According to the comparison difference information, first face basis identification information is corrected；To repair
Face's basis identification information after just is defined as the second face basis identification information.
Second aspect, the embodiment of the present application provides a kind of equipment for being identified for destination object, is applied to
Unmanned plane, the equipment includes：Position module, the first anticipation positional information for obtaining destination object；Acquisition module, is used for
The first face basis identification information of the destination object is obtained according to the first anticipation positional information；First contrast module,
For first face basis identification information to be carried out with the face's standard logo information in the advance standard database for building
Contrast；First locking module, if for first face basis identification information and face's standard logo information match,
Then send lock instruction and lock the destination object；Judge module, if for first face basis identification information with it is described
Face standard logo information is mismatched, then judge whether the first face basis identification information is the destination object by whole
The face's basis identification information obtained after appearance；Recovery module, for if so, then reducing the first face basis identification information
The second face basis identification information before to the destination object lift face；Second contrast module, for by second face base
Plinth identification information is contrasted with face's standard logo information；Second locking module, if for second face basis
Identification information and face's standard logo information match, then send lock instruction and lock the destination object.
Optionally, first contrast module includes：First contrast submodule, for first face basis to be identified
Information carries out priority classification, and the first face basis identification information includes the first priority match information, second after classification
Priority match information and third priority match information；Second contrast submodule, for first face basis to be identified
Information is contrasted according to priority orders with face's standard logo information；The priority orders include：From described
The order of one priority match information, the second priority match information to the third priority match information；Described
One locking module is additionally operable to：If the first priority match information and face's standard logo information match, judge
The first face basis identification information and face's standard logo information match；Or, if second priority
With information and the third priority match information with face's standard logo information match, then judge first face
Portion's basis identification information and face's standard logo information match.
Optionally, the first face basis identification information includes：First cheekbone basis identification information, the first eye basis
Identification information, the first nose basis identification information, the first supercilium basis identification information, the first ear basis identification information, first
Tooth portion identification information；Wherein, the first cheekbone basis identification information is the first priority match information；The first eye base
Plinth identification information, first nose basis identification information and first supercilium basis identification information are the second priority match
Information；The first ear basis identification information and the first tooth portion identification information are third priority match information；It is described
Face's standard logo information includes：Cheekbone standard logo information, eye standard logo information, nose standard logo information, supercilium
Standard logo information, ear standard logo information, tooth ministerial standard identification information.
Optionally, the judge module also includes：First judging submodule, the tune for building the standard logo information
Whole range areas；Second judging submodule, for obtaining the first face basis identification information relative to face's standard
The comparison difference information of identification information；3rd judging submodule, for judging the comparison difference information whether in the adjustment
Between range areas；4th judging submodule, for if so, then the first face basis identification information is the destination object
By the face's basis identification information obtained after lift face.
Optionally, the recovery module includes：First reduction submodule, for according to the comparison difference information, to institute
The first face basis identification information is stated to be corrected；Second reduction submodule, for by revised face basis identification information
It is defined as the second face basis identification information.
The method and apparatus that the embodiment of the present application is provided, when unmanned plane is applied to, judges the first face basis mark letter
After breath and face's standard logo information are mismatched, increased and judge whether the first face basis identification information is destination object warp
The face's basis identification information obtained after lift face is crossed, and where it has, by reducing the first face basis mark letter
Cease to the second face basis identification information before destination object lift face；Then again by reduction after the second face basis identification information
Contrasted with face standard logo information, the final face's basis mark for the application is effectively ensured the contrast of participation information
The accuracy of knowledge information, solves unmanned plane of the prior art during being identified to destination object, existing
The inaccurate technical problem of identification information.
Described above is only the general introduction of technical solution of the present invention, in order to better understand technological means of the invention,
And can be practiced according to the content of specification, and in order to allow the above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by specific embodiment of the invention.
Brief description of the drawings
In order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are this hairs
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart of method being identified for target in the embodiment of the present application；
Fig. 2 is the contrast schematic flow sheet of basic identification information and standard logo information in the embodiment of the present application；
Fig. 3 be the embodiment of the present application in destination object whether by shaping determination methods flow chart；
Fig. 4 is the theory diagram of equipment being identified for target in the embodiment of the present application.
Specific embodiment
A kind of method and apparatus that repeatedly contrast identification is carried out for destination object of confession that the embodiment of the present application is carried, is used to solve
There is the inaccurate technology of identification information and ask in unmanned plane certainly of the prior art during being identified to destination object
Topic, has reached accuracy of identification technique effect high.
Technical scheme in the embodiment of the present application, general thought is as follows：
When unmanned plane is identified for destination object, the first face basis mark letter of destination object is obtained first
Breath；It is right that the face's standard logo information in standard database by first face basis identification information with advance structure is carried out
Than；If the first face basis identification information and face's standard logo information match, send lock instruction locking
The destination object；If the first face basis identification information is mismatched with face's standard logo information, institute is judged
Whether state the first face basis identification information is the destination object by face's basis identification information for being obtained after lift face；If
It is then to reduce the second face basis identification information before the first face basis identification information to destination object lift face；
Second face basis identification information is contrasted with face's standard logo information；If the second face basis mark
Knowledge information and face's standard logo information match, then send lock instruction and lock the destination object.
