CN107607203B - Conspicuousness band selection method based on structural similarity - Google Patents
Conspicuousness band selection method based on structural similarity Download PDFInfo
- Publication number
- CN107607203B CN107607203B CN201710803169.4A CN201710803169A CN107607203B CN 107607203 B CN107607203 B CN 107607203B CN 201710803169 A CN201710803169 A CN 201710803169A CN 107607203 B CN107607203 B CN 107607203B
- Authority
- CN
- China
- Prior art keywords
- band
- wave band
- wave
- sub
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of conspicuousness band selection method based on structural similarity, comprising the following steps: Step 1: using the target in hyperspectral remotely sensed image data Jing Guo denoising；Step 2: being ranked up from high to low to image all band by selected target region in the significant difference degree of each wave band；Step 3: being screened two-by-two based on structural similarity to Band Set after sequence, the removal wave band that similarity is big and significance is low；Step 4: selecting preceding several wave bands of wave band collection after screening, waveband selection is completed.The present invention is accordingly ranked up all wave bands using the significance apart from each wave band target area of significant transformation calculations, and screens the biggish wave band of similarity, the final preceding several wave bands chosen after screening by structural similarity.Such band selection method can obtain different waveband selections towards different target, preferably promotion succeeding target detection effect.
Description
Technical field
The present invention relates to remote sensing fields, specifically make a kind of succeeding target detection effect preferably band selection method.
Background technique
Conspicuousness refers to based under human vision cognition system, diversity factor of the target relative to background, when target is more held
Easily notice that its brightness in notable figure is higher by human eye, it is also more significant.Significance has measured the difference of target and background
Degree, it is clear that significance is higher, and target is more easily detected.Vision significance transformation, will be former i.e. by range conversion function
Figure is transformed to significant distance map, and each point pixel value is the significance of the point in original image in notable figure.
If high spectrum image thinks investment application, it is necessary first to which the redundancy for rejecting initial data will be believed in not weight losses
Reduce the dimension of data in the case where breath as far as possible, main method is divided into waveband selection and feature extraction two major classes, and wave band
Selection remains the physical meaning and the spectral charactersitics of targets of original wave band relative to feature extraction.Existing band selection method
It is to estimate with the diversity factor between the information content and wave band of wave band itself, it is desirable to choose that self-information amount is big, difference between each wave band
Spend big wave band.However existing method is not directed to specific objective information, chooses the wave band for being more suitable for specific objective detection.
Summary of the invention
The present invention provides a kind of significant difference degree waveband selection side to overcome drawbacks described above existing in the prior art
Method calculates the significance of each wave band target area and is ranked up accordingly to all wave bands, and screens phase by structural similarity
Like biggish wave band is spent, preceding several wave bands after screening are finally chosen.Such band selection method can towards different target,
Different waveband selections is obtained, preferably promotion succeeding target detection effect.
To solve the above problems, significant difference degree band selection method proposed by the present invention, comprising the following steps:
Step 1: using the target in hyperspectral remotely sensed image data Jing Guo denoising；
Step 2: asking selected target region in the visual saliency of each wave band, according to each wave band visual saliency by up to
It is low that image all band is ranked up；
Step 3: being screened two-by-two based on structural similarity to Band Set after sequence, removal similarity is big and significant
Spend low wave band；
Step 4: selecting preceding several wave bands of wave band collection after screening, waveband selection is completed, the bloom of wave band number reduction is obtained
Compose remote sensing image.
In above-mentioned technical proposal, the significant difference degree of foundation is sought when the step 2 carries out band ordering, is used aobvious
The range conversion of work property.The wave band screening that step 3 carries out, estimating for two wave band similarity degrees is structural similarity.
In above scheme, significant difference degree band ordering specifically includes following sub-step in the step 2:
Sub-step S21, target region on image is chosen；
Sub-step S22, each wave band is regarded as different images, carries out the transformation of view-based access control model conspicuousness respectively；
Sub-step S23, it averages to each point significance in target region, obtains average significance；
Sub-step S24, the significance that is averaged according to each wave band are from high to low ranked up all wave bands of image.
In above scheme, the wave band screening based on structural similarity of the step 3 specifically includes following sub-step:
Sub-step S31, shape similarity is sought two-by-two to Band Set after sequence
Wherein μx、μyIt is the pixel average of x, y band image respectively；It is the variance of x, y band image, σxyIt is two images
Covariance.
