CN109215056A - Target tracking method and device - Google Patents
Target tracking method and device Download PDFInfo
- Publication number
- CN109215056A CN109215056A CN201710534218.9A CN201710534218A CN109215056A CN 109215056 A CN109215056 A CN 109215056A CN 201710534218 A CN201710534218 A CN 201710534218A CN 109215056 A CN109215056 A CN 109215056A
- Authority
- CN
- China
- Prior art keywords
- information
- characteristic information
- image
- matched
- needing
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of target tracking method and devices.This method and device are applied to be equipped with the unmanned plane of image capture device.This method comprises: obtaining the clarification of objective information for needing to track;It is matched using this feature information with object in image capture device image-capture field;The object of tracking and this feature information matches.The target tracking method and device of the embodiment of the present invention can be improved tracking efficiency.
Description
Technical field
The present invention relates to air vehicle technique field more particularly to a kind of target tracking methods and device.
Background technique
Currently, the police when chasing offender, mainly employ police car, police and police dog tracking offender.
But offender is tracked using police car, police and police dog, it is affected by various factors (for example, police car not crime
The vehicle that the car speed that molecule drives is fast, offender drives drives into that police car cannot be introduced into region, police does not have offender
Fast, the offender run removes smell etc.) it is easy to cause tracking to fail, tracking efficiency is lower.
Summary of the invention
The embodiment of the present invention provides a kind of target tracking method and device, can be improved tracking efficiency.
On the one hand, the embodiment of the invention provides a kind of target tracking method, this method is applied to be equipped with Image Acquisition
The unmanned plane of equipment, method include:
Obtain the clarification of objective information for needing to track;
It is matched using characteristic information with object in image capture device image-capture field;
Tracking and the matched object of characteristic information.
On the other hand, the embodiment of the invention provides a kind of target follow up mechanism, which, which is applied to be equipped with image, is adopted
Collect the unmanned plane of equipment, device includes: to obtain module, matching module and tracing module, wherein
Module is obtained, for obtaining the clarification of objective information for needing to track;
Matching module, for being matched using characteristic information with object in image capture device image-capture field;
Tracing module, for tracking and the matched object of characteristic information.
The target tracking method and device of the embodiment of the present invention, can be improved tracking efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will make below to required in the embodiment of the present invention
Attached drawing is briefly described, for those of ordinary skill in the art, without creative efforts, also
Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 shows the first flow diagram of target tracking method provided in an embodiment of the present invention;
Fig. 2 shows second of flow diagrams of target tracking method provided in an embodiment of the present invention;
Fig. 3 shows the first structural schematic diagram of target follow up mechanism provided in an embodiment of the present invention;
Fig. 4 shows second of structural schematic diagram of target follow up mechanism provided in an embodiment of the present invention.
Specific embodiment
The feature and exemplary embodiment of various aspects of the invention is described more fully below, in order to make mesh of the invention
, technical solution and advantage be more clearly understood, with reference to the accompanying drawings and embodiments, the present invention is further retouched in detail
It states.It should be understood that specific embodiment described herein is only configured to explain the present invention, it is not configured as limiting the present invention.
To those skilled in the art, the present invention can be real in the case where not needing some details in these details
It applies.Below the description of embodiment is used for the purpose of better understanding the present invention to provide by showing example of the invention.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including
There is also other identical elements in the process, method, article or equipment of the element.
In order to solve prior art problem, the embodiment of the invention provides a kind of target tracking method and devices.It needs
Bright, target tracking method and device provided in an embodiment of the present invention are preferably applied to be equipped with the nothing of image capture device
It is man-machine, and it is preferably applied to the scene that the police chase offender, naturally it is also possible to it is applied to other scenes, for example, children
It is on night shift, parent protects scene etc. in the dark.Target tracking method is provided for the embodiments of the invention first below to be introduced.
Fig. 1 shows the first flow diagram of target tracking method provided in an embodiment of the present invention.It may include:
S101: the clarification of objective information for needing to track is obtained.
S102: it is matched using this feature information with object in image capture device image-capture field.
S103: the object of tracking and this feature information matches.
The clarification of objective information that the acquisition of the embodiment of the present invention needs to track may include: to receive including needing to track
Clarification of objective information image;Characteristic information is extracted from image;Or, receiving includes the clarification of objective letter for needing to track
The text data of breath.
Illustratively, by taking the police chase offender as an example.