The above method increased and judge whether the first face basis identification information is destination object by being obtained after lift face
Face's basis identification information judgement step so that when the identification of destination object is carried out by unmanned plane, when running into detection
To the first face basis identification information and standard database in face's standard logo information mismatch when, determine whether it
Whether it is, by inaccurate information acquired after lift face, to solve current unmanned plane in the process being identified to destination object
In, image information collecting and identification that identification target escapes unmanned plane imaging identification system by the method for lift face are run into, after
And caused unmanned plane cannot be obtained accurately and recognize the technological deficiency of the identification information of destination object.
To make the purpose, technical scheme and advantage of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In accompanying drawing, the technical scheme in the embodiment of the present application is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
The terms "and/or", only a kind of incidence relation for describing affiliated partner, represents there may be three kinds of passes
System, for example, A and/or B, can represent：Individualism A, while there is A and B, individualism B these three situations.In addition, herein
Middle character "/", typicallys represent forward-backward correlation pair as if a kind of relation of "or".
Embodiment one
The present embodiment provides a kind of method and apparatus being identified for destination object, refer to Fig. 1, methods described bag
Include：
Step S100, obtains the first face basis identification information of destination object；
Step S200, the face's standard in standard database by first face basis identification information with advance structure
Identification information is contrasted；
Step S300a, if first face basis identification information and face's standard logo information match, send out
Lock instruction is sent to lock the destination object；
Step S300b, if first face basis identification information is mismatched with face's standard logo information, sentences
Whether disconnected first face basis identification information is that face basis mark of the destination object by being obtained after lift face is believed
Breath；
Step S400, if so, then reducing the before first face basis identification information to the destination object lift face
Two faces basis identification information；
Step S500, second face basis identification information is contrasted with face's standard logo information；
Step S600, if second face basis identification information and face's standard logo information match, send out
Lock instruction is sent to lock the destination object.
For example, methods described can apply to unmanned plane, it is not intended that methods described can be only applied to unmanned plane.
In other words, the methods described that the present embodiment is provided can be additionally used in other electronic equipments with Functions of Transportation, for example
For：With having for electronic information communication function be man-machine, automobile with electronic information communication function, with electronic information communication work(
Motorcycle, the steamer with electronic information communication function of energy etc..
Specifically, continuing to develop with shaping technique, and shaping trend rapidly spreads in recent years, big people from portion is special
It is not purposive related personnel such as crime one's share of expenses for a joint undertaking, information spy etc., it will usually unmanned plane is escaped by face's shaping and is taken the photograph
Image information collecting and identification as identifying system.Studied according to inventor and found, once destination object is by way of shaping pair
The partial parameters information of face is modified adjustment, such as cheekbone information, eye information, nose information, supercilium information, ear's letter
Breath, tooth portion information etc., then just cannot be with standard by the facial information of the destination object acquired in unmanned plane imaging identification system
Information in database carries out contrast matching, to cause unmanned plane accurately to obtain and recognize the identification information of destination object,
Then great obstacle is caused to the technology for being identified tracking to destination object by unmanned plane.The side that the present invention is provided
Method, increased face standard logo information in it run into the first face for detecting basis identification information and standard database not
During matching, determine whether whether it is by inaccurate information acquired after lift face, with high beneficial of accuracy of identification
Effect.
Below, the method being identified for destination object that the application is provided is described in detail with reference to Fig. 1：
First, step S100 is performed, the first face basis identification information of destination object is obtained；
Specifically, the first face basis identification information for obtaining destination object can be affixed to unmanned aerial vehicle body bottom
Camera system with camera function is obtained, and the camera system can include a video camera.The video camera photographs pre-
During the destination object for first determining, the light reflected on destination object is collected by camera lens, is focused on it and is taken the photograph smooth surface and (for example take the photograph
Row amplifies), then processed and adjusted by the internal circuit of video camera, the standard signal for finally obtaining is remembered on the recording medium
Record is got off, while passed by the number inside unmanned plane or scheme biography passage that the standard signal is sent into ground based terminal such as earth station
On show.
Certainly, due to during shooting destination object may be an object for static state, it is also possible to be one move
The object of state.Introduced one by one below for two kinds of situations：
The first situation, when destination object is the object of static state, the camera lock onto target object of video camera enters
Row information is gathered, if be now adjusted without the camera orientation to video camera, nothing is can control by ground station terminal
Man-machine hovering is aerial, and then realizes when being acquired for destination object on a direction.And when adjustment unmanned plane is relative to mesh
The collection orientation of object is marked, it is necessary to when controlling the rotation angle of camera of video camera, then can control nobody by ground station terminal
Machine does corresponding flight adjustment action, such as flight forward in the air, or flies backward, or flies to the left, or flight etc. to the right, comes
Complete the angle adjustment of the camera relative to destination object of video camera.In addition, in the process, except flying for control unmanned plane
Action is made, realize the camera of video camera relative to the angle adjustment of destination object outside, the embodiment of the present application can also be by control
Video camera on head processed carries out rotary oscillation, realizes that video camera itself is adjusted relative to the acquisition angles of destination object,
Now unmanned plane can be still within the state of hovering in whole process.
