CN106709426A - Ship target detection method based on infrared remote sensing image - Google Patents
Ship target detection method based on infrared remote sensing image Download PDFInfo
- Publication number
- CN106709426A CN106709426A CN201611076345.0A CN201611076345A CN106709426A CN 106709426 A CN106709426 A CN 106709426A CN 201611076345 A CN201611076345 A CN 201611076345A CN 106709426 A CN106709426 A CN 106709426A
- Authority
- CN
- China
- Prior art keywords
- image
- ship target
- target
- ship
- remote sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention puts forward a ship target detection method based on an infrared remote sensing image. The method comprises the following steps that: S1: carrying out water-coast separation on an infrared remote sensing image, and segmenting a sea area image which contains a ship target; S2: carrying out contrast enhancement processing on the sea area image obtained after the water-coast separation is carried out, highlighting the ship target in the image, and selecting the candidate area of the ship target according to the highlighted ship target; and S3: determining a ship suspected target in the candidate area, and extracting the ship target according to the personalized features of the ship. Under a situation of complex background interference including wind waves, cloud backgrounds, ship tracks, solar flares, islands and the like, the ship target can be accurately detected in real time.
Description
Technical field
It is more particularly to a kind of to be based on infrared remote sensing the present invention relates to the target detection identification technology of infrared remote sensing image domains
The Ship Target Detection method of image.
Background technology
Although the Ship Target Detection based on infrared remote sensing image is started to walk than later with identification technology research, with load
The continuous improvement of resolution ratio, high-resolution Thermo-imaging system show in terms of the Ship Recognition prominent advantage and it is wide before
Scape.At present, the Ship Target Detection based on infrared remote sensing image under complex background is still a difficult point；On the one hand due to ocean face
Product is big, and the naval vessel information on sea is enriched very much, causes data volume very big, the existing inspection based on naval vessel histogram hangover property
Survey method and the detection method based on C-V Threshold segmentations take very much, are unfavorable for real-time processing；On the other hand due to by wind
The interference of the factor such as wave, cloud background, ship Wake, solar flare, island, often leads to false-alarm when naval vessel is detected more.
The content of the invention
The technical problems to be solved by the invention how are overcome in stormy waves, cloud background, ship Wake, solar flare, sea
In the case that the complex backgrounds such as island are disturbed, exactly, Ship Target is detected in real time.
To solve the above problems, the present invention proposes a kind of Ship Target Detection method based on infrared remote sensing image, including
Following steps：
S1：Waterfront separation is carried out to infrared remote sensing image, by the marine site image segmentation comprising Ship Target out；
S2：The marine site image obtained after being separated to waterfront carries out contrast enhancement processing, protrudes the Ship Target in image,
According to the candidate region of the selected Ship Target of prominent Ship Target；
S3：Naval vessel suspected target is determined from the candidate region, Ship Target is extracted according to naval vessel individualized feature.
According to one embodiment of present invention, in the step S1, the picture frequency spectrum intermediate frequency according to infrared remote sensing image
Image is divided into pelagic division, land part and extra large land mixing portion by image entropy statistics of the rate in the range of setting frequency range,
Determine coastline by edge extracting, by marine site image segmentation out.
According to one embodiment of present invention, the step S1 is comprised the following steps：
S11：By infrared remote sensing image segmentation into some image fritters, spectrum calculation is carried out to each image fritter, calculated
Image entropy of the frequency in the range of setting frequency range, and cumulative statistics is carried out, try to achieve the image entropy total value of each image fritter；
S12：The image entropy total value of each image fritter is compared with default upper threshold value and default lower threshold value, image entropy is total
The image fritter that value is less than default lower threshold value is judged to pelagic division, and the image fritter that image entropy is more than default upper threshold value is assert
It is land part, remaining image fritter is judged to extra large land mixing portion；
S13：The border of extra large Lu Bianhua of image fritter is extracted as seed point, region growing is carried out, coastline is sketched the contours of
Realize that waterfront is separated, by the marine site image segmentation comprising Ship Target out.
According to one embodiment of present invention, the setting frequency range scope is 4~20Hz.
According to one embodiment of present invention, in the step S2, by being separated to waterfront after obtain marine site image enter
Row Top-Hat is converted and Bottom-Hat conversion, the grey-scale contrast of enhancing Ship Target and marine background, prominent naval vessel mesh
Mark.
According to one embodiment of present invention, naval vessel suspected target is determined from the candidate region in the step S3
Comprise the following steps：
S31：Image to Ship Target candidate region carries out Top-Hat conversion process；
S32：Grayscale reconstruction is carried out to the image after conversion process；
S33：Image to rebuilding enters row threshold division, determines naval vessel suspected target.
According to one embodiment of present invention, optimal naval vessel mesh is extracted according to naval vessel individualized feature in the step S3
Mark is comprised the following steps：
S34：For the image of Threshold segmentation, the elemental area in each UNICOM region is counted, retain elemental area in target
UNICOM region in UNICOM's setting range, rejects remaining UNICOM region, and target UNICOM setting range is according to Ship Target
Depending on size；
S35：The skeleton in the UNICOM region for retaining is extracted, the length-width ratio of skeleton is calculated, reservation meets the setting of target length-width ratio
The skeleton of scope, rejects remaining skeleton, depending on target length-width ratio setting range is according to Ship Target skeleton length-width ratio；
S36：Calculate the grey scale change of the skeleton for retaining, by gray scale is unchanged and backbone length more than preset length value bone
Frame is rejected, and retains remaining target skeleton；
S37：Image according to Threshold segmentation in the target skeleton and step S34 retained in step S36 carries out morphology weight
Build, so as to extract Ship Target.
According to one embodiment of present invention, in the step S34, morphology is first carried out for the image of Threshold segmentation swollen
After swollen, then count the elemental area in each UNICOM region.
After adopting the above technical scheme, the present invention has the advantages that compared to existing technology：
1) by waterfront split reduce Ship Target Detection scope, then to split image carry out denoising, suppress
Ocean background noise, strengthens Ship Target, and false-alarm is removed finally according to Ship Target feature, extracts real Ship Target, drop
The false alarm rate of low naval vessel detection, is adapted to the Ship Target Detection of complex environment；
2) gray scale in waterfront region, textural characteristics difference is not obvious, adds the interference of naval vessel shade, it is difficult to extracts complete
Waterfront profile, compose statistics by the way that segmented areas are carried out with image, image is divided into smooth, complicated and mixing three parts, base
In priori, smooth is seawater, and complicated part is land, and the seed point for calculating mixing portion carries out region growing, will
Waterfront is complete to be split, can quickly Ground Split land and ocean, improve naval vessel detection efficiency；
3) according to the feature of Ship Target, by connected region differentiation, skeletal extraction, length-width ratio judgement, greyness discriminance etc.
Method, the detection method has very strong adaptability by real Ship Target Detection out.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the Ship Detection based on infrared remote sensing image of one embodiment of the invention；
Fig. 2 is the schematic flow sheet of the waterfront segmentation of one embodiment of the invention；
Fig. 3 a, 3b are the different images fritter and its image spectrum schematic diagram of the embodiment of the present invention；
Fig. 4 is the design sketch of the image after original image and segmentation；
Fig. 5 is the design sketch that background suppresses and carried out again to background histamine result gray scale reconstruction；
Fig. 6 is the schematic flow sheet that Ship Target Detection confirms；
Fig. 7 is segmentation and recognition effect figure under different background disturbed condition.
Specific embodiment
To enable the above objects, features and advantages of the present invention more obvious understandable, below in conjunction with the accompanying drawings to the present invention
Specific embodiment be described in detail.
Elaborate many details in order to fully understand the present invention in the following description.But the present invention can be with
Much it is different from other manner described here to implement, those skilled in the art can be in the situation without prejudice to intension of the present invention
Under do similar popularization, therefore the present invention is not limited by following public specific implementation.
Referring to Fig. 1, in one embodiment, the Ship Target Detection method based on infrared remote sensing image includes following step
Suddenly：
S1：Waterfront separation is carried out to infrared remote sensing image, by the marine site image segmentation comprising Ship Target out；
S2：The marine site image obtained after being separated to waterfront carries out contrast enhancement processing, protrudes the Ship Target in image,
According to the candidate region of the selected Ship Target of prominent Ship Target；
S3：Naval vessel suspected target is determined from the candidate region, Ship Target is extracted according to naval vessel individualized feature.
