CN110398720A - A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method - Google Patents
A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method Download PDFInfo
- Publication number
- CN110398720A CN110398720A CN201910773981.6A CN201910773981A CN110398720A CN 110398720 A CN110398720 A CN 110398720A CN 201910773981 A CN201910773981 A CN 201910773981A CN 110398720 A CN110398720 A CN 110398720A
- Authority
- CN
- China
- Prior art keywords
- target
- unmanned plane
- frame
- detection
- tracking
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000013135 deep learning Methods 0.000 claims abstract description 28
- 238000004891 communication Methods 0.000 claims abstract description 14
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 30
- 238000010586 diagram Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 2
- 238000002156 mixing Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/38—Jamming means, e.g. producing false echoes
Abstract
The present invention provides a kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method, wherein a kind of anti-unmanned plane detection tracking interference system, including radar, photoelectric follow-up, unmanned plane interference unit and holder；Photoelectric follow-up includes motion detection block, correlation filtering target tracking module, deep learning module of target detection and deep learning target tracking module；Radar and the photoelectric follow-up communication connection；Photoelectric follow-up and the holder communication connection.Anti- unmanned plane detection tracking interference system, when target range farther out, deep learning module of target detection extracts fall short feature, carries out target detection with motion detection block；When target range farther out, deep learning target tracking module extract fall short feature in the case where, target following is carried out using correlation filtering target tracking module；Solve the problems, such as that deep learning target tracking module cannot provide confidence level using the data of correlation filtering target tracking module.
Description
Technical field
The present invention relates to anti-unmanned plane tracking technique field, in particular to a kind of anti-unmanned plane detection tracking interference system and
Photoelectric follow-up working method.
Background technique
Radar is responsible for search discovery target in anti-UAV system, the target angle that electro-optical system is provided according to radar with
Range data controls platform-lens, completes the detection, locking and tracing task of target, then controls jamming equipment transmitting interference letter
Number to around UAV targets, until unmanned plane is dislodged.The system of traditional anti-unmanned plane, including radar, photoelectric tracking dress
Set, holder, satellite navigation and remote signal jamming equipment.Radar is responsible for finding unmanned plane target and by target angle and distance
Data are sent to photoelectronic tracking device；Photoelectronic tracking device is mainly made of target detection and target following two large divisions, target
Camera lens is directed toward target area by the target angle data control holder that detection module is provided according to radar, then according to range data
Imaging is focused to target area, target detection is then carried out according to the target signature of unmanned plane, it is automatic after finding target
Or by lock artificially target, the information of lock onto target is transmitted to target tracking module；The tracking module of photoelectronic tracking device exists
Previous frame target original position peripheral region carries out feature extraction, finds with target signature matching degree extreme higher position and as target
Then holder and camera lens are adjusted this new position, the countermeasure set then either automatically or manually to link, to mesh by new position
Field emission satellite navigation and remote control interference signal are marked, until unmanned plane is dislodged.At present using conventional target detection and target
The electro-optical system of track algorithm in unmanned plane hovering, blocks and is easily lost target in the case where deformation；And it is based on deep learning
The target detection track algorithm of technology
There is good detecting and tracking ability for the complete object under simple scenario, have to dimensional variation, deformation etc.
Stronger robustness is able to solve unmanned plane hovering, blocks and problem on deformation, but distance farther out, target is smaller, target is special
It is to be improved to levy detecting and tracking effect in unconspicuous situation.It is therefore desirable to combine conventional target detecting and tracking algorithm and depth
The advantage of learning objective detecting and tracking algorithm respectively designs a kind of novel trans unmanned plane light that can be detected, be locked with tracking automatically
Electric tracing system.
Summary of the invention
To solve the problems, such as that background technique is mentioned, the present invention provides a kind of anti-unmanned plane detection tracking interference system, including
Radar, photoelectric follow-up, unmanned plane interference unit and holder；
Wherein, the photoelectric follow-up includes motion detection block, correlation filtering target tracking module, deep learning mesh
Mark detection module and deep learning target tracking module；
Motion detection block, for moving the target detection of unmanned plane at a distance；
Correlation filtering target tracking module, for moving the target following of unmanned plane at a distance；
Deep learning module of target detection, be used in, the target detection of short distance unmanned plane；
Deep learning target tracking module, be used in, the target following of short distance unmanned plane；
The detection radar and the photoelectric follow-up communication connection；
The photoelectric follow-up and the holder communication connection；
Unmanned plane interference unit described in unmanned plane interference unit and the photoelectric follow-up communication connection.
Further, the unmanned plane interference unit includes locating channel interference unit and remote control channel disturbance device two parts.
Further, motion detection block, including foreground extraction, edge extracting, prospect merge scheduling algorithm.
Further, correlation filtering target tracking module, including feature extraction, template renewal, frequency domain dot product scheduling algorithm.
Further, deep learning module of target detection, including multiple convolutional layers and multiple full articulamentums, using convolution net
Network extracts feature, then obtains predicted value using full articulamentum.
Further, deep learning target tracking module, including multiple convolutional layers and multiple full articulamentums are rolled up using two sets
Product network extracts the feature of target area and region of search to former frame and present frame respectively, and full articulamentum is for comparing target spy
It seeks peace region of search feature, exports new target position.
The present invention also provides a kind of anti-unmanned plane detection tracking interference system working methods, comprising the following steps:
S10, Utilization prospects extract the prospect that operator obtains the movement of video frame；
S20, the foreground edge that video frame is carried out using arithmetic operators are extracted；
S30, the sport foreground extracted and edge are merged, obtains the prospect and target frame of current video frame；
S40, type, size, position and the confidence for extracting target from video frame using trained convolutional neural networks
Degree；
S50, whether it is greater than the target frame data that threshold value determines locking according to confidence level；
S60, the target assessed process is manually or automatically set as lock onto target；
S70, video sequence first frame is read, extracts the characteristics of image of target, filtered target track algorithm is closed according to nuclear phase
Training obtains KCF template；
S80, read next frame image, extract current frame image in potential target region characteristics of image, with KCF template into
Row convolution obtains KCF response diagram and tracking KCF target frame；Current frame image is input in trained CNN network simultaneously and is obtained
To the CNN target frame of tracking target；
S90, the secondary lobe ratio PSR that target is calculated according to KCF response diagram；
If S100, PSR are greater than algorithm threshold value, the final target that tracks is KCF target frame；Otherwise finally tracking target be for
CNN target frame；
If S110, PSR, which are greater than first, updates threshold value, the input of CNN network is updated with KCF target frame；If PSR is less than
Two update threshold value, then update KCF template with CNN target frame, while updating the input of CNN network；Otherwise KCF target frame is used.
S120, KCF template is updated, CNN target frame updates the input of CNN network；
S130, S80~S120 is repeated, until sequence of video images terminates.
Compared with the structure of traditional anti-UAV system of tradition, the present invention is had a characteristic that
1, target detection is realized in such a way that deep learning is combined with motion detection, also can under target floating state
It was found that target；
2, target following is realized in such a way that deep learning is combined with core correlation filtering, in target occlusion and deformation
In the case of will not lose target；
3, automatic target lock function is increased on the basis of original manual locking, is realized unattended.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the structural schematic diagram of anti-unmanned plane detection tracking interference system provided by the invention；
Fig. 2 is the trace flow schematic diagram of electro-optical system；
Fig. 3 is the analysis schematic diagram of embodiment；
Fig. 4 is the analysis schematic diagram of embodiment.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
The present invention provides a kind of anti-unmanned plane detection tracking interference system, including radar, photoelectric follow-up and holder；
Wherein, the photoelectric follow-up includes motion detection block, correlation filtering target tracking module, deep learning mesh
Mark detection module and deep learning target tracking module；
Motion detection block, for moving the target detection of unmanned plane at a distance；
Correlation filtering target tracking module, for moving the target following of unmanned plane at a distance；
Deep learning module of target detection, be used in, the target detection of short distance unmanned plane；
Deep learning target tracking module, be used in, the target following of short distance unmanned plane；
The radar and the photoelectric follow-up communication connection；
The photoelectric follow-up and the holder communication connection.
When it is implemented, as shown in Figure 1, automatic locking tracking electro-optical system includes radar, photoelectric follow-up and holder；
Wherein, photoelectric follow-up includes motion detection block, correlation filtering target tracking module, the inspection of deep learning target
Survey module and deep learning target tracking module；
Radar and photoelectric follow-up communication connection, radar are used to send the position signal of target to photoelectric follow-up
Communication connection；Photoelectric follow-up communication even analyzes the position signal of the target received；
Photoelectric follow-up and holder communication connection, photoelectric follow-up can be adjusted according to the target position analyzed
The position of holder.
Preferably, automatic locking tracking electro-optical system further includes countermeasure set；Countermeasure set and photoelectric follow-up communicate
Connection；Countermeasure set issues interference signal and expels target.
As shown in Fig. 2, the present invention also provides a kind of anti-unmanned plane detection tracking interference system working method, including following step
It is rapid:
S10, Utilization prospects extract the prospect that operator obtains the movement of video frame；
S20, the foreground edge that video frame is carried out using arithmetic operators are extracted；
S30, the sport foreground extracted and edge are merged, obtains the prospect and target frame of current video frame；
S40, type, size, position and the confidence for extracting target from video frame using trained convolutional neural networks
Degree；
S50, whether it is greater than the target frame data that threshold value determines locking according to confidence level；
S60, the target assessed process is manually or automatically set as lock onto target；
S70, video sequence first frame is read, extracts the characteristics of image of target, filtered target track algorithm is closed according to nuclear phase
Training obtains KCF template；
S80, read next frame image, extract current frame image in potential target region characteristics of image, with KCF template into
Row convolution obtains KCF response diagram and tracking KCF target frame；Current frame image is input in trained CNN network simultaneously and is obtained
To the CNN target frame of tracking target；
S90, the secondary lobe ratio PSR that target is calculated according to KCF response diagram；
If S100, PSR are greater than algorithm threshold value, the final target that tracks is KCF target frame；Otherwise finally tracking target be for
CNN target frame；
If S110, PSR, which are greater than first, updates threshold value, the input of CNN network is updated with KCF target frame；If PSR is less than
Two update threshold value, then update KCF template with CNN target frame, while updating the input of CNN network；Otherwise KCF target frame is used.
S120, KCF template is updated, CNN target frame updates the input of CNN network；
S130, S80~S120 is repeated, until sequence of video images terminates.
Embodiment:
Target detection model based on deep learning is as shown in Figure 3.Firstly, using selective search algorithm from present frame figure
The appropriate candidate region of extracted region as in.Then, candidate region is subjected to dimension normalization, and the convolutional layer for passing through pre-training
The target signature expression of candidate region is extracted, is full articulamentum after convolutional layer, uses whether SVM distinguishes target as classifier
It is unmanned plane, and exports position and the confidence information of unmanned plane.
Target following model based on deep learning is as shown in Figure 4.In the model, target area and mesh to be tracked are tracked
Mark region incoming convolutional neural networks simultaneously.The two convolutional neural networks have same model structure, and a parameter sharing, and two
A convolutional neural networks model is almost the same in addition to inputting.Therefore it is known as twin neural network.The output of convolutional layer is special
Sign is subsequently fed into several full articulamentums.Full articulamentum is a kind of regression model, and effect is to compare clarification of objective and current
The feature of frame returns out the shift position of target.Between frames, target may have occurred translation, rotation, illumination, block
Or deformation, therefore, full articulamentum is accomplished that a complicated regression function, by the numerous samples learnt before it,
So that it there are many factors preferable robustness, and the relative motion of target can be exported.
Specifically, the convolutional layer used is first five layer of convolutional layer and sample level of Caffe Net.By the defeated of these convolutional layers
It is a whole vector that series connection, which becomes, out, is then input to 3 full articulamentums, every layer has 4096 nodes.Finally, by last
As soon as the full articulamentum of layer is connected with the output layer comprising 4 nodes, this 4 nodes represent the rectangle frame of output, that is,
The current position of unmanned plane.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (7)
1. a kind of anti-unmanned plane detection tracking interference system, it is characterised in that: dry including radar, photoelectric follow-up, unmanned plane
Disturb device and holder；
Wherein, the photoelectric follow-up includes motion detection block, correlation filtering target tracking module, the inspection of deep learning target
Survey module and deep learning target tracking module；
Motion detection block, for moving the target detection of unmanned plane at a distance；
Correlation filtering target tracking module, for moving the target following of unmanned plane at a distance；
Deep learning module of target detection, be used in, the target detection of short distance unmanned plane；
Deep learning target tracking module, be used in, the target following of short distance unmanned plane；
The detection radar and the photoelectric follow-up communication connection；
The photoelectric follow-up and the holder communication connection；
Unmanned plane interference unit described in unmanned plane interference unit and the photoelectric follow-up communication connection.
2. anti-unmanned plane detection tracking interference system according to claim 1, it is characterised in that: the unmanned plane interference unit
Including locating channel interference unit and remote control channel disturbance device two parts.
3. anti-unmanned plane detection tracking interference system according to claim 1, it is characterised in that: motion detection block, packet
Include foreground extraction, edge extracting, prospect blending algorithm.
4. anti-unmanned plane detection tracking interference system according to claim 1, it is characterised in that: correlation filtering target following
Module, including feature extraction, template renewal, frequency domain Algorithm for Scalar Multiplication.
5. anti-unmanned plane detection tracking interference system according to claim 1, it is characterised in that: deep learning target detection
Module, including multiple convolutional layers and multiple full articulamentums, feature is extracted using convolutional network, is then come using full articulamentum
To predicted value.
6. anti-unmanned plane detection tracking interference system according to claim 1, it is characterised in that: deep learning target following
Module, including multiple convolutional layers and multiple full articulamentums extract mesh to former frame and present frame using two sets of convolutional networks respectively
The feature in region and region of search is marked, full articulamentum exports new target position for comparing target signature and region of search feature
It sets.
7. a kind of photoelectric follow-up working method, it is characterised in that: the following steps are included:
S10, Utilization prospects extract the prospect that operator obtains the movement of video frame；
S20, the foreground edge that video frame is carried out using arithmetic operators are extracted；
S30, the sport foreground extracted and edge are merged, obtains the prospect and target frame of current video frame；
S40, type, size, position and the confidence level for extracting target from video frame using trained convolutional neural networks；
S50, whether it is greater than the target frame data that threshold value determines locking according to confidence level；
S60, the target assessed process is manually or automatically set as lock onto target；
S70, video sequence first frame is read, extracts the characteristics of image of target, the training of filtered target track algorithm is closed according to nuclear phase
Obtain KCF template；
S80, next frame image is read, extracts the characteristics of image in potential target region in current frame image, is rolled up with KCF template
Product obtains KCF response diagram and tracking KCF target frame；Simultaneously current frame image is input in trained CNN network obtain with
The CNN target frame of track target；
S90, the secondary lobe ratio PSR that target is calculated according to KCF response diagram；
If S100, PSR are greater than algorithm threshold value, the final target that tracks is KCF target frame；Otherwise finally tracking target is CNN
Target frame；
If S110, PSR, which are greater than first, updates threshold value, the input of CNN network is updated with KCF target frame；If PSR is more less than second
New threshold value then updates KCF template with CNN target frame, while updating the input of CNN network；Otherwise KCF target frame is used.
S120, KCF template is updated, CNN target frame updates the input of CNN network；
S130, S80~S120 is repeated, until sequence of video images terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910773981.6A CN110398720B (en) | 2019-08-21 | Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910773981.6A CN110398720B (en) | 2019-08-21 | Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110398720A true CN110398720A (en) | 2019-11-01 |
| CN110398720B CN110398720B (en) | 2024-05-03 |
Family
ID=
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111121541A (en) * | 2019-12-27 | 2020-05-08 | 江苏中戎帝晓曼安防科技有限公司 | Anti-unmanned aerial vehicle radar system with radio interference function |
| CN111145217A (en) * | 2019-12-27 | 2020-05-12 | 湖南华诺星空电子技术有限公司 | KCF-based unmanned aerial vehicle tracking method |
| CN111323756A (en) * | 2019-12-30 | 2020-06-23 | 北京海兰信数据科技股份有限公司 | Deep learning-based marine radar target detection method and device |
| CN111323757A (en) * | 2019-12-30 | 2020-06-23 | 北京海兰信数据科技股份有限公司 | Target detection method and device for marine radar |
| CN111369589A (en) * | 2020-02-26 | 2020-07-03 | 桂林电子科技大学 | Unmanned aerial vehicle tracking method based on multi-strategy fusion |
| CN111679257A (en) * | 2019-12-30 | 2020-09-18 | 中国船舶集团有限公司 | Light and small unmanned aerial vehicle target identification method and device based on radar detection data |
| CN111932588A (en) * | 2020-08-07 | 2020-11-13 | 浙江大学 | Tracking method of airborne unmanned aerial vehicle multi-target tracking system based on deep learning |
| CN112485781A (en) * | 2020-11-18 | 2021-03-12 | 济南和普威视光电技术有限公司 | Anti-unmanned aerial vehicle unattended system and method based on deep learning |
| CN112731918A (en) * | 2020-11-30 | 2021-04-30 | 北京理工大学 | Ground unmanned platform autonomous following system based on deep learning detection tracking |
| CN112945015A (en) * | 2019-12-11 | 2021-06-11 | 杭州海康机器人技术有限公司 | Unmanned aerial vehicle monitoring system, method, device and storage medium |
| CN115355764A (en) * | 2022-09-02 | 2022-11-18 | 中交遥感载荷(江苏)科技有限公司 | Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets |
| CN115562330A (en) * | 2022-11-04 | 2023-01-03 | 哈尔滨工业大学 | Unmanned aerial vehicle control method for restraining wind disturbance of similar field |
| WO2024051574A1 (en) * | 2022-09-06 | 2024-03-14 | 亿航智能设备（广州）有限公司 | Target tracking method and system for unmanned aerial vehicle, unmanned aerial vehicle gimbal, and unmanned aerial vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190034734A1 (en) * | 2017-07-28 | 2019-01-31 | Qualcomm Incorporated | Object classification using machine learning and object tracking |
| CN109459750A (en) * | 2018-10-19 | 2019-03-12 | 吉林大学 | A kind of more wireless vehicle trackings in front that millimetre-wave radar is merged with deep learning vision |
| CN109859202A (en) * | 2019-02-18 | 2019-06-07 | 哈尔滨工程大学 | A kind of deep learning detection method based on the tracking of USV water surface optical target |
| CN210487967U (en) * | 2019-08-21 | 2020-05-08 | 深圳耐杰电子技术有限公司 | Anti-unmanned aerial vehicle detection tracking interference system |
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190034734A1 (en) * | 2017-07-28 | 2019-01-31 | Qualcomm Incorporated | Object classification using machine learning and object tracking |
| CN109459750A (en) * | 2018-10-19 | 2019-03-12 | 吉林大学 | A kind of more wireless vehicle trackings in front that millimetre-wave radar is merged with deep learning vision |
| CN109859202A (en) * | 2019-02-18 | 2019-06-07 | 哈尔滨工程大学 | A kind of deep learning detection method based on the tracking of USV water surface optical target |
| CN210487967U (en) * | 2019-08-21 | 2020-05-08 | 深圳耐杰电子技术有限公司 | Anti-unmanned aerial vehicle detection tracking interference system |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112945015A (en) * | 2019-12-11 | 2021-06-11 | 杭州海康机器人技术有限公司 | Unmanned aerial vehicle monitoring system, method, device and storage medium |
| CN112945015B (en) * | 2019-12-11 | 2023-08-22 | 杭州海康威视数字技术股份有限公司 | Unmanned aerial vehicle monitoring system, unmanned aerial vehicle monitoring method, unmanned aerial vehicle monitoring device and storage medium |
| CN111145217A (en) * | 2019-12-27 | 2020-05-12 | 湖南华诺星空电子技术有限公司 | KCF-based unmanned aerial vehicle tracking method |
| CN111121541A (en) * | 2019-12-27 | 2020-05-08 | 江苏中戎帝晓曼安防科技有限公司 | Anti-unmanned aerial vehicle radar system with radio interference function |
| CN111323757B (en) * | 2019-12-30 | 2022-04-05 | 北京海兰信数据科技股份有限公司 | Target detection method and device for marine radar |
| CN111679257B (en) * | 2019-12-30 | 2023-05-23 | 中国船舶集团有限公司 | Target recognition method and device for light unmanned aerial vehicle based on radar detection data |
| CN111323756A (en) * | 2019-12-30 | 2020-06-23 | 北京海兰信数据科技股份有限公司 | Deep learning-based marine radar target detection method and device |
| CN111323757A (en) * | 2019-12-30 | 2020-06-23 | 北京海兰信数据科技股份有限公司 | Target detection method and device for marine radar |
| CN111323756B (en) * | 2019-12-30 | 2022-05-13 | 北京海兰信数据科技股份有限公司 | Marine radar target detection method and device based on deep learning |
| CN111679257A (en) * | 2019-12-30 | 2020-09-18 | 中国船舶集团有限公司 | Light and small unmanned aerial vehicle target identification method and device based on radar detection data |
| CN111369589A (en) * | 2020-02-26 | 2020-07-03 | 桂林电子科技大学 | Unmanned aerial vehicle tracking method based on multi-strategy fusion |
| CN111369589B (en) * | 2020-02-26 | 2022-04-22 | 桂林电子科技大学 | Unmanned aerial vehicle tracking method based on multi-strategy fusion |
| CN111932588A (en) * | 2020-08-07 | 2020-11-13 | 浙江大学 | Tracking method of airborne unmanned aerial vehicle multi-target tracking system based on deep learning |
| CN111932588B (en) * | 2020-08-07 | 2024-01-30 | 浙江大学 | Tracking method of airborne unmanned aerial vehicle multi-target tracking system based on deep learning |
| CN112485781B (en) * | 2020-11-18 | 2022-10-28 | 济南和普威视光电技术有限公司 | Anti-unmanned aerial vehicle unmanned system and method based on deep learning |
| CN112485781A (en) * | 2020-11-18 | 2021-03-12 | 济南和普威视光电技术有限公司 | Anti-unmanned aerial vehicle unattended system and method based on deep learning |
| CN112731918A (en) * | 2020-11-30 | 2021-04-30 | 北京理工大学 | Ground unmanned platform autonomous following system based on deep learning detection tracking |
| CN115355764A (en) * | 2022-09-02 | 2022-11-18 | 中交遥感载荷(江苏)科技有限公司 | Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets |
| WO2024051574A1 (en) * | 2022-09-06 | 2024-03-14 | 亿航智能设备（广州）有限公司 | Target tracking method and system for unmanned aerial vehicle, unmanned aerial vehicle gimbal, and unmanned aerial vehicle |
| CN115562330A (en) * | 2022-11-04 | 2023-01-03 | 哈尔滨工业大学 | Unmanned aerial vehicle control method for restraining wind disturbance of similar field |
| CN115562330B (en) * | 2022-11-04 | 2023-08-22 | 哈尔滨工业大学 | Unmanned aerial vehicle control method for inhibiting wind disturbance of quasi-field |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10719940B2 (en) | Target tracking method and device oriented to airborne-based monitoring scenarios | |
| CN109800689B (en) | Target tracking method based on space-time feature fusion learning | |
| Craye et al. | Spatio-temporal semantic segmentation for drone detection | |
| CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
| US20180247126A1 (en) | Method and system for detecting and segmenting primary video objects with neighborhood reversibility | |
| CN104050471A (en) | Natural scene character detection method and system | |
| CN109063559A (en) | A kind of pedestrian detection method returned based on improvement region | |
| CN105654508B (en) | Monitor video method for tracking moving target and system based on adaptive background segmentation | |
| CN110633632A (en) | Weak supervision combined target detection and semantic segmentation method based on loop guidance | |
| CN108038415B (en) | Unmanned aerial vehicle automatic detection and tracking method based on machine vision | |
| CN111161309B (en) | Searching and positioning method for vehicle-mounted video dynamic target | |
| CN102034247A (en) | Motion capture method for binocular vision image based on background modeling | |
| CN105740835A (en) | Preceding vehicle detection method based on vehicle-mounted camera under night-vision environment | |
| CN103577832B (en) | A kind of based on the contextual people flow rate statistical method of space-time | |
| CN113763427A (en) | Multi-target tracking method based on coarse-fine shielding processing | |
| CN103198491A (en) | Indoor visual positioning method | |
| Xu et al. | Convolutional neural network based traffic sign recognition system | |
| Elihos et al. | Deep learning based segmentation free license plate recognition using roadway surveillance camera images | |
| CN115035159A (en) | Video multi-target tracking method based on deep learning and time sequence feature enhancement | |
| CN104182976A (en) | Field moving object fining extraction method | |
| CN103996207A (en) | Object tracking method | |
| Chen et al. | Single-object tracking algorithm based on two-step spatiotemporal deep feature fusion in a complex surveillance scenario | |
| CN103778644A (en) | Infrared motion object detection method based on multi-scale codebook model | |
| CN111814760B (en) | Face recognition method and system | |
| Deepan et al. | Road recognition from remote sensing imagery using machine learning |
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 |