Second situation, when destination object is a dynamic object, the camera lock onto target object of video camera enters
Row information is gathered, and now because destination object is a dynamic motion process, then the camera in order to make video camera is locked
The object that sets the goal is identified, it is necessary to which unmanned plane and camera system are also integrally a dynamic motion process, only in this way,
Just can guarantee that video camera camera can real-time capture to destination object image/video information.Therefore, in this case,
The embodiment of the present application synchronously controls the state of flight of unmanned plane in destination object moving process by ground station terminal, with
And rotary oscillation is carried out by the video camera on ground station terminal's control head, and then come by both unmanned plane and video camera
It is synchronized with the movement and guarantees real-time capture to the image/video information of destination object.
It should be noted that above-mentioned two situations are not in the embodiment of the present application two kinds of fixed situations.In other words
Say, whether the movement of destination object is uncertain, and at the t1 moment, destination object is a static state in location A, in t2
Carve, destination object is possible to still in location A, but be also possible to destination object and B location is moved to by location A.Now target pair
As just switching to posterior dynamic process by first static process.And then it is also required to the control shape of unmanned plane and/or video camera
State is switched over according to the method described above, has matched the status information of corresponding destination object.Being finally reached being capable of real-time capture mesh
Mark the technique effect of the image/video information of object.
In addition, before step S100 is performed, namely before the first face basis identification information for obtaining destination object,
The the first anticipation positional information for obtaining destination object can also be increased.
In other words, unmanned plane is being needed to go to catch the first face basis identification information of destination object by camera system
When, due to being not aware that accurate location or the band of position of destination object.Now, in order to avoid unmanned plane is in the boundless and indistinct sea of faces
The single comparison of object is looked for, comparison time is saved, comparison efficiency is improved.The embodiment of the present invention before step S100 is performed,
The first anticipation positional information of destination object can be also in advance obtained, the first anticipation positional information can be by official or media
The destination object of offer it is possible that precise area, or the region that destination object often occurs so gets this
After first anticipation positional information, you can targetedly go to obtain the first face basis mark of destination object in the band of position
Knowledge information.Comparison time is highly shortened, comparison efficiency is improve.
Next, after the first face basis identification information for getting destination object, step S200 is performed, will be described
First face basis identification information is contrasted with the face's standard logo information in the advance standard database for building；
In the embodiment of the present application, the standard database of advance structure here can be collected for destination object
" true information ", i.e. should " true information " can be understood as the information of true identity destination object identity characteristic.The information can be with
Or its place where his residence is registered by public security organ, or the authoritative institution such as medical institutions provide such as suspect or feelings
Spy etc. is reported truly to record record information on record, the application is built into above-mentioned normal data by by above-mentioned record information
Storehouse, and in certain period of time, such as every month, or per the first quarter, or each half a year continuation are updated, to ensure
The information accuracy of the standard database.
You need to add is that, in the embodiment of the present application, the mode being updated of continuation has many kinds, in this this Shen
Please embodiment be mainly described below two kinds：
The first, substituting renewal, the data that will update every time replace first data, and the mode of this kind of renewal can be with
The accuracy on the one hand ensureing data message is reached, the beneficial effect of internal memory occupancy volume is on the other hand reduced；
Second, cumulative bad updates, and the data that will be updated every time are found memory space and existed again, this kind of renewal
Mode can reach the technique effect for ensuring data message integrality.
Further, on the premise of above-mentioned second update mode, the step of painting table analysis can also be increased, i.e., every
After secondary renewal obtains new data message, can add up to paint table, form status tracking figure, splay is entered with lasting understanding destination object
Line, reaches the technique effect for controlling the action of its next step in advance.
Further, Fig. 2 is referred to, the face in standard database by the first face basis identification information with advance structure
Ministerial standard identification information carries out contrast can compare according to following sub-step：
Step S201, carries out priority classification, first face after classification by first face basis identification information
Basic identification information includes the first priority match information, the second priority match information and third priority match information；
Step S202, first face basis identification information is believed according to priority orders with face's standard logo
Breath is contrasted；The priority orders include：From the first priority match information, the second priority match information
To the order of the third priority match information；
Before step S201 and step S202 is discussed in detail, in order to preferably illustrate the application, below first to the application
The the first face basis identification information and the type of face's standard logo information that embodiment is provided elaborate：
In the embodiment of the present application, the first face basis identification information can include：First cheekbone basis mark letter
Breath, the first eye basis identification information, the first nose basis identification information, the first supercilium basis identification information, first ear's base
Plinth identification information, the first tooth portion identification information；Wherein, the first cheekbone basis identification information is the first priority match letter
Breath；First eye basis identification information, first nose basis identification information and first supercilium basis mark letter
It is the second priority match information to cease；The first ear basis identification information and the first tooth portion identification information are the 3rd excellent
First level match information.Face's standard logo information can include：Cheekbone standard logo information, eye standard logo information,
Nose standard logo information, supercilium standard logo information, ear standard logo information, tooth ministerial standard identification information.
