CN103985117A - Method for capturing and determining object based on remote sensing image - Google Patents
Method for capturing and determining object based on remote sensing image Download PDFInfo
- Publication number
- CN103985117A CN103985117A CN201410175257.0A CN201410175257A CN103985117A CN 103985117 A CN103985117 A CN 103985117A CN 201410175257 A CN201410175257 A CN 201410175257A CN 103985117 A CN103985117 A CN 103985117A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- target
- parameter
- sensing images
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method for capturing and determining an object based on a remote sensing image. The method comprises the following steps that 1, the remote sensing image in an object area is selected; 2, observation and real-time image-based modeling are carried out on the image based on a sensor of an aircraft air line; 3, the remote sensing image in the object area is automatically changed over; 4, registration is carried out on a dynamic image and the changed remote sensing image; 5, the object is dynamically captured and determined. The remote sensing image is adopted to manufacture a template, object feature information is detailed and can be foreseen, the noise influence can be restrained in the capturing process, and the object is captured and determined under the condition of the low signal-to-noise ratio. According to the method, template comparison and feature determination can be fast executed in a sequential operation mode, and the whole method can be operated at high speed.
Description
Technical field
The present invention relates to target acquistion and the confirmation method in image guidance field, particularly, relate to a kind of target acquistion and confirmation method based on remote sensing images, can be used in TV seeker, the first-class equipment of infrared seeker, compared with fast Acquisition under Low SNR and confirm target.
Background technology
At present, TV seeker and infrared seeker are in the time of target acquistion and confirmation, that the image that obtains according to self is as template, need run-home in advance, according to set threshold value as feature, in image, find target and confirm, then making template, the tracking that follow-up formation is stable according to the target of confirming.The problem one that this method is brought is may catch fall short under the lower state of signal to noise ratio (S/N ratio), the 2nd, need to aim in advance.
In prior art, as the publication number Chinese patent (application number: 201210331861.9), this patent provides a kind of method of the pilot's of raising target acquisition precision, it is characterized in that is 102929287A, comprise the steps: the first step, target seeker start; Second step, pilot manipulation target seeker search target, finds and lock onto target; The 3rd step, when target seeker tenacious tracking target, adopts image zoom technology, and target seeker starts automatically to enter image amplification procedure, generates and amplifies n2 video image doubly for output display; Target seeker when tenacious tracking target, does not repeat second step; The 4th step, video image is just carrying out refine after amplifying.But this technology still cannot solve the above problems.
Remote sensing images, as the technology with its own strategic significance, are more and more subject to the attention of countries in the world, have also obtained application more and more widely.As the publication number Chinese patent (application number: 201310176638.6), this patent provides a kind of Remote Sensing Target monitoring method that is 103268476A; Publication number is 103489191A (application number: 201310449448.7), this patent provides a kind of remote sensing images well-marked target change detecting method.
The present invention adopts remote sensing images to make template, and a kind of target acquistion and confirmation method based on remote sensing images is provided.
Summary of the invention
For defect of the prior art, the object of this invention is to provide a kind of target acquistion and confirmation method based on remote sensing images, can reduce TV, infrared seeker and catch and confirm the signal to noise ratio (S/N ratio) that target is required, improve the acquisition probability of image guidance class target seeker.
For achieving the above object, a kind of target acquistion and confirmation method based on remote sensing images of the present invention, the method adopts the images match method of remote sensing images as initial conditions, specifically comprises the steps:
Step 1, target area remote sensing images are chosen.
First obtain remote sensing images, then, according to aircraft (carrier of target seeker) flight characteristic parameter and sensor parameters, using remote sensing images as basis, automatically generate benchmark image, spotting information on image.
Step 2, sensor based on aircraft course line are observed realtime graphic modeling to target.
Aircraft is bound behind course line in advance, calculates the parameter set of Real-time Motion Image by sensor parameters.The conversion such as realtime graphic only, according to default feature extraction parameter, is not hinted obliquely at, correction.
Step 3, target area remote sensing images auto-changing.