Sub-step S32, it is screened according to threshold value, if structural similarity is greater than given threshold, deletes in two wave bands and show
The smaller wave band of work degree, that is, serial number is in wave band below
Beneficial effects of the present invention:
Conspicuousness band selection method proposed by the present invention based on structural similarity, for specific objective, to each wave band
The significant difference degree mean value of target area is sought, and all wave bands of image are ranked up according to mean value, the wave band filtered out in this way,
Target is all more prominent for background, and target detection effect is improved.Then redundancy is weeded out by shape similarity
Big wave band is spent, so that it is smaller to select band class information redundancy.
The present invention can finally obtain the image of wave band number reduction, which remains original image information well, and
Better effect can be obtained in target detection, i.e., the present invention processing after image can higher efficiency, in high quality carry out after
Continuous target detection.
Specific embodiment
Below in conjunction with specific embodiment, the present invention is described in further detail:
In the present embodiment, the conspicuousness band selection method proposed by the present invention based on structural similarity, including following step
It is rapid:
Step 1: using the target in hyperspectral remotely sensed image data Jing Guo denoising；
Step 2: asking selected target region in the visual saliency of each wave band, according to each wave band visual saliency by up to
It is low that image all band is ranked up；
Step 3: being screened two-by-two based on structural similarity to Band Set after sequence, removal similarity is big and significant
Spend low wave band；
Step 4: selecting preceding several wave bands of wave band collection after screening, waveband selection is completed, the bloom of wave band number reduction is obtained
Compose remote sensing image.
Significant difference degree band ordering specifically includes following sub-step in step 2:
Sub-step S21, for the subsequent vehicle target to be detected, optionally take one piece of area on image where target
Domain；
Sub-step S22, each wave band is regarded as different images, carries out the transformation of view-based access control model conspicuousness respectively, use base here
In the conspicuousness range conversion of minimum distance of obstacleWherein π
() is some point being linked to be on path from target point to image border background dot, and f (π ()) is the pixel value of the point.Each
Each pixel of band image can access the significant angle value of correspondence.
Sub-step S23, it each wave band is regarded as different images is handled as follows respectively: to vehicle target optional in image
Each pixel corresponds to significance and averages in region, obtains average significance；
Sub-step S24, the significance that is averaged according to each wave band are from high to low ranked up all wave bands of image.
In above scheme, the wave band screening based on structural similarity of the step 3 specifically includes following sub-step:
Sub-step S31, shape similarity is sought two-by-two to Band Set after sequence
Wherein μx、μyIt is the pixel average of x, y band image respectively；It is the variance of x, y band image, σxyIt is two images
Covariance；
Sub-step S32, it is screened according to threshold value, selected threshold is 0.95 here, if structural similarity is greater than setting threshold
Value 0.95 then deletes the smaller wave band of significance in two wave bands, that is, serial number in wave band below.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to compared with
Good embodiment describes the invention in detail, those skilled in the art should understand that, it can be to skill of the invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of technical solution of the present invention, should all be covered at this
In the scope of the claims of invention.
Claims (2)
1. a kind of conspicuousness band selection method based on structural similarity, which comprises the following steps:
Step 1: using the target in hyperspectral remotely sensed image data Jing Guo denoising；
Step 2: ask selected target region in the visual saliency of each wave band, it is right from high to low according to each wave band visual saliency
Image all band is ranked up, and specifically includes following sub-step:
Sub-step S21, target region on image is chosen；
Sub-step S22, each wave band is regarded as different images, carries out the transformation of view-based access control model conspicuousness respectively；
Sub-step S23, it averages to each point significance in target region, obtains average significance；
Sub-step S24, the significance that is averaged according to each wave band are from high to low ranked up all wave bands of image；
Step 3: being screened two-by-two based on structural similarity to Band Set after sequence, removal similarity is big and significance is low
Wave band, specifically include following sub-step:
Sub-step S31, shape similarity is sought two-by-two to Band Set after sequence；
Wherein、It is the pixel average of x, y band image respectively；、It is the variance of x, y band image,It is two figures
The covariance of picture；
Sub-step S32, it is screened according to threshold value, if structural similarity is greater than given threshold, deletes significance in two wave bands
Smaller wave band, that is, serial number is in wave band below；
Step 4: selecting preceding several wave bands of wave band collection after screening, waveband selection is completed, the EO-1 hyperion for obtaining wave band number reduction is distant
Feel image.
2. the conspicuousness band selection method according to claim 1 based on structural similarity, which is characterized in that the step
In rapid two by target area visual saliency to wave band be ranked up preferably and step 3 screened by structural similarity it is similar
Spend big wave band.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710803169.4A CN107607203B (en) | 2017-09-08 | 2017-09-08 | Conspicuousness band selection method based on structural similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710803169.4A CN107607203B (en) | 2017-09-08 | 2017-09-08 | Conspicuousness band selection method based on structural similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107607203A CN107607203A (en) | 2018-01-19 |
| CN107607203B true CN107607203B (en) | 2019-08-06 |
Family
ID=61063101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710803169.4A Active CN107607203B (en) | 2017-09-08 | 2017-09-08 | Conspicuousness band selection method based on structural similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107607203B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116563571B (en) * | 2023-05-16 | 2023-11-21 | 北京师范大学 | Boltzmann entropy similarity-based hyperspectral image band selection method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007265248A (en) * | 2006-03-29 | 2007-10-11 | Toshiba Corp | Structured document management device, structured document sub management device, program and structured document managing method |
| CN102096180A (en) * | 2009-12-11 | 2011-06-15 | 奥林巴斯株式会社 | Super-resolution microscope |
| CN106204510A (en) * | 2016-07-08 | 2016-12-07 | 中北大学 | A kind of infrared polarization based on structural similarity constraint and intensity image fusion method |
| CN106525238A (en) * | 2016-10-27 | 2017-03-22 | 中国科学院光电研究院 | Spaceborne multispectral imaging system design method based on super-resolution reconstruction |
-
2017
- 2017-09-08 CN CN201710803169.4A patent/CN107607203B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007265248A (en) * | 2006-03-29 | 2007-10-11 | Toshiba Corp | Structured document management device, structured document sub management device, program and structured document managing method |
| CN102096180A (en) * | 2009-12-11 | 2011-06-15 | 奥林巴斯株式会社 | Super-resolution microscope |
| CN106204510A (en) * | 2016-07-08 | 2016-12-07 | 中北大学 | A kind of infrared polarization based on structural similarity constraint and intensity image fusion method |
| CN106525238A (en) * | 2016-10-27 | 2017-03-22 | 中国科学院光电研究院 | Spaceborne multispectral imaging system design method based on super-resolution reconstruction |
Non-Patent Citations (1)
| Title |
|---|
| 基于结构相似度的视觉显著性检测方法;李崇飞等;《计算机工程与科学》;20131031;第35卷(第10期);全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107607203A (en) | 2018-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10635929B2 (en) | Saliency-based method for extracting road target from night vision infrared image | |
| CN107918927B (en) | Matching strategy fusion and low-error rapid image splicing method | |
| CN104134200B (en) | Mobile scene image splicing method based on improved weighted fusion | |
| CN103745449A (en) | Rapid and automatic mosaic technology of aerial video in search and tracking system | |
| CN102509262B (en) | Method for removing thin cloud of remote sensing image | |
| CN103093444A (en) | Image super-resolution reconstruction method based on self-similarity and structural information constraint | |
| CN105989611B (en) | The piecemeal perceptual hash tracking of hatched removal | |
| CN106846289A (en) | A kind of infrared light intensity and polarization image fusion method based on conspicuousness migration with details classification | |
| CN105976330A (en) | Embedded foggy-weather real-time video image stabilization method | |
| CN103927741A (en) | SAR image synthesis method for enhancing target characteristics | |
| CN107609571B (en) | Adaptive target tracking method based on LARK features | |
| CN112184604A (en) | Color image enhancement method based on image fusion | |
| CN107610093B (en) | Full-reference image quality evaluation method based on similarity feature fusion | |
| CN102236785B (en) | Method for pedestrian matching between viewpoints of non-overlapped cameras | |
| CN107527370A (en) | A kind of method for tracking target based on camshift | |
| CN105469392B (en) | High spectrum image conspicuousness detection method based on the comparison of region spectrum Gradient Features | |
| CN109215003B (en) | Image fusion method and device | |
| CN108171656A (en) | Adaptive Global Dictionary remote sensing images ultra-resolution method based on rarefaction representation | |
| CN109886336A (en) | A kind of object detection method and system based on warship basic image | |
| CN107607203B (en) | Conspicuousness band selection method based on structural similarity | |
| CN106780326A (en) | A kind of fusion method for improving panoramic picture definition | |
| CN109635809B (en) | Super-pixel segmentation method for visual degradation image | |
| CN111311503A (en) | Night low-brightness image enhancement system | |
| CN109946670A (en) | A kind of polarization radar information extracting method of optical image driving | |
| CN105528772B (en) | A kind of image interfusion method based on directiveness filtering |
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 |