The police can send the image for the offender that monitoring camera takes during chasing offender
To unmanned plane, offender can also be shot using video camera during chasing, the image of shooting is sent to
Unmanned plane, unmanned plane extract the characteristic information of offender from the image received.
The scope that feature (abbreviation image characteristics extraction) belongs to image analysis is extracted from image, is Digital Image Processing
The high-order stage, while being also the beginning of image recognition.For image, every piece image all has and can be different from other classes
The unique characteristics of image, some are the physical feature that can be perceive intuitively that, such as brightness, edge, texture and color;Some
It is then to need, such as square, histogram and main composition just getable by transformation or processing.
The police directly can also send the feature including offender to unmanned plane and believe during chasing offender
The text data of breath, such as: offender wears black peaked cap, wears black T-shirt and blue jeans, wears black fortune
Dynamic shoes.Unmanned plane directly obtains the characteristic information of offender from this article notebook data.
In practical applications, the clarification of objective information tracked in order to avoid the needs sent to unmanned plane is by offender
It intercepting and capturing, offender changes feature (for example change the outfit or change trains) in turn after knowing this feature information, and so that unmanned plane is lost target,
Tracking is caused to fail.Therefore it can be encrypted to the clarification of objective information that the needs that unmanned plane is sent are tracked, even if
Offender intercepts and captures the data transmitted to unmanned plane, timely learning or can not cannot know characteristic information.
The clarification of objective information that the acquisition of the embodiment of the present invention needs to track may include: to receive to utilize predetermined encryption
Algorithm carries out encrypted data to the data for including characteristic information;It is docked using decipherment algorithm corresponding with predetermined encryption algorithm
The data received are decrypted;Characteristic information is extracted from the data after decryption.
In practical applications, predetermined encryption algorithm can be Message Digest Algorithm 5 (Message Digest
Algorithm, MD5), Secure Hash Algorithm (Secure Hash Algorithm, SHA), cyclic redundancy check (Cyclic
Redundancy Check, CRC) algorithm, symmetric encipherment algorithm etc. can also be bar code generating algorithm certainly.
It should be noted that the embodiment of the present invention is not defined predetermined encryption algorithm, any Encryption Algorithm
To be applied in the embodiment of the present invention.
Illustratively, two dimensional code is received, wherein the two dimensional code is using two dimensional code generating algorithm to including needing to track
The data of clarification of objective information carry out encrypted data.The two dimensional code received is carried out using two dimensional code decipherment algorithm
The clarification of objective information for needing to track is extracted in decryption from the data after decryption.
In practical applications, the data for including characteristic information can repeatedly can be encrypted, accordingly to encrypted number
According to repeatedly being decrypted.
For example, encrypting using the first Encryption Algorithm to the data for including characteristic information, the first encryption data is obtained, benefit
The first encryption data is encrypted again with the second Encryption Algorithm, obtains the second encryption data.Using with the second Encryption Algorithm pair
The second encryption data is decrypted in the decipherment algorithm answered, and obtains the first ciphertext data, recycles corresponding with the first Encryption Algorithm
Decipherment algorithm the first ciphertext data is decrypted, obtain the original data including characteristic information.Above-mentioned first Encryption Algorithm
Can be identical with the second Encryption Algorithm, it can not also be identical.
In practical applications, the target for needing to track is behaved, correspondingly, the clarification of objective information that needs are tracked can be
The face feature information for the people for needing to track.
Being matched using characteristic information with object in image capture device image-capture field for the embodiment of the present invention, can
To include:, using model matching technologies, to identify whether object is people for each object in image-capture field;It is identifying
In the case that object is behaved, using face recognition technology, the face feature information of object is extracted;Using characteristic information with extracted
Face feature information matched.
Specifically, the technology of object can be identified based on robot, by the corresponding pixel of unmanned plane acquired image
The object representation of composition is converted into the object representation that unmanned plane is capable of Direct Recognition.Different objects model can be stored in nobody
In machine, for example, auto model, people's model, electric wire rod model, rubbish barrel mould, chair model etc..When unmanned plane utilizes image
In capture setting acquisition image-capture field after the image of object, the pixel in image can be handled, and then obtain
The shape of each object in acquired image.Using model matching technologies, by the body form of acquisition and the progress of people's model
Match, if the body form obtained matches with people's model, further utilize face recognition technology to the facial characteristics of people into
Row extracts, then the face feature information of the people tracked with the needs obtained is matched with the face feature information of the people of extraction.
In practical applications, the target for needing to track is behaved, correspondingly, the clarification of objective information that needs are tracked can be
The dress ornament information for the people for needing to track.Such as: the dress ornament information for the people for needing to track are as follows: black peaked cap, black T-shirt, indigo plant
Color jeans, black sport footwear.
Being matched using characteristic information with object in image capture device image-capture field for the embodiment of the present invention, can
To include:, using model matching technologies, to identify whether object is people for each object in image-capture field;It is identifying
In the case that object is behaved, using model matching technologies and color identification technology, the dress ornament information of object is extracted;Utilize feature
Information is matched with extracted dress ornament information.
Specifically, the technology of object can be identified based on robot, by the corresponding pixel of unmanned plane acquired image
The object representation of composition is converted into the object representation that unmanned plane is capable of Direct Recognition.Different objects model can be stored in nobody
In machine, for example, auto model, people's model, electric wire rod model, rubbish barrel mould, various chair models, various cap models, each
Kind jacket model, various trousers models, various skirt models, various shoes models etc..When unmanned plane is arranged using Image Acquisition
In acquisition image-capture field after the image of object, the pixel in image can be handled, and then obtained collected
The shape of each object in image.Using model matching technologies, the body form of acquisition is matched with people's model, if obtained
The body form obtained matches with people's model, then further utilizes model matching technologies and color identification technology to the dress ornament of people
Information extracts, for example, the dress ornament information of the people extracted are as follows: white shirt, black Western-style trousers, black leather shoes.Again with acquisition
The dress ornament information for the people for needing to track is matched with the dress ornament information of the people of extraction.
In the case where the target for needing to track is behaved, in order to improve tracking efficiency, thermal imaging can use to figure
As object is filtered in acquisition range.
Specifically, the detection range that thermal imaging system can be set is identical with the image-capture field of image capture device, benefit
Object in image-capture field is filtered with thermal imaging, filters out the region of not thermal imaging, and then only to image
There are the objects in thermal imaging region to be matched for acquisition range.
In practical applications, the target for needing to track is vehicle, correspondingly, needing the clarification of objective information tracked can be with
License plate number for the vehicle for needing to track.
Being matched using characteristic information with object in image capture device image-capture field for the embodiment of the present invention, can
To include:, using model matching technologies, to identify whether object is vehicle for each object in image-capture field;Knowing
In the case that other object is vehicle, using license plate recognition technology, the license plate number of object is identified;Using characteristic information with extracted
License plate number matched.
Specifically, the technology of object can be identified based on robot, by the corresponding pixel of unmanned plane acquired image
The object representation of composition is converted into the object representation that unmanned plane is capable of Direct Recognition.Different objects model can be stored in nobody
In machine, for example, auto model, people's model, electric wire rod model, rubbish barrel mould, chair model etc..When unmanned plane utilizes image
In capture setting acquisition image-capture field after the image of object, the pixel in image can be handled, and then obtain
The shape of each object in acquired image.Using model matching technologies, the body form of acquisition and auto model are carried out
Matching utilizes license plate recognition technology, identifies the license plate number of vehicle if the body form obtained matches with auto model
Code, then matched with the license plate number of license plate that the needs of acquisition are tracked with the license plate number of the vehicle of extraction.
In the case where the target for needing to track is vehicle, in order to improve tracking efficiency, thermal imaging also can use
Object in image-capture field is filtered.Specifically, the detection range and image capture device of thermal imaging system can be set
Image-capture field it is identical, object in image-capture field is filtered using thermal imaging, be filled into without heat at
The region of picture, and then only to image-capture field, there are the objects in thermal imaging region to match.
Illustratively, for offender when driving vehicle is escaped, the police send thermal imaging system open command, heat to unmanned plane
Imager and image capture device are used in combination, and to image-capture field, there are the objects in thermal imaging region to match, into
And vehicle is tracked.
Certainly, the target for needing to track is not limited to people and vehicle, can also be other objects such as luggage.Illustratively, should
Luggage can be drug trafficker for filling the suitcase of drugs or money.
When the characteristic information using acquisition is matched with object in image capture device image-capture field, object is matched
When body, tracking and the matched object of characteristic information obtained.
In practical applications, discovery target instruction target word can be sent to unmanned controller, received unmanned controller and sent
The trace command for target, target is tracked.It is also based on automatic tracking technology tracking target.Wherein, automatically
Tracking is to be continuously tracked and measure movement objective orbit parameter.Automatically track the space orientation that can provide moving target, posture, knot
Structure behavior and performance are the multi-functional and high-precision tracking and measurement means of moving target.
Fig. 2 shows second of flow diagrams of target tracking method provided in an embodiment of the present invention.Fig. 2 institute of the present invention
On the basis of showing embodiment embodiment shown in Fig. 1, increase following two step:
S104: the determining geographical location with the object of this feature information matches.
S105: the determining geographical location with the object of this feature information matches is reported.
Determine the geographical location of object, can longitude and latitude based on unmanned plane, unmanned plane flying height, unmanned plane distance
The distance of object and the shooting angle (angle of unmanned plane shooting direction and direct north) of unmanned plane, calculate the longitude and latitude of object
Degree, which is the geographical location of object.
The geographical location for determining object is also based on unmanned plane acquired image and determines geographical location.For example, nobody
Have street sign, firm name in the current acquired image of machine, the geographical location of the object determined can be with are as follows: XXXX
Near the shop XXXX of street.
After determining the geographical location of object, it will determine that geographical location reports.
When chasing the scene of offender applied to the police, geographical location can be reported to and be arrested in command and control
The heart;It is on night shift when applied to children, when parent protects scene in the dark, geographical location can be reported to the mobile phone of parent.
Target tracking method provided in an embodiment of the present invention reduces influence of the various factors to tracking in the prior art,
Tracking should not fail, and improve tracking efficiency.
Corresponding with above-mentioned embodiment of the method, the embodiment of the present invention also provides a kind of target follow up mechanism.
Fig. 3 shows the first structural schematic diagram of target follow up mechanism provided in an embodiment of the present invention.It may include:
Obtain module 301, matching module 302 and tracing module 303, wherein
Module 301 is obtained, for obtaining the clarification of objective information for needing to track;
Matching module 302, for utilizing the characteristic information and image capture device Image Acquisition model for obtaining the acquisition of module 301
Interior object is enclosed to be matched;
Tracing module 303, for tracking and obtaining the matched object of characteristic information of the acquisition of module 301.
The acquisition module 301 of the embodiment of the present invention, specifically can be used for: receiving includes the clarification of objective letter for needing to track
The image of breath;Characteristic information is extracted from image;Or, receiving includes the text data for needing the clarification of objective information tracked.
Illustratively, by taking the police chase offender as an example.
The police can send the image for the offender that monitoring camera takes during chasing offender
To unmanned plane, offender can also be shot using video camera during chasing, the image of shooting is sent to
Unmanned plane, unmanned plane extract the characteristic information of offender from the image received.Feature (abbreviation image is extracted from image
Feature extraction) scope that belongs to image analysis is the high-order stage of Digital Image Processing, while being also the beginning of image recognition.
For image, every piece image all has the unique characteristics that can be different from other class images, some are can be intuitively
The physical feature experienced, such as brightness, edge, texture and color;Some are then to need just obtain by transformation or processing
, such as square, histogram and main composition.
The police directly can also send the feature including offender to unmanned plane and believe during chasing offender
The text data of breath, such as: offender wears black peaked cap, wears black T-shirt and blue jeans, wears black fortune
Dynamic shoes.Unmanned plane directly obtains the characteristic information of offender from this article notebook data.
In practical applications, the clarification of objective information tracked in order to avoid the needs sent to unmanned plane is by offender
It intercepting and capturing, offender changes feature (for example change the outfit or change trains) in turn after knowing this feature information, and so that unmanned plane is lost target,
Tracking is caused to fail.Therefore it can be encrypted to the clarification of objective information that the needs that unmanned plane is sent are tracked, even if
Offender intercepts and captures the data transmitted to unmanned plane, timely learning or can not cannot know characteristic information.
The acquisition module 301 of the embodiment of the present invention, specifically can be used for: receive using predetermined encryption algorithm to including feature
The data of information carry out encrypted data;The data received are carried out using decipherment algorithm corresponding with predetermined encryption algorithm
Decryption;Characteristic information is extracted from the data after decryption.
In practical applications, predetermined encryption algorithm can be MD5, SHA, CRC algorithm, symmetric encipherment algorithm etc., certainly
It can also be bar code generating algorithm.
It should be noted that the embodiment of the present invention is not defined predetermined encryption algorithm, any Encryption Algorithm
To be applied in the embodiment of the present invention.
Illustratively, two dimensional code is received, wherein the two dimensional code is using two dimensional code generating algorithm to including needing to track
The data of clarification of objective information carry out encrypted data.The two dimensional code received is carried out using two dimensional code decipherment algorithm
The clarification of objective information for needing to track is extracted in decryption from the data after decryption.
In practical applications, the data for including characteristic information can repeatedly can be encrypted, accordingly to encrypted number
According to repeatedly being decrypted.
For example, encrypting using the first Encryption Algorithm to the data for including characteristic information, the first encryption data is obtained, benefit
The first encryption data is encrypted again with the second Encryption Algorithm, obtains the second encryption data.Using with the second Encryption Algorithm pair
The second encryption data is decrypted in the decipherment algorithm answered, and obtains the first ciphertext data, recycles corresponding with the first Encryption Algorithm
Decipherment algorithm the first ciphertext data is decrypted, obtain the original data including characteristic information.Above-mentioned first Encryption Algorithm
Can be identical with the second Encryption Algorithm, it can not also be identical.
In practical applications, the target for needing to track is behaved, correspondingly, the clarification of objective information that needs are tracked can be
The face feature information for the people for needing to track.
The matching module 302 of the embodiment of the present invention, specifically can be used for: for each object in image-capture field,
Using model matching technologies, identify whether object is people;In the case where identifying that object is behaved, using face recognition technology, mention
Take the face feature information of object;It is matched using characteristic information with extracted face feature information.
Specifically, the technology of object can be identified based on robot, by the corresponding pixel of unmanned plane acquired image
The object representation of composition is converted into the object representation that unmanned plane is capable of Direct Recognition.Different objects model can be stored in nobody
In machine, for example, auto model, people's model, electric wire rod model, rubbish barrel mould, chair model etc..When unmanned plane utilizes image
In capture setting acquisition image-capture field after the image of object, the pixel in image can be handled, and then obtain
The shape of each object in acquired image.Using model matching technologies, by the body form of acquisition and the progress of people's model
Match, if the body form obtained matches with people's model, further utilize face recognition technology to the facial characteristics of people into
Row extracts, then the face feature information of the people tracked with the needs obtained is matched with the face feature information of the people of extraction.
In practical applications, the target for needing to track is behaved, correspondingly, the clarification of objective information that needs are tracked can be
The dress ornament information for the people for needing to track.Such as: the dress ornament information for the people for needing to track are as follows: black peaked cap, black T-shirt, indigo plant
Color jeans, black sport footwear.
The matching module 302 of the embodiment of the present invention, specifically can be used for: for each object in image-capture field,
Using model matching technologies, identify whether object is people;In the case where identifying that object is behaved, using model matching technologies and
Color identification technology extracts the dress ornament information of object;It is matched using characteristic information with extracted dress ornament information.
Specifically, the technology of object can be identified based on robot, by the corresponding pixel of unmanned plane acquired image
The object representation of composition is converted into the object representation that unmanned plane is capable of Direct Recognition.Different objects model can be stored in nobody
In machine, for example, auto model, people's model, electric wire rod model, rubbish barrel mould, various chair models, various cap models, each
Kind jacket model, various trousers models, various skirt models, various shoes models etc..When unmanned plane is arranged using Image Acquisition
In acquisition image-capture field after the image of object, the pixel in image can be handled, and then obtained collected
The shape of each object in image.Using model matching technologies, the body form of acquisition is matched with people's model, if obtained
The body form obtained matches with people's model, then further utilizes model matching technologies and color identification technology to the dress ornament of people
Information extracts, for example, the dress ornament information of the people extracted are as follows: white shirt, black Western-style trousers, black leather shoes.Again with acquisition
The dress ornament information for the people for needing to track is matched with the dress ornament information of the people of extraction.
In the case where the target for needing to track is behaved, in order to improve tracking efficiency, thermal imaging can use to figure
As object is filtered in acquisition range.
Specifically, the detection range that thermal imaging system can be set is identical with the image-capture field of image capture device, benefit
Object in image-capture field is filtered with thermal imaging, is filled into the region of not thermal imaging, and then only to image
There are the objects in thermal imaging region to be matched for acquisition range.
In practical applications, the target for needing to track is vehicle, correspondingly, needing the clarification of objective information tracked can be with
License plate number for the vehicle for needing to track.
The matching module 302 of the embodiment of the present invention, specifically can be used for: for each object in image-capture field,
Using model matching technologies, identify whether object is vehicle;In the case where identifying object is vehicle, Car license recognition skill is utilized
Art identifies the license plate number of object;It is matched using characteristic information with extracted license plate number.
Specifically, the technology of object can be identified based on robot, by the corresponding pixel of unmanned plane acquired image
The object representation of composition is converted into the object representation that unmanned plane is capable of Direct Recognition.Different objects model can be stored in nobody
In machine, for example, auto model, people's model, electric wire rod model, rubbish barrel mould, chair model etc..When unmanned plane utilizes image
In capture setting acquisition image-capture field after the image of object, the pixel in image can be handled, and then obtain
The shape of each object in acquired image.Using model matching technologies, the body form of acquisition and auto model are carried out
Matching utilizes license plate recognition technology, identifies the license plate number of vehicle if the body form obtained matches with auto model
Code, then matched with the license plate number of license plate that the needs of acquisition are tracked with the license plate number of the vehicle of extraction.
In the case where the target for needing to track is vehicle, in order to improve tracking efficiency, thermal imaging also can use
Object in image-capture field is filtered.Specifically, the detection range and image capture device of thermal imaging system can be set
Image-capture field it is identical, object in image-capture field is filtered using thermal imaging, be filled into without heat at
The region of picture, and then only to image-capture field, there are the objects in thermal imaging region to match.
Illustratively, for offender when driving vehicle is escaped, the police send thermal imaging system open command, heat to unmanned plane
Imager and image capture device are used in combination, and to image-capture field, there are the objects in thermal imaging region to match, into
And vehicle is tracked.
Certainly, the target for needing to track is not limited to people and vehicle, can also be other objects such as luggage.Illustratively, should
Luggage can be drug trafficker for filling the suitcase of drugs or money.
When the characteristic information using acquisition is matched with object in image capture device image-capture field, object is matched
When body, tracking and the matched object of characteristic information obtained.
In practical applications, discovery target instruction target word can be sent to unmanned controller, received unmanned controller and sent
The trace command for target, target is tracked.It is also based on automatic tracking technology tracking target.Wherein, automatically
Tracking is to be continuously tracked and measure movement objective orbit parameter.Automatically track the space orientation that can provide moving target, posture, knot
Structure behavior and performance are the multi-functional and high-precision tracking and measurement means of moving target.
Fig. 4 shows second of structural schematic diagram of target follow up mechanism provided in an embodiment of the present invention.Fig. 4 institute of the present invention
On the basis of showing embodiment embodiment shown in Fig. 3, increase determining module 304 and reporting module 305, wherein
Determining module 304, for the determining geographical location with the object of this feature information matches.
Reporting module 305, the geographical location for determining determining module 304 report.
Determining module 304 determines the geographical location of object, can longitude and latitude based on unmanned plane, the flight of unmanned plane it is high
The shooting angle (angle of unmanned plane shooting direction and direct north) of degree, distance and unmanned plane of the unmanned plane apart from object,
The longitude and latitude of object is calculated, which is the geographical location of object.
Determining module 304 determines the geographical location of object, is also based on unmanned plane acquired image and determines geographical position
It sets.For example, having street sign, firm name, the geographical position for the object determined in the current acquired image of unmanned plane
Setting can be with are as follows: near the shop XXXX of the street XXXX.
After determining the geographical location of object, it will determine that geographical location reports.
When chasing the scene of offender applied to the police, geographical location can be reported to and be arrested in command and control
The heart;It is on night shift when applied to children, when parent protects scene in the dark, geographical location can be reported to the mobile phone of parent.
Target follow up mechanism provided in an embodiment of the present invention reduces influence of the various factors to tracking in the prior art,
Tracking should not fail, and improve tracking efficiency.
It should be clear that the invention is not limited to specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, several tools have been described and illustrated
The step of body, is as example.But method process of the invention is not limited to described and illustrated specific steps, this field
Technical staff can be variously modified, modification and addition after understanding spirit of the invention, or suitable between changing the step
Sequence.
Functional block shown in structures described above block diagram can be implemented as hardware, software, firmware or their group
It closes.When realizing in hardware, it may, for example, be electronic circuit, specific integrated circuit (ASIC), firmware appropriate, insert
Part, function card etc..When being realized with software mode, element of the invention is used to execute program or the generation of required task
Code section.Perhaps code segment can store in machine readable media program or the data-signal by carrying in carrier wave is passing
Defeated medium or communication links are sent." machine readable media " may include any medium for capableing of storage or transmission information.
The example of machine readable media includes electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), soft
Disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via such as internet, inline
The computer network of net etc. is downloaded.
It should also be noted that, the exemplary embodiment referred in the present invention, is retouched based on a series of step or device
State certain methods or system.But the present invention is not limited to the sequence of above-mentioned steps, that is to say, that can be according in embodiment
The sequence referred to executes step, may also be distinct from that the sequence in embodiment or several steps are performed simultaneously.
The above description is merely a specific embodiment, it is apparent to those skilled in the art that,
For convenience of description and succinctly, the system, module of foregoing description and the specific work process of unit can refer to preceding method
Corresponding process in embodiment, details are not described herein.It should be understood that scope of protection of the present invention is not limited thereto, it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of target tracking method, which is characterized in that the method is applied to be equipped with the unmanned plane of image capture device, institute
The method of stating includes:
Obtain the clarification of objective information for needing to track;
It is matched using the characteristic information with object in described image acquisition equipment image-capture field;
Tracking and the matched object of the characteristic information.
2. the method according to claim 1, wherein described obtain the clarification of objective information for needing to track, packet
It includes:
Receive the image including the clarification of objective information for needing to track;The characteristic information is extracted from described image;
Or,
Receive the text data including the clarification of objective information for needing to track.
3. the method according to claim 1, wherein the target behaviour for needing to track, the characteristic information
For face feature information;
It is described to be matched using the characteristic information with object in described image acquisition equipment image-capture field, comprising:
For each object in described image acquisition range, using model matching technologies, identify whether the object is people;
In the case where identifying that the object is behaved, using face recognition technology, the face feature information of the object is extracted;
It is matched using the characteristic information with extracted face feature information.
4. the method according to claim 1, wherein the target behaviour for needing to track, the characteristic information
For dress ornament information;
It is described to be matched using the characteristic information with object in described image acquisition equipment image-capture field, comprising:
For each object in described image acquisition range, using model matching technologies, identify whether the object is people;
In the case where identifying that the object is behaved, using model matching technologies and color identification technology, the object is extracted
Dress ornament information;
It is matched using the characteristic information with extracted dress ornament information.
5. the method according to claim 1, wherein the method also includes:
The determining geographical location with the matched object of the characteristic information;
The determining geographical location with the matched object of the characteristic information is reported.
6. a kind of target follow up mechanism, which is characterized in that described device is applied to be equipped with the unmanned plane of image capture device, institute
Stating device includes: to obtain module, matching module and tracing module, wherein
The acquisition module, for obtaining the clarification of objective information for needing to track;
The matching module, for being carried out using object in the characteristic information and described image acquisition equipment image-capture field
Matching;
The tracing module, for tracking and the matched object of the characteristic information.
7. device according to claim 6, which is characterized in that the acquisition module is specifically used for:
Receive the image including the clarification of objective information for needing to track;The characteristic information is extracted from described image;
Or,
Receive the text data including the clarification of objective information for needing to track.
8. device according to claim 6, which is characterized in that the target for needing to track is behaved, the characteristic information
For face feature information;
The matching module, is specifically used for:
For each object in described image acquisition range, using model matching technologies, identify whether the object is people;
In the case where identifying that the object is behaved, using face recognition technology, the face feature information of the object is extracted;
It is matched using the characteristic information with extracted face feature information.
9. device according to claim 6, which is characterized in that the target for needing to track is behaved, the characteristic information
For dress ornament information;
The matching module, is specifically used for:
For each object in described image acquisition range, using model matching technologies, identify whether the object is people;
In the case where identifying that the object is behaved, using model matching technologies and color identification technology, the object is extracted
Dress ornament information;
It is matched using the characteristic information with extracted dress ornament information.
10. device according to claim 6, which is characterized in that described device further include: determining module and reporting module,
Wherein,
The determining module, for the determining geographical location with the matched object of the characteristic information;
The reporting module is reported for will determine with the geographical location of the characteristic information matched object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710534218.9A CN109215056A (en) | 2017-07-03 | 2017-07-03 | Target tracking method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710534218.9A CN109215056A (en) | 2017-07-03 | 2017-07-03 | Target tracking method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109215056A true CN109215056A (en) | 2019-01-15 |
Family
ID=64991887
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710534218.9A Pending CN109215056A (en) | 2017-07-03 | 2017-07-03 | Target tracking method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109215056A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110495954A (en) * | 2019-08-30 | 2019-11-26 | 深圳市汇健医疗工程有限公司 | Ultra high-definition surgical assistant system based on 5G communication |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130002866A1 (en) * | 2010-12-20 | 2013-01-03 | International Business Machines Corporation | Detection and Tracking of Moving Objects |
EP2698740A2 (en) * | 2012-08-17 | 2014-02-19 | GE Aviation Systems LLC | Method of identifying a tracked object for use in processing hyperspectral data |
CN105447459A (en) * | 2015-11-18 | 2016-03-30 | 上海海事大学 | Unmanned plane automation detection target and tracking method |
CN105578034A (en) * | 2015-12-10 | 2016-05-11 | 深圳市道通智能航空技术有限公司 | Control method, control device and system for carrying out tracking shooting for object |
CN105759839A (en) * | 2016-03-01 | 2016-07-13 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle (UAV) visual tracking method, apparatus, and UAV |
CN106157630A (en) * | 2016-08-01 | 2016-11-23 | 百度在线网络技术(北京)有限公司 | The monitoring method of suspicion of crime target, vehicle and system |
CN106713845A (en) * | 2015-11-16 | 2017-05-24 | 南京三宝弘正视觉技术有限公司 | Drone connected monitoring CCTV apparatus and method for photographing image thereby |
-
2017
- 2017-07-03 CN CN201710534218.9A patent/CN109215056A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130002866A1 (en) * | 2010-12-20 | 2013-01-03 | International Business Machines Corporation | Detection and Tracking of Moving Objects |
EP2698740A2 (en) * | 2012-08-17 | 2014-02-19 | GE Aviation Systems LLC | Method of identifying a tracked object for use in processing hyperspectral data |
CN106713845A (en) * | 2015-11-16 | 2017-05-24 | 南京三宝弘正视觉技术有限公司 | Drone connected monitoring CCTV apparatus and method for photographing image thereby |
CN105447459A (en) * | 2015-11-18 | 2016-03-30 | 上海海事大学 | Unmanned plane automation detection target and tracking method |
CN105578034A (en) * | 2015-12-10 | 2016-05-11 | 深圳市道通智能航空技术有限公司 | Control method, control device and system for carrying out tracking shooting for object |
CN105759839A (en) * | 2016-03-01 | 2016-07-13 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle (UAV) visual tracking method, apparatus, and UAV |
CN106157630A (en) * | 2016-08-01 | 2016-11-23 | 百度在线网络技术(北京)有限公司 | The monitoring method of suspicion of crime target, vehicle and system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110495954A (en) * | 2019-08-30 | 2019-11-26 | 深圳市汇健医疗工程有限公司 | Ultra high-definition surgical assistant system based on 5G communication |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110210276A (en) | A kind of motion track acquisition methods and its equipment, storage medium, terminal | |
CN112166439A (en) | True-to-composite image domain transfer | |
EP4116462A3 (en) | Method and apparatus of processing image, electronic device, storage medium and program product | |
CN112419233B (en) | Data annotation method, device, equipment and computer readable storage medium | |
CN105022999A (en) | Man code company real-time acquisition system | |
CN109409250A (en) | A kind of across the video camera pedestrian of no overlap ken recognition methods again based on deep learning | |
CN108430032A (en) | A kind of method and apparatus for realizing that VR/AR device locations are shared | |
CN110267010A (en) | Image processing method, device, server and storage medium | |
CN110022355A (en) | The storage method of environmental data, verification method and apparatus under special scenes | |
Mishra et al. | Recent trends in pedestrian detection for robotic vision using deep learning techniques | |
Tomešek et al. | CrossLocate: cross-modal large-scale visual geo-localization in natural environments using rendered modalities | |
KR101906560B1 (en) | Server, method, wearable device for supporting maintenance of military apparatus based on correlation data between object in augmented reality | |
CN105144193A (en) | A method and apparatus for estimating a pose of an imaging device | |
CN109215056A (en) | Target tracking method and device | |
CN110211181A (en) | Visual positioning method and device, storage medium and electronic equipment | |
JP6976731B2 (en) | Information processing equipment, information processing methods, and programs | |
CN116057570A (en) | Machine learning device and image processing device | |
Byukusenge et al. | Life detection based on uavs-thermal images in search and rescue operation | |
CN106612414A (en) | Tracking control method for suspicious target of key region video | |
Yeh et al. | Detection and Recognition of Arrow Traffic Signals using a Two-stage Neural Network Structure. | |
US11222427B2 (en) | Image compression | |
CN108234929A (en) | Image processing method and equipment in unmanned plane | |
Kim et al. | Robust multi-object tracking to acquire object oriented videos in indoor sports | |
JP2023527679A (en) | Panorama generation using mobile camera | |
Parikh et al. | Optimal camera placement for multimodal video summarization |
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: 20190115 |