According to aircraft prebriefed pattern, reference sensor parameter, is transformed into the image template consistent with dynamic image feature selected remote sensing benchmark image, with the difference in a dynamic image existence range and region.
Remote sensing image registration after step 4, dynamic image and conversion.
Two images in limited range, same feature are realized registration, set up the quantitative relationship of prophet's information and real-time information.
Step 5, target dynamic are caught and are confirmed.
Image registration is transplanted to target information on remote sensing images benchmark after confirming, forms the template that merges dynamic image data, become the target indication information of aircraft, under this information instruction, through three to five width image duplicate acknowledgments, complete and catch, enter track homing state; Along with distance is approached, there is more information in target imaging on sensor, by repeatedly with remote sensing template database in after information matches, complete final confirmation.
The present invention adopts remote sensing images to make template, and target signature information in detail and can predict, can suppress noise effect in acquisition procedure, and target acquisition realize target are confirmed in compared with low signal-to-noise ratio situation.The inventive method can be carried out template relatively and feature confirmation fast with a kind of pattern of sequential analysis, and whole method can be with speed operation faster.
Compared with prior art, the present invention has following beneficial effect: the target acquistion and the confirmation method that the present invention is based on remote sensing images, can, compared with catching under Low SNR and confirming target, reduce the requirement of target seeker to service condition, improve the usefulness of target acquistion and confirmation.
Brief description of the drawings
By reading the detailed description of non-limiting example being done with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 is target acquistion based on remote sensing images and the process flow diagram of confirmation method.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail.Following examples will contribute to those skilled in the art further to understand the present invention, but not limit in any form the present invention.It should be pointed out that to those skilled in the art, without departing from the inventive concept of the premise, can also make some distortion and improvement.These all belong to protection scope of the present invention.
As shown in Figure 1, the present embodiment provides a kind of target acquistion and confirmation method based on remote sensing images, specific as follows:
Selected application scenarios is assumed to certain type guided missile terminal flight height 5km, and flying speed mach one adopts TV seeker as terminal guidance, 5 ° × 4 ° of TV seeker visual fields.
Step 1, target area remote sensing images are chosen.
First obtain remote sensing images, then, according to aircraft (carrier of target seeker) flight characteristic parameter and sensor parameters, using remote sensing images as basis, automatically generate benchmark image, spotting information on image.
The detailed operation of this step specific implementation is as follows:
Step 1.1: according to mission requirements, extract target area image collection in visible remote sensing image storehouse.
Step 1.2: according to aircraft characteristic parameter, comprise the region that visual field, flying speed, flying height are calculated required image, extract required picture size and resolution in image set, generate benchmark image sequence.Ground image size is not less than 1km, and resolution is chosen and is better than 0.1m, and according to heading, image generally should be chosen and be no less than 8 projecting directions.As not having enough images to use in remote sensing images storehouse, require to have at least 1 width image coverage goal.
Step 1.3: spotting in benchmark image sequence.
Step 2, sensor based on aircraft course line are observed realtime graphic modeling to target.
Aircraft is bound behind course line in advance, calculates the parameter set of Real-time Motion Image by sensor parameters.The conversion such as realtime graphic only, according to default feature extraction parameter, is not hinted obliquely at, correction.
The detailed operation of this step specific implementation is as follows:
Step 2.1: determine dynamic image parameter set according to the parameter of sensor; As: parameter set comprises geometric configuration, object edge yardstick, area, target area contrast, target image spectrum signature etc.;
Step 2.2: using the parameter set of step 2.1 as template, extract characteristic parameter in realtime graphic.
Step 3, target area remote sensing images auto-changing.
According to aircraft prebriefed pattern, reference sensor parameter, is transformed into the image template consistent with dynamic image feature selected remote sensing benchmark image, with the difference in a dynamic image existence range and region.
The detailed operation of this step specific implementation is as follows:
Step 3.1: the picture parameter set forming in read step 2.1;
Step 3.2: remote sensing benchmark image series is extracted to feature according to parameter set in 2.1.
Remote sensing image registration after step 4, dynamic image and conversion.