Wherein, the first cheekbone basis identification information and cheekbone standard logo information Corresponding matching；First eye basis mark
Information is matched with the contrast of eye standard logo information；First nose basis identification information and the contrast of nose standard logo information
Match somebody with somebody；First supercilium basis identification information is matched with the contrast of supercilium standard logo information；First ear basis identification information and ear
The contrast matching of standard logo information；First tooth portion identification information is matched with the contrast of tooth ministerial standard identification information.
Specifically, the first cheekbone basis identification information is the first priority match information；The first eye base
Plinth identification information, first nose basis identification information and first supercilium basis identification information are the second priority match
Information；The first ear basis identification information and the first tooth portion identification information are third priority match information.Here
It should be noted that the first priority match information, the second priority match information and third priority match information is preferential
Level grade is reduced successively.That is, priority of the priority of the first priority match information more than the second priority match information,
Priority of the priority of the second priority match information more than third priority match information.
It is very representative mark meaning it should be noted that identification information of the cheekbone as face, and the later stage
The difficulty that destination object changes it adjustment is also maximum, namely identification meaning highest, therefore in the embodiment of the present application by cheekbone
Basic identification information is used as priority-level highest the first priority match information.Nose, supercilium, eye are representative due to it
Mark meaning be not it is obvious that and later stage destination object easily changes it adjustment, therefore in the embodiment of the present application by nose
Basic identification information, supercilium basis identification information, eye basis identification information are as priority-level inferior to cheekbone basis mark
Second priority match information of information.And ear and tooth, do not collected because the two identification informations are easily blocked,
Easily blocked by hair such as ear, tooth is caught when destination object does not open face less than etc., therefore by ear's basis mark
Information and tooth basis identification information are used as the minimum third priority match information of priority-level.
Therefore, in above-mentioned matching order, the embodiment of the present application is according to from the first priority match information, described
Second priority match information is matched to the order of the third priority match information.
Subsequently, according to the judged result of step S200, selection performs step S300a or step S300b：
Step S300a, if first face basis identification information and face's standard logo information match, send out
Lock instruction is sent to lock the destination object；
Step S300b, if first face basis identification information is mismatched with face's standard logo information, sentences
Whether disconnected first face basis identification information is that face basis mark of the destination object by being obtained after lift face is believed
Breath；
In specific implementation process, as stated above, with continuing to develop for shaping technique, and shaping becomes in recent years
Gesture rapidly spreads, and big people from portion is particularly purposive related personnel such as crime one's share of expenses for a joint undertaking, information spy etc., it will usually by face
Image information collecting and the identification of unmanned plane imaging identification system are escaped in portion's shaping, once and side that destination object passes through shaping
Formula to being modified for characterizing the parameter of facial information, then by the destination object acquired in unmanned plane imaging identification system
Facial information just cannot carry out contrast and match with " true information " in standard database, to cause unmanned plane accurately to obtain simultaneously
The identification information of destination object is recognized, is then caused greatly to the technology for being identified tracking to destination object by unmanned plane
Obstacle.
Therefore, the application is the contrast according to step S200, can there are two as described in step S300a and step S300b
Plant match condition.
Referring initially to step S300a, the step refers to when first face basis identification information and face's standard logo
During information match, then it represents that the destination object is the object that unmanned plane wants recognition and tracking, lock instruction locking is now sent
The destination object is tracked.
Specifically, if first face basis identification information can with face's standard logo information match
At least to include the following two kinds match condition：
The first match condition, if the first priority match information and face's standard logo information match,
Then judge the first face basis identification information and face's standard logo information match；
Second match condition, if the second priority match information and the third priority match information are and institute
Face's standard logo information match is stated, then judges the first face basis identification information and face's standard logo information
Match.
In other words, in priority-level highest the first priority match information and face's standard logo information phase
In the case of matching, now can be without matching the second priority match information and the third priority match information again
Whether with face's standard logo information match.And when in priority-level highest the first priority match information and institute
State face's standard logo information it is unmatched in the case of, at this point it is possible to respectively by the second priority match information and described
Third priority match information and face's standard logo information match, in this application, when priority-level highest
When first priority match information is mismatched with face's standard logo information, now only described second priority match is believed
Breath and the third priority match information with face's standard logo information match, then just can determine that first face
Portion's basis identification information and face's standard logo information match.The accuracy of identification of the embodiment of the present application is improved with this.
Step S300b is seen again, and the step refers to when first face basis identification information and face's standard logo
When information is mismatched, then it represents that the destination object is possible to not be object that unmanned plane wants recognition and tracking.Now in the application reality
Apply and the destination object is carried out in order to more accurately accurately identify judgement in example, to improve the accuracy of identification of the application, in this regard,
The application continues executing with following step：Judge whether first face basis identification information is the destination object by lift face
The face's basis identification information for being obtained afterwards.
Certainly, supplement is needed exist for, when step S300b is performed, if first face basis mark for judging
Information is not the destination object by the face's basis identification information obtained after lift face, then send switching command switching next
Individual destination object is identified.That is, step S100 is re-executed, re-recognizing for next destination object is carried out.
Where like, go to catch the first face basis of next destination object by camera system unmanned plane is needed
During identification information, if now unmanned plane camera system is the identification contrast carried out based on the first first anticipation positional information,
Now have determined that mismatch, then it represents that the first anticipation positional information is wrong.That is, the first anticipation positional information is changed herein,
The second anticipation positional information of destination object, the second anticipation positional information and the first anticipation position are obtained by official or media
Confidence breath is the same, be represent destination object it is possible that precise area, or the region that destination object often occurs,
After so getting the second anticipation positional information, you can targetedly go in the band of position to obtain the of destination object
One face basis identification information.Comparison time is extremely shorten, comparison efficiency is improve.
And when first face basis identification information for judging is the destination object by the face that is obtained after lift face
During the identification information of portion basis, then step S400 is performed, if so, then reducing the first face basis identification information to the target
The second face basis identification information before object lift face.
In the embodiment of the present application, please continue to refer to Fig. 3, it is described judge first face basis identification information whether be
The destination object can specifically include following steps by the face's basis identification information obtained after lift face：
Step 300b1, builds the adjusting range region of the standard logo information；
Wherein, the adjusting range region of standard logo information is built in the step, the adjusting range region can basis
History shape data is calculated or analyzed in reforming process, can maximized shaping for destination object different parts institute
Modification scope, using on the basis of this scope as the adjusting range region in the step.
Words sentence is talked about, and what cheekbone identification information was corresponding in the embodiment of the present application has cheekbone adjusting range region；Eye is identified
Information is corresponding eye adjusting range region；Nose identification information it is corresponding have nose adjusting range region；Supercilium mark letter
Breath is corresponding supercilium adjusting range region；Ear's identification information it is corresponding have ear's adjusting range region；Tooth portion identification information
It is corresponding to have tooth portion adjusting range region.
Step 300b2, obtains ratio of the first face basis identification information relative to face's standard logo information
To difference information；
Wherein, described " comparison difference information " is the difference after basic identification information is contrasted with standard logo information, for example
After first cheekbone basis identification information is compared with cheekbone standard logo information, the parameter values for mutually coming in and going out are comparison difference letter
Breath, and when the parameter values for mutually coming in and going out are 0, then it represents that the first cheekbone basis identification information is complete with cheekbone standard logo information
It is identical.
Whether step 300b3, judge the comparison difference information between the adjusting range region；
Specifically, by taking cheekbone identification information as an example, if the first cheekbone basis identification information and cheekbone standard logo information
After comparison, the parameter values (comparison difference information) for mutually coming in and going out between above-mentioned cheekbone adjusting range region, then such as following steps
It is rapid described：
Step 300b4, if so, then the first face basis identification information is the destination object by being obtained after lift face
The face's basis identification information for obtaining.
Now, step 300b4 is performed, step 400 is being performed, the first face basis identification information to the mesh is reduced
The second face basis identification information before mark object lift face, specific restoring method can include in the embodiment of the present application：According to
According to the comparison difference information, first face basis identification information is corrected；Revised face basis is identified
Information is defined as the second face basis identification information.
Then perform, step S500, second face basis identification information is entered with face's standard logo information
Row contrast；
Step S600 is finally performed, if second face basis identification information and face's standard logo information phase
Match somebody with somebody, then send lock instruction and lock the destination object.
Likewise, second face basis identification information is carried out with face's standard logo information in step S500
Contrast can also compare according to following sub-step：
First sub-step, carries out priority classification, second face after classification by second face basis identification information
Portion basis identification information includes the first priority match information, the second priority match information and third priority match information；
Second sub-step, by second face basis identification information according to priority orders and face's standard logo
Information is contrasted；The priority orders include：Believe from the first priority match information, second priority match
Cease the order of the third priority match information；
Further, in the embodiment of the present application, the second face basis identification information can also include：Second cheekbone
Bone basis identification information, the second eye basis identification information, the second nose basis identification information, the second supercilium basis mark letter
Breath, the second ear basis identification information, the second tooth portion identification information；Wherein, the second cheekbone basis identification information is first
Priority match information；Second eye basis identification information, second nose basis identification information and second eyebrow
Portion basis identification information is the second priority match information；The second ear basis identification information and the second tooth portion mark
Information is third priority match information.Face's standard logo information can include：Cheekbone standard logo information, eye mark
Quasi- identification information, nose standard logo information, supercilium standard logo information, ear standard logo information, tooth ministerial standard mark letter
Breath.
Wherein, the second cheekbone basis identification information and cheekbone standard logo information Corresponding matching；Second eye basis mark
Information is matched with the contrast of eye standard logo information；Second nose basis identification information and the contrast of nose standard logo information
Match somebody with somebody；Second supercilium basis identification information is matched with the contrast of supercilium standard logo information；Second ear basis identification information and ear
The contrast matching of standard logo information；Second tooth portion identification information is matched with the contrast of tooth ministerial standard identification information.
Specifically, the second cheekbone basis identification information is the first priority match information；The second eye base
Plinth identification information, second nose basis identification information and second supercilium basis identification information are the second priority match
Information；The second ear basis identification information and the second tooth portion identification information are third priority match information.Here
It should be noted that the first priority match information, the second priority match information and third priority match information is preferential
Level grade is reduced successively.That is, priority of the priority of the first priority match information more than the second priority match information,
Priority of the priority of the second priority match information more than third priority match information.
It is and above-mentioned here, for the contrast matching way of the second face basis identification information and face's standard logo information
First face basis identification information is identical with the contrast matching way of face's standard logo information, herein for the second face
Basic identification information matches not detailed part with the contrast of face's standard logo information, see the first face basis identification information
With the contrast matching way of face's standard logo information, here is omitted.
More than, the method that the embodiment of the present application is provided, when unmanned plane is applied to, judges the first face basis identification information
After being mismatched with face standard logo information, increased and judge whether the first face basis identification information is destination object process
The face's basis identification information obtained after lift face, and where it has, by reducing the first face basis identification information
The second face basis identification information before to destination object lift face；Then again by reduction after the second face basis identification information with
Face's standard logo information is contrasted, the final face's basis mark for the application is effectively ensured the contrast of participation information
The accuracy of information, solves unmanned plane of the prior art during being identified to destination object, existing to know
The inaccurate technical problem of other information.
Based on same inventive concept, the embodiment of the present application additionally provides equipment corresponding with method in embodiment one, sees reality
Apply example two.
Embodiment two
A kind of equipment is present embodiments provided, Fig. 4 is refer to, the equipment includes：
Acquisition module 1000, the first face basis identification information for obtaining destination object；
First contrast module 2000, for by first face basis identification information and in advance build standard database
In face's standard logo information contrasted；
First locking module 3000a, if believing with face's standard logo for first face basis identification information
Manner of breathing is matched, then send lock instruction and lock the destination object；
Judge module 3000b, if for first face basis identification information with face's standard logo information not
Matching, then judge whether first face basis identification information is the destination object by face's base for being obtained after lift face
Plinth identification information；
Recovery module 4000, for if so, then to reduce first face basis identification information whole to the destination object
The second face basis identification information before appearance；
Second contrast module 5000, for by second face basis identification information and face's standard logo information
Contrasted；
Second locking module 6000, if for second face basis identification information and face's standard logo information
Match, then send lock instruction and lock the destination object.
In the embodiment of the present application, first contrast module also includes：
First contrast submodule；For first face basis identification information to be carried out into priority classification, institute after classification
Stating the first face basis identification information includes the first priority match information, the second priority match information and third priority
With information；
Second contrast submodule；For by first face basis identification information according to priority orders and the face
Standard logo information is contrasted；The priority orders include：From the first priority match information, described second preferential
Order of the level match information to the third priority match information；
In the embodiment of the present application, if first locking module be additionally operable to the first priority match information with it is described
Face's standard logo information match, then judge the first face basis identification information and face's standard logo information phase
Matching；
Or,
If the second priority match information and the third priority match information with face's standard logo
Information match, then judge the first face basis identification information and face's standard logo information match.
In the embodiment of the present application, the first face basis identification information includes：First cheekbone basis identification information, the
One eye basis identification information, the first nose basis identification information, the first supercilium basis identification information, the first ear basis mark
Information, the first tooth portion identification information；Wherein, the first cheekbone basis identification information is the first priority match information；It is described
First eye basis identification information, first nose basis identification information and first supercilium basis identification information are second
Priority match information；The first ear basis identification information and the first tooth portion identification information are third priority matching
Information；
Face's standard logo information includes：Cheekbone standard logo information, eye standard logo information, nose standard mark
Knowledge information, supercilium standard logo information, ear standard logo information, tooth ministerial standard identification information.
In the embodiment of the present application, the judge module 3000b also includes following submodule：
First judging submodule；Adjusting range region for building the standard logo information；
Second judging submodule；For obtaining the first face basis identification information relative to face's standard logo
The comparison difference information of information；
3rd judging submodule；For judging the comparison difference information whether between the adjusting range region；
4th judging submodule；For if so, then the first face basis identification information is that the destination object passes through
The face's basis identification information obtained after lift face.
In the embodiment of the present application, the recovery module 4000 also includes following submodule：
First reduction submodule, for according to the comparison difference information, entering to first face basis identification information
Row correction；
Second reduction submodule, for revised face basis identification information to be defined as into the second face basis mark
Knowledge information.