In step sl, infrared remote sensing image can be obtained by existing infrared remote sensing image collecting device, but not made
It is limitation, it is also possible to obtained by other channels.Waterfront separation, primary segmentation ocean and land are carried out to infrared remote sensing image first
Ground, by the marine site image segmentation comprising Ship Target out, reduces the scope of Ship Target Detection.Marine site image contains naval vessel
Target information and ocean background noise, so that further rejecting ocean background noise.
In one embodiment, in step sl, the statistical analysis primary segmentation ocean and land composed by picture frequency,
With specific reference to image entropy statistics of the frequency in the range of setting frequency range in the picture frequency spectrum of infrared remote sensing image by image
It is divided into pelagic division, land part and extra large land mixing portion, coastline is determined by edge extracting, marine site image segmentation is gone out
Come.The gray scale in waterfront region, textural characteristics difference is not obvious, adds the interference of naval vessel shade, it is difficult to extracts complete waterfront
Profile, statistics is composed by carrying out image to image, and image is divided into smooth, complicated and mixing three parts, based on priori,
Smooth is seawater, and complicated part is land, and carrying out edge extracting according to this primary segmentation can be by the complete Ground Split of waterfront
Out.
Referring to Fig. 2, in one embodiment, step S1 is further comprising the steps：
S11：By infrared remote sensing image segmentation into some image fritters, spectrum calculation is carried out to each image fritter, calculated
Image entropy of the frequency in the range of setting frequency range, and cumulative statistics is carried out, try to achieve the image entropy total value of each image fritter；
S12：The image entropy total value of each image fritter is compared with default upper threshold value and default lower threshold value, image entropy is total
The image fritter that value is less than default lower threshold value is judged to pelagic division, and the image fritter that image entropy is more than default upper threshold value is assert
It is land part, remaining image fritter is judged to extra large land mixing portion；
S13：The border of extra large Lu Bianhua of image fritter is extracted as seed point, region growing is carried out, coastline is sketched the contours of
Realize that waterfront is separated, by the marine site image segmentation comprising Ship Target out.
Specifically, in step s 11, infrared remote sensing image segmentation into the image fritter of 50 × 50 can be distinguished
The picture frequency spectrum for obtaining each image fritter is calculated, each image entropy of image fritter frequency in the range of setting frequency range is entered
Row is calculated and cumulative statistics, obtains the image entropy total value of each image fritter.Preferably, setting frequency range scope is 4~20Hz, should
Frequency spectrum in frequency range is particularly suited for extra large land graphical analysis.
In step s 12, the image entropy total value of each image fritter is compared with default upper threshold value and default lower threshold value, is joined
The land image of Fig. 3 a and the ocean imagery of 3b are seen, because the entropy of land image is than larger, the entropy of ocean imagery is smaller, is based on
This, pelagic division is judged to by the image fritter that image entropy total value is less than default lower threshold value, and image entropy is more than into default upper threshold value
Image fritter regard as land part, remaining image fritter is judged to extra large land mixing portion.Preset upper threshold value and set threshold in advance
Value can set according to test of many times experience accumulation, specifically without limitation.
In step s 13, the border of extra large Lu Bianhua of image fritter is extracted as seed point, such as by image binaryzation
Reason, the border for extracting 0~1 change carries out region growing as seed point, and the border of 0~1 change can refer to pelagic division
Extra large land boundary in the intersection of the image fritter of image fritter and land part, or the image fritter of extra large land mixing portion
Line, accurately coastline is sketched the contours of after region growing, realizes that waterfront is separated, by the marine site image segmentation comprising Ship Target out,
Referring to the image after the original image in Fig. 4 and segmentation.It is normal image treatment technology to carry out region growing according to seed point,
This is repeated no more.
In step s 2, the marine site image obtained after being separated to waterfront carries out contrast enhancement processing, in prominent image
Ship Target, according to the candidate region of the selected Ship Target of prominent Ship Target.