Two images in limited range, same feature are realized registration, set up the quantitative relationship of prophet's information and real-time information.
The detailed operation of this step specific implementation is as follows:
Step 4.1: according to the scope of realtime graphic in step 2.2, choose relevant feature parameters sequence in remote sensing benchmark image.
Step 4.2: the image features of choosing in the image features in comparison step 2.2 and step 4.1, set up parameter similarity data sequence;
First two argument sequence errors are normalized, then according to square weighting accumulation algorithm as similarity numerical value, computing formula is as formula 1
λ
i----i width remote sensing images matching similarity;
P
ij---j parameter of-i width remote sensing images;
Pt
j---j parameter of-realtime graphic.
Step 5, target dynamic are caught and are confirmed.
Image registration is transplanted to target information on remote sensing images benchmark after confirming, forms the template that merges dynamic image data, become the target indication information of aircraft, under this information instruction, through three to five width image duplicate acknowledgments, complete and catch, enter track homing state; Along with distance is approached, there is more information in target imaging on sensor, by repeatedly with remote sensing template database in after information matches, complete final confirmation.
The detailed operation of this step specific implementation is as follows:
Step 5.1: select remote sensing benchmark image that mxm. corresponding in the similarity data sequence forming in step 4.2.
Step 5.2: adopt weighted sum method to obtain new parameter set remote sensing benchmark image and corresponding realtime graphic real-time parameter, replace remote sensing benchmark image parameter set, form new To Template parameter set, as To Template.
Step 5.3: be as the criterion with fresh target template, mate in realtime graphic, adopt three width images three to sentence two or five width images five and sentence three standard real-time target confirmation, if confirmed successfully, enter autotracking guiding state.
Above-described three sentence two or five sentences three, refer to according to the threshold value of setting, template matches similarity exceedes threshold value and thinks that target described target by template, and in three width images, two width images exceed threshold value through matching similarity and think goal verification success, is three to sentence two; In like manner, five sentence three width images in three expression five width images exceedes threshold value through matching similarity, goal verification success.
Step 5.4: if goal verification is unsuccessful in step 5.3, remove current remote sensing benchmark image, again implement from step 5.1.
The present invention utilizes the basis of satellite remote sensing images as target seeker target image coupling, the method that adopts satellite remote sensing images feature and realtime graphic feature to match, in realization, can adopt sequential programme execution pattern, accelerate travelling speed, improve acquisition probability, can be used for TV, infrared seeker fast Acquisition and confirmation target under low signal-to-noise ratio.
Above specific embodiments of the invention are described.It will be appreciated that, the present invention is not limited to above-mentioned specific implementations, and those skilled in the art can make various distortion or amendment within the scope of the claims, and this does not affect flesh and blood of the present invention.
Claims (6)
1. the target acquistion based on remote sensing images and a confirmation method, is characterized in that, the method adopts the images match method of remote sensing images as initial conditions, specifically comprises the steps:
Step 1, target area remote sensing images are chosen
First obtain remote sensing images, then according to aircraft flight characteristic parameter and sensor parameters, using remote sensing images as basis, automatically generate benchmark image, spotting information on image;
Step 2, sensor based on aircraft course line are observed realtime graphic modeling to target
Aircraft is bound behind course line in advance, calculates the parameter set of Real-time Motion Image by sensor parameters, and realtime graphic is only according to default feature extraction parameter;
Step 3, target area remote sensing images auto-changing
According to aircraft prebriefed pattern, reference sensor parameter, is transformed into the image template consistent with dynamic image feature selected remote sensing benchmark image, with the difference in a dynamic image existence range and region;
Remote sensing image registration after step 4, dynamic image and conversion
Two images in limited range, same feature are realized registration, set up the quantitative relationship of prophet's information and real-time information;
Step 5, target dynamic are caught and are confirmed
Image registration is transplanted to target information on remote sensing images benchmark after confirming, forms the template that merges dynamic image data, become the target indication information of aircraft, under this information instruction, through three to five width image duplicate acknowledgments, complete and catch, enter track homing state; Along with distance is approached, there is more information in target imaging on sensor, by repeatedly with remote sensing template database in after information matches, complete final confirmation.
2. target acquistion and the confirmation method based on remote sensing images according to claim 1, is characterized in that, described step 1, is implemented as follows:
Step 1.1: according to mission requirements, extract target area image collection in remote sensing images storehouse;
Step 1.2: according to aircraft characteristic parameter, comprise the region that visual field, flying speed, flying height are calculated required image, extract required picture size and resolution in image set, generate benchmark image sequence;
Step 1.3: spotting in benchmark image sequence.
3. target acquistion and the confirmation method based on remote sensing images according to claim 1, is characterized in that, described step 2, is implemented as follows:
Step 2.1: determine dynamic image parameter set according to the parameter of sensor, parameter set comprises geometric configuration, object edge yardstick, area, target area contrast, target image spectrum signature;
Step 2.2: using the parameter set of step 2.1 as template, extract characteristic parameter in realtime graphic.
4. target acquistion and the confirmation method based on remote sensing images according to claim 3, is characterized in that, described step 3, is implemented as follows:
Step 3.1: the picture parameter set forming in read step 2.1;
Step 3.2: remote sensing benchmark image series is extracted to feature according to parameter set in step 2.1.
5. target acquistion and the confirmation method based on remote sensing images according to claim 2, is characterized in that, described step 4, is implemented as follows:
Step 4.1: according to the scope of realtime graphic in step 2.2, the characteristic parameter sequence that extraction step 2.1 is described in remote sensing benchmark image;
Step 4.2: the image features of choosing in the image features in comparison step 2.2 and step 4.1, set up parameter similarity data sequence.
6. target acquistion and the confirmation method based on remote sensing images according to claim 5, is characterized in that, described step 5, is implemented as follows:
Step 5.1: select remote sensing benchmark image that mxm. corresponding in the similarity data sequence forming in step 4.2;
Step 5.2: remote sensing benchmark image and corresponding realtime graphic real-time parameter are merged, replace remote sensing benchmark image parameter set, form new To Template parameter set, as To Template;
Step 5.3: be as the criterion with fresh target template, mate in realtime graphic, adopt three width images three to sentence two or five width images five and sentence three standard real-time target confirmation, if confirmed successfully, enter autotracking guiding state;
Step 5.4: if goal verification is unsuccessful in step 5.3, remove current remote sensing benchmark image, again implement from step 5.1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410175257.0A CN103985117A (en) | 2014-04-28 | 2014-04-28 | Method for capturing and determining object based on remote sensing image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410175257.0A CN103985117A (en) | 2014-04-28 | 2014-04-28 | Method for capturing and determining object based on remote sensing image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103985117A true CN103985117A (en) | 2014-08-13 |
Family
ID=51277075
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410175257.0A Pending CN103985117A (en) | 2014-04-28 | 2014-04-28 | Method for capturing and determining object based on remote sensing image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103985117A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019042067A1 (en) * | 2017-08-29 | 2019-03-07 | 深圳市大疆创新科技有限公司 | Aerial vehicle control method, aerial vehicle, program and recording medium |
CN112149753A (en) * | 2020-10-07 | 2020-12-29 | 智博云信息科技(广州)有限公司 | Remote sensing image data processing method and system and cloud platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5430455A (en) * | 1991-08-30 | 1995-07-04 | Gfc Alsthom S A | Microwave location system |
CN101726298A (en) * | 2009-12-18 | 2010-06-09 | 华中科技大学 | Three-dimensional landmark selection and reference map preparation method for front-view navigation guidance |
CN103093193A (en) * | 2012-12-28 | 2013-05-08 | 中国航天时代电子公司 | Space image guided weapon object identification method |
CN103268496A (en) * | 2013-06-08 | 2013-08-28 | 中国人民解放军国防科学技术大学 | Target identification method of SAR (synthetic aperture radar) images |
CN103473787A (en) * | 2013-07-29 | 2013-12-25 | 华中科技大学 | On-bridge-moving-object detection method based on space geometry relation |
-
2014
- 2014-04-28 CN CN201410175257.0A patent/CN103985117A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5430455A (en) * | 1991-08-30 | 1995-07-04 | Gfc Alsthom S A | Microwave location system |
CN101726298A (en) * | 2009-12-18 | 2010-06-09 | 华中科技大学 | Three-dimensional landmark selection and reference map preparation method for front-view navigation guidance |
CN103093193A (en) * | 2012-12-28 | 2013-05-08 | 中国航天时代电子公司 | Space image guided weapon object identification method |
CN103268496A (en) * | 2013-06-08 | 2013-08-28 | 中国人民解放军国防科学技术大学 | Target identification method of SAR (synthetic aperture radar) images |
CN103473787A (en) * | 2013-07-29 | 2013-12-25 | 华中科技大学 | On-bridge-moving-object detection method based on space geometry relation |
Non-Patent Citations (2)
Title |
---|
任三孩: "弹载SAR景象匹配制导关键技术研究", 《中国博士学位论文全文数据库(信息科技辑)》 * |
陈浩: "图像制导***图像匹配算法研究", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019042067A1 (en) * | 2017-08-29 | 2019-03-07 | 深圳市大疆创新科技有限公司 | Aerial vehicle control method, aerial vehicle, program and recording medium |
CN112149753A (en) * | 2020-10-07 | 2020-12-29 | 智博云信息科技(广州)有限公司 | Remote sensing image data processing method and system and cloud platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9817107B2 (en) | Above-ground building recognition method and navigation method combining laser and infrared | |
CN102393912B (en) | Comprehensive target identification method based on uncertain reasoning | |
CN103679674A (en) | Method and system for splicing images of unmanned aircrafts in real time | |
CN103824302A (en) | SAR (synthetic aperture radar) image change detecting method based on direction wave domain image fusion | |
CN101799968A (en) | Detection method and device for oil well intrusion based on video image intelligent analysis | |
CN109375177A (en) | A kind of moving target detecting method for airport surface detection radar system | |
CN109711256B (en) | Low-altitude complex background unmanned aerial vehicle target detection method | |
CN102867309A (en) | SAR (Synthetic Aperture Radar) image change detection method based on mixing model | |
CN103593679A (en) | Visual human-hand tracking method based on online machine learning | |
CN111323756B (en) | Marine radar target detection method and device based on deep learning | |
CN104574335A (en) | Infrared and visible image fusion method based on saliency map and interest point convex hulls | |
CN116958907B (en) | Method and system for inspecting surrounding hidden danger targets of gas pipeline | |
CN104569923B (en) | Velocity restraint-based Hough transformation fast track starting method | |
CN105787470A (en) | Method for detecting power transmission line tower in image based on polymerization multichannel characteristic | |
CN106156467A (en) | Lower whorl shelves time detecting method and system on aircraft based on ADSB | |
CN104881561A (en) | Hough transform-based track-before-detect method of multidimensional parameters | |
CN111323757B (en) | Target detection method and device for marine radar | |
CN112907520A (en) | Single tree crown detection method based on end-to-end deep learning method | |
CN105116394A (en) | Object trace point extraction method based on multi-dimensional fine characteristic analysis | |
CN105354824A (en) | Region extraction-based two-parameter constant false alarm detection method | |
US11519853B2 (en) | Method for evaluating the suitability for power generation using biogas, server and system using the same | |
CN103985117A (en) | Method for capturing and determining object based on remote sensing image | |
CN108073865B (en) | Aircraft trail cloud identification method based on satellite data | |
CN111325076B (en) | Aviation ground building extraction method based on fusion of U-net and Seg-net networks | |
CN104537690A (en) | Moving point target detection method based on maximum value-time index combination |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Inventor after: Xue Haizhong Inventor after: Zhang Huanqin Inventor after: Dong Xiaoyan Inventor before: Xue Haizhong Inventor before: Zhang Huanqin Inventor before: Shen Yan |
|
CB03 | Change of inventor or designer information | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140813 |
|
WD01 | Invention patent application deemed withdrawn after publication |