The technical scheme provided in the embodiment of the present application, at least has the following technical effect that or advantage：
When unmanned plane is applied to, judge that the first face basis identification information mismatches it with face's standard logo information
Afterwards, increased and judge whether the first face basis identification information is that face basis of the destination object by being obtained after lift face identifies
Information, and where it has, by reducing the second face before basis identification information to the destination object lift face of the first face
Basic identification information；Then again by reduction after the second face basis identification information contrasted with face standard logo information,
The accuracy of the final face's basis identification information for the application is effectively ensured the contrast of participation information, solves existing skill
Unmanned plane in art is existing to obtain the inaccurate technical problem of identification information during being identified to destination object.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.And, the present invention can be used and wherein include the computer of computer usable program code at one or more
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) is produced
The form of product.
The present invention is the flow with reference to method, equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram are described.It should be understood that every first-class during flow chart and/or block diagram can be realized by computer program instructions
The combination of flow and/or square frame in journey and/or square frame and flow chart and/or block diagram.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The equipment of the function of being specified in present one flow of flow chart or multiple one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices with spy
In determining the computer-readable memory that mode works so that instruction of the storage in the computer-readable memory is produced and include finger
Make the manufacture of equipment, the commander equipment realize in one flow of flow chart or multiple one square frame of flow and/or block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented treatment, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the scope of the invention.Obviously, those skilled in the art can be to the application
Embodiment carries out the spirit and scope of various changes and modification without deviating from the embodiment of the present application.So, if the application is implemented
These modifications of example and modification belong within the scope of the claims in the present invention and its equivalent technologies, then the present invention is also intended to include
Including these changes and modification.
Claims (10)
1. one kind carries out repeatedly contrast knowledge method for distinguishing for destination object, is applied to unmanned plane, it is characterised in that methods described
Including：
Obtain the first anticipation positional information of destination object；
The first face basis identification information of the destination object is obtained according to the first anticipation positional information；
First face basis identification information is carried out with the face's standard logo information in the advance standard database for building
Contrast；
If the first face basis identification information and face's standard logo information match, send lock instruction locking
The destination object；
If the first face basis identification information is mismatched with face's standard logo information, first face is judged
Whether basic identification information is the destination object by the basic identification information of the face obtained after lift face；
If so, then reducing the second face basis mark before the first face basis identification information to destination object lift face
Information；
Second face basis identification information is contrasted with face's standard logo information；
If the second face basis identification information and face's standard logo information match, send lock instruction locking
The destination object.
2. the method for claim 1, it is characterised in that described by first face basis identification information and advance structure
Face's standard logo information in the standard database built carries out contrast to be included：
First face basis identification information is carried out into priority classification, the first face basis identification information bag after classification
Include the first priority match information, the second priority match information and third priority match information；
First face basis identification information is contrasted according to priority orders with face's standard logo information；Institute
Stating priority orders includes：It is excellent to the described 3rd from the first priority match information, the second priority match information
The order of first level match information；
If the first face basis identification information includes with face's standard logo information match：
If the first priority match information and face's standard logo information match, judge first face base
Plinth identification information and face's standard logo information match；
Or,
If the second priority match information and the third priority match information with face's standard logo information
Match, then judge the first face basis identification information and face's standard logo information match.
3. method as claimed in claim 2, it is characterised in that
First face basis identification information includes：First cheekbone basis identification information, the first eye basis identification information, the
One nose basis identification information, the first supercilium basis identification information, the first ear basis identification information, the first tooth portion mark letter
Breath；Wherein, the first cheekbone basis identification information is the first priority match information；The first eye basis mark letter
Breath, first nose basis identification information and first supercilium basis identification information are the second priority match information；Institute
It is third priority match information to state the first ear basis identification information and the first tooth portion identification information；
Face's standard logo information includes：Cheekbone standard logo information, eye standard logo information, nose standard logo letter
Breath, supercilium standard logo information, ear standard logo information, tooth ministerial standard identification information.
4. the method for claim 1, it is characterised in that it is described judge the first face basis identification information whether be
The destination object includes by the face's basis identification information obtained after lift face：
Build the adjusting range region of the standard logo information；
Obtain comparison difference information of the first face basis identification information relative to face's standard logo information；
Judge the comparison difference information whether between the adjusting range region；
If so, then the first face basis identification information is that face basis of the destination object by being obtained after lift face is marked
Knowledge information.
5. method as claimed in claim 4, it is characterised in that reduction the first face basis identification information is to described
The second face basis identification information before destination object lift face includes：
According to the comparison difference information, first face basis identification information is corrected；
Revised face basis identification information is defined as the second face basis identification information.
6. a kind of equipment for being identified for destination object, is applied to unmanned plane, it is characterised in that the equipment bag
Include：
Position module, the first anticipation positional information for obtaining destination object；
Acquisition module, the first face basis mark letter for obtaining the destination object according to the first anticipation positional information
Breath；
First contrast module, for the face in the standard database by first face basis identification information with advance structure
Standard logo information is contrasted；
First locking module, if for first face basis identification information and face's standard logo information match,
Then send lock instruction and lock the destination object；
Judge module, if being mismatched with face's standard logo information for first face basis identification information, sentences
Whether disconnected first face basis identification information is that face basis mark of the destination object by being obtained after lift face is believed
Breath；
Recovery module, for if so, before then reducing first face basis identification information to the destination object lift face the
Two faces basis identification information；
Second contrast module is right for second face basis identification information to be carried out with face's standard logo information
Than；
Second locking module, if for second face basis identification information and face's standard logo information match,
Then send lock instruction and lock the destination object.
7. equipment as claimed in claim 6, it is characterised in that first contrast module includes：
First contrast submodule, for first face basis identification information to be carried out into priority classification, described the after classification
One face basis identification information includes the first priority match information, the second priority match information and third priority matching letter
Breath；
Second contrast submodule, for will the basic identification information of first face according to priority orders and face's standard
Identification information is contrasted；The priority orders include：From the first priority match information, second priority
Order with information to the third priority match information；
First locking module is additionally operable to：
If the first priority match information and face's standard logo information match, judge first face base
Plinth identification information and face's standard logo information match；
Or,
If the second priority match information and the third priority match information with face's standard logo information
Match, then judge the first face basis identification information and face's standard logo information match.
8. equipment as claimed in claim 7, it is characterised in that
First face basis identification information includes：First cheekbone basis identification information, the first eye basis identification information, the
One nose basis identification information, the first supercilium basis identification information, the first ear basis identification information, the first tooth portion mark letter
Breath；Wherein, the first cheekbone basis identification information is the first priority match information；The first eye basis mark letter
Breath, first nose basis identification information and first supercilium basis identification information are the second priority match information；Institute
It is third priority match information to state the first ear basis identification information and the first tooth portion identification information；
Face's standard logo information includes：Cheekbone standard logo information, eye standard logo information, nose standard logo letter
Breath, supercilium standard logo information, ear standard logo information, tooth ministerial standard identification information.
9. equipment as claimed in claim 6, it is characterised in that the judge module also includes：
First judging submodule, the adjusting range region for building the standard logo information；
Second judging submodule, for obtaining the first face basis identification information relative to face's standard logo information
Comparison difference information；
3rd judging submodule, for judging the comparison difference information whether between the adjusting range region；
4th judging submodule, for if so, then the first face basis identification information is the destination object by lift face
The face's basis identification information for being obtained afterwards.
10. equipment as claimed in claim 9, it is characterised in that the recovery module includes：
First reduction submodule, for according to the comparison difference information, school being carried out to first face basis identification information
Just；
Second reduction submodule, for revised face basis identification information to be defined as into the second face basis mark letter
Breath.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611262770.9A CN106815569A (en) | 2016-12-30 | 2016-12-30 | The method and apparatus of repeatedly contrast identification is carried out for destination object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611262770.9A CN106815569A (en) | 2016-12-30 | 2016-12-30 | The method and apparatus of repeatedly contrast identification is carried out for destination object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106815569A true CN106815569A (en) | 2017-06-09 |
Family
ID=59109975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611262770.9A Pending CN106815569A (en) | 2016-12-30 | 2016-12-30 | The method and apparatus of repeatedly contrast identification is carried out for destination object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106815569A (en) |
-
2016
- 2016-12-30 CN CN201611262770.9A patent/CN106815569A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778669A (en) | The method and device that destination object is identified is carried out based on unmanned plane | |
| CN107128492B (en) | A kind of unmanned plane tracking, device and unmanned plane based on number of people detection | |
| CN101930543B (en) | Method for adjusting eye image in self-photographed video | |
| CN105205785B (en) | A kind of orientable oversize vehicle operation management system and its operation method | |
| US9007481B2 (en) | Information processing device and method for recognition of target objects within an image | |
| CN108304819B (en) | Gesture recognition system and method, and storage medium | |
| WO2020249088A1 (en) | Moving target tracking method and apparatus, and unmanned aerial vehicle | |
| CN105892474A (en) | Unmanned plane and control method of unmanned plane | |
| CN105678241B (en) | A kind of cascade two dimensional image face pose estimation | |
| CN110705357A (en) | Face recognition method and face recognition device | |
| CN104978548A (en) | Visual line estimation method and visual line estimation device based on three-dimensional active shape model | |
| JP2012155391A (en) | Posture state estimation device and posture state estimation method | |
| CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
| US20220318369A1 (en) | Face recognition system and method capable of updating registered face templates | |
| CN108089695A (en) | A kind of method and apparatus for controlling movable equipment | |
| CN106874839A (en) | The method and device of facial information identification | |
| CN109993108B (en) | Gesture error correction method, system and device under a kind of augmented reality environment | |
| CN107341460A (en) | Face tracking method and device | |
| CN116453198B (en) | Sight line calibration method and device based on head posture difference | |
| CN107066923A (en) | The method and apparatus of target identification is carried out based on unmanned plane | |
| CN106815569A (en) | The method and apparatus of repeatedly contrast identification is carried out for destination object | |
| CN106815568A (en) | For the method and system being identified for destination object | |
| CN116866719A (en) | Intelligent analysis processing method for high-definition video content based on image recognition | |
| CN106778673A (en) | It is applied to the recognizable method and system of unmanned plane | |
| CN113449566A (en) | Intelligent image tracking method and system for low-speed small target in human-in-loop |
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: 20170609 |