CN110244314A - One kind " low slow small " target acquisition identifying system and method - Google Patents
One kind " low slow small " target acquisition identifying system and method Download PDFInfo
- Publication number
- CN110244314A CN110244314A CN201910548691.1A CN201910548691A CN110244314A CN 110244314 A CN110244314 A CN 110244314A CN 201910548691 A CN201910548691 A CN 201910548691A CN 110244314 A CN110244314 A CN 110244314A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- image
- suspicious object
- sensor
- 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
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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/42—Simultaneous measurement of distance and other co-ordinates
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/50—Systems of measurement based on relative movement of target
- G01S17/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/66—Tracking systems using electromagnetic waves other than radio waves
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The present invention relates to a kind of " low slow small " target acquisition identifying system and methods, belong to target acquisition technical field, solve the problems, such as the detection identification of " low slow small " unmanned plane target.Panorama stares unit in system, detects for full view target alert;Target information sension unit is used to perceive the range information, visible light image information and Infrared Image Information of suspicious object;Image synthesis treatment box is used to search for target area according to the early warning detection information, calculate azimuth and the pitch angle information of suspicious object;Suspicious object in the target information sension unit alignment prewarning area is controlled, target information perception is carried out;And sensing results information based on the received, carry out suspicious object feature information extraction and comprehensive identification, determine suspicious object type.The present invention can be under the complex environment of city in 360 ° × 30 ° range covering airspaces, and " low slow small " unmanned plane target no more than 2km, the span not less than 0.6m × 0.6m of adjusting the distance implements alarm.
Description
Technical field
The present invention relates in target acquisition technical field, especially a kind of " low slow small " target acquisition identifying system and side
Method.
Background technique
The radar scattering area of " low slow small " unmanned plane target is small, flying height is low, speed is slow, Doppler frequency shift is unknown
Aobvious, the complexity of usage scenario, environmental disturbances are more in addition, so that the detection and identification of " low slow small " unmanned plane target become a generation
Criticality problem.Photoelectricity means currently used for the detection identification of " low slow small " unmanned plane target mainly have laser ranging, visible light at
The Detection Techniques such as picture or array type camera imaging, infrared imaging.These detection means characteristics are different, detective distance, sensitivity,
Tracking ability etc. has his own strong points simultaneously for efficiency range, anti-harsh weather ability, multiple target, but still difficult effectively solution city
" low slow small " unmanned plane target detects identification problem under complex environment.
Summary of the invention
In view of above-mentioned analysis, the present invention is intended to provide a kind of " low slow small " target acquisition identifying system and method, solve
The detection of " low slow small " unmanned plane target under the complex environment of city identifies problem.
The purpose of the present invention is mainly achieved through the following technical solutions:
A kind of " low slow small " target acquisition identifying system, including panorama stare unit (1), target information sension unit (2)
With image synthesis treatment box (3);
The panorama stares unit (1), for carrying out the detection of full view target alert to detection mission region;And by early warning
Detection information is sent to image synthesis treatment box (3);
The target information sension unit (2), for perceiving the range information of suspicious object, visible light image information and red
Outer image information;And image synthesis treatment box (3) are sent by sensing results information;
Described image integrated treatment case (3) calculates suspicious for searching for suspicious object according to the early warning detection information
The azimuth of target and pitch angle information;The target information sension unit is controlled according to the azimuth and pitch angle information
(2) it is directed at suspicious object in prewarning area, carries out target information perception;And sensing results information, progress are suspicious based on the received
Clarification of objective information extraction and comprehensive identification, determine suspicious object type.
Further, it includes multiple early warning subelements that the panorama, which stares unit (1), and each early warning subelement is corresponding
One early warning subregion, multiple early warning subregions form one 360 ° of full view prewarning area by splicing;
The early warning subelement uses the high frame frequency visible light probe assembly of high-resolution, carries out the spy of early warning image information
It surveys.
Further, the target information sension unit (2) includes laser range sensor (201), visible images biography
Sensor (202), infrared image sensor (203) and ray machine platform (204);
The laser range sensor (201) for carrying out laser ranging to the suspicious object by laser, and will survey
The target range information of amount is sent to image synthesis treatment box (3);
The visible light image sensor (202) for carrying out visual light imaging to the suspicious object, and will be seen that light
Image information is sent to image synthesis treatment box (3);
The infrared image sensor (203), for carrying out infrared imaging to target in early warning area of space, and will be red
Outer image information is sent to image synthesis treatment box (3);
The ray machine platform (204), for carrying the laser range sensor (201), visible light image sensor
(202) and infrared image sensor (203);The photodetection instruction that described image integrated treatment case (3) is sent based on the received,
Drive the laser range sensor (201), visible light image sensor (202) and infrared image sensor (203) alignment mesh
Mark region.
Further, described image integrated treatment case (3) includes early warning image processing unit (301), cradle head control unit
(302), comprehensive recognition unit (304) and target information output unit (305);
The early warning image processing unit (301) carries out figure for staring unit (1) upload early warning detection information to panorama
As processing, suspicious object is searched for, determines azimuth and the pitch angle information of suspicious object;
The cradle head control unit (302), for according to suspicious object azimuth and pitch angle information, generate photoelectricity visit
Instruction is surveyed, ray machine platform (204) are sent to, laser range sensor (201), the visible light figure for carrying ray machine platform (204)
As suspicious object direction is directed toward in sensor (202) and infrared image sensor (203);
Comprehensive recognition unit (303), the suspicious object distance letter for being perceived from the target information sension unit (2)
Breath, visible light image information
Or suspicious object characteristic information is extracted in Infrared Image Information, and comprehensive knowledge is carried out according to suspicious object characteristic information
Not, target type is determined.
Further, described image integrated treatment case (3) further includes perception control unit (304), for according to suspicious mesh
Target distance, controls the visible light image sensor (202) and infrared image sensor (203) carries out Image Acquisition;
When the distance of suspicious object is within the scope of the first pre-determined distance, unlatching visible light image sensor (202), progress can
Light-exposed Image Acquisition;When target range information is within the scope of the second pre-determined distance, while opening visible light sensor (202) and red
Outer imaging sensor (203), while carrying out visible images and infrared image acquisition.
A kind of target acquisition recognition methods using above-mentioned target acquisition identifying system, which is characterized in that including following step
It is rapid:
Step S1, system is powered on, and panorama stares the real-time acquisition that unit (1) carries out panoramic picture to detection mission region;
Image synthesis treatment box (3) handles the image of the acquisition, and search whether there is suspicious object;
Step S2, after searching suspicious object, image synthesis treatment box (3) calculates azimuth and the pitching of suspicious object
Angle information, and be converted into photodetection command signal and be output to ray machine platform (204), it transfers ray machine platform (204) and drives laser
Distance measuring sensor (201), visible light image sensor (202) and infrared image sensor (203) are directed toward suspicious object direction;
Step S3, the described laser range sensor (201), visible light image sensor (202) and infrared image sensor
(202) to that can detect with target, the range information, visible light image information and Infrared Image Information of suspicious object are perceived;
Step S4, it is extracted according in the suspicious object range information of perception, visible light image information or Infrared Image Information
Suspicious object characteristic information, and comprehensive identification is carried out according to suspicious object characteristic information, determine target type.
Further, in the step S1, image synthesis treatment box (3) using frame difference method to the image of acquisition at
Reason, is confirmed whether that there are suspicious objects.
Further, include in step S3,
Laser range sensor (201) carries out laser ranging to target and obtains the range information of suspicious object, is sent to figure
As integrated treatment case (3);
Described image integrated treatment case (3) judges the range information, when target range information is default first
It in distance range, opens visible light image sensor (202), carries out visible images acquisition;When target range information is second
Within the scope of pre-determined distance, while visible light sensor (202) and infrared image sensor (203) are opened, carries out visible images
And infrared image acquisition.
Further, in the step S4, the suspicious object characteristic information includes objective contour information, by suspicious
The visible images or infrared image of target carry out median filtering, binaryzation, edge detection and morphological image process and obtain institute
State objective contour information.
Further, in the step S4, comprehensive knowledge is carried out using support vector machines (SVM) method learnt based on either shallow
Not, target type is obtained.
The present invention has the beneficial effect that:
" low slow small " target acquisition identifying system and method provided by the invention, be stared by panorama unit to 360 ° ×
Implement in 30 ° of range covering airspaces, apart from " low slow small " unmanned plane target no more than 2km, the span not less than 0.6m × 0.6m
Alarm obtains the information such as azimuth of target, pitch angle, and can export the panoramic mosaic image in detection mission region in real time for showing
Show detection mission region situation;Alarm target is accurately detected by photoelectric tracking unit, identification obtains the shape of target
The features such as state, distance, speed and track, line trace of going forward side by side monitoring.
Detailed description of the invention
Attached drawing is only used for showing the purpose of specific embodiment, and is not to be construed as limiting the invention, in entire attached drawing
In, identical reference symbol indicates identical component.
Fig. 1 is that " low slow small " target acquisition identifying system in present example forms connection schematic diagram;
Fig. 2 is that the panorama in present example stares unit schematic illustration;
Fig. 3 is the photoelectric turntable schematic diagram in present example
Fig. 4 is the target acquisition recognition methods flow chart in present example.
Specific embodiment
Specifically describing the preferred embodiment of the present invention with reference to the accompanying drawing, wherein attached drawing constitutes the application a part, and
Together with embodiments of the present invention for illustrating the principle of the present invention.
Present embodiment discloses a kind of " low slow small " target acquisition identifying systems, by will be seen that light/infrared/laser " three
Photosynthetic one " detects " low slow small " unmanned plane target under the complex environment of city, is identified, realizes in prevention and control mission area
The early warning and monitoring of " low slow small " unmanned plane target.
As shown in Figure 1, " low slow small " target acquisition identifying system of the present embodiment includes that panorama stares unit (1), target
Information Perception unit (2) and image synthesis treatment box (3);
The panorama stares unit (1), for carrying out the detection of full view target alert to detection mission region;And by early warning
Detection information is sent to image synthesis treatment box (3);
The target information sension unit (2), for perceiving the range information of suspicious object, visible light image information and red
Outer image information;And image synthesis treatment box (3) are sent by sensing results information;
Described image integrated treatment case (3) calculates suspicious for searching for suspicious object according to the early warning detection information
The azimuth of target and pitch angle information;The target information sension unit is controlled according to the azimuth and pitch angle information
(2) it is directed at suspicious object in prewarning area, carries out target information perception;And sensing results information, progress are suspicious based on the received
Clarification of objective information extraction and comprehensive identification, determine suspicious object type.
Specifically, it includes multiple early warning subelements that the panorama, which stares unit (1), each early warning subelement corresponding one
A early warning subregion, multiple early warning subregions form one 360 ° of full view prewarning area by splicing;
Preferably, as shown in Fig. 2, it includes 11 early warning subelements that panorama, which stares unit (1), each early warning subelement is used
Modular assembly design, modules rationalize layout, and after correction, (single portion's camera covers 44.2 ° for 360 ° × 30 ° of splicing covering
× 30 °) area of space of range;
Also, early warning subelement uses the high frame frequency visible light probe assembly of high-resolution, and data transfer rate is not less than 25Hz, by mirror
The composition such as head, detector, imaging circuit, video and communication processing circuit, ray machine platform, the preferred LEM1616CE- of optical lens
H1;And adapted Mars5000-60UM model array image device.
As shown in figure 3, the target information sension unit (2) includes laser range sensor (201), visible images biography
Sensor (202), infrared image sensor (203) and ray machine platform (204);
The laser range sensor (201) for carrying out laser ranging to the suspicious object by laser, and will survey
The target range information of amount is sent to image synthesis treatment box (3);
Specifically, the laser range sensor selection peak power is high, pulse recurrence frequency is high, within the scope of safe wavelength
The semiconductor pumped solid Nd of 1.064um Wind-cooling type Gao Zhongying: YAG laser or optical fiber laser are worked using pulse laser
Mode obtains the range information of detected target.
The visible light image sensor (202) for carrying out visual light imaging to the suspicious object, and will be seen that light
Image information is sent to image synthesis treatment box (3);
Specifically, the visible light image sensor is using cmos sensor, having selected has one near infrared band
The high-resolution digital picture sensor devices of the FLIR model CM3-U3-50S5M-CS of provisioning response, cooperation JZ10100R MP are electronic
Zoom lens, focal length 10-1000mm, it is seen that optical image sensor 3 can realize 50-2000m >=" low slow small " of 0.6 span
The detection of unmanned plane target.
The infrared image sensor (203), for carrying out infrared imaging to target in early warning area of space, and will be red
Outer image information is sent to image synthesis treatment box (3);
Specifically, the infrared image sensor use CUBE817, it can be achieved that 50-500m >=0.6 span
The detection of " low slow small " unmanned plane target.
The ray machine platform (204), for carrying the laser range sensor (201), visible light image sensor
(202) and infrared image sensor (203);The photodetection instruction that described image integrated treatment case (3) is sent based on the received,
Drive the laser range sensor (201), visible light image sensor (202) and infrared image sensor (203) alignment mesh
Mark region;
In order to guarantee the consistency of detection optical axis, laser range sensor (201), visible light image sensor (202) and
Infrared image sensor (203) uses " the three photosynthetic coaxial mounted modes of one ".
Described image integrated treatment case (3) includes, early warning image processing unit (301), cradle head control unit (302), comprehensive
Close recognition unit (304) and target information output unit (305);
The early warning image processing unit (301) carries out figure for staring unit (1) upload early warning detection information to panorama
As processing, suspicious object is searched for, determines azimuth and the pitch angle information of suspicious object;
Specifically, early warning image processing unit (301) the real-time reception panorama stares the detection mission of unit (1) upload
Regional image information, using Jetson TX2Arm processing board, the 11 width images for staring unit (1) upload to panorama realize splicing,
Form detection mission region situation map.When " low slow small " target enters detection mission region, the early warning image processing unit
(301) serial number of capture imagery optical camera lens is obtained, and image is handled using frame difference method, is in image according to target
Position and the serial number for capturing imagery optical camera lens, calculate the azimuth information and pitch angle information of target.It is solidifying to handle panorama
Depending on the image that unit (1) uploads, suspicious object azimuth and pitch angle information are extracted.
The cradle head control unit (302), for according to suspicious object azimuth and pitch angle information, generate photoelectricity visit
Instruction is surveyed, ray machine platform (204) are sent to, laser range sensor (201), the visible light figure for carrying ray machine platform (204)
As suspicious object direction is directed toward in sensor (202) and infrared image sensor (203);
Comprehensive recognition unit (303), the suspicious object distance letter for being perceived from the target information sension unit (2)
Suspicious object characteristic information is extracted in breath, visible light image information or Infrared Image Information, and according to suspicious object characteristic information
Comprehensive identification is carried out, determines target type.
It perceives control unit (304) and controls the visible light image sensor for the distance according to suspicious object
(202) and infrared image sensor (203) carries out Image Acquisition;
When the distance of suspicious object is in first distance preset range, unlatching visible light image sensor (202), progress can
Light-exposed Image Acquisition;When target range information is in second distance preset range, while opening visible light sensor (202) and red
Outer imaging sensor (203), while carrying out visible images and infrared image acquisition.
Wherein, first distance preset range is 500-2000m;Second distance preset range is less than 500m.
Under conditions of visibility good, in the range of 0-2000m, it is preferred to use visible light image information carries out suspicious
Target signature information extracts;
Under conditions of poor visibility, visible light image sensor (202) is impacted, to be less than 500m within the scope of,
It is preferred using visible light image information carry out suspicious object feature information extraction.
More specifically, image synthesis treatment box (3) includes to be based on Jetson TX2 platform image processing circuit, image data
Memory plane, master board, cloud platform control system etc. are acquired, for placing data acquisition, image procossing, target detection, data are led to
The circuit boards such as news, secondary power supply and electric component.Unit (1), laser range sensor are stared by connector, cable and panorama
(201), visible light image sensor (202), infrared image sensor (203) connection, complete image procossing, image mosaic, mesh
Mark the work such as Morphology observation, the processing of target signature Data Data, distance exam, targeting accuracy tracking.
The present embodiment also discloses a kind of " low slow small " target acquisition recognition methods, as shown in figure 4, the specific steps are that:
Step S1, system is powered on, and panorama stares the real-time acquisition that unit (1) carries out panoramic picture to detection mission region;
Image synthesis treatment box (3) handles the image of the acquisition, and search whether there is suspicious object;
Laser range sensor (201), visible light image sensor (202), infrared image sensor (203) and photoelectricity turn
Platform (204) is in standby.
Specifically, image synthesis treatment box (3) is handled the image of acquisition using frame difference method in the step S1,
It is confirmed whether that there are suspicious objects.
Step S2, after searching suspicious object, image synthesis treatment box (3) calculates azimuth and the pitching of suspicious object
Angle information, and be converted into photodetection command signal and be output to ray machine platform (204), it is suspicious to transfer ray machine platform (204) direction
Target direction;
Step S3, the described laser range sensor (201), visible light image sensor (202) and infrared image sensor
(202) to that can detect with target, the range information, visible light image information and Infrared Image Information of suspicious object are perceived;
Specifically, including following sub-step in step S3:
Step S301, laser range sensor (201) carries out laser ranging to target and obtains the range information of suspicious object;
Step S302, the range information of suspicious object is sent image synthesis treatment box by laser range sensor (201)
(3);
Step S303, described image integrated treatment case (3) judges the range information, when target range information exists
It in first distance preset range, opens visible light image sensor (202), carries out visible images acquisition;When target range is believed
Breath opens visible light sensor (202) and infrared image sensor (203) in second distance preset range, and progress can
Light-exposed image and infrared image acquisition.
Wherein, first distance preset range is 500-2000m;Second distance preset range is less than 500m.
Step S4, it is extracted according in the suspicious object range information of perception, visible light image information or Infrared Image Information
Suspicious object characteristic information, and comprehensive identification is carried out according to suspicious object characteristic information, determine target type.
Specifically, the suspicious object characteristic information includes objective contour information, by suspicious mesh in the step S4
Target visible images or infrared image progress median filtering, binaryzation, edge detection and morphological image process obtain described
Objective contour information.
Under conditions of visibility good, in the range of 0-2000m, it is preferred to use visible light image information carries out suspicious
Target signature information extracts;
Under conditions of poor visibility, visible light image sensor (202) is impacted, to be less than 500m within the scope of,
It is preferred using visible light image information carry out suspicious object feature information extraction.
In the step S4, comprehensive identification is carried out using support vector machines (SVM) method learnt based on either shallow, obtains mesh
Mark type.
More specifically, when visible light image sensor and infrared image sensor receive image acquisition commands, to can
It doubts target and carries out Image Acquisition, and image information is transferred to image synthesis treatment box, image synthesis treatment box is to target image
The purpose of processing is to extract clarification of objective information and carry out comprehensive identification to target to need to extract target image information
Image preprocessing is carried out to image object, carries out image deblurring, denoising, image object binaryzation including the use of median filtering
Edge detection is carried out with using Canny operator, the series of algorithms such as morphological image process obtain objective contour information;
The acquisition objective contour information includes profile circularity, rectangular degree, Hu not bending moment, affine invariant moment features;And
Data normalizing is carried out using minimax normalization method, using Principal Component Analysis, selected characteristic data are big to result contribution degree
In 10% characteristic;
Preferably, is extracted by data and is melted using support vector machines (SVM) method learnt based on either shallow for suspicious object identification
The big characteristic of contribution degree in conjunction, as positive sample, negative sample is the characteristic of pseudo- Objective extraction, trains svm classifier model,
Whether final identification one group of data of test set are suspicious " the low slow small " targets of certain class, and multiple groups feature is obtained in sequential frame image
Data obtain target type according to multi-group data;Pixel coordinate of the target in panoramic picture in unit is stared using panorama, is tied
Range information to be closed, its flying speed, height are obtained, flight path information carries out image preprocessing to visible light, infrared image,
Target image profile information is obtained, obtains Target type information using target identification method.
So far, detection and identification of the photoelectric detecting system to " low slow small " unmanned plane target are realized.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of " low slow small " target acquisition identifying system, which is characterized in that stare unit (1), target information sense including panorama
Know unit (2) and image synthesis treatment box (3);
The panorama stares unit (1), for carrying out the detection of full view target alert to detection mission region;And by early warning detection
Information is sent to image synthesis treatment box (3);
The target information sension unit (2), for perceiving the range information, visible light image information and infrared figure of suspicious object
As information;And image synthesis treatment box (3) are sent by sensing results information;
Described image integrated treatment case (3) calculates suspicious object for searching for suspicious object according to the early warning detection information
Azimuth and pitch angle information;It is right that the target information sension unit (2) is controlled according to the azimuth and pitch angle information
Suspicious object in quasi- prewarning area carries out target information perception;And sensing results information based on the received, carry out suspicious object
Feature information extraction and comprehensive identification, determine suspicious object type.
2. target acquisition identifying system according to claim 1, which is characterized in that the panorama stares unit (1) and includes
Multiple early warning subelements, the corresponding early warning subregion of each early warning subelement, multiple early warning subregions pass through splicing, shape
At one 360 ° of full view prewarning area;
The early warning subelement uses the high frame frequency visible light probe assembly of high-resolution, carries out the detection of early warning image information.
3. target acquisition identifying system according to claim 1, which is characterized in that the target information sension unit (2)
Including laser range sensor (201), visible light image sensor (202), infrared image sensor (203) and ray machine platform
(204);
The laser range sensor (201), for carrying out laser ranging to the suspicious object by laser, and by measurement
Target range information is sent to image synthesis treatment box (3);
The visible light image sensor (202) for carrying out visual light imaging to the suspicious object, and will be seen that light image
Information is sent to image synthesis treatment box (3);
The infrared image sensor (203), for carrying out infrared imaging to target in early warning area of space, and by infrared figure
As information is sent to image synthesis treatment box (3);
The ray machine platform (204), for carry the laser range sensor (201), visible light image sensor (202) and
Infrared image sensor (203);The photodetection instruction that described image integrated treatment case (3) is sent based on the received, drives institute
State laser range sensor (201), visible light image sensor (202) and infrared image sensor (203) alignment target region.
4. target acquisition identifying system according to claim 1, which is characterized in that described image integrated treatment case (3) packet
It includes, early warning image processing unit (301), cradle head control unit (302), comprehensive recognition unit (304) and target information output are single
First (305);
The early warning image processing unit (301) uploads at early warning detection information progress image for staring unit (1) to panorama
Reason searches for suspicious object, determines azimuth and the pitch angle information of suspicious object;
The cradle head control unit (302), for according to suspicious object azimuth and pitch angle information, generate photodetection refer to
It enables, is sent to ray machine platform (204), laser range sensor (201), the visible images for carrying ray machine platform (204) pass
Sensor (202) and infrared image sensor (203) are directed toward suspicious object direction;
Comprehensive recognition unit (303), suspicious object range information for being perceived from the target information sension unit (2), can
Light-exposed image information
Or suspicious object characteristic information is extracted in Infrared Image Information, and comprehensive identification is carried out according to suspicious object characteristic information,
Determine target type.
5. target acquisition identifying system according to claim 1, which is characterized in that described image integrated treatment case (3) is also
Including perceiving control unit (304), for the distance according to suspicious object, control the visible light image sensor (202) and
Infrared image sensor (203) carries out Image Acquisition;
When the distance of suspicious object is within the scope of the first pre-determined distance, unlatching visible light image sensor (202) carries out visible light
Image Acquisition;When target range information is within the scope of the second pre-determined distance, while opening visible light sensor (202) and infrared figure
As sensor (203), while carrying out visible images and infrared image acquisition.
6. a kind of target acquisition recognition methods using target acquisition identifying system as claimed in claims 1-5, feature exist
In, comprising the following steps:
Step S1, system is powered on, and panorama stares the real-time acquisition that unit (1) carries out panoramic picture to detection mission region;Image
Integrated treatment case (3) handles the image of the acquisition, and search whether there is suspicious object;
Step S2, after searching suspicious object, image synthesis treatment box (3) calculates azimuth and the pitch angle letter of suspicious object
Breath, and be converted into photodetection command signal and be output to ray machine platform (204), it transfers ray machine platform (204) and drives laser ranging
Sensor (201), visible light image sensor (202) and infrared image sensor (203) are directed toward suspicious object direction;
Step S3, the described laser range sensor (201), visible light image sensor (202) and infrared image sensor (202)
To that can detect with target, the range information, visible light image information and Infrared Image Information of suspicious object are perceived;
Step S4, suspicious according to being extracted in the suspicious object range information of perception, visible light image information or Infrared Image Information
Target signature information, and comprehensive identification is carried out according to suspicious object characteristic information, determine target type.
7. target acquisition identifying system according to claim 6, which is characterized in that in the step S1, at image synthesis
Reason case (3) is handled the image of acquisition using frame difference method, is confirmed whether that there are suspicious objects.
8. the target acquisition identifying system stated according to claim 6, which is characterized in that include in step S3,
Laser range sensor (201) carries out laser ranging to target and obtains the range information of suspicious object, and it is comprehensive to be sent to image
It closes treatment box (3);
Described image integrated treatment case (3) judges the range information, when target range information is in the first pre-determined distance
It in range, opens visible light image sensor (202), carries out visible images acquisition;When target range information is default second
In distance range, while visible light sensor (202) and infrared image sensor (203) are opened, carries out visible images and red
Outer Image Acquisition.
9. target acquisition identifying system according to claim 6, which is characterized in that in the step S4, the suspicious mesh
Marking characteristic information includes objective contour information, by visible images to suspicious object or infrared image carry out median filtering,
Binaryzation, edge detection and morphological image process obtain the objective contour information.
10. target acquisition identifying system according to claim 7, which is characterized in that in the step S4, using based on shallow
Support vector machines (SVM) method of degree study carries out comprehensive identification, obtains target type.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910548691.1A CN110244314B (en) | 2019-06-24 | 2019-06-24 | Low-slow small target detection and identification system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910548691.1A CN110244314B (en) | 2019-06-24 | 2019-06-24 | Low-slow small target detection and identification system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110244314A true CN110244314A (en) | 2019-09-17 |
CN110244314B CN110244314B (en) | 2022-04-19 |
Family
ID=67889092
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910548691.1A Active CN110244314B (en) | 2019-06-24 | 2019-06-24 | Low-slow small target detection and identification system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110244314B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111077533A (en) * | 2019-12-27 | 2020-04-28 | 湖南傲英创视信息科技有限公司 | Multispectral wide-area panoramic photoelectric radar system and detection method thereof |
CN111190156A (en) * | 2020-01-08 | 2020-05-22 | 中国船舶重工集团公司第七二四研究所 | Radar and photoelectric based low-slow small target and sea surface small target identification method |
CN111208581A (en) * | 2019-12-16 | 2020-05-29 | 长春理工大学 | Unmanned aerial vehicle multi-dimensional identification system and method |
CN111223122A (en) * | 2020-01-20 | 2020-06-02 | 四川九洲电器集团有限责任公司 | Low-slow small target rapid detection and tracking device based on cloud |
CN111325772A (en) * | 2020-02-19 | 2020-06-23 | 四川九洲电器集团有限责任公司 | Low-slow small target detection device and method based on photoelectric equipment array |
CN111427387A (en) * | 2020-04-26 | 2020-07-17 | 北京都是科技有限公司 | Laser aiming system, method and device and artificial intelligent image processor |
CN111709385A (en) * | 2020-06-22 | 2020-09-25 | 电子科技大学 | Low, small and slow aircraft target detection system and identity identification method thereof |
CN112584015A (en) * | 2020-12-02 | 2021-03-30 | 达闼机器人有限公司 | Object detection method, device, storage medium and electronic equipment |
CN113655488A (en) * | 2021-06-30 | 2021-11-16 | 武汉高德红外股份有限公司 | Infrared alarm system for rapid periodic scanning directional distance measurement and distance measurement method thereof |
CN114518582A (en) * | 2020-11-18 | 2022-05-20 | 北京机械设备研究所 | Target detection device and method based on panoramic detection and photoelectric tracking |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201754214U (en) * | 2010-07-20 | 2011-03-02 | 北京四维图新科技股份有限公司 | Panorama shooting device |
CN102890823A (en) * | 2011-07-19 | 2013-01-23 | 株式会社东芝 | Motion object outline extraction and left ventricular image segmentation method and device |
CN104113733A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Television search detection method for small slow low-altitude target |
CN106341206A (en) * | 2016-08-26 | 2017-01-18 | 广东容祺智能科技有限公司 | Low-altitude unmanned aerial vehicle defense system |
WO2017106005A1 (en) * | 2015-12-15 | 2017-06-22 | Tradewinds Technology, Llc | Uav defense system |
CN108170139A (en) * | 2017-12-12 | 2018-06-15 | 武汉华之洋科技有限公司 | A kind of photoelectricity multitask system for unmanned boat and perform method |
CN108761403A (en) * | 2018-05-31 | 2018-11-06 | 智飞智能装备科技东台有限公司 | A kind of anti-unmanned plane system of defense based on radar |
CN109461168A (en) * | 2018-10-15 | 2019-03-12 | 腾讯科技(深圳)有限公司 | The recognition methods of target object and device, storage medium, electronic device |
CN109737981A (en) * | 2019-01-11 | 2019-05-10 | 西安电子科技大学 | Unmanned vehicle target-seeking device and method based on multisensor |
CN109873669A (en) * | 2019-04-04 | 2019-06-11 | 北京环境特性研究所 | A kind of unmanned plane detection method and unmanned plane detection system |
-
2019
- 2019-06-24 CN CN201910548691.1A patent/CN110244314B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201754214U (en) * | 2010-07-20 | 2011-03-02 | 北京四维图新科技股份有限公司 | Panorama shooting device |
CN102890823A (en) * | 2011-07-19 | 2013-01-23 | 株式会社东芝 | Motion object outline extraction and left ventricular image segmentation method and device |
CN104113733A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Television search detection method for small slow low-altitude target |
WO2017106005A1 (en) * | 2015-12-15 | 2017-06-22 | Tradewinds Technology, Llc | Uav defense system |
CN106341206A (en) * | 2016-08-26 | 2017-01-18 | 广东容祺智能科技有限公司 | Low-altitude unmanned aerial vehicle defense system |
CN108170139A (en) * | 2017-12-12 | 2018-06-15 | 武汉华之洋科技有限公司 | A kind of photoelectricity multitask system for unmanned boat and perform method |
CN108761403A (en) * | 2018-05-31 | 2018-11-06 | 智飞智能装备科技东台有限公司 | A kind of anti-unmanned plane system of defense based on radar |
CN109461168A (en) * | 2018-10-15 | 2019-03-12 | 腾讯科技(深圳)有限公司 | The recognition methods of target object and device, storage medium, electronic device |
CN109737981A (en) * | 2019-01-11 | 2019-05-10 | 西安电子科技大学 | Unmanned vehicle target-seeking device and method based on multisensor |
CN109873669A (en) * | 2019-04-04 | 2019-06-11 | 北京环境特性研究所 | A kind of unmanned plane detection method and unmanned plane detection system |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111208581A (en) * | 2019-12-16 | 2020-05-29 | 长春理工大学 | Unmanned aerial vehicle multi-dimensional identification system and method |
CN111208581B (en) * | 2019-12-16 | 2022-07-05 | 长春理工大学 | Unmanned aerial vehicle multi-dimensional identification system and method |
CN111077533A (en) * | 2019-12-27 | 2020-04-28 | 湖南傲英创视信息科技有限公司 | Multispectral wide-area panoramic photoelectric radar system and detection method thereof |
CN111190156A (en) * | 2020-01-08 | 2020-05-22 | 中国船舶重工集团公司第七二四研究所 | Radar and photoelectric based low-slow small target and sea surface small target identification method |
CN111223122A (en) * | 2020-01-20 | 2020-06-02 | 四川九洲电器集团有限责任公司 | Low-slow small target rapid detection and tracking device based on cloud |
CN111325772A (en) * | 2020-02-19 | 2020-06-23 | 四川九洲电器集团有限责任公司 | Low-slow small target detection device and method based on photoelectric equipment array |
CN111427387A (en) * | 2020-04-26 | 2020-07-17 | 北京都是科技有限公司 | Laser aiming system, method and device and artificial intelligent image processor |
CN111709385A (en) * | 2020-06-22 | 2020-09-25 | 电子科技大学 | Low, small and slow aircraft target detection system and identity identification method thereof |
CN114518582A (en) * | 2020-11-18 | 2022-05-20 | 北京机械设备研究所 | Target detection device and method based on panoramic detection and photoelectric tracking |
CN112584015A (en) * | 2020-12-02 | 2021-03-30 | 达闼机器人有限公司 | Object detection method, device, storage medium and electronic equipment |
CN112584015B (en) * | 2020-12-02 | 2022-05-17 | 达闼机器人股份有限公司 | Object detection method, device, storage medium and electronic equipment |
CN113655488A (en) * | 2021-06-30 | 2021-11-16 | 武汉高德红外股份有限公司 | Infrared alarm system for rapid periodic scanning directional distance measurement and distance measurement method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN110244314B (en) | 2022-04-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110244314A (en) | One kind " low slow small " target acquisition identifying system and method | |
CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
US11017228B2 (en) | Method and arrangement for condition monitoring of an installation with operating means | |
CN101969548B (en) | Active video acquiring method and device based on binocular camera shooting | |
US9488630B2 (en) | Integrated remote aerial sensing system | |
CN103941746B (en) | Image processing system and method is patrolled and examined without man-machine | |
CN110132226B (en) | System and method for measuring distance and azimuth angle of unmanned aerial vehicle line patrol | |
CN109737981B (en) | Unmanned vehicle target searching device and method based on multiple sensors | |
CN105741379A (en) | Method for panoramic inspection on substation | |
CN111324143A (en) | Unmanned aerial vehicle autonomous patrol obstacle avoidance system, method and computer equipment | |
JP6858415B2 (en) | Sea level measurement system, sea level measurement method and sea level measurement program | |
CN103400463B (en) | A kind of forest fires localization method based on two dimensional image and device | |
CN106210484A (en) | Waters surveillance polynary associating sensing device and cognitive method thereof | |
CN104125372A (en) | Target photoelectric search and detection method | |
CN104567692B (en) | Automatic monitoring system for underwater dragging operation width | |
CN207082909U (en) | A kind of power circuit intelligent inspection system | |
EP4296973A1 (en) | System and method for localization of anomalous phenomena in assets | |
CN108802742A (en) | Abnormal object monitoring method, apparatus and system | |
CN107256034B (en) | Change distribution room multiple spot environmental data collection system based on unmanned aerial vehicle | |
CN110267004A (en) | A kind of small drone detection monitoring system | |
WO2017047873A1 (en) | Scanning method using high-speed scanning apparatus | |
CN109862263B (en) | Moving target automatic tracking method based on image multi-dimensional feature recognition | |
CN207067421U (en) | A kind of radar and the target detection system of optics linkage | |
CN116580107A (en) | Cross-view multi-target real-time track tracking method and system | |
CN111402324A (en) | Target measuring method, electronic equipment and computer storage medium |
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 |