CN107944337A - A kind of low target intelligent-tracking method and system, storage medium and electric terminal - Google Patents
A kind of low target intelligent-tracking method and system, storage medium and electric terminal Download PDFInfo
- Publication number
- CN107944337A CN107944337A CN201710952377.0A CN201710952377A CN107944337A CN 107944337 A CN107944337 A CN 107944337A CN 201710952377 A CN201710952377 A CN 201710952377A CN 107944337 A CN107944337 A CN 107944337A
- Authority
- CN
- China
- Prior art keywords
- tracking
- target
- image file
- testing result
- operation label
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/223—Analysis of motion using block-matching
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
This disclosure relates to image identification technical field, and in particular to a kind of low target intelligent-tracking method, a kind of low target intelligent tracking device, a kind of storage medium and a kind of electric terminal.Shown method includes:An image file and one first operation label are generated, in order to which a detection module obtains described image file and the first operation label;The detection module is detected with the presence or absence of tracking target in described image file according to the first operation label of acquisition, and there are the first testing result that generation one during the tracking target includes the tracking position of object information in detection;First testing result of the detection module generation is obtained, target and real-time judge tracking mode are tracked according to the positional information.
Description
Technical field
This disclosure relates to image identification technical field, and in particular to a kind of low target intelligent-tracking method, a kind of low latitude
Intelligent target tracks of device, a kind of storage medium and a kind of electric terminal.
Background technology
Tracking target is carried out under complex background real-time detect and track be photoelectricity precise guidance, it is target acquisition, automatic
The Key Common Technologies in the field such as identification and the independent navigation of mobile vehicle and Context aware.It is how automatic, accurate and quick
Ground detects strategic objective from complex background and carries out tenacious tracking, is of great significance to movable object tracking.
At present, existing military target detection and tracking technique can only be directed to pinpoint target mostly, but in complex background
Often there are multiple suspected targets, direction, distribution, size, the content of each suspected target to be all not quite similar;Also need to realize at the same time
To the quick detection of tracking target and tenacious tracking, and the prior art can not realize this demand well.It is in addition, existing
Passive type radar is easily subject to electronic interferences during target reconnaissance, so as to can not detect that target position information causes to track
Mission failure.In civil field there is also the unmanned plane detect and track under similar problem, such as low latitude background, easily it is subject to
The influence of the objects such as building member, treetop, UFO, leads to not accurately detection and realizes stable tracking.
It should be noted that information is only used for strengthening the reason to the background of the disclosure disclosed in above-mentioned background section
Solution, therefore can include not forming the information to the prior art known to persons of ordinary skill in the art.
The content of the invention
The purpose of the disclosure is to provide a kind of low target intelligent-tracking method, a kind of low target intelligent-tracking system
System, a kind of storage medium and a kind of electric terminal, so overcome at least to a certain extent due to correlation technique limitation and
One or more problem caused by defect.
Other characteristics and advantage of the disclosure will be apparent from by following detailed description, or partially by the disclosure
Practice and acquistion.
According to the first aspect of the disclosure, there is provided a kind of low target intelligent-tracking method, including:
Generate an image file and one first operation label, in order to a detection module obtain described image file and
First operation label;
The detection module is detected in described image file with the presence or absence of tracking according to the first operation label of acquisition
Target, and there are the first testing result that generation one during the tracking target includes the tracking position of object information in detection;
First testing result of detection module generation is obtained, target and real-time is tracked according to the positional information
Judge tracking mode.
In a kind of exemplary embodiment of the disclosure, one image file of the generation and the first operation label include:
A tracking video is obtained, the two field picture for intercepting the tracking video is used as described image file, and generation one the
One operation label;
Described image file and the first operation label are stored to a communication file and pressed from both sides.
In a kind of exemplary embodiment of the disclosure, the detection module is examined according to the first operation label of acquisition
Survey with the presence or absence of tracking target in described image file, and there are generate one to include the tracking during tracking target in detection
First testing result of target position information includes:
The detection module judges to whether there is the first operation label in the communication file;
Judging that acquisition is stored in the described image file in the communication file folder there are during the first operation label
And described image file is detected with the presence or absence of tracking target;
When detecting described image file in the presence of tracking target, the positional information of the acquisition tracking target simultaneously generates one and wraps
The first testing result containing the positional information;
First testing result is stored to the communication file and is pressed from both sides.
In a kind of exemplary embodiment of the disclosure, the first detection knot for obtaining the detection module generation
Fruit, tracking target according to the positional information includes:
Judge to whether there is one first testing result in the communication file folder;
Judging that there are during first testing result, read first testing result and opened according to the positional information
Begin tracking target.
In a kind of exemplary embodiment of the disclosure, the detection module is examined according to the first operation label of acquisition
Survey in described image file and further included with the presence or absence of tracking target:
The detection module judges to whether there is the first operation label in the communication file;
Judging that acquisition is stored in the described image file in the communication file folder there are during the first operation label
And it is no in the presence of tracking target to detect described image file;
When the tracking target is not present in detecting described image file, generation one, which includes to be not present, tracks target information
The second testing result;
Second testing result is stored to the communication file and is pressed from both sides.
In a kind of exemplary embodiment of the disclosure, the method further includes:
Judge to whether there is one second testing result in the communication file folder;
Judging, there are during second testing result, to read second testing result, and obtain described image file
Next frame image file;
The next frame image file of described image file and one first operation label are stored to the communication file and pressed from both sides
In order to which the detection module is detected next two field picture according to the first operation label;
The above method is repeated to detecting that there are the tracking target in a two field picture file.
In a kind of exemplary embodiment of the disclosure, the testing result further includes one and is used to distinguish first detection
As a result and the second testing result class label.
In a kind of exemplary embodiment of the disclosure, first testing result includes:
The coordinate information and tracking target region image information of the tracking target.
In a kind of exemplary embodiment of the disclosure, the method further includes:
When starting to track target according to the positional information, generation one is used to identify the second operation into tracking mode
Label, and the second operation label is sent into communication file folder and is made in order to which the tracking module obtains described second
Industry label.
In a kind of exemplary embodiment of the disclosure, the real-time judge tracking mode includes:
Judge the current tracking mode of the tracking target;
When judging the tracking mode to lose, the image file at current time is obtained;
The image file at the current time and one first operation label are stored to a communication file and pressed from both sides in order to institute
State in the image file that detection module detects the current time according to the first operation label.
In a kind of exemplary embodiment of the disclosure, the method further includes:
The detection module judges to whether there is the first operation label in the communication file;
Judging that acquisition is stored in the current time in the communication file folder there are during the first operation label
Image file and detect described image file with the presence or absence of tracking target;
In the no target in the presence of tracking of detection described image file, positional information and the generation one of the tracking target are obtained
The first testing result comprising the positional information;
First testing result is stored to the communication file and is pressed from both sides.
In a kind of exemplary embodiment of the disclosure, the method further includes:
There is no during the tracking target in the image file that the detection module detects the current time, one is generated
Comprising there is no tracking target information the second testing result and store to the communication file press from both sides.
In a kind of exemplary embodiment of the disclosure, the method further includes:
Judge whether to receive an END instruction;
Judge receive an END instruction when, generate one second operation label and store to a communication file press from both sides in order to
Detection module end operation after the second operation label is obtained.
According to the second aspect of the disclosure, there is provided a kind of low target intelligent tracking system, including:
Detection module, whether the one first operation label for being generated according to a tracking module is detected in an image file deposits
In tracking target, and in detection, there are the detection knot that generation one during the tracking target includes the tracking position of object information
Fruit;
Tracking module, tracks for generating described image file and the first operation label, and according to the testing result
Target and real-time judge tracking mode;
Communication file presss from both sides, for storing described image file, the first operation label and the testing result.
According to the third aspect of the disclosure, there is provided a kind of storage medium, is stored thereon with computer program, described program quilt
Processor realizes above-mentioned low target intelligent-tracking method when performing.
According to the fourth aspect of the disclosure, there is provided a kind of electric terminal, including:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to perform following operation via the executable instruction is performed:
Generate an image file and one first operation label, in order to a detection module obtain described image file and
First operation label;
The detection module is detected in described image file with the presence or absence of tracking according to the first operation label of acquisition
Target, and there are the first testing result that generation one during the tracking target includes the tracking position of object information in detection;
First testing result of detection module generation is obtained, target and real-time is tracked according to the positional information
Judge tracking mode.
In the low target intelligent-tracking method that a kind of embodiment of the disclosure is provided, by using a detection module root
The positional information of simultaneously output tracking target is detected to image file according to the first operation label received, and according to detection mould
The positional information of block output starts to track to tracking target.By being detected acquisition positional information to image file, so that real
To tracking the detection of target and effectively tracking in present complex background.Meanwhile by being carried out during tracking to tracking mode
Judge in real time, and adjusted in real time for the change of tracking mode, and then realize the tenacious tracking to tracking target.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Attached drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the disclosure
Example, and be used to together with specification to explain the principle of the disclosure.It should be evident that drawings in the following description are only the disclosure
Some embodiments, for those of ordinary skill in the art, without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of low target intelligent-tracking method schematic diagram in disclosure exemplary embodiment;
Fig. 2 schematically shows a kind of low target intelligent-tracking method flow diagram in disclosure exemplary embodiment;
Fig. 3 schematically shows the first two field picture in disclosure exemplary embodiment and detects view;
Fig. 4 schematically shows tenacious tracking state next frame image file schematic diagram in disclosure exemplary embodiment;
Fig. 5 schematically shows tracking in disclosure exemplary embodiment and loses and be not detected by a two field picture of tracking target
File schematic diagram;
Fig. 6 schematically shows tracking in disclosure exemplary embodiment detects tracking target two field picture text after losing
Part schematic diagram;
Fig. 7 schematically shows the view that two field picture when losing is tracked in disclosure exemplary embodiment;
Fig. 8 schematically shows the view for detecting tracking target in disclosure exemplary embodiment again;
Fig. 9 schematically shows the state for being tracked in disclosure exemplary embodiment and loss being tracked after target is blocked by barrier
Schematic diagram;
Figure 10 schematically shows the view for detecting tracking target in disclosure exemplary embodiment again;
Figure 11 schematically shows a kind of composition signal of low target intelligent tracking system in disclosure exemplary embodiment
Figure;
Figure 12 schematically shows a kind of a kind of signal of low target intelligent tracking device in disclosure exemplary embodiment
Figure;
Figure 13 schematically shows a kind of another kind of low target intelligent tracking device in disclosure exemplary embodiment and shows
It is intended to.
Embodiment
Example embodiment is described more fully with referring now to attached drawing.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein;On the contrary, these embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in one or more embodiments in any suitable manner.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note represents same or similar part, thus will omit repetition thereof.Some block diagrams shown in attached drawing are work(
Can entity, not necessarily must be corresponding with physically or logically independent entity.These work(can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
It provide firstly a kind of low target intelligent-tracking method in this example embodiment, can be applied to civilian or army
Tracking of the low target under complex background is directed to, such as in the city with more building or timbered jungle
In;It can effectively solve the problems, such as electronic interferences at the same time.With reference to shown in figure 1, above-mentioned low target intelligent-tracking method
It may comprise steps of:
S1, generates an image file and one first operation label, in order to which a detection module obtains described image file
And the first operation label;
S2, the detection module according to the first operation label of acquisition detect described image file in whether there is with
Track target, and there are first detection knot of the generation one during the tracking target comprising the tracking position of object information in detection
Fruit;
S3, obtains first testing result of the detection module generation, target is tracked simultaneously according to the positional information
Real-time judge tracking mode.
The low target intelligent-tracking method that this example embodiment is provided is by using a detection module according to reception
To the first operation label image file is detected and the positional information of output tracking target, and exported according to detection module
Positional information to tracking target start to track.By being detected acquisition positional information to image file, so as to fulfill multiple
To tracking the detection of target and effectively tracking in miscellaneous background.It is meanwhile real-time by being carried out during tracking to tracking mode
Judge, and adjusted in real time for the change of tracking mode, and then realize the tenacious tracking to tracking target.
In the following, each step of the accompanying drawings and embodiments to the active-mode intelligent tracking in this example embodiment will be combined
Suddenly it is described in detail.
Step S1, generates an image file and one first operation label, in order to which a detection module obtains described image
File and the first operation label.
In this example embodiment, a tracking module can be provided, for generating above-mentioned image file and the first work
Industry label.It may comprise steps of in one initial pictures file of generation and the first operation label:
S11, obtains a tracking video, intercepts a two field picture of the tracking video as described image file, and generate
One first operation label;
S12, described image file and the first operation label are stored to a communication file and pressed from both sides.
When proceeding by tracking, refering to what is shown in Fig. 2, can at the same time start-up trace module and detection module so that institute
Tracking module and the mutual independent operating of detection module are stated, is not clashed.Start in the tracking module and detection module
Afterwards, the video flowing that waiting needs to track enters.After video flowing to be tracked is received, due to initial pictures can not determine with
The coordinate information of track target and cannot normally be tracked, refering to what is shown in Fig. 3, tracking module can intercept the of video flowing at this time
One two field picture generates one first operation label as initial pictures, by the initial pictures and the first operation label store to
One communication file presss from both sides.
For example, the first above-mentioned operation label can be the numeral combination comprising flag information, such as:【3.0.0】.
In other examples of the disclosure, the first above-mentioned operation Shipping Options Page can use the digital or alphabetical combination of logo role
In order to which it is identified in the detection module, such as:【S.0.0】, wherein s can be expressed as search, that is, search for.This public affairs
Open and particular determination is not done to the specific manifestation form of the first operation label.Information of the detection module in communication file folder is read
When, primary flag information can be read first.
In this example embodiment, above-mentioned detection module obtains described image file and the first operation label specifically may be used
With including:
Step S13, the detection module judge to whether there is the first operation label in the communication file;
Step S14, is judging that reading is stored in described in the communication file folder there are during the first operation label
Image file.
Refering to what is shown in Fig. 2, after the detection module is activated, can active cycle detect in the communication file folder
With the presence or absence of the operation label and image file of tracking module storage.And there are operation mark in communication file folder is detected
When label and image file, it is read out.For example, when first flag bit for reading the first operation label is " 3 "
Or when " s ", just start to be detected the initial pictures file of reading, judge whether a tracking target.
Whether step S2, the detection module detect in described image file according to the first operation label of acquisition and deposit
In tracking target, and in detection, there are first detection of the generation one during the tracking target comprising the tracking position of object information
As a result the detection module is detected in the initial pictures file with the presence or absence of tracking according to the first operation label of acquisition
Target.
In this example embodiment, above-mentioned step S2 can specifically include:
Step S21, the detection module detection described image file is with the presence or absence of tracking target;
Step S212, when detecting described image file in the presence of tracking target, obtains the positional information of the tracking target
And generate first testing result for including the positional information;
Step S213, first testing result is stored to the communication file and is pressed from both sides.
Refering to what is shown in Fig. 3, the video flowing gathered in this example comes from low latitude unmanned plane during flying video, unmanned plane distance is about
1.5 kilometers are maintained at, the video resolution of real-time Transmission is 720*576.When the detection module detects the initial pictures
There is tracking target in file, that is, when detecting unmanned plane target, the specific of the tracking target can be obtained using detection algorithm
Coordinate information;And the coordinate information is generated into one first testing result, while first testing result is stored to described logical
Believe in file and read for tracking module.
For example, when being detected to a two field picture file, the unmanned machine testing mould of such as deep learning can be utilized
Type is detected current frame image.The wherein described deep learning unmanned plane detection model is by gathering 1.5 kilometers of nothing
Man-machine low-latitude flying video and arrange marked substantial amounts of unmanned plane image pattern, then deep learning detection model is instructed
Unmanned plane detection model under the low latitude scene is got.In addition, other can also be used in other exemplary embodiments
Mode with the presence or absence of tracking target in truncated picture to judging that the disclosure is not particularly limited this.
Based on the above, in order to further improve the accuracy of positional information, the first above-mentioned testing result is being wrapped
While containing the tracking coordinates of targets information, the image information of the tracking target region can also be included, in order to
Tracking module reads line trace of going forward side by side.
Step S3, obtains first testing result of the detection module generation, mesh is tracked according to the positional information
Mark simultaneously real-time judge tracking mode.
In this example embodiment, above-mentioned step S3 can specifically include:
Step S311, judges to whether there is one first testing result in the communication file folder;
Step S312, is judging there are during first testing result, reads first testing result and according to described
Positional information starts to track target.
Refering to what is shown in Fig. 2, the first operation label is detected and the initial pictures file in the tracking module
After storing to the communication file in pressing from both sides, it can start the cycle over and judge to whether there is the detection mould in the communication file folder
The testing result of block storage, and judging that there are testing result is read out during testing result.Judge in the tracking module
There are the coordinate information for during the first testing result, reading tracking target described in first testing result, and believed according to coordinate
Breath starts to track.
In other this example embodiments of the disclosure, refering to what is shown in Fig. 2, in the tracking module according to positional information
Start track target after, tracking module can generate one be used for identify enter tracking mode the 3rd operation label, such as
【0.0.0】Or【S.0.0】Deng, and the 3rd operation label is sent into communication file folder in order to the tracking module
Read the 3rd operation label.
For example, can be for example, by when carrying out target following:Mean shift algorithm, the drift of continuous adaptive average
Move the classical calculations such as algorithm, particle filter algorithm, tracking study detection algorithm, maximal correlation matching algorithm or measuring similarity algorithm
Method is to tracking target into line trace.The disclosure is not particularly limited this.
In addition, in other illustrative embodiments of the disclosure, above-mentioned steps S2 can also include:
Step S21, the detection module detection described image file is with the presence or absence of tracking target;
Step S222, in detecting described image file there is no it is described tracking target when, generation one include be not present with
Second testing result of track target information;
Step S223, second testing result is stored to the communication file and is pressed from both sides.
In this example embodiment, refering to what is shown in Fig. 2, when detection module detect be not present in the initial pictures file with
Track target, that is, when being not detected by unmanned plane target, can generate the second testing result of above-mentioned first testing result of a difference,
And the testing result is stored in the communication file folder and is read for the tracking module.
For example, the first above-mentioned testing result and the second testing result can carry out table using number combinatorics on words respectively
Show, and include the class label one for distinguishing testing result.Such as first testing result can be expressed as【1.x.y】, wherein
" 1 " can be used as flag, and tracking target is detected for being identified as, and " x.y " can represent the detailed coordinate of tracking target.Or
Person can also use the mode of " x.y.z " to represent the coordinate information of the tracking target.Second testing result can be expressed as
【2.0.0】, wherein " 2 " are used as flag, tracking target is not detected by for being identified as.By setting testing result
Flag, easy to reading of the tracking module to testing result.
In other illustrative embodiments of the disclosure, it can also be tied using letter and the result of numeral to represent to detect
Fruit.Such as first testing result be【Y.x.y】, wherein " Y " is used as flag, it is expressed as detecting tracking target, " x.y " is represented
Specific coordinate information;Second testing result is【N.0.0】, wherein " N " is used as flag, it is expressed as being not detected by tracking mesh
Mark.The disclosure does not do particular determination to the form of expression of testing result.Each detection in tracking target reads communication file folder
During result information, primary sign position information can also be read first.
Based on the above, above-mentioned step S3 can also comprise the following steps:
Step S321, judges to whether there is second testing result in the communication file folder;
Step S322, is judging there are during second testing result, reads second testing result, and described in obtaining
The next frame image file of image file;
Step S323, the next frame image file of described image file and one first operation label are stored to described logical
Letter file is detected next two field picture according to the first operation label in order to the detection module;
Step S324, repeat step S1~S3 are to detecting that there are the tracking target in a two field picture file.
In this example embodiment, the testing result in tracking module cycle criterion and the reading communication file,
Detect the second testing result and judge to choose institute there is no during tracking target in the initial pictures file after reading flag
Next two field picture generation image file of initial pictures in video flowing is stated, while generates one first operation label again, and should
Two field picture file and the first operation label send to communication file and press from both sides in order to which detection module is read out it and to the frame figure
As file is detected.
Step S1-S3 is performed again, detects each two field picture in video flowing successively, until detecting one in video flowing
There is tracking target in two field picture, then started to track target according to the coordinate information detected.
In other examples of the disclosure, or the detection module sets a prompting message, that is, works as detection module
When continuous n two field picture files are not detected by tracking target, generate one the 4th testing result, and by the 4th testing result store to
In the communication file folder, to remind the tracking module for tracking mesh and may be not present in the initial video stream of receiving
Mark.
The detection to each two field picture into line trace target can be realized by above-mentioned steps, and then is realized under complex background
Accurate judgement to tracking target, so as to fulfill the active tracking to target, and can solve to work as thunder to a certain extent
Target position information can not be detected up to after being subject to electronic interferences and is supplied to the situation of tracking equipment.
Based on the above, in this example embodiment, above-mentioned real-time judge tracking mode can include:
Step S411, judges the current tracking mode of the tracking target;
Step S412, when judging the tracking mode to lose, obtains the image file at current time;
Step S413, the image file at the current time and one first operation label are stored to a communication file and pressed from both sides
In order in image file of the detection module according to the first operation label detection current time.
After successfully tracking is started, tracking module can carry out real-time judge to tracking mode.With reference to shown in figure 5, Fig. 7,
Tracking target is lost in the 166th frame, the 798th two field picture during tracking.When being judged as that tracking is lost, tracking module can
Pressed from both sides with intercepting the two field picture at current time and being stored to the communication file, while one first operation label is stored to institute
State communication file folder.
The detection module reads above-mentioned work as after cycle detection communication file presss from both sides and detects the first operation label
The two field picture at preceding moment is simultaneously detected it with the presence or absence of tracking target.There is tracking in the two field picture at detection current time
When the first testing result is generated during target, which is stored in the communication file folder, so that tracking module
Read first testing result and tracking target is continued to track.As shown in fig. 6, after tracking loss in the 167th two field picture again
It is secondary to detect tracking target.I.e. when judging that tracking is lost, tracking module performs step by generating one first operation mark cycle
Rapid S1~S3.
In addition, in other illustrative embodiments of the disclosure, above-mentioned real-time judge tracking mode can also include:
There is no during the tracking target in the two field picture file that the detection module detects the current time, such as scheme
Shown in 5, tracking target is lost in the 166th frame and is not detected by tracking target.One can be generated at this time comprising there is no tracking
Second testing result of target information is simultaneously stored to communication file folder.
Tracking module gives birth to result into one first operation label again after second detection is read, and obtains continuous next
Two field picture file is stored to communication file and pressed from both sides in the lump, in order to which the detection module is next again according to the detection of the first operation label
The image file of frame.
Repeat above step to the detection module and detect that there are the tracking target in a two field picture file.
During tracking, tracking mode can be judged for example, by modes such as Normalized Cross Correlation Algorithms.
By being judged in real time tracking mode after tracking successfully, and current frame image is obtained in time when judging that tracking is lost
And it is detected, in detection there is no can be detected during tracking target to continuous multiple image, until detecting a frame
There are the tracking in image target and to send positional information to tracking module, make tracking module according to positional information continue with
Track, realizes the circulate operation to " tracking loss-startup detection module detects again-tracks " of target.It is achieved thereby that to mesh
Target continues, tenacious tracking, and then solves the situation that radar is subject to not detecting target position information after electronic interferences, realizes
More intelligent tracking.
Based on above content, in the present example embodiment, refering to what is shown in Fig. 3, the intelligent-tracking method further includes:
Step S51, judges whether to receive an END instruction;
Step S52, when judging to receive an END instruction, generates one second operation label and stores to a communication file
Folder end operation after the second operation label is obtained in order to the detection module.
Refering to what is shown in Fig. 2, when tracking module receives the instruction that a tracking terminates, stored in being pressed from both sides to communication file
One and operation label, such as【4.0.0】Or【O.0.0】.Detection module read this and after operation label, then stop pair
The detection of communication file folder.If tracking module does not receive END instruction, each step of the above is continuously carried out.
In above-mentioned communication file folder, each command information can include:One communication file, and one or two image text
Part.It can include above-mentioned each command information or coordinate information for example in communication file【1.x.y】、【2.0.0】、【3.0.0】、
【0.0.0】Or【4.0.0】Any one of;Image file can be one in target image file and target area image file
It is a or two.During work, every time read or write-in data line arrive communication file, or write data line to communication file with
And one or two image file.Initial data can be covered during write-in so that all the time only comprising a letter in communication file folder
Breath, reads easy to each module.
In order to further verify that the disclosure provides accuracy of the method for low target intelligent measurement and tracking, below
Embodiment carries out experimental verification with one section of UAV Video.
As shown in Figure 2, it is the first frame picture of tracking video.Tracking module sends one first operation label first at this time
Enter detection:[3 0 0] read in order to detection module, and preserve current initial two field picture.When detection module is read
When first flag bit to the first operation label is 3, the current initial two field picture of preservation is detected.As shown in figure 3, inspection
Survey module and detect unmanned plane target, coordinate information [1 482 124] is write into communication file, and export in display terminal
Send Detection Status:[1 482 124], wherein flag bit 1 represent and detect target, and the center of unmanned plane
Point coordinates position is [482 124].
As shown in Figure 4, the 26th~31 frame tracking module of this secondary tracking video is in tenacious tracking, exports tenacious tracking
State Stable Tracking:[0 0 0].As shown in figure 5, the 165th frame BREAK TRACK (Tracking of video
Lost), tracking module sends the first operation label E nter detection again:[3 0 0], and current frame image is preserved, but
Detection module is simultaneously not detected by present frame there are target, sends the second testing result Send Detection Status:[2 0
0].As shown in fig. 6, detection module detects unmanned plane target in the 166th two field picture, the first testing result Send is sent
Detection Status:[1 405 195]。
As shown in fig. 7, unmanned plane the 798th frame during tracking tracks loss suddenly, be not subject to it is any block, at this time
Tracking module sends the first operation label E nter detection again:[3 0 0], preserve current frame image.Work as detection module
Read and the present frame of preservation is detected after this first operation label.As shown in figure 8, detection module detects nothing
Man-machine target, sends the first testing result Send Detection Status:[1 409 125], tracking module continue to track.
As shown in figure 9, this video tracking causes tracking to be lost to during 1378 frame since light pole blocks, tracking module
The first detection label E nter detection are sent again:[3 0 0], preserve current frame image.When detection module reads
The current frame image of preservation is detected after one detection label.As shown in Figure 10, detection module detects unmanned plane mesh
Mark, sends the first testing result Send Detection Status:[1 90 91], tracking module are again at tenacious tracking shape
State.
By manually sending tracing task END instruction at the end of tracing task, tracking module judges whether video terminates,
Write-in END instruction [4 0 0] is pressed from both sides to communication file if terminating, detection module stops Detection task after reading instruction.
It can be seen from the above embodiments that, the tracking that the disclosure provides can be after tracking be lost, active detecting
To realize the tracking for continuing, stablizing, there is good tracking effect under the complex background of low latitude.
The intelligent measurement tracking applied to low target that the disclosure provides, by setting detection module and tracking mould
Block starts, works independently and circulates respectively at the same time reads communication file folder progress co-ordination so that at work mutually not
Conflict, so as to provide a more complete communication mechanism so that detection module and tracking module efficiently combine.Tracking
Cheng Zhong, by carrying out lasting judgement to tracking mode, and is timely reacquired again when determining tracking and losing
Image file simultaneously detects and obtains positional information, so as to ensure the tracking that target Continuous is stablized, and can effectively solve to work as
Radar is subject to the situation that target location can not be detected after electronic interferences.
It should be noted that above-mentioned attached drawing is only showing for the processing included by method according to an exemplary embodiment of the present invention
Meaning property explanation, rather than limitation purpose.It can be readily appreciated that it is above-mentioned it is shown in the drawings processing be not intended that or limit these processing when
Between order.In addition, being also easy to understand, these processing for example can be performed either synchronously or asynchronously in multiple modules.
Further, with reference to shown in figure 11, a kind of low target intelligent-tracking system is also provided in this exemplary embodiment
System 2, including:Detection module 21,22 and one communication file of tracking module folder 23.Wherein:
The one first operation label that the detection module 21 can be used for being generated according to a tracking module detects image text
With the presence or absence of tracking target in part, and there are generate one to include the tracking position of object information during tracking target in detection
Testing result.
The tracking module 22 can be used for generating described image file and the first operation label, and according to the detection
As a result target and real-time judge tracking mode are tracked.
The communication file folder 23 can be used for being used to store described image file, the operation label and the detection
As a result.
In above-mentioned low target intelligent tracking system the detail of each module corresponding active-mode intelligent with
It is described in detail in track method, therefore details are not described herein again.
It should be noted that although some modules or list of the equipment for action executing are referred in above-detailed
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Either the feature of unit and function can embody module in a module or unit.A conversely, above-described mould
Either the feature of unit and function can be further divided into being embodied by multiple modules or unit block.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can realize the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be implemented as following form, i.e.,:It is complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.), or hardware and software, can unite here
Referred to as " circuit ", " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Figure 12.The electricity that Figure 12 is shown
Sub- equipment 600 is only an example, should not bring any restrictions to the function and use scope of the embodiment of the present invention.
As shown in figure 12, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can be with
Including but not limited to:Above-mentioned at least one processing unit 610, above-mentioned at least one storage unit 620, connection different system component
The bus 630 of (including storage unit 620 and processing unit 610), display unit 640.
Wherein, the storage unit has program stored therein code, and said program code can be held by the processing unit 610
OK so that the processing unit 610 performs various according to the present invention described in above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can perform step S1 as shown in fig. 1:Generate a figure
As file and one first operation label, in order to which a detection module obtains described image file and the first operation label;Step
Rapid S2:The detection module is detected in described image file with the presence or absence of tracking mesh according to the first operation label of acquisition
Mark, and there are the first testing result that generation one during the tracking target includes the tracking position of object information in detection;Step
Rapid S3:First testing result of the detection module generation is obtained, target is tracked according to the positional information and is sentenced in real time
Disconnected tracking mode.
Storage unit 620 can include the computer-readable recording medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but not limited to:Operating system, one or more application program, other program moulds
Block and routine data, may include the realization of network environment in each or certain combination in these examples.
Bus 630 can be the one or more in a few class bus structures of expression, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment communication interacted with the electronic equipment 600 can be also enabled a user to one or more, and/or with causing
Any equipment that the electronic equipment 600 can communicate with one or more of the other computing device (such as router, modulation /demodulation
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown in the figure, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, can combine electronic equipment 600 does not use other hardware and/or software module, including but not
It is limited to:Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can be realized by software, can also be realized by way of software is with reference to necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software product, the software product can be stored in one it is non-volatile
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is performed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer-readable recording medium is additionally provided, is stored thereon with energy
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product, it includes program code, when described program product is run on the terminal device, institute
State program code be used for make the terminal device perform described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
With reference to shown in figure 13, the program product for being used for realization the above method according to the embodiment of the present invention is described
800, it can use portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as run on PC.However, the program product not limited to this of the present invention, in this document, readable storage medium storing program for executing can be with
Be it is any include or the tangible medium of storage program, the program can be commanded execution system, device either device use or
It is in connection.
Described program product can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any combination above.The more specifically example of readable storage medium storing program for executing is (non exhaustive
List) include:It is electrical connection, portable disc, hard disk, random access memory (RAM) with one or more conducting wires, read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media can be including the data-signal in a base band or as carrier wave part propagation, its
In carry readable program code.The data-signal of this propagation can take various forms, include but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie beyond readable storage medium storing program for executing
Matter, which can send, propagate either transmission be used to be used by instruction execution system, device or device or and its
The program of combined use.
The program code included on computer-readable recording medium can be transmitted with any appropriate medium, including but not limited to wirelessly, be had
Line, optical cable, RF etc., or above-mentioned any appropriate combination.
It can be write with any combination of one or more programming languages for performing the program that operates of the present invention
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
Perform on computing device, partly perform on a user device, the software kit independent as one performs, is partly calculated in user
Its upper side point is performed or performed completely in remote computing device or server on a remote computing.It is remote being related to
In the situation of journey computing device, remote computing device can pass through the network of any kind, including LAN (LAN) or wide area network
(WAN), user calculating equipment is connected to, or, it may be connected to external computing device (such as utilize ISP
To pass through Internet connection).
In addition, above-mentioned attached drawing is only schematically saying for the processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limitation purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings was not intended that or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing for example can be performed either synchronously or asynchronously in multiple modules.
Those skilled in the art will readily occur to the disclosure its after considering specification and putting into practice invention disclosed herein
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principle of the disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.Description and embodiments are considered only as exemplary, and the true scope and spirit of the disclosure are by claim
Point out.
It should be appreciated that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by appended claim.
Claims (16)
- A kind of 1. low target intelligent-tracking method, it is characterised in that including:An image file and one first operation label are generated, in order to which a detection module obtains described image file and first Operation label;The detection module is detected according to the first operation label of acquisition whether there is tracking target in described image file, And there are the first testing result that generation one during the tracking target includes the tracking position of object information in detection;First testing result of the detection module generation is obtained, target and real-time judge are tracked according to the positional information Tracking mode.
- 2. low target intelligent-tracking method according to claim 1, it is characterised in that it is described generation one image file with And first operation label include:A tracking video is obtained, intercepts a two field picture of the tracking video as described image file, and generate one first and make Industry label;Described image file and the first operation label are stored to a communication file and pressed from both sides.
- 3. low target intelligent-tracking method according to claim 2, it is characterised in that the detection module is according to acquisition The first operation label detection described image file in the presence or absence of tracking target, and there are the tracking target in detection The first testing result that Shi Shengcheng mono- includes the tracking position of object information includes:The detection module judges to whether there is the first operation label in the communication file;Judging that there are during the first operation label, obtain the described image file being stored in the communication file folder and examine Described image file is surveyed with the presence or absence of tracking target;When detection described image file has tracking target, the positional information and generation one that obtain the tracking target include institute State the first testing result of positional information;First testing result is stored to the communication file and is pressed from both sides.
- 4. low target intelligent-tracking method according to claim 3, it is characterised in that described to obtain the detection module life Into first testing result, according to the positional information track target include:Judge to whether there is one first testing result in the communication file folder;Judging there are during first testing result, read first testing result and according to the positional information start with Track target.
- 5. low target intelligent-tracking method according to claim 2, it is characterised in that the detection module is according to acquisition Further included in the first operation label detection described image file with the presence or absence of tracking target:The detection module inspection judgement, which is stated, whether there is the first operation label in communication file;Judging that there are during the first operation label, obtain the described image file being stored in the communication file folder and examine It is no in the presence of tracking target to survey described image file;There is no during the tracking target, generation one includes that there is no the of tracking target information in detecting described image file Two testing results;Second testing result is stored to the communication file and is pressed from both sides.
- 6. low target intelligent-tracking method according to claim 5, it is characterised in that the method further includes:Judge to whether there is one second testing result in the communication file folder;Judging, there are during second testing result, to read second testing result, and obtain under described image file One two field picture file;By the next frame image file of described image file and one first operation label store to the communication file press from both sides so as to Next two field picture is detected according to the first operation label in the detection module;The above method is repeated to detecting that there are the tracking target in a two field picture file.
- 7. according to the low target intelligent-tracking method of claim 3 or 5, it is characterised in that the testing result further includes One class label for distinguishing first testing result and the second testing result.
- 8. low target intelligent-tracking method according to claim 7, it is characterised in that first testing result includes:The coordinate information and tracking target region image information of the tracking target.
- 9. low target intelligent-tracking method according to claim 3, it is characterised in that the method further includes:When starting to track target according to the positional information, generation one is used to identify the second operation mark into tracking mode Label, and the second operation label is sent into communication file folder in order to which the tracking module obtains second operation Label.
- 10. low target intelligent-tracking method according to claim 1, it is characterised in that the real-time judge tracking mode Including:Judge the current tracking mode of the tracking target;When judging the tracking mode to lose, the image file at current time is obtained;The image file at the current time and one first operation label are stored to a communication file and pressed from both sides in order to the inspection Survey in the image file that module detects the current time according to the first operation label.
- 11. low target intelligent-tracking method according to claim 10, it is characterised in that the method further includes:The detection module, which is detected in the communication file, whether there is the first operation label;Judging that there are the figure for during the first operation label, obtaining the current time being stored in the communication file folder As file and described image file is detected with the presence or absence of tracking target;When detection described image file has tracking target, the positional information and generation one that obtain the tracking target include institute State the first testing result of positional information;First testing result is stored to the communication file and is pressed from both sides.
- 12. according to the low target intelligent-tracking method of claim 10 or 11, it is characterised in that the method further includes:There is no during the tracking target in the image file that the detection module detects the current time, generation one includes There is no the second testing result for tracking target information and store to communication file folder.
- 13. according to claim 1-12 any one of them low target intelligent-tracking methods, it is characterised in that the method is also Including:Judge whether to receive an END instruction;When judging to receive an END instruction, generate one second operation label and store to a communication file and press from both sides in order to described Detection module end operation after the second operation label is obtained.
- A kind of 14. low target intelligent tracking system, it is characterised in that including:Detection module, detected for the one first operation label that is generated according to a tracking module whether there is in an image file with Track target, and there are the testing result that generation one during the tracking target includes the tracking position of object information in detection;Tracking module, target is tracked for generating described image file and the first operation label, and according to the testing result And real-time judge tracking mode;Communication file presss from both sides, for storing described image file, operation label and the testing result.
- 15. a kind of storage medium, is stored thereon with computer program, being realized when described program is executed by processor will according to right Seek the low target intelligent-tracking method any one of 1 to 14.
- A kind of 16. electric terminal, it is characterised in that including:Processor;AndMemory, for storing the executable instruction of the processor;Wherein, the processor is configured to perform following operation via the executable instruction is performed:An image file and one first operation label are generated, in order to which a detection module obtains described image file and first Operation label;The detection module is detected according to the first operation label of acquisition whether there is tracking target in described image file, And there are the first testing result that generation one during the tracking target includes the tracking position of object information in detection;First testing result of the detection module generation is obtained, target and real-time judge are tracked according to the positional information Tracking mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710952377.0A CN107944337A (en) | 2017-10-13 | 2017-10-13 | A kind of low target intelligent-tracking method and system, storage medium and electric terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710952377.0A CN107944337A (en) | 2017-10-13 | 2017-10-13 | A kind of low target intelligent-tracking method and system, storage medium and electric terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107944337A true CN107944337A (en) | 2018-04-20 |
Family
ID=61935269
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710952377.0A Pending CN107944337A (en) | 2017-10-13 | 2017-10-13 | A kind of low target intelligent-tracking method and system, storage medium and electric terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944337A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111045446A (en) * | 2019-11-04 | 2020-04-21 | 西安天和防务技术股份有限公司 | Maintenance method, equipment and system for unmanned aerial vehicle |
WO2021208257A1 (en) * | 2020-04-15 | 2021-10-21 | 上海摩象网络科技有限公司 | Tracking state determination method and device, and handheld camera |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1968352A (en) * | 2005-11-17 | 2007-05-23 | 中国科学院半导体研究所 | High-speed target tracking method and its circuit system |
CN102136147A (en) * | 2011-03-22 | 2011-07-27 | 深圳英飞拓科技股份有限公司 | Target detecting and tracking method, system and video monitoring device |
CN104777478A (en) * | 2015-04-16 | 2015-07-15 | 电子科技大学 | Target searching and acquisition method of phased array radar |
CN104992452A (en) * | 2015-06-25 | 2015-10-21 | 中国计量学院 | Flight object automatic tracking method based on thermal imaging video |
CN106131506A (en) * | 2016-08-23 | 2016-11-16 | 北京汉博信息技术有限公司 | A kind of visualization data tracking acquisition terminal |
CN106713862A (en) * | 2016-12-23 | 2017-05-24 | 浙江宇视科技有限公司 | Tracking monitoring method and apparatus |
CN106951871A (en) * | 2017-03-24 | 2017-07-14 | 北京地平线机器人技术研发有限公司 | Movement locus recognition methods, device and the electronic equipment of operating body |
CN107170011A (en) * | 2017-04-24 | 2017-09-15 | 杭州司兰木科技有限公司 | A kind of robot vision tracking and system |
-
2017
- 2017-10-13 CN CN201710952377.0A patent/CN107944337A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1968352A (en) * | 2005-11-17 | 2007-05-23 | 中国科学院半导体研究所 | High-speed target tracking method and its circuit system |
CN102136147A (en) * | 2011-03-22 | 2011-07-27 | 深圳英飞拓科技股份有限公司 | Target detecting and tracking method, system and video monitoring device |
CN104777478A (en) * | 2015-04-16 | 2015-07-15 | 电子科技大学 | Target searching and acquisition method of phased array radar |
CN104992452A (en) * | 2015-06-25 | 2015-10-21 | 中国计量学院 | Flight object automatic tracking method based on thermal imaging video |
CN106131506A (en) * | 2016-08-23 | 2016-11-16 | 北京汉博信息技术有限公司 | A kind of visualization data tracking acquisition terminal |
CN106713862A (en) * | 2016-12-23 | 2017-05-24 | 浙江宇视科技有限公司 | Tracking monitoring method and apparatus |
CN106951871A (en) * | 2017-03-24 | 2017-07-14 | 北京地平线机器人技术研发有限公司 | Movement locus recognition methods, device and the electronic equipment of operating body |
CN107170011A (en) * | 2017-04-24 | 2017-09-15 | 杭州司兰木科技有限公司 | A kind of robot vision tracking and system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111045446A (en) * | 2019-11-04 | 2020-04-21 | 西安天和防务技术股份有限公司 | Maintenance method, equipment and system for unmanned aerial vehicle |
CN111045446B (en) * | 2019-11-04 | 2023-03-10 | 西安天和防务技术股份有限公司 | Maintenance method, equipment and system for unmanned aerial vehicle |
WO2021208257A1 (en) * | 2020-04-15 | 2021-10-21 | 上海摩象网络科技有限公司 | Tracking state determination method and device, and handheld camera |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3944147A1 (en) | Target detection method, model training method, device, apparatus and storage medium | |
EP3961485A1 (en) | Image processing method, apparatus and device, and storage medium | |
CN109947886B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
US10430707B2 (en) | Information processing device | |
KR102078427B1 (en) | Augmented reality with sound and geometric analysis | |
KR20190062171A (en) | Deep learning-based real-time detection and correction of compromised sensors in autonomous machines | |
US11893702B2 (en) | Virtual object processing method and apparatus, and storage medium and electronic device | |
CN107450088A (en) | A kind of location Based service LBS augmented reality localization method and device | |
CN109582880A (en) | Interest point information processing method, device, terminal and storage medium | |
US11111785B2 (en) | Method and device for acquiring three-dimensional coordinates of ore based on mining process | |
CN109344804A (en) | A kind of recognition methods of laser point cloud data, device, equipment and medium | |
CN110349212A (en) | Immediately optimization method and device, medium and the electronic equipment of positioning and map structuring | |
JP2021534480A (en) | Face recognition methods, devices, electronics and computers Non-volatile readable storage media | |
CN111095170B (en) | Virtual reality scene, interaction method thereof and terminal equipment | |
CN108876857A (en) | Localization method, system, equipment and the storage medium of automatic driving vehicle | |
WO2022257614A1 (en) | Training method and apparatus for object detection model, and image detection method and apparatus | |
CN107832001A (en) | Information processing method, device, electronic equipment and storage medium | |
CN109656319B (en) | Method and equipment for presenting ground action auxiliary information | |
CN108268831A (en) | The robustness test method and system of a kind of unmanned vehicle vision-based detection | |
CN109447996A (en) | Hand Segmentation in 3-D image | |
CN113378605B (en) | Multi-source information fusion method and device, electronic equipment and storage medium | |
CN107992366A (en) | Method, system and the electronic equipment that multiple destination objects are detected and tracked | |
CN109815854A (en) | It is a kind of for the method and apparatus of the related information of icon to be presented on a user device | |
CN107944337A (en) | A kind of low target intelligent-tracking method and system, storage medium and electric terminal | |
US9301722B1 (en) | Guiding computational perception through a shared auditory space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |
|
RJ01 | Rejection of invention patent application after publication |