In one embodiment, in step S2, due to doing for the ocean background noises such as solar flare, stormy waves, ship Wake
Disturb, Ship Target is carried out image segmentation recognize when can produce false alarm rate very high, by being separated to waterfront after obtain sea
Area image carry out Top-Hat conversion (image after opening operation, a kind of mode of image enhaucament are subtracted from original image) and
Bottom-Hat converts (subtracting each other through the image after closed operation and original image, a kind of mode of image enhaucament), strengthens Ship Target
With the grey-scale contrast of marine background, suppress ambient noise, protrude Ship Target, so that it is determined that the candidate region of Ship Target,
Naval vessel detection range is further reduced, candidate region can be the region as small as possible comprising prominent Ship Target.Fig. 5 is
The image with complicated ocean background noise after being separated to waterfront carries out the design sketch (left side) after background suppression and background is pressed down
The design sketch (right side) that gray scale after system is rebuild.
WTH (x)=(f-fg) (x) (1)
BTH (x)=(fg-f) (x) (2)
Wherein, (1) is Top-Hat transformation for mula, and (2) are Bottom-Hat transformation for mula, and f is gradation of image, and fg is the back of the body
Scape gray scale, x is Ship Target.
In step s3, naval vessel suspected target is determined from candidate region, naval vessel mesh is extracted according to naval vessel individualized feature
Mark.First determine that naval vessel suspected target can mitigate the complexity of individualized feature analysis.
Referring to Fig. 6, in one embodiment, determine that naval vessel suspected target is further wrapped from candidate region in step S3
Include following steps：
S31：Image to Ship Target candidate region carries out Top-Hat conversion process；
S32：Grayscale reconstruction is carried out to the image after conversion process；
S33：Image to rebuilding enters row threshold division, determines naval vessel suspected target.
Threshold segmentation can be image binary segmentation, and naval vessel suspected target is determined whether by the gray scale of binaryzation.
In one embodiment, with continued reference to Fig. 6, optimal naval vessel mesh is extracted according to naval vessel individualized feature in step S3
Mark is further comprising the steps：
S34：For the image of Threshold segmentation, the elemental area in each UNICOM region is counted, retain elemental area in target
UNICOM region in UNICOM's setting range, rejects remaining UNICOM region, and target UNICOM setting range is according to Ship Target
Depending on size；
S35：The skeleton in the UNICOM region for retaining is extracted, the length-width ratio of skeleton is calculated, reservation meets the setting of target length-width ratio
The skeleton of scope, rejects remaining skeleton, depending on target length-width ratio setting range is according to Ship Target skeleton length-width ratio；Target length and width
It is such as, but not limited to less than 5 than setting range；
S36：Calculate the grey scale change of the skeleton for retaining, by gray scale is unchanged and backbone length more than preset length value bone
Frame is rejected, and retains remaining target skeleton；Preset length value is such as, but not limited to more than 30；
S37：Image according to Threshold segmentation in the target skeleton and step S34 retained in step S36 carries out morphology weight
Build, so as to extract Ship Target.
Referring to Fig. 7, the image after Threshold segmentation is carried out into morphological dilations, reject the undesirable connected region of size
Domain, skeletal extraction is carried out to satisfactory connected region, calculates length-width ratio and grey scale change, rejects undesirable falseness
Target, reduces false alarm rate, identifies real Ship Target.The detection method local adaptability, extracts Ship Target exactly,
Reduce the false alarm rate of naval vessel detection.
In one embodiment, in step S34, after first carrying out morphological dilations for the image of Threshold segmentation, then carry out
Count the elemental area in each UNICOM region.
Although the present invention is disclosed as above with preferred embodiment, it is not for limiting claim, any this area
Technical staff without departing from the spirit and scope of the present invention, can make possible variation and modification, therefore of the invention
The scope that protection domain should be defined by the claims in the present invention is defined.
Claims (8)
1. a kind of Ship Target Detection method based on infrared remote sensing image, it is characterised in that comprise the following steps：
S1：Waterfront separation is carried out to infrared remote sensing image, by the marine site image segmentation comprising Ship Target out；
S2：The marine site image obtained after being separated to waterfront carries out contrast enhancement processing, protrudes the Ship Target in image, according to
The candidate region of the selected Ship Target of prominent Ship Target；
S3：Naval vessel suspected target is determined from the candidate region, Ship Target is extracted according to naval vessel individualized feature.
2. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 1, it is characterised in that the step
In S1, image entropy statistics of the frequency in the range of setting frequency range is by image in picture frequency according to infrared remote sensing image spectrum
It is divided into pelagic division, land part and extra large land mixing portion, coastline is determined by edge extracting, marine site image segmentation is gone out
Come.
3. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 1 or 2, it is characterised in that described
Step S1 is comprised the following steps：
S11：By infrared remote sensing image segmentation into some image fritters, spectrum calculation is carried out to each image fritter, calculate frequency
Image entropy in the range of setting frequency range, and cumulative statistics is carried out, try to achieve the image entropy total value of each image fritter；
S12：The image entropy total value of each image fritter is compared with default upper threshold value and default lower threshold value, image entropy total value is small
It is judged to pelagic division in the image fritter of default lower threshold value, the image fritter that image entropy is more than default upper threshold value is regarded as into land
Ground part, remaining image fritter is judged to extra large land mixing portion；
S13：The border of extra large Lu Bianhua of image fritter is extracted as seed point, region growing is carried out, coastline realization is sketched the contours of
Waterfront is separated, by the marine site image segmentation comprising Ship Target out.
4. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 3, it is characterised in that the setting
Band limits is 4~20Hz.
5. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 1, it is characterised in that the step
In S2, by being separated to waterfront after obtain marine site image carry out Top-Hat conversion and Bottom-Hat conversion, strengthen naval vessel mesh
The grey-scale contrast of mark and marine background, prominent Ship Target.
6. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 1, it is characterised in that the step
Determine that naval vessel suspected target is comprised the following steps from the candidate region in S3：
S31：Image to Ship Target candidate region carries out Top-Hat conversion process；
S32：Grayscale reconstruction is carried out to the image after conversion process；
S33：Image to rebuilding enters row threshold division, determines naval vessel suspected target.
7. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 6, it is characterised in that the step
Being comprised the following steps according to the naval vessel individualized feature optimal Ship Target of extraction in S3：
S34：For the image of Threshold segmentation, the elemental area in each UNICOM region is counted, retain elemental area in target UNICOM
UNICOM region in setting range, rejects remaining UNICOM region, and target UNICOM setting range is according to Ship Target size
Depending on；
S35：The skeleton in the UNICOM region for retaining is extracted, the length-width ratio of skeleton is calculated, reservation meets target length-width ratio setting range
Skeleton, remaining skeleton is rejected, depending on target length-width ratio setting range is according to Ship Target skeleton length-width ratio；
S36：The grey scale change of the skeleton for retaining is calculated, by gray scale is unchanged and backbone length is picked more than the skeleton of preset length value
Remove, retain remaining target skeleton；
S37：Image according to Threshold segmentation in the target skeleton and step S34 retained in step S36 carries out morphological reconstruction, from
And extracted Ship Target.
8. the Ship Target Detection method of infrared remote sensing image is based on as claimed in claim 7, it is characterised in that the step
In S34, after first carrying out morphological dilations for the image of Threshold segmentation, then count the elemental area in each UNICOM region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611076345.0A CN106709426B (en) | 2016-11-29 | 2016-11-29 | Ship target detection method based on infrared remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611076345.0A CN106709426B (en) | 2016-11-29 | 2016-11-29 | Ship target detection method based on infrared remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106709426A true CN106709426A (en) | 2017-05-24 |
| CN106709426B CN106709426B (en) | 2020-04-14 |
Family
ID=58934098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611076345.0A Active CN106709426B (en) | 2016-11-29 | 2016-11-29 | Ship target detection method based on infrared remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106709426B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255301A (en) * | 2018-08-14 | 2019-01-22 | 北京航空航天大学 | A kind of infrared remote sensing image naval vessel detection false-alarm elimination method based on FPGA |
| CN109583319A (en) * | 2018-11-07 | 2019-04-05 | 北京市遥感信息研究所 | A kind of Ship Detection based on sea infrared remote sensing image |
| CN109859178A (en) * | 2019-01-18 | 2019-06-07 | 北京航空航天大学 | A kind of infrared remote sensing image real-time target detection method based on FPGA |
| CN110109189A (en) * | 2019-05-17 | 2019-08-09 | 中国人民解放军92942部队 | Naval target infrared control method and device |
| CN110133668A (en) * | 2019-05-17 | 2019-08-16 | 中国人民解放军92942部队 | Naval target infrared detection method and device |
| CN110728635A (en) * | 2019-09-10 | 2020-01-24 | 中国科学院上海技术物理研究所 | Contrast enhancement method for dim and weak target |
| CN111105419A (en) * | 2019-10-09 | 2020-05-05 | 中国船舶重工集团公司第七0九研究所 | Vehicle and ship detection method and device based on polarized SAR image |
| CN111178230A (en) * | 2019-12-26 | 2020-05-19 | 武汉大学 | Intelligent extraction method for river beach in remote sensing image |
| CN113192059A (en) * | 2021-05-24 | 2021-07-30 | 北京市遥感信息研究所 | On-orbit ship detection method based on infrared remote sensing image |
| CN115222758A (en) * | 2022-09-21 | 2022-10-21 | 北京九章星图科技有限公司 | Low-resolution wide-area sequence remote sensing image ship moving target real-time detection algorithm |
| CN115661434A (en) * | 2022-10-17 | 2023-01-31 | 中国人民解放军61540部队 | Night marine ship automatic identification method, system, electronic equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663348A (en) * | 2012-03-21 | 2012-09-12 | 中国人民解放军国防科学技术大学 | Marine ship detection method in optical remote sensing image |
| CN104077777A (en) * | 2014-07-04 | 2014-10-01 | 中国科学院大学 | Sea surface vessel target detection method |
| CN104732215A (en) * | 2015-03-25 | 2015-06-24 | 广西大学 | Remote-sensing image coastline extracting method based on information vector machine |
| CN105184804A (en) * | 2015-10-12 | 2015-12-23 | 上海海大技术转移有限公司 | Sea surface small target detection method based on airborne infrared camera aerially-photographed image |
| CN105303526A (en) * | 2015-09-17 | 2016-02-03 | 哈尔滨工业大学 | Ship target detection method based on coastline data and spectral analysis |
| CN105335978A (en) * | 2015-10-28 | 2016-02-17 | 上海斐讯数据通信技术有限公司 | Image edge detection method and system |
-
2016
- 2016-11-29 CN CN201611076345.0A patent/CN106709426B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663348A (en) * | 2012-03-21 | 2012-09-12 | 中国人民解放军国防科学技术大学 | Marine ship detection method in optical remote sensing image |
| CN104077777A (en) * | 2014-07-04 | 2014-10-01 | 中国科学院大学 | Sea surface vessel target detection method |
| CN104732215A (en) * | 2015-03-25 | 2015-06-24 | 广西大学 | Remote-sensing image coastline extracting method based on information vector machine |
| CN105303526A (en) * | 2015-09-17 | 2016-02-03 | 哈尔滨工业大学 | Ship target detection method based on coastline data and spectral analysis |
| CN105184804A (en) * | 2015-10-12 | 2015-12-23 | 上海海大技术转移有限公司 | Sea surface small target detection method based on airborne infrared camera aerially-photographed image |
| CN105335978A (en) * | 2015-10-28 | 2016-02-17 | 上海斐讯数据通信技术有限公司 | Image edge detection method and system |
Non-Patent Citations (3)
| Title |
|---|
| BAI X等: "Analysis of new top-hat transformation and the application for infrared dim small target detection", 《PATTERN RECOGNITION》 * |
| 常兴华: "基于无人机红外遥感图像的海上目标识别系统设计及其应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 黄姗: "遥感图像目标检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255301A (en) * | 2018-08-14 | 2019-01-22 | 北京航空航天大学 | A kind of infrared remote sensing image naval vessel detection false-alarm elimination method based on FPGA |
| CN109583319A (en) * | 2018-11-07 | 2019-04-05 | 北京市遥感信息研究所 | A kind of Ship Detection based on sea infrared remote sensing image |
| CN109583319B (en) * | 2018-11-07 | 2020-12-15 | 北京市遥感信息研究所 | Ship detection method based on sea surface infrared remote sensing image |
| CN109859178B (en) * | 2019-01-18 | 2020-11-03 | 北京航空航天大学 | FPGA-based infrared remote sensing image real-time target detection method |
| CN109859178A (en) * | 2019-01-18 | 2019-06-07 | 北京航空航天大学 | A kind of infrared remote sensing image real-time target detection method based on FPGA |
| CN110133668A (en) * | 2019-05-17 | 2019-08-16 | 中国人民解放军92942部队 | Naval target infrared detection method and device |
| CN110109189A (en) * | 2019-05-17 | 2019-08-09 | 中国人民解放军92942部队 | Naval target infrared control method and device |
| CN110728635A (en) * | 2019-09-10 | 2020-01-24 | 中国科学院上海技术物理研究所 | Contrast enhancement method for dim and weak target |
| CN110728635B (en) * | 2019-09-10 | 2023-07-07 | 中国科学院上海技术物理研究所 | Contrast enhancement method for dark and weak target |
| CN111105419A (en) * | 2019-10-09 | 2020-05-05 | 中国船舶重工集团公司第七0九研究所 | Vehicle and ship detection method and device based on polarized SAR image |
| CN111105419B (en) * | 2019-10-09 | 2023-04-18 | 中国船舶重工集团公司第七0九研究所 | Vehicle and ship detection method and device based on polarized SAR image |
| CN111178230A (en) * | 2019-12-26 | 2020-05-19 | 武汉大学 | Intelligent extraction method for river beach in remote sensing image |
| CN113192059A (en) * | 2021-05-24 | 2021-07-30 | 北京市遥感信息研究所 | On-orbit ship detection method based on infrared remote sensing image |
| CN115222758A (en) * | 2022-09-21 | 2022-10-21 | 北京九章星图科技有限公司 | Low-resolution wide-area sequence remote sensing image ship moving target real-time detection algorithm |
| CN115222758B (en) * | 2022-09-21 | 2023-01-10 | 北京九章星图科技有限公司 | Real-time detection method for ship moving target of low-resolution wide-area sequence remote sensing image |
| CN115661434A (en) * | 2022-10-17 | 2023-01-31 | 中国人民解放军61540部队 | Night marine ship automatic identification method, system, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106709426B (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709426A (en) | Ship target detection method based on infrared remote sensing image | |
| CN103942803B (en) | SAR (Synthetic Aperture Radar) image based automatic water area detection method | |
| CN106022288B (en) | The identification of marine oil spill information and extracting method based on SAR image | |
| CN103442209B (en) | Video monitoring method of electric transmission line | |
| CN103886285B (en) | Optical remote sensing image Ship Detection under priori geography information auxiliary | |
| CN102867196B (en) | Based on the complicated sea remote sensing image Ship Detection of Gist feature learning | |
| CN109145872B (en) | CFAR and Fast-RCNN fusion-based SAR image ship target detection method | |
| CN103778627B (en) | A kind of marine site based on SAR image oil spilling detection method | |
| CN109410230A (en) | One kind can antimierophonic improvement Canny method for detecting image edge | |
| CN104217196B (en) | A kind of remote sensing image circle oil tank automatic testing method | |
| CN104361582B (en) | Method of detecting flood disaster changes through object-level high-resolution SAR (synthetic aperture radar) images | |
| CN109427055B (en) | Remote sensing image sea surface ship detection method based on visual attention mechanism and information entropy | |
| CN109978869A (en) | A kind of sea horizon detection method and system based on gray level co-occurrence matrixes and Hough transform | |
| CN103914834A (en) | Significant object detection method based on foreground priori and background priori | |
| CN101359365A (en) | Iris positioning method based on Maximum between-Cluster Variance and gray scale information | |
| CN106886747B (en) | It is a kind of based on extension wavelet transformation complex background under Ship Detection | |
| CN105741276B (en) | A kind of ship waterline extracting method | |
| CN109191432A (en) | The remote sensing images cloud detection method of optic of filtering multi-resolution decomposition is converted based on domain | |
| CN110490904B (en) | Weak and small target detection and tracking method | |
| CN109815807A (en) | A kind of ship detecting method of pulling in shore based on edge line analysis and converging channels feature | |
| CN105389826A (en) | High-resolution SAR remote sensing extraction method for coastline of coral island | |
| CN109712158A (en) | A kind of infrared small target catching method based on target background pixel statistical restraint | |
| CN107154044B (en) | Chinese food image segmentation method | |
| Ouyang et al. | The research of the strawberry disease identification based on image processing and pattern recognition | |
| CN107704865A (en) | Fleet Targets Detection based on the extraction of structure forest edge candidate region |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201109 Minhang District, Shanghai Road, No. 1777 spring Applicant after: Shanghai Spaceflight Institute of TT&C And Telecommunication Address before: 200080 Shanghai city Hongkou District street Xingang Tianbao Road No. 881 Applicant before: Shanghai Spaceflight Institute of TT&C And Telecommunication |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |