CN109583383A - A kind of unmanned plane life detection method and system based on Multiple Source Sensor - Google Patents
A kind of unmanned plane life detection method and system based on Multiple Source Sensor Download PDFInfo
- Publication number
- CN109583383A CN109583383A CN201811458266.5A CN201811458266A CN109583383A CN 109583383 A CN109583383 A CN 109583383A CN 201811458266 A CN201811458266 A CN 201811458266A CN 109583383 A CN109583383 A CN 109583383A
- Authority
- CN
- China
- Prior art keywords
- detection
- sensor
- unmanned plane
- target
- life
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The present invention discloses a kind of unmanned plane life detection method and system based on Multiple Source Sensor, this method step includes: that S1. by UAV flight's Multiple Source Sensor carries out detection search to target area, and Multiple Source Sensor includes for the radar sensor of detection radar image, the visible light image sensor for acquiring visible images and the infrared thermal imagery sensor for acquiring infrared image；S2. the signal that each sensor detects is received respectively and is merged, and obtains in target area that there are life detection mesh target areas by fusion results；The system includes detection search module and Multi-source Information Fusion module.The present invention can realize a wide range of interior fast, accurately life detection based on unmanned plane, and applied widely, flexibility and environmental suitability are strong.
Description
Technical field
The present invention relates to large-scale life detections, rescue technique field more particularly to a kind of based on Multiple Source Sensor
Unmanned plane life detection method and system.
Background technique
When the large-scale natural calamity of such as earthquake, landslide occurs, the tool that quick detection searches stranded pile things on personnel is needed
Body position, to organize Quick rescue.It is usually used as at present using life detection radar and searches for equipment, but life detection thunder
Up to that need to be checked by manual operation in the point-by-point blanket type in region of search, it is floating that life detection radar can penetrate shrub, thick grass, shallow-layer
The non-metal barriers such as soil, building ruins, detect vital sign human body target below, but the region that can be detected has
Limit, the human body target searching and detecting generally being suitable in the case of ruins, thin solum/rubble/floating grass burial, and dangerous is fallen
Building of collapsing is since there may be the danger of secondary collapsing, unsuitable personnel enter and can not implement detection and search for, and life detection thunder
Narrow up to each search coverage, each change sensing point requires professional's measuring and calculating and moves, and not only inefficiency, is not able to satisfy
On a large scale, the fast search demand of large area personnel, it is also possible to will lead to collapsing ruins and shake to cause secondary harm.
There is practitioner to propose that treating region of search using unmanned platform carries out contactless detection, search, has controllability
It is high, without secondary harm, a variety of advantages such as will not jeopardize rescuer, but visited currently based on the unmanned plane life of Multiple Source Sensor
Survey method is usually all that the carrying life detection radar mode directly on unmanned plane is used to realize, such as above-mentioned, life detection radar
It generally is suitable for underground life detection, it is not high for the life detection precision of earth's surface, and the letter that single type sensor can obtain
Cease limited, when detection is easy to happen misjudgement or fails to judge, while noiseproof feature is not strong, and detection accuracy is easy to by environmental factor shadow
It rings, and the regional environment of practical detection search required in rescue is severe, there are the environmental aspects of Various Complex, is taken by unmanned plane
Carry quick, accurate scan that single life detection radar is difficult to realize in a wide range of.
Chinese patent open file CN201610557419.6 discloses a kind of unmanned plane and unmanned plane searches and rescues localization method, should
Method is based on unmanned plane and is searched and rescued using radio signal strength, i.e., is differently directed the people in danger that antenna receives according to unmanned plane
The wireless signal strength that member sends, judges the geographical location of distress personnel.Such method is sentenced using unmanned plane by directional aerial
Disconnected distress personnel position, actual detection precision is not still high, and judges distress personnel information, nothing using wireless signal strength merely
Method distinguishes the source of the signal, and probability of miscarriage of justice is higher, be equally difficult to realize in a wide range of in a wide range of it is quick, accurately sweep
It retouches.
In conclusion needing to propose a kind of life detection method based on unmanned plane at present, can be realized in a wide range of
Fast, accurately life detection.
Summary of the invention
The technical problem to be solved in the present invention is that, for technical problem of the existing technology, the present invention provides one
Kind implementation method is simple, the required unmanned plane at low cost, that applied widely and environmental suitability is strong based on Multiple Source Sensor is raw
Detection method and system are ordered, can be realized the fast, accurately life detection in a wide range of.
In order to solve the above technical problems, technical solution proposed by the present invention are as follows:
A kind of unmanned plane life detection method based on Multiple Source Sensor, step include:
S1. detection search is carried out to target area by UAV flight's Multiple Source Sensor, the Multiple Source Sensor includes using
In the radar sensor of detection radar image, the visible light image sensor for acquiring visible images and for acquiring it is red
The infrared thermal imagery sensor of outer image；
S2. the signal that each sensor detects is received respectively and is merged, and must be determined in target area by fusion results
There are life detection mesh target areas.
As the further improvement of the method for the present invention, the step S2 include: by the visible images with it is described infrared
Image carries out data fusion and simultaneously carries out target identification, obtains first object testing result, the first object testing result with by
The radar image carries out the second object detection results that target identification obtains and carries out decision level fusion, obtains final target inspection
Survey result output.
Further improvement as the method for the present invention: the visible images and the infrared image use neural network side
Method carries out data fusion, specific steps are as follows: the visible images data and the infrared picture data are used building in advance
Neural network algorithm handled, obtain the regression relation between visible images and infrared picture data, complete data and melt
It closes.
As the further improvement of the method for the present invention, the first object testing result and second object detection results
Decision level fusion is carried out based on Bayesian decision, is specifically included: when the first object testing result, the second object detection results
When identical, directly obtain final target detection result output, when the first object testing result, the second object detection results not
When identical, obtaining target to be detected respectively is human body, non-human prior probability P (tE), P (tN), and general according to the priori
When rate P (tE), P (tN) calculate separately first object testing result, the second object detection results are k target true identity respectively by
It is determined as human body and non-human posterior probability CptP{tE|k},CfP tN | and k }, the posterior probability CptP{tE|k},CfP
The size of { tN | k } finally determines target identities, obtains final target detection result and exports.
It further include review step S3 in key area as the further improvement of the method for the present invention, after the step S2, specifically
Step includes: that there are life detection mesh target areas in the target area that determining will be obtained as key area, and controls nobody
Machine carries out secondary review to the key area and detects, final to determine life detection result.
As the further improvement of the method for the present invention, in the step S3, control unmanned plane uses the key area
Radar sensor carries out approaching formula detection, the final life state for determining detection target and position.
A kind of unmanned plane life-detection system based on Multiple Source Sensor, comprising:
Search module is detected, it is described more for carrying out detection search to target area by UAV flight's Multiple Source Sensor
Source sensor includes the radar sensor for detection radar image, the visible light image sensor for acquiring visible images
And the infrared thermal imagery sensor for acquiring infrared image；
Multisource data fusion module is tied for receiving signal that each sensor detects respectively and being merged by fusion
Fruit must determine that there are life detection mesh target areas in target area；
Further improvement as apparatus of the present invention: further including the remote control terminal connecting with the unmanned plane, for connecing
Receive the data and send control data to unmanned plane, the multisource data fusion module setting that the Multiple Source Sensor detects
On the unmanned plane or in the remote control terminal.
Further improvement as apparatus of the present invention: the detection search module further includes the positioning being arranged on unmanned plane
Module is exported for the location information where obtaining unmanned plane in real time.
Further improvement as apparatus of the present invention: further including the key area connecting with the multisource data fusion module
Review module for using there are life detection mesh target areas in the target area determined as key area, and controls
Unmanned plane carries out secondary review to the key area and detects, final to determine life detection result.
Compared with the prior art, the advantages of the present invention are as follows:
1, the present invention is based on the unmanned plane life detection method and system of Multiple Source Sensor, are carried using unmanned aerial vehicle platform more
The detection search of the different sensor progress inanimate object of kind, it can be achieved that cruise, detect operation, while abundant combination is more on a large scale
The respective characteristic of source heterogeneous sensor carries out work compound, can satisfy the detection demand of varying environment operating condition, improves detection
Anti-interference and environmental suitability can effectively improve detection accuracy in combination with Multi-source Information Fusion, to realize a wide range of area
The quick of domain, accurately detecting and search.
2, the present invention is based on the unmanned plane life detection method and system of Multiple Source Sensor, by by UAV flight's difference
The sensor of system can carry out coarse scanning, wide area search by visible light/infrared sensor, it is achievable in no trees, build
Vital sign target search when blocking such as build；Life detection radar can penetrate nonmetal medium, detect by surface dust, rubble, tree
The target that wood, building ruins etc. are blocked is used cooperatively, it can be achieved that low-light (level), the complex conditions such as blocking by three kinds of sensors
Target fast search can be big compared to single-sensor while by the data fusion between each sensor, information mutual communication
It is big to improve detection accuracy and accuracy, so as to realize that round-the-clock, low illumination, medium blocks and all kinds of items such as target is hidden
Seamless detection under part, greatly improves the environmental suitability of detection.
3, the present invention is based on the unmanned plane life detection method and system of Multiple Source Sensor, the imaging based on different sensors
Principle and picture characteristics, by first it will be seen that the image data of optical sensor and infrared sensor uses pixel-based fusion side
Formula can make full use of the correlation between two kinds of sensing datas to merge to obtain more accurate detection result, then it will be seen that
Result and the data of radar sensor realize that imaging is merged again using decision level fusion after light image is merged with infrared image, can be with
That realizes visible light/infrared and bioradar imaging cooperates with detection, thus sufficiently fusion visible images, infrared image and thunder
Accurate detection result is obtained up to image.
4, the present invention is based on the unmanned plane life detection method and system of Multiple Source Sensor, further by first by unmanned plane
Region-wide extensive search is carried out, after locking key area using Multi-source Information Fusion, then small range two is carried out to key area
Secondary review, quickly to navigate to detection target in small-scale key area, it can be achieved that by obscuring accurate scanning probe,
Further increase detection accuracy and efficiency.
Detailed description of the invention
Fig. 1 is the implementation process schematic diagram of unmanned plane life detection method of the present embodiment based on Multiple Source Sensor.
Fig. 2 is the implementation process schematic diagram that the present embodiment carries out data fusion using neural network method.
Fig. 3 is the implementation process schematic diagram that the present embodiment carries out decision level fusion based on Bayesian decision method.
Fig. 4 is the structural principle signal of unmanned plane life-detection system employed in concrete application embodiment of the present invention
Figure.
Fig. 5 is the realization principle schematic diagram that unmanned plane life detection is realized in concrete application embodiment of the present invention.
Specific embodiment
Below in conjunction with Figure of description and specific preferred embodiment, the invention will be further described, but not therefore and
It limits the scope of the invention.
As shown in Figure 1, unmanned plane life detection method and step of the present embodiment based on Multiple Source Sensor includes:
S1. detection search, Multiple Source Sensor packet detection search: are carried out to target area by UAV flight's Multiple Source Sensor
Include the radar sensor for detection radar image, the visible light image sensor for acquiring visible images and for adopting
Collect the infrared thermal imagery sensor of infrared image；
S2. Multi-source Information Fusion: the signal that each sensor detects is received respectively and is merged, is obtained really by fusion results
Setting the goal in region, there are life detection mesh target areas.
Multi-source Information Fusion is by the information resources using different time and multiple sensors in space, using calculating
Machine technology is detected according to certain criterion, is interconnected, is related, estimation and group to the multisensor observation information chronologically obtained
It closes, automatically analyzes, the information process of Optimum Synthesis to obtain more accurate state and identity estimation obtains measurand
Consistency explain and description, so that system is obtained more superior than its component part performance.The present embodiment is flat using unmanned plane
Platform carries a variety of different sensors and carries out the detection search of inanimate object, it can be achieved that a wide range of cruise, detect operation, fill simultaneously
Divide the respective characteristic for combining multi-source heterogeneous sensor to carry out work compound, can satisfy the detection demand of varying environment operating condition, mention
The anti-interference and environmental suitability of height detection, can effectively improve detection accuracy in combination with Multi-source Information Fusion, to realize
The quick of extensive area, accurately detecting and search.
, the Multiple Source Sensor that in the present embodiment unmanned plane carries different with the detection physical sign parameters of target according to working mechanism
Including radar sensor, visible light sensor and infrared thermal imagery sensor etc., ground/shallow-layer may search for by radar sensor
Buried target is buried, ground target may search for by visible light sensor and infrared thermal imagery sensor, so that can both detect
It searches for extensive area ground/shallow-layer and buries buried target, also may search for ground target.
In concrete application embodiment, radar sensor specifically uses ultra wide band life detection radar, is taken by unmanned plane
It carries life detection radar and detection search is carried out to regions such as large area, the big scale of construction, high-risk multilayer ruins, it can be round-the-clock, full-time
Section work, is generated by radar when work and by transmitting antenna (containing array) electromagnetic radiation signal, can penetrate building ruins, ground
The complex barriers object such as shallow-layer surface dust realizes to vital sign target acquisition, identification and positioning, can detecting for efficiently and accurately hindered
Hinder the indicator of trapped personnel that object blocks.
In concrete application embodiment, it is seen that optical image sensor uses low-light (level) Visible Light Camera, in normal light
According to and severe illumination condition (such as night) under acquisition detection scene optical imagery, then depth/machine learning by being internally integrated
Algorithm can distinguish human body/animal target.Digital noise reduction further can also be carried out to image when collecting image, to eliminate
Interference source in signal, makes that image is apparent, profile is clearly more demarcated, contrast is stronger；It can be mended with further progress digital backlight
It repays, so that can be adapted for the Image Acquisition under the scenes such as low-light (level), backlight.
In concrete application embodiment, infrared thermal imagery sensor uses thermal infrared imager, for detecting the infrared heat at scene
Image, can round-the-clock work, and work is not limited by daytime, night light differential, then depth/machine by being internally integrated
Learning algorithm can distinguish human body/animal target with vital sign.
By the sensor of above-mentioned three kinds different systems of UAV flight, wherein low-light (level) visible light/infrared sensor can be with
Coarse scanning, wide area search are carried out, since it does not have penetration capacity, the achievable life when no trees, building etc. are blocked
Order sign target search；And ultra wide band life detection radar can penetrate nonmetal medium, for by surface dust, rubble, trees, building
The target that ruins etc. are blocked can be detected by ultra wide band life detection radar sensor, be cooperated by above-mentioned three kinds of sensors
Using, it can be achieved that low-light (level), the target fast search of complex conditions such as block, while being melted by the data between each sensor
Close, information mutual communication, detection accuracy and accuracy can be greatly improved compared to single-sensor, so as to realize round-the-clock/
Low illumination, medium block/target it is hidden etc. it is all kinds of under the conditions of seamless detection, greatly improve the environmental suitability of detection.
It is understood that above-mentioned radar sensor, visible light image sensor and infrared sensor can also bases
Actual demand uses other types, other sensors can also be arranged further to further increase detection performance.
In concrete application embodiment, in advance by above-mentioned three kinds of sensor integrations unmanned plane the same rotating platform
On, the antenna of ultra wide band life detection radar is face-down, and low-light (level) camera and infrared sensor are embedded in radar host computer, low photograph
The probe of the camera lens and infrared sensor of spending camera is integrated to be arranged together, and is leaked out from radar antenna test surface centre, and
It is rotated with radar detection face.By integrating the end of probe of low-light (level) camera and infrared sensor, can be convenient for
Heterologous image registration is carried out, low-light (level) camera, infrared sensor are rotated with radar, and multi-faceted detection may be implemented and search
Rope, and can guarantee that each sensor acquired image data are consistent.
It specifically will be seen that light image and infrared image carry out data fusion and carry out target identification in the present embodiment step S2,
First object testing result is obtained, first object testing result carries out the second mesh that target identification obtains with by radar image data
Mark testing result and carry out decision level fusion, obtain final object detection results output, i.e., first by visible light sensor with it is infrared
Sensing data is merged using pixel-based fusion mode, then with radar sensor be based on decision level fusion mode carry out it is secondary
Decision level fusion, to merge to obtain by visible images, infrared image whether there is or not on the basis of detection target, with radar detection knot
Fruit shape is at unified decision.
In view of the image-forming principle of visible light image sensor, infrared sensor is identical, imaging effect is by target
Correlation is strong between the image that geometry, physical property decision, i.e. the two obtain, while considering visible light/infrared sensor
Image-forming principle it is different from life detection radar image-forming principle, obtained image data structure is different, and the present embodiment is above-mentioned logical
After first it will be seen that the image data of optical sensor and infrared sensor can make full use of two kinds of biographies using pixel-based fusion mode
Correlation between sensor data merges to obtain more accurate detection result, then it will be seen that light image merges with infrared image after
As a result decision level fusion is used to realize merging again for imaging again with the data of radar sensor, may be implemented visible light/infrared with
The collaboration detection of bioradar imaging, exports final fusion detection imaging results, to sufficiently merge visible images, infrared figure
As and radar image obtain accurate detection result.
In the present embodiment, it is seen that light image data specifically use neural network method progress data to melt with infrared picture data
Close, specific steps are as follows: it will be seen that light image data and infrared picture data using the neural network algorithm constructed in advance at
Reason obtains the regression relation between visible images and infrared picture data, completes data fusion.Since visible images sense
Device, infrared image sensor are mainly used for the search positioning that such as trees, thick grass on ground block the wounded, to the anti-interference of fusion
Performance requirement is higher, and the present embodiment, which is based on neural network fashion, will be seen that light image and infrared image carry out data fusion, can be with
The correlation between light-exposed image data and infrared picture data is sufficiently excavated, fusion obtains more accurate imaging data, and
Strong interference immunity can be further improved detection accuracy and environmental suitability.
In the present embodiment, it is seen that further include respectively to can before light image data and infrared picture data carry out data fusion
Light-exposed image data, the infrared picture data carry out image registration step, by visible images, the infrared figure obtained after being registrated
As carrying out data fusion.
As shown in Fig. 2, the present embodiment will be seen that optical sensor image data, infrared sensor image data are merged
When, after will be seen that optical sensor image data, infrared sensor image data are pre-processed respectively first, then carries out image and match
Standard obtains the regression relation between visible light and thermal infrared sensor data by constructing neural network algorithm, realizes data level
Fusion；The image aspects and textural characteristics for finally utilizing human body target complete human body target using Digital Image Processing algorithm
Feature extraction and target identification obtain first object testing result.
In the present embodiment, first object testing result and the second object detection results are based on Bayesian decision grade amalgamation mode
Carry out decision level fusion.Visible light/infrared imaging is different with bioradar image-forming principle, obtains in fusion visible light/infrared imaging
To on the basis of detection result, since the target information of visible light/infrared heat and the acquisition of bioradar sensor has independence,
The reasoning process of the two meets mutually independent condition between characteristic parameter, and the present embodiment further may be used using Bayesian decision
Light-exposed/infrared imaging fusion results and radar detection result carry out decision level fusion and are further mentioned with finally obtaining the result of decision
High detection accuracy.
In the present embodiment, decision level fusion is carried out based on Bayesian decision and is specifically included: when first object testing result, the
When two object detection results are identical, the output of final target detection result is directly obtained, when first object testing result, the second target
When testing result is not identical, target to be detected is obtained respectively as human body, non-human prior probability P (tE), P (tN), and according to
Target true identity when prior probability P (tE), P (tN) calculate separately first object testing result, the second object detection results are k
It is judged as human body and non-human posterior probability C respectivelyptP{tE|k},CfP tN | and k }, compare posterior probability CptP{tE|k},
CfThe size of P { tN | k } finally determines target identities, obtains final target detection result and exports, wherein if CptP tE | and k } >
CfP tN | and k }, target identities are finally determined after fusion for human body target, if CptP tE | and k } < CfP tN | and k }, final after fusion
Judgement target identities are non-human target.
As shown in figure 3, the present embodiment first will be seen that light/infrared fusion of imaging is registrated with life detection radar imaging,
After carrying out feature extraction and target identification respectively, first object detection result is obtained by visible light/infrared fusion of imaging, by life
Detection radar is imaged to obtain the second target acquisition as a result, first object detection result, the second target acquisition result are based on pattra leaves
This estimation fusion decision obtains final detection result output.
It further include review step S3 in key area in the present embodiment, after step S2, specific steps include: to obtain determination
There are life detection mesh target areas in target area as key area, and controls unmanned plane and carry out two to the key area
Secondary review detection, it is final to determine life detection result.Region-wide extensive search is first carried out by unmanned plane, utilizes multi-source information
Fusion locking key area, then the secondary review of small range is carried out to key area, it can be sufficiently in conjunction with each of multi-source heterogeneous sensor
Work compound is carried out from characteristic, realizes in combination with Multi-source Information Fusion by obscuring accurate scanning probe, can effectively mention
High detection accuracy and efficiency are particularly suitable for realizing quick, accurately detecting and search in extensive area.
When the present embodiment executes detection search, it is specific first by the multi-source heterogeneous sensor of UAV flight specified altitude assignment (such as
20-100m) section cruised on a large scale, detect operation, visual range is wide, single search coverage is big, search efficiency is high, and right
Danger zone is insensitive, while will not generate secondary disaster risk to the region, is marked out based on Multi-source Information Fusion result doubtful
Behind key area like target area, then secondary review is carried out to key area by unmanned plane and is detected, in small-scale emphasis
Detection target is quickly navigated in region, improves detection efficient and precision.
In the present embodiment step S3, the specific unmanned plane that controls carries out key area using radar sensor to approach formula spy
It surveys, the final life state for determining detection target and position.Target area is carried out by UAV flight's Multiple Source Sensor quick
Coarse scanning such as quickly carries out coarse scanning to target area by low-light (level) Visible Light Camera, thermal infrared sensor, determines and doubts on ground
Seemingly there is mesh target area, determines that subsurface buries vital sign target by ultra wide band life detection radar sensor large area scanning
Suspicious region；After the detection data of Multiple Source Sensor is carried out fusion treatment, calibration needs to carry out the weight of secondary review detection
Point region；Key area is carried out again to approach formula detection, to obtain clearer image and by ultra wide band life detection radar
Sensor determines that the vital sign state of human body target finally determines the state for obtaining detection target and position.Further to ground
The location point of target is not found on face, life detection radar can be used to carry out penetration detection search, with the doubtful ruins of determination, screening
Whether there is detection target below block material.
Unmanned plane life-detection system of the present embodiment based on Multiple Source Sensor characterized by comprising
Search module is detected, it is described more for carrying out detection search to target area by UAV flight's Multiple Source Sensor
Source sensor includes the radar sensor for detection radar image, the visible light image sensor for acquiring visible images
And the infrared thermal imagery sensor for acquiring infrared image；
Multisource data fusion module is tied for receiving signal that each sensor detects respectively and being merged by fusion
Fruit must determine that there are life detection mesh target areas in target area.
In the present embodiment, it will be seen that light image and infrared image carry out data fusion in multisource data fusion module, obtain
First object testing result, first object testing result carry out the second target detection knot that target identification obtains with by radar image
Fruit carries out decision level fusion, obtains final object detection results output.
In the present embodiment, visible images data and infrared picture data are using mind in further multisource data fusion module
Data fusion is carried out through network method.
In the present embodiment, first object testing result and the second object detection results in further multisource data fusion module
Decision level fusion is carried out based on Bayesian decision.
In the present embodiment, further comprises the key area review module connecting with multisource data fusion module, be used for
There are life detection mesh target areas in the target area that determining will be obtained as key area, and controls unmanned plane to described heavy
Point region carries out secondary review detection, final to determine life detection result.
The present embodiment unmanned plane life-detection system and above-mentioned unmanned plane life detection method correspond, not another herein
One repeats.
In the present embodiment, further comprise the remote control terminal connecting with unmanned plane, is detected for receiving unmanned plane
Data and send control data to unmanned plane, multisource data fusion module can be set on unmanned aerial vehicle platform, complete number
According to remote control terminal is transmitted to after fusion again, the remote control terminal connecting with UAV Communication also can be arranged directly on.
In the present embodiment, it is additionally provided on further unmanned plane for providing the locating module of location information, can be specifically adopted
The location information of target can be directly determined by carrying locating module by unmanned aerial vehicle platform with Beidou positioning module, is convenient for group
It knits and sues and labours.Be additionally provided with image transmission system on further unmanned plane, for real-time transmission data, live image/video etc., it can be achieved that
Presence states Real time visible.
As shown in Figure 4,5, unmanned plane life-detection system includes three parts in concrete application embodiment of the present invention: multi-source is different
Structure sensor load, unmanned aerial vehicle platform and rear method, apparatus control terminal, wherein Multiple Source Sensor load includes that ultra wide band life is visited
Radar, low-light (level) visible light sensor and infrared sensor are surveyed, for detecting the target in search setting regions, and will be obtained
Data, image pass back to rear method, apparatus control terminal；Multiple Source Sensor is mounted on unmanned aerial vehicle platform, and rear method, apparatus control terminal is made
To accuse platform, controls the flight path of unmanned plane, control Multiple Source Sensor load operation, receives what Multiple Source Sensor detected
Data/image carries out Multi-source Information Fusion processing, and rear method, apparatus control terminal may be provided at several hundred rice or several in distance objective region
At kilometer, communicated with unmanned aerial vehicle platform by figure biography/data transmission equipment, rear method, apparatus control terminal further may be configured so that tool
The data fusion of standby three kinds of sensors unifies display function.
Between the above-mentioned multi-source heterogeneous sensor load of the present embodiment and unmanned aerial vehicle platform be equipped with power interface, data-interface,
Control interface, Multiple Source Sensor take electricity from unmanned aerial vehicle platform, receive under the rear method, apparatus control terminal that unmanned aerial vehicle platform passes over
The operational order of hair, and the results/data that each sensor itself detects is passed back to rear method, apparatus control terminal and is shown,
Unmanned aerial vehicle platform can directly determine the location information of target by the locating module carried.
As shown in figure 5, carrying out life detection using above-mentioned unmanned plane life-detection system in concrete application embodiment
Process includes:
1) by equipped with life detection radar, low-light (level) Visible Light Camera, infrared sensor etc. Multiple Source Sensor and
The unmanned aerial vehicle platform of Beidou satellite alignment system according to preset flight path, is planned to carry out cruise search in target area overhead；
2) unmanned aerial vehicle platform is in flight course, the region of search image detected by each sensor, on the ground
The data such as the target position information of movement/static human body target carry out image procossing with live scene and merge, and scheme treated
Picture and result pass link by figure biography/number and send back to rear method, apparatus control terminal；
3) method, apparatus control terminal according to each sensor detection result for receiving carries out Multi-source Information Fusion afterwards, wherein it will be seen that
Light image and infrared image carry out data fusion, obtain first object testing result, first object testing result with by radar map
Decision level fusion is carried out as carrying out the second object detection results that target identification obtains, obtains final object detection results, and
There is the key area of detection target in locking；
4) control UAV flight's radar life-detection instrument carries out all key areas to approach formula detection, determines target
Vital sign state simultaneously carries out Precise imaging confirmation；For not finding the location point of target on ground, carries out penetration detection and search
Rope determines doubtful ruins, whether has detection target below shelter, if any then marking and pass back to rear method, apparatus control terminal.
Above-mentioned only presently preferred embodiments of the present invention, is not intended to limit the present invention in any form.Although of the invention
It has been disclosed in a preferred embodiment above, however, it is not intended to limit the invention.Therefore, all without departing from technical solution of the present invention
Content, technical spirit any simple modifications, equivalents, and modifications made to the above embodiment, should all fall according to the present invention
In the range of technical solution of the present invention protection.
Claims (10)
1. a kind of unmanned plane life detection method based on Multiple Source Sensor, which is characterized in that step includes:
S1. detection search is carried out to target area by UAV flight's Multiple Source Sensor, the Multiple Source Sensor includes for visiting
Survey the radar sensor of radar image, the visible light image sensor for acquiring visible images and for acquiring infrared figure
The infrared thermal imagery sensor of picture；
S2. the signal that each sensor detects is received respectively and is merged, and must determine in target area exist by fusion results
Life detection mesh target area.
2. the unmanned plane life detection method according to claim 1 based on Multiple Source Sensor, which is characterized in that the step
Rapid S2 includes: that the visible images and the infrared image are carried out data fusion and carry out target identification, obtains the first mesh
Testing result is marked, the first object testing result carries out the second target detection that target identification obtains with by the radar image
As a result decision level fusion is carried out, final object detection results output is obtained.
3. the unmanned plane life detection method according to claim 2 based on Multiple Source Sensor, it is characterised in that: it is described can
Light-exposed image and the infrared image are using neural network method progress data fusion, specific steps are as follows: by the visible light figure
As data are handled with the infrared picture data using the neural network algorithm constructed in advance, obtain visible images with it is red
Regression relation between outer image data completes data fusion.
4. the unmanned plane life detection method according to claim 3 based on Multiple Source Sensor, which is characterized in that described
One object detection results and second object detection results are based on Bayesian decision and carry out decision level fusion, specifically include: when
When the first object testing result, the second object detection results are identical, the output of final target detection result is directly obtained, institute is worked as
State first object testing result, the second object detection results it is not identical when, obtaining target to be detected respectively is human body, non-human
Prior probability P (tE), P (tN), and first object testing result, are calculated separately according to the prior probability P (tE), P (tN)
Target true identity is judged as human body and non-human posterior probability C respectively when two object detection results are kptP{tE|k},
CfP tN | and k }, the posterior probability CptP{tE|k},CfThe size of P { tN | k } finally determines target identities, obtains most
Whole object detection results output.
5. the unmanned plane life detection method described according to claim 1~any one of 4 based on Multiple Source Sensor, special
Sign is: further including review step S3 in key area after the step S2, specific steps include: that will determine obtained target area
In there are life detection mesh target areas as key area, and control unmanned plane and secondary review spy carried out to the key area
It surveys, it is final to determine life detection result.
6. the unmanned plane life detection method according to claim 5 based on Multiple Source Sensor, it is characterised in that: the step
In rapid S3, control unmanned plane carries out the key area using radar sensor to approach formula detection, final to determine detection target
Life state and position.
7. a kind of unmanned plane life-detection system based on Multiple Source Sensor characterized by comprising
Search module is detected, for carrying out detection search to target area by UAV flight's Multiple Source Sensor, the multi-source is passed
Sensor include for the radar sensor of detection radar image, the visible light image sensor for acquiring visible images and
For acquiring the infrared thermal imagery sensor of infrared image；
Multisource data fusion module is obtained for receiving signal that each sensor detects respectively and being merged by fusion results
Determine that there are life detection mesh target areas in target area.
8. the unmanned plane life-detection system according to claim 7 based on Multiple Source Sensor, which is characterized in that further include
The remote control terminal being connect with the unmanned plane, for receiving the data and send control number that the Multiple Source Sensor detects
According to unmanned plane is given, the multisource data fusion module setting is on the unmanned plane or in the remote control terminal.
9. the unmanned plane life-detection system according to claim 7 or 8 based on Multiple Source Sensor, which is characterized in that institute
Stating detection search module further includes the locating module being arranged on unmanned plane, for obtaining the location information where unmanned plane in real time
Output.
10. the unmanned plane life-detection system according to claim 7 or 8 based on Multiple Source Sensor, further include with it is described
The key area review module of multisource data fusion module connection, for by there are life detections in the target area determined
Mesh target area controls unmanned plane and carries out secondary review detection to the key area as key area, final to determine life
Order detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811458266.5A CN109583383A (en) | 2018-11-30 | 2018-11-30 | A kind of unmanned plane life detection method and system based on Multiple Source Sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811458266.5A CN109583383A (en) | 2018-11-30 | 2018-11-30 | A kind of unmanned plane life detection method and system based on Multiple Source Sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583383A true CN109583383A (en) | 2019-04-05 |
Family
ID=65926609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811458266.5A Pending CN109583383A (en) | 2018-11-30 | 2018-11-30 | A kind of unmanned plane life detection method and system based on Multiple Source Sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583383A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110650530A (en) * | 2019-09-24 | 2020-01-03 | 北京佰才邦技术有限公司 | Unmanned aerial vehicle searching and positioning method and device and unmanned aerial vehicle |
| CN111175833A (en) * | 2020-03-15 | 2020-05-19 | 湖南科技大学 | Thunder field synchronous detection method based on multi-source information |
| CN111402134A (en) * | 2020-03-15 | 2020-07-10 | 国科天成（北京）科技有限公司 | Visible/infrared double-light fusion system |
| CN111563559A (en) * | 2020-05-18 | 2020-08-21 | 国网浙江省电力有限公司检修分公司 | Imaging method, device, equipment and storage medium |
| CN112633326A (en) * | 2020-11-30 | 2021-04-09 | 电子科技大学 | Unmanned aerial vehicle target detection method based on Bayesian multi-source fusion |
| CN112987014A (en) * | 2021-02-20 | 2021-06-18 | 纳瓦电子（上海）有限公司 | Vehicle and detection system and detection method thereof |
| CN113034615A (en) * | 2021-03-30 | 2021-06-25 | 南方电网电力科技股份有限公司 | Equipment calibration method for multi-source data fusion and related device |
| CN113126050A (en) * | 2021-03-05 | 2021-07-16 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
| CN113225706A (en) * | 2021-05-06 | 2021-08-06 | 中国人民解放军空军军医大学 | Battlefield wounded personnel searching method and system based on unmanned aerial vehicle cluster |
| CN113438449A (en) * | 2021-06-07 | 2021-09-24 | 西安恒盛安信智能技术有限公司 | Video image transmission method |
| CN114463792A (en) * | 2022-02-10 | 2022-05-10 | 厦门熵基科技有限公司 | Multispectral identification method, multispectral identification device, multispectral identification equipment and readable storage medium |
| CN116369864A (en) * | 2023-06-02 | 2023-07-04 | 长春中医药大学 | Sleep monitoring data intelligent management method and system based on data coding |
| CN116757981A (en) * | 2023-06-19 | 2023-09-15 | 北京拙河科技有限公司 | Multi-terminal image fusion method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104244175A (en) * | 2013-06-14 | 2014-12-24 | 长沙恒茂电子信息技术有限公司 | Mine environmental monitoring and rescue management system based on UWB technology |
| CN108387944A (en) * | 2018-02-01 | 2018-08-10 | 北京理工大学 | Minimize the life-detection instrument of visible light and the fusion of LONG WAVE INFRARED two-waveband video |
| CN108509918A (en) * | 2018-04-03 | 2018-09-07 | 中国人民解放军国防科技大学 | Target detection and tracking method fusing laser point cloud and image |
| CN108832997A (en) * | 2018-08-07 | 2018-11-16 | 湖南华诺星空电子技术有限公司 | A kind of unmanned aerial vehicle group searching rescue method and system |
-
2018
- 2018-11-30 CN CN201811458266.5A patent/CN109583383A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104244175A (en) * | 2013-06-14 | 2014-12-24 | 长沙恒茂电子信息技术有限公司 | Mine environmental monitoring and rescue management system based on UWB technology |
| CN108387944A (en) * | 2018-02-01 | 2018-08-10 | 北京理工大学 | Minimize the life-detection instrument of visible light and the fusion of LONG WAVE INFRARED two-waveband video |
| CN108509918A (en) * | 2018-04-03 | 2018-09-07 | 中国人民解放军国防科技大学 | Target detection and tracking method fusing laser point cloud and image |
| CN108832997A (en) * | 2018-08-07 | 2018-11-16 | 湖南华诺星空电子技术有限公司 | A kind of unmanned aerial vehicle group searching rescue method and system |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110650530A (en) * | 2019-09-24 | 2020-01-03 | 北京佰才邦技术有限公司 | Unmanned aerial vehicle searching and positioning method and device and unmanned aerial vehicle |
| CN111175833A (en) * | 2020-03-15 | 2020-05-19 | 湖南科技大学 | Thunder field synchronous detection method based on multi-source information |
| CN111402134A (en) * | 2020-03-15 | 2020-07-10 | 国科天成（北京）科技有限公司 | Visible/infrared double-light fusion system |
| CN111402134B (en) * | 2020-03-15 | 2020-12-22 | 国科天成（北京）科技有限公司 | Visible/infrared double-light fusion system |
| CN111175833B (en) * | 2020-03-15 | 2022-06-28 | 湖南科技大学 | Thunder field synchronous detection method based on multi-source information |
| CN111563559A (en) * | 2020-05-18 | 2020-08-21 | 国网浙江省电力有限公司检修分公司 | Imaging method, device, equipment and storage medium |
| CN111563559B (en) * | 2020-05-18 | 2024-03-29 | 国网浙江省电力有限公司检修分公司 | Imaging method, device, equipment and storage medium |
| CN112633326B (en) * | 2020-11-30 | 2022-04-29 | 电子科技大学 | Unmanned aerial vehicle target detection method based on Bayesian multi-source fusion |
| CN112633326A (en) * | 2020-11-30 | 2021-04-09 | 电子科技大学 | Unmanned aerial vehicle target detection method based on Bayesian multi-source fusion |
| CN112987014A (en) * | 2021-02-20 | 2021-06-18 | 纳瓦电子（上海）有限公司 | Vehicle and detection system and detection method thereof |
| CN113126050A (en) * | 2021-03-05 | 2021-07-16 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
| CN113126050B (en) * | 2021-03-05 | 2022-08-19 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
| CN113034615A (en) * | 2021-03-30 | 2021-06-25 | 南方电网电力科技股份有限公司 | Equipment calibration method for multi-source data fusion and related device |
| CN113225706A (en) * | 2021-05-06 | 2021-08-06 | 中国人民解放军空军军医大学 | Battlefield wounded personnel searching method and system based on unmanned aerial vehicle cluster |
| CN113438449A (en) * | 2021-06-07 | 2021-09-24 | 西安恒盛安信智能技术有限公司 | Video image transmission method |
| CN114463792A (en) * | 2022-02-10 | 2022-05-10 | 厦门熵基科技有限公司 | Multispectral identification method, multispectral identification device, multispectral identification equipment and readable storage medium |
| CN116369864A (en) * | 2023-06-02 | 2023-07-04 | 长春中医药大学 | Sleep monitoring data intelligent management method and system based on data coding |
| CN116369864B (en) * | 2023-06-02 | 2023-08-08 | 长春中医药大学 | Sleep monitoring data intelligent management method and system based on data coding |
| CN116757981A (en) * | 2023-06-19 | 2023-09-15 | 北京拙河科技有限公司 | Multi-terminal image fusion method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583383A (en) | A kind of unmanned plane life detection method and system based on Multiple Source Sensor | |
| CN108832997B (en) | Unmanned aerial vehicle group searching and rescuing method and system | |
| CN109073348B (en) | Airborne system and method for detecting, locating and image acquisition of buried objects, method for characterizing subsoil composition | |
| CN109558848A (en) | A kind of unmanned plane life detection method based on Multi-source Information Fusion | |
| US9784836B2 (en) | System for monitoring power lines | |
| CN107015193B (en) | A kind of binocular CCD vision mine movable object localization method and system | |
| KR101533905B1 (en) | A surveillance system and a method for detecting a foreign object, debris, or damage in an airfield | |
| US20160217578A1 (en) | Systems and methods for mapping sensor feedback onto virtual representations of detection surfaces | |
| CN105829920B (en) | Active microwave equipment and detection method | |
| CN104590319A (en) | Device for foreign body invasion detection and method for foreign body invasion detection | |
| JP6858415B2 (en) | Sea level measurement system, sea level measurement method and sea level measurement program | |
| Tommaselli et al. | Development and assessment of a data set containing frame images and dense airborne laser scanning point clouds | |
| Arfaoui | Unmanned aerial vehicle: Review of onboard sensors, application fields, open problems and research issues | |
| Hausamann et al. | Monitoring of gas transmission pipelines—a customer driven civil UAV application | |
| CN209402517U (en) | A kind of unmanned aerial vehicle group searching rescue system | |
| CN116323393A (en) | System for detecting foreign matter on runway and method thereof | |
| CN105116908B (en) | The communication means of unmanned plane vision formation collaboration | |
| Müller et al. | Drone detection, recognition, and assistance system for counter-UAV with VIS, radar, and radio sensors | |
| US10718613B2 (en) | Ground-based system for geolocation of perpetrators of aircraft laser strikes | |
| KR101248150B1 (en) | Distance estimation system of concealed object using stereoscopic passive millimeter wave imaging and method thereof | |
| Yamauchi | All-weather perception for small autonomous UGVs | |
| Schraml et al. | Precise radionuclide localization using uav-based lidar and gamma probe with real-time processing | |
| Sniatala | Drone as a sensors’ platform | |
| Zhang | Ten years of technology advancement in remote sensing and the research in the CRC-AGIP lab in GCE | |
| Amami et al. | Topographic Surveying using low-cost amateur drones & 4K ultra-high-definition videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190405 |
|
| RJ01 | Rejection of invention patent application after publication |