CN110398720B - Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system - Google Patents
Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system Download PDFInfo
- Publication number
- CN110398720B CN110398720B CN201910773981.6A CN201910773981A CN110398720B CN 110398720 B CN110398720 B CN 110398720B CN 201910773981 A CN201910773981 A CN 201910773981A CN 110398720 B CN110398720 B CN 110398720B
- Authority
- CN
- China
- Prior art keywords
- target
- tracking
- aerial vehicle
- unmanned aerial
- frame
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000013135 deep learning Methods 0.000 claims abstract description 30
- 238000004891 communication Methods 0.000 claims abstract description 15
- 238000001914 filtration Methods 0.000 claims abstract description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 2
- 239000000523 sample Substances 0.000 claims 4
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000033748 Device issues Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000006467 substitution reaction 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
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an anti-unmanned aerial vehicle detection tracking interference system and a working method of a photoelectric tracking system, wherein the anti-unmanned aerial vehicle detection tracking interference system comprises a radar, the photoelectric tracking system, an unmanned aerial vehicle interference device and a cradle head; the photoelectric tracking system comprises a motion detection module, a related filtering target tracking module, a deep learning target detection module and a deep learning target tracking module; the radar is in communication connection with the photoelectric tracking system; and the photoelectric tracking system is in communication connection with the cradle head. According to the anti-unmanned aerial vehicle detection tracking interference system, when the target distance is far, the deep learning target detection module cannot extract the target characteristics, and the target detection is carried out by the motion detection module; when the target distance is far, the deep learning target tracking module is used for tracking the target under the condition that the target characteristics cannot be extracted by the deep learning target tracking module; the data of the relevant filtering target tracking module is adopted to solve the problem that the deep learning target tracking module cannot provide confidence.
Description
Technical Field
The invention relates to the technical field of anti-unmanned aerial vehicle tracking, in particular to an anti-unmanned aerial vehicle detection tracking interference system and a working method of a photoelectric tracking system.
Background
In the anti-unmanned aerial vehicle system, a radar is responsible for searching and finding a target, a photoelectric system controls a tripod head lens according to target angle and distance data provided by the radar to complete detection, locking and tracking tasks of the target, and then interference equipment is controlled to transmit interference signals to the periphery of the target unmanned aerial vehicle until the unmanned aerial vehicle is driven off. The traditional anti-unmanned aerial vehicle system comprises radar, a photoelectric tracking device, a cradle head, satellite navigation and interference equipment of remote control signals. The radar is responsible for finding an unmanned aerial vehicle target and sending target angle and distance data to the photoelectric tracking device; the photoelectric tracking device mainly comprises two parts of target detection and target tracking, wherein the target detection module controls the holder to point the lens to a target area according to target angle data provided by a radar, then focuses and images the target area according to distance data, then carries out target detection according to target characteristics of the unmanned aerial vehicle, automatically or manually locks the target after the target is found, and transmits information of the locked target to the target tracking module; the tracking module of the photoelectric tracking device performs feature extraction on the surrounding area of the original position of the target in the previous frame, finds the position with the highest matching degree with the target feature and serves as a new position of the target, adjusts the new position of the holder and the lens, and automatically or manually controls the linked interference device to emit satellite navigation and remote control interference signals to the target area until the unmanned aerial vehicle is driven off. At present, a photoelectric system adopting a traditional target detection and target tracking algorithm is easy to lose a target under the conditions of hovering, shielding and deformation of an unmanned aerial vehicle; target detection tracking algorithm based on deep learning technology
The method has good detection and tracking capability on complete targets in a simple scene, has strong robustness on scale change, deformation and the like, can solve the problems of hovering, shielding and deformation of an unmanned aerial vehicle, and has the advantages that the detection and tracking effect is to be improved under the conditions of long distance, small target and unobvious target characteristics. Therefore, the photoelectric tracking system of the novel anti-unmanned aerial vehicle capable of automatically detecting, locking and tracking is designed by combining the respective advantages of the traditional target detection tracking algorithm and the deep learning target detection tracking algorithm.
Disclosure of Invention
In order to solve the problems in the background art, the invention provides an anti-unmanned aerial vehicle detection tracking interference system, which comprises a radar, a photoelectric tracking system, an unmanned aerial vehicle interference device and a cradle head;
The photoelectric tracking system comprises a motion detection module, a related filtering target tracking module, a deep learning target detection module and a deep learning target tracking module;
The motion detection module is used for detecting targets of the unmanned aerial vehicle in long-distance motion;
the related filtering target tracking module is used for tracking the target of the remote unmanned aerial vehicle;
the deep learning target detection module is used for target detection of the middle-distance unmanned aerial vehicle and the short-distance unmanned aerial vehicle;
The deep learning target tracking module is used for target tracking of the middle-distance unmanned aerial vehicle and the short-distance unmanned aerial vehicle;
the detection radar is in communication connection with the photoelectric tracking system;
The photoelectric tracking system is in communication connection with the cradle head;
Unmanned aerial vehicle interference ware with photoelectric tracking system communication connection.
Further, the unmanned aerial vehicle jammer comprises a positioning channel jammer and a remote control channel jammer.
Further, the motion detection module comprises algorithms such as foreground extraction, edge extraction, foreground fusion and the like.
Further, the relevant filtering target tracking module comprises algorithms such as feature extraction, template updating, frequency domain dot multiplication and the like.
Further, the deep learning object detection module comprises a plurality of convolution layers and a plurality of full connection layers, adopts a convolution network to extract characteristics, and then uses the full connection layers to obtain predicted values.
Further, the deep learning target tracking module comprises a plurality of convolution layers and a plurality of full connection layers, wherein the two sets of convolution networks are adopted to extract the characteristics of a target area and a search area for a previous frame and a current frame respectively, and the full connection layers are used for comparing the characteristics of the target and the characteristics of the search area and outputting a new target position.
The invention also provides a working method of the anti-unmanned aerial vehicle detection tracking interference system, which comprises the following steps:
s10, obtaining a motion foreground of a video frame by utilizing a foreground extraction operator;
S20, extracting the foreground edge of the video frame by using an edge extraction operator;
S30, fusing the extracted motion foreground and the edges to obtain a foreground and a target frame of the current video frame;
s40, extracting the type, the size, the position and the confidence coefficient of the target from the video frame by using the trained convolutional neural network;
S50, determining locked target frame data according to whether the confidence coefficient is larger than a threshold value;
S60, manually or automatically setting the evaluated target as a locking target;
S70, reading a first frame of the video sequence, extracting image features of a target, and training according to a kernel-related filtering target tracking algorithm to obtain a KCF template;
S80, reading a next frame of image, extracting image features of a potential target area in a current frame of image, and convolving with a KCF template to obtain a KCF response chart and tracking a KCF target frame; simultaneously inputting the current frame image into a trained CNN network to obtain a CNN target frame of a tracking target;
s90, calculating a sidelobe ratio PSR of the target according to the KCF response chart;
s100, if the PSR is larger than an algorithm threshold, the final tracking target is a KCF target frame; otherwise, the final tracking target is a CNN target frame;
s110, if the PSR is larger than a first updating threshold value, updating the input of the CNN network by using a KCF target frame; if the PSR is smaller than the second updating threshold value, updating the KCF template by using the CNN target frame, and updating the input of the CNN network; otherwise, adopting a KCF target frame.
S120, updating a KCF template, and updating the input of a CNN network by a CNN target frame;
S130, repeating S80-S120 until the video image sequence is ended.
Compared with the structure of the traditional anti-unmanned aerial vehicle system, the invention has the following characteristics:
1. the method has the advantages that the method combines deep learning and motion detection to realize target detection, and targets can be found in a target hovering state;
2. The method has the advantages that the target tracking is realized by combining deep learning with kernel-related filtering, and the target is not lost under the conditions of target shielding and deformation;
3. An automatic target locking function is added on the basis of original manual locking, and unattended operation is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of an anti-unmanned aerial vehicle detection tracking interference system provided by the invention;
FIG. 2 is a schematic diagram of a tracking flow of an optoelectronic system;
FIG. 3 is an analytical schematic of an embodiment;
Fig. 4 is an analytical schematic of an example.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, merely to facilitate description of the present invention and simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The invention provides an anti-unmanned aerial vehicle detection tracking interference system, which comprises a radar, a photoelectric tracking system and a cradle head;
The photoelectric tracking system comprises a motion detection module, a related filtering target tracking module, a deep learning target detection module and a deep learning target tracking module;
The motion detection module is used for detecting targets of the unmanned aerial vehicle in long-distance motion;
the related filtering target tracking module is used for tracking the target of the remote unmanned aerial vehicle;
the deep learning target detection module is used for target detection of the middle-distance unmanned aerial vehicle and the short-distance unmanned aerial vehicle;
The deep learning target tracking module is used for target tracking of the middle-distance unmanned aerial vehicle and the short-distance unmanned aerial vehicle;
the radar is in communication connection with the photoelectric tracking system;
and the photoelectric tracking system is in communication connection with the cradle head.
In specific implementation, as shown in fig. 1, the automatic locking tracking photoelectric system comprises a radar, a photoelectric tracking system and a cradle head;
The photoelectric tracking system comprises a motion detection module, a related filtering target tracking module, a deep learning target detection module and a deep learning target tracking module;
the radar is in communication connection with the photoelectric tracking system and is used for transmitting a position signal of a target to the photoelectric tracking system for communication connection; the photoelectric tracking system is in communication connection with the received position signal of the target for analysis;
The photoelectric tracking system is in communication connection with the cradle head, and can adjust the position of the cradle head according to the analyzed target position.
Preferably, the automatic locking tracking photoelectric system further comprises an interference device; the interference device is in communication connection with the photoelectric tracking system; the interfering device issues an interfering signal to expel the target.
As shown in fig. 2, the invention further provides a working method of the anti-unmanned aerial vehicle detection tracking interference system, which comprises the following steps:
s10, obtaining a motion foreground of a video frame by utilizing a foreground extraction operator;
S20, extracting the foreground edge of the video frame by using an edge extraction operator;
S30, fusing the extracted motion foreground and the edges to obtain a foreground and a target frame of the current video frame;
s40, extracting the type, the size, the position and the confidence coefficient of the target from the video frame by using the trained convolutional neural network;
S50, determining locked target frame data according to whether the confidence coefficient is larger than a threshold value;
S60, manually or automatically setting the evaluated target as a locking target;
S70, reading a first frame of the video sequence, extracting image features of a target, and training according to a kernel-related filtering target tracking algorithm to obtain a KCF template;
S80, reading a next frame of image, extracting image features of a potential target area in a current frame of image, and convolving with a KCF template to obtain a KCF response chart and tracking a KCF target frame; simultaneously inputting the current frame image into a trained CNN network to obtain a CNN target frame of a tracking target;
s90, calculating a sidelobe ratio PSR of the target according to the KCF response chart;
s100, if the PSR is larger than an algorithm threshold, the final tracking target is a KCF target frame; otherwise, the final tracking target is a CNN target frame;
s110, if the PSR is larger than a first updating threshold value, updating the input of the CNN network by using a KCF target frame; if the PSR is smaller than the second updating threshold value, updating the KCF template by using the CNN target frame, and updating the input of the CNN network; otherwise, adopting a KCF target frame.
S120, updating a KCF template, and updating the input of a CNN network by a CNN target frame;
S130, repeating S80-S120 until the video image sequence is ended.
Examples:
The deep learning-based object detection model is shown in fig. 3. First, an appropriate amount of candidate regions are extracted from regions in the current frame image using a selective search algorithm. And then, carrying out scale normalization on the candidate region, extracting target feature expression of the candidate region through a pre-trained convolution layer, wherein the convolution layer is followed by a full connection layer, using an SVM (support vector machine) as a classifier to distinguish whether the target is the unmanned aerial vehicle or not, and outputting position and confidence information of the unmanned aerial vehicle.
The deep learning based object tracking model is shown in fig. 4. In the model, the target area to be tracked and the target area to be tracked are simultaneously transmitted into a convolutional neural network. The two convolutional neural networks have the same model structure and share parameters, and the two convolutional neural network models are almost identical except for input. And thus becomes a twin neural network. The output characteristics of the convolutional layers are then fed into several fully-connected layers. The full connection layer is a regression model, which is used for comparing the characteristics of the target with the characteristics of the current frame and regressing the moving position of the target. The target may be translated, rotated, illuminated, blocked or deformed from frame to frame, so that the fully connected layer implements a complex regression function, which is robust to various factors and capable of outputting the relative motion of the target by virtue of the numerous samples that have been learned before.
Specifically, the convolution layers used are the first five convolution layers of Caffe Net and the sampling layer. The outputs of these convolutional layers are concatenated into one overall vector and then input to 3 fully connected layers, each layer having 4096 nodes. Finally, the last full connection layer is connected to an output layer comprising 4 nodes, which represent the rectangular frame of the output, i.e. the current position of the drone.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. An anti-unmanned aerial vehicle detects and tracks interference system which characterized in that: the system comprises a radar, a photoelectric tracking system, an unmanned aerial vehicle interference device and a cradle head;
The photoelectric tracking system comprises a motion detection module, a related filtering target tracking module, a deep learning target detection module and a deep learning target tracking module;
The motion detection module is used for detecting targets of the unmanned aerial vehicle in long-distance motion;
the related filtering target tracking module is used for tracking the target of the remote unmanned aerial vehicle;
the deep learning target detection module is used for target detection of the middle-distance unmanned aerial vehicle and the short-distance unmanned aerial vehicle;
The deep learning target tracking module is used for target tracking of the middle-distance unmanned aerial vehicle and the short-distance unmanned aerial vehicle;
the radar is in communication connection with the photoelectric tracking system;
The photoelectric tracking system is in communication connection with the cradle head;
The unmanned aerial vehicle interference device is in communication connection with the photoelectric tracking system;
The unmanned aerial vehicle jammer comprises a positioning channel jammer and a remote control channel jammer.
2. The anti-drone probe tracking jamming system of claim 1, wherein: the motion detection module comprises a foreground extraction algorithm, an edge extraction algorithm and a foreground fusion algorithm.
3. The anti-drone probe tracking jamming system of claim 1, wherein: the related filtering target tracking module comprises a feature extraction, a template updating and a frequency domain point multiplication algorithm.
4. The anti-drone probe tracking jamming system of claim 1, wherein: the deep learning target detection module comprises a plurality of convolution layers and a plurality of full connection layers, adopts a convolution network to extract characteristics, and then uses the full connection layers to obtain predicted values.
5. The anti-drone probe tracking jamming system of claim 1, wherein: the deep learning target tracking module comprises a plurality of convolution layers and a plurality of full connection layers, wherein the two sets of convolution networks are adopted to extract characteristics of a target area and a search area for a previous frame and a current frame respectively, and the full connection layers are used for comparing the characteristics of the target and the characteristics of the search area and outputting a new target position.
6. The working method of the photoelectric tracking system is characterized by comprising the following steps of: the method comprises the following steps:
s10, obtaining a motion foreground of a video frame by utilizing a foreground extraction operator;
S20, extracting the foreground edge of the video frame by using an edge extraction operator;
S30, fusing the extracted motion foreground and the edges to obtain a foreground and a target frame of the current video frame;
s40, extracting the type, the size, the position and the confidence coefficient of the target from the video frame by using the trained convolutional neural network;
S50, determining locked target frame data according to whether the confidence coefficient is larger than a threshold value;
S60, manually or automatically setting the evaluated target as a locking target;
S70, reading a first frame of the video sequence, extracting image features of a target, and training according to a kernel-related filtering target tracking algorithm to obtain a KCF template;
S80, reading a next frame of image, extracting image features of a potential target area in a current frame of image, and convolving with a KCF template to obtain a KCF response chart and tracking a KCF target frame; simultaneously inputting the current frame image into a trained CNN network to obtain a CNN target frame of a tracking target;
s90, calculating a sidelobe ratio PSR of the target according to the KCF response chart;
s100, if the PSR is larger than an algorithm threshold, the final tracking target is a KCF target frame; otherwise, the final tracking target is a CNN target frame;
S110, if the PSR is larger than a first updating threshold value, updating the input of the CNN network by using a KCF target frame; if the PSR is smaller than the second updating threshold value, updating the KCF template by using the CNN target frame, and updating the input of the CNN network; otherwise, adopting a KCF target frame;
S120, updating a KCF template, and updating the input of a CNN network by a CNN target frame;
S130, repeating S80-S120 until the video image sequence is ended.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910773981.6A CN110398720B (en) | 2019-08-21 | 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 | 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 CN110398720A (en) | 2019-11-01 |
CN110398720B true CN110398720B (en) | 2024-05-03 |
Family
ID=68328884
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910773981.6A Active CN110398720B (en) | 2019-08-21 | 2019-08-21 | Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110398720B (en) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
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 |
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 |
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 |
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 |
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 |
CN112731918B (en) * | 2020-11-30 | 2022-02-11 | 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 |
CN115526906A (en) * | 2022-09-06 | 2022-12-27 | 亿航智能设备(广州)有限公司 | Unmanned aerial vehicle target tracking method and system, unmanned aerial vehicle holder and unmanned aerial vehicle |
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 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Family Cites Families (1)
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 |
-
2019
- 2019-08-21 CN CN201910773981.6A patent/CN110398720B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Also Published As
Publication number | Publication date |
---|---|
CN110398720A (en) | 2019-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110398720B (en) | Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system | |
CN109579843B (en) | Multi-robot cooperative positioning and fusion image building method under air-ground multi-view angles | |
CN107886048B (en) | Target tracking method and system, storage medium and electronic terminal | |
Levinson et al. | Traffic light mapping, localization, and state detection for autonomous vehicles | |
US10013765B2 (en) | Method and system for image registrations | |
US10671068B1 (en) | Shared sensor data across sensor processing pipelines | |
US9760791B2 (en) | Method and system for object tracking | |
US11694436B2 (en) | Vehicle re-identification method, apparatus, device and storage medium | |
US20170102699A1 (en) | Drone control through imagery | |
CN108038415B (en) | Unmanned aerial vehicle automatic detection and tracking method based on machine vision | |
US20220309767A1 (en) | Object tracking in local and global maps systems and methods | |
CN108664930A (en) | A kind of intelligent multi-target detection tracking | |
CN111602139A (en) | Image processing method and device, control terminal and mobile device | |
CN111784737B (en) | Automatic target tracking method and system based on unmanned aerial vehicle platform | |
CN111652067B (en) | Unmanned aerial vehicle identification method based on image detection | |
CN210487967U (en) | Anti-unmanned aerial vehicle detection tracking interference system | |
CN112927264B (en) | Unmanned aerial vehicle tracking shooting system and RGBD tracking method thereof | |
CN112529962A (en) | Indoor space key positioning technical method based on visual algorithm | |
CN113052870A (en) | Target tracking method, target detection method and device | |
CN109324638A (en) | Quadrotor drone Target Tracking System based on machine vision | |
CN112381858B (en) | Target detection method, device, storage medium and equipment | |
US20230028196A1 (en) | User-in-the-loop object detection and classification systems and methods | |
JP2022537557A (en) | Method and apparatus for determining drivable area information | |
CN113139985B (en) | Tracking target framing method for eliminating communication delay influence of unmanned aerial vehicle and ground station | |
CN111538009A (en) | Radar point marking method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |