CN102800086A - Offshore scene significance detection method - Google Patents
Offshore scene significance detection method Download PDFInfo
- Publication number
- CN102800086A CN102800086A CN2012102072715A CN201210207271A CN102800086A CN 102800086 A CN102800086 A CN 102800086A CN 2012102072715 A CN2012102072715 A CN 2012102072715A CN 201210207271 A CN201210207271 A CN 201210207271A CN 102800086 A CN102800086 A CN 102800086A
- Authority
- CN
- China
- Prior art keywords
- significantly
- brightness
- frame
- color
- marine scene
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an offshore scene significance detection method. The method comprises the following steps of: 1, extracting an offshore scene image sequence; 2, transferring each frame image to the CIELab colour space, and extracting the characteristic pattern of luminance and colour passages; 3, using the absolute value of the difference between the extracted characteristics and the global mid value as the global significance map; 4, using the absolute value of the difference between the characteristics and the local mean value filtration as the local significance map; 5, combining the global significance map and the local significance map of the characteristics to obtain an overall significance map; 6, linearly combining the significance maps of the colour passages of frame images, and respectively combining the combined significance maps with the luminance significance maps to form an overall significance map; 7, accumulating by using each frame detection result as the centre and modifying the significance map of the current frame; and 8, converting the overall significance map into a binarization image to obtain an offshore scene significance target area. By adopting the method, the significance area in the offshore scene can be extracted rapidly, and the interference of sea noise wave can be favorably inhibited. The method is simple in implementation, and is suitable for real-time application.
Description
Technical field
The present invention relates to the detection technique of a kind of machine vision and image processing field, be specifically related to the marine scene conspicuousness detection method that a kind of utilization utilizes Flame Image Process and machine vision technique.
Background technology
At present, domestic and international most visual attention computation model directly carries out conspicuousness in the spatial domain of image and detects, and extracts significantly figure.These class methods are utilized the thinking of image spectrum relatively, need not image carried out orthogonal transformations such as Fourier transform or discrete cosine transform.
Based on the conspicuousness detection method of spatial domain, its core is how to define conspicuousness.Each class methods that proposes are at present mainly utilized the feature difference tolerance conspicuousness between the spatial domain pixel, and common feature comprises brightness, color, direction, texture etc.Simultaneously, a lot of scholars introduce information theory, graph theory and bayesian theory etc. in the calculating of conspicuousness, in the natural scene conspicuousness detects, have obtained better effects.Significantly scheme the not high problem of resolution in order to solve frequency domain conspicuousness detection method; Frequency tuning conspicuousness detection method (the Frequency tuned method that propositions such as Achanta realize on former figure size; FrT), each characteristic mean in the definition image C IELab color space be significance to the difference value behind its gaussian filtering.This method is simple and easy to realize that can extract more complete well-marked target, its internal consistency is good.
The scholar of domestic part to based on ship detection problem in the marine scene of visible images, uses vision noticing mechanism and has carried out preliminary discussion.Leaf is intelligent to wait the people to propose the (Hue based on HIS; Saturation, Intensity) boats and ships in space detect visual attention model, promptly in the HSI color space; Adopt multiple dimensioned Difference Calculation to obtain each component characteristic pattern to three components, and then it is carried out significantly figure of linearity fusion acquisition.Introduce vision noticing mechanism in people such as Wu Qiying moving target monitoring in real time at sea and the tracker, proposed a kind of linear LPF method based on the little template of inverted triangle of iteration, the smoothing denoising on the Rapid Realization coarse resolution image highlights target with this.Wu Qiying etc. also propose the movement overseas target method for quick based on the visible images sequence; Utilize at first segmented sense region-of-interest (ROI in still image of visual attention model; Region of interest), and then only the time differencing method of application enhancements detects moving target in area-of-interest.
Yet there is limitation in the method for these propositions.At first, notice that these methods all are that therefore, mostly target is general objective to the detection of well-marked target in natural scene or the land scene; Simultaneously, because algorithm is complicated, before carrying out conspicuousness calculating, often need carry out down-sampling to original image.As far as large-sized well-marked target, down-sampling can not cause target information to be lost too much, so the conspicuousness testing result is more satisfactory.But because the singularity of marine scene, promptly mostly naval target is little target, especially point target; And be scattered in the marine scene; Therefore directly use existing spatial domain conspicuousness detection method, its result is undesirable, and is especially not good enough to the detection effect of little target; Analyzing its essential reason, is because image down sampling causes little target information to be lost too much.Frequency tuning conspicuousness detection method realizes simple; But owing to only considered that global contrast as conspicuousness, directly applies to marine scene with it in this model, because the characteristic of a large amount of extra large clutters; All be higher than characteristic mean far away; Be that its global contrast and target are very approaching, cause the testing result target, also comprised a large amount of clutters by outside outstanding.In addition, existing marine scene visual attention model has been used for reference the visual attention computation model of Itti, realizes relative complex.
In sum, existing related work mainly solves the conspicuousness detection problem in land scene or the natural scene.Because exist a large amount of extra large clutters and naval target to be mostly little target in the marine scene, the existing methods effect is undesirable.To the defective of prior art, a kind of new marine scene conspicuousness detection method of utilizing is proposed especially, with the problem of mentioning more than solving.
Summary of the invention
The invention provides a kind of marine scene conspicuousness detection method, utilize the characteristic of marine scene image self, realize extracting marking area at the CIELab color space.
For realizing above-mentioned purpose, the invention provides a kind of marine scene conspicuousness detection method, be characterized in that the method includes the steps of:
Every two field picture of step 2, marine scene image to the CIELab color space, and extracts its brightness and two Color Channels as essential characteristic by the RGB color space conversion, obtains the characteristic pattern of brightness and two Color Channels;
The brightness of all two field pictures of step 3, marine scene image and two color characteristics absolute value of median difference overall with it are respectively significantly schemed as the overall situation;
If of input image sequence
Frame
, L
iBe brightness, a
iAnd b
iBe two color characteristics, this is years old
Frame is any frame in the marine scene image;
To brightness and two color characteristics, calculate its overall intermediate value respectively,
L wherein
ImBe the overall intermediate value of brightness, a
ImAnd b
ImIt is the overall intermediate value of two colors;
Then, the overall situation of calculating each characteristic is significantly schemed:
Wherein, Represent absolute value;
is that the overall situation of brightness is significantly schemed, and
and
is respectively the remarkable figure of the overall situation of two color characteristics;
The brightness of all two field pictures of step 4, marine scene image and two color characteristics are significantly schemed as the part with the absolute value of its local mean value filtering difference respectively:
Wherein,
is the local mean value template of
; I.e.
; Symbol
representation space territory convolution algorithm;
is the local significantly figure of brightness, and
and
is the local significantly figure of two color characteristics;
The overall situation of the brightness of all two field pictures of step 5, marine scene image and two color characteristics is significantly schemed and local significantly figure merges respectively, obtains the total of these three characteristics and significantly schemes:
Wherein,
is total significantly figure of brightness, and
and
is total significantly figure of two color characteristics;
The remarkable figure of two Color Channels of all two field pictures of step 6, marine scene image carries out linearity respectively and merges, and significantly schemes to be fused to total significantly figure with its brightness respectively again;
In every frame, the linear remarkable figure of the Color Channel that obtains that merges of the remarkable figure of two Color Channels is:
Color Channel is significantly schemed significantly to scheme to merge with brightness, obtains the total remarkable figure of the marine scene of this frame:
(14)
Step 7, to every frame testing result, utilizing with it is the center, with the time window of regular length, should be in the time altogether the corresponding significantly figure of n frame accumulate, the remarkable figure of present frame is revised:
Step 8, according to preset threshold, convert total significantly figure into binary image, obtain marine scene well-marked target zone.
In the above-mentioned step 7, n desirable 5 or 7 or 9 or 11.
Threshold value described in the above-mentioned step 8 is a normalized threshold, and its span is 0.2 to 0.5.
A kind of marine scene conspicuousness detection method of the present invention is compared with prior art; Its advantage is; Marking area in can the rapid extraction marine scene of use of the present invention helps target detection in the marine scene, better inhibited the interference of extra large clutter; Under situation about flooded by wave the medium and small target of some frame and the situation that stronger extra large noise jamming occurs, guarantee the detection of marine remarkable little target.Method of the present invention realizes simple, is fit to use in real time, and the supplementary means of machine vision can be provided for all kinds of maritime affairs monitor staff.
Description of drawings
Fig. 1 is the method flow diagram of a kind of marine scene conspicuousness detection method of the present invention.
Embodiment
Below in conjunction with accompanying drawing, further specify specific embodiment of the present invention.
The invention discloses a kind of marine scene conspicuousness detection method, utilize the space domain characteristic of marine scene image, in the conspicuousness detection method of CIELab color space realization.This method is utilized the overall situation and the local conspicuousness of marine scene, extracts significantly figure and it is merged of brightness of image and Color Channel respectively, with outstanding target area.Simultaneously,, further remove extra large clutter, the remarkable figure between multiframe is accumulated in order to strengthen the marking area of marine scene.
The present invention is a space domain characteristic of utilizing marine scene image, in the conspicuousness detection method of CIELab color space realization.Utilize marine scene image brightness and the Color Channel overall situation and the local significantly fusion of figure in this method, obtain marking area.Simultaneously, in order better to remove extra large clutter, adopted simple interframe conspicuousness accumulation method.
The present invention has mainly adopted when implementing: the conspicuousness computing method of the marine scene image of every frame, and interframe is significantly schemed accumulation method.
The present invention can be applicable to search and rescue in the perils of the sea, the maritime affairs patrol, based on fields such as the ship collision prevention of video, anti-pirate monitoring, Zhi Ban lookouts, the while with infrared, remote sensing, radar imagery is technological combines, can be maritime traffic safety etc. comprehensive visual information be provided.
As shown in Figure 1, the marine scene conspicuousness of the present invention detection method comprises following steps:
Every two field picture of step 2, marine scene image to the CIELab color space, and extracts its luminance channel L and two Color Channel a and b as essential characteristic by the RGB color space conversion, obtains the characteristic pattern of brightness and two Color Channels.
This is owing to correlativity between each passage in the RGB color space is higher, therefore adopts the CIELab color space, extracts the brightness and the color characteristic of visual scene.
Wherein above-mentioned CIELab color space has only two color space a or b.
The brightness of all two field pictures of step 3, marine scene image and two color characteristics absolute value of median difference overall with it are respectively significantly schemed as the overall situation.
Calculation process is an example with a frame wherein, establishes of input image sequence
Frame
, its brightness and two color characteristics are respectively:
, L
iBe brightness, a
iAnd b
iBe two color characteristics.
To brightness and two color characteristics, calculate its overall intermediate value respectively,
L wherein
ImBe the overall intermediate value of brightness, a
ImAnd b
ImIt is the overall intermediate value of two colors.
And utilize the overall situation of each characteristic of computes significantly to scheme, be respectively:
Wherein, Represent absolute value;
is that the overall situation of brightness is significantly schemed, and
and
is respectively the remarkable figure of the overall situation of two color characteristics.
The brightness of all two field pictures of step 4, marine scene image and two color characteristics are significantly schemed as the part with the absolute value of its local mean value filtering difference respectively.
With
frame is example; The absolute value that utilizes each characteristic local mean value filtering and each characteristic difference is respectively above-mentioned three passages as its local significantly figure:
(9)
Wherein,
is the local mean value template of
, i.e.
.Symbol
representation space territory convolution algorithm.
is the local significantly figure of brightness, and
and
is the local significantly figure of two color characteristics.
The overall situation of the brightness of all two field pictures of step 5, marine scene image and two color characteristics is significantly schemed and local significantly figure merges respectively, obtains the total of these three characteristics and significantly schemes.
With
frame is example, and total significantly figure of brightness and two color characteristics is shown below:
(11)
Wherein,
is total significantly figure of brightness, and
and
is total significantly figure of two color characteristics.
The remarkable figure of two Color Channels of all two field pictures of step 6, marine scene image carries out linearity respectively and merges, and significantly schemes to be fused to total significantly figure with its brightness respectively again.
With
frame is example, and the linear remarkable figure of the Color Channel that obtains that merges of the remarkable figure of two Color Channels is:
The result and the brightness of following formula (13) are significantly schemed to merge, and the total significantly figure that finally obtains the marine scene of this frame is:
(14)
Step 7, to every frame testing result, utilizing with it is the center, the testing result of each 3 frame of front and back is significantly schemed accumulation; To preceding 3 frames and back 3 two field pictures of image sequence, then utilize continuous 7 frames that comprise this frame significantly to scheme to accumulate.
The present invention utilizes the time window of regular length, and corresponding significantly figure accumulates with all frames in this time, and the remarkable figure of present frame is revised, and purpose is to strengthen target, suppresses extra large clutter.
Wherein
is the length of time window; The value of n is generally got odd number; N desirable 5 or 7 or 9 or 11 for example; The value of this n can not be excessive or too small, and the frame per second when itself and video acquisition has relation.
gets 7 in the present embodiment;
; It is the normalization sign of operation; Purpose is the gray-scale value of significantly scheming is united, so that the accumulation of the conspicuousness of back.
Special, to preceding 3 frames and last 3 frames of image sequence, then significantly scheme to do accumulation with continuous 7 frames that comprise this frame.
Step 8, according to preset threshold, convert total significantly figure into binary image, obtain marine scene well-marked target zone.Wherein above-mentioned preset threshold value is a normalized threshold, and its span is the numerical value between 0.2 to 0.5, and this threshold value is an empirical value.
Although content of the present invention has been done detailed introduction through above-mentioned preferred embodiment, will be appreciated that above-mentioned description should not be considered to limitation of the present invention.After those skilled in the art have read foregoing, for multiple modification of the present invention with to substitute all will be conspicuous.Therefore, protection scope of the present invention should be limited appended claim.
Claims (3)
1. marine scene conspicuousness detection method is characterized in that the method includes the steps of:
Step 1, the marine scene image sequence of extraction;
Every two field picture of step 2, marine scene image to the CIELab color space, and extracts its brightness and two Color Channels as essential characteristic by the RGB color space conversion, obtains the characteristic pattern of brightness and two Color Channels;
The brightness of all two field pictures of step 3, marine scene image and two color characteristics absolute value of median difference overall with it are respectively significantly schemed as the overall situation;
If of input image sequence
Frame
, L
iBe brightness, a
iAnd b
iBe two color characteristics, this is years old
Frame is any frame in the marine scene image;
To brightness and two color characteristics, calculate its overall intermediate value respectively,
L wherein
ImBe the overall intermediate value of brightness, a
ImAnd b
ImIt is the overall intermediate value of two colors;
Then, the overall situation of calculating each characteristic is significantly schemed:
(5)
Wherein, Represent absolute value;
is that the overall situation of brightness is significantly schemed, and
and
is respectively the remarkable figure of the overall situation of two color characteristics;
The brightness of all two field pictures of step 4, marine scene image and two color characteristics are significantly schemed as the part with the absolute value of its local mean value filtering difference respectively:
(9)
Wherein,
is the local mean value template of
; I.e.
; Symbol
representation space territory convolution algorithm;
is the local significantly figure of brightness, and
and
is the local significantly figure of two color characteristics;
The overall situation of the brightness of all two field pictures of step 5, marine scene image and two color characteristics is significantly schemed and local significantly figure merges respectively, obtains the total of these three characteristics and significantly schemes:
Wherein,
is total significantly figure of brightness, and
and
is total significantly figure of two color characteristics;
The remarkable figure of two Color Channels of all two field pictures of step 6, marine scene image carries out linearity respectively and merges, and significantly schemes to be fused to total significantly figure with its brightness respectively again;
In every frame, the linear remarkable figure of the Color Channel that obtains that merges of the remarkable figure of two Color Channels is:
Color Channel is significantly schemed significantly to scheme to merge with brightness, obtains the total remarkable figure of the marine scene of this frame:
Step 7, to every frame testing result, utilizing with it is the center, with the time window of regular length, should be in the time altogether the corresponding significantly figure of n frame accumulate, the remarkable figure of present frame is revised:
Step 8, according to preset threshold, convert total significantly figure into binary image, obtain marine scene well-marked target zone.
2. a kind of marine scene conspicuousness detection method as claimed in claim 1 is characterized in that, in the described step 7, and n desirable 5 or 7 or 9 or 11.
3. a kind of marine scene conspicuousness detection method as claimed in claim 1 is characterized in that the threshold value described in the described step 8 is a normalized threshold, and its span is 0.2 to 0.5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210207271.5A CN102800086B (en) | 2012-06-21 | 2012-06-21 | Offshore scene significance detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210207271.5A CN102800086B (en) | 2012-06-21 | 2012-06-21 | Offshore scene significance detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102800086A true CN102800086A (en) | 2012-11-28 |
CN102800086B CN102800086B (en) | 2015-02-04 |
Family
ID=47199184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210207271.5A Expired - Fee Related CN102800086B (en) | 2012-06-21 | 2012-06-21 | Offshore scene significance detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102800086B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103020965A (en) * | 2012-11-29 | 2013-04-03 | 奇瑞汽车股份有限公司 | Foreground segmentation method based on significance detection |
CN103268586A (en) * | 2013-04-27 | 2013-08-28 | 电子科技大学 | Window fusion method based on heat diffusion theory |
CN103337075A (en) * | 2013-06-20 | 2013-10-02 | 浙江大学 | Image significant degree calculation method based on isolux curve |
CN103413127A (en) * | 2013-09-10 | 2013-11-27 | 上海海事大学 | Marine target significance detection method based on spectrum singular value decomposition |
CN103413320A (en) * | 2013-08-30 | 2013-11-27 | 上海海事大学 | Port contaminant saliency detection method |
CN105893957A (en) * | 2016-03-30 | 2016-08-24 | 上海交通大学 | Method for recognizing and tracking ships on lake surface on the basis of vision |
CN104050674B (en) * | 2014-06-27 | 2017-01-25 | 中国科学院自动化研究所 | Salient region detection method and device |
CN106991682A (en) * | 2016-01-21 | 2017-07-28 | 深圳中兴力维技术有限公司 | The extracting method and device of automatic harbour freighter |
CN107169516A (en) * | 2017-05-11 | 2017-09-15 | 上海海事大学 | The marine Small object conspicuousness detection method converted based on K L |
CN107862262A (en) * | 2017-10-27 | 2018-03-30 | 中国航空无线电电子研究所 | A kind of quick visible images Ship Detection suitable for high altitude surveillance |
CN107886533A (en) * | 2017-10-26 | 2018-04-06 | 深圳大学 | Vision significance detection method, device, equipment and the storage medium of stereo-picture |
CN107967474A (en) * | 2017-11-24 | 2018-04-27 | 上海海事大学 | A kind of sea-surface target conspicuousness detection method based on convolutional neural networks |
CN108009984A (en) * | 2017-11-21 | 2018-05-08 | 中国地质大学(武汉) | A kind of detection method of water surface salient region towards monitoring water environment |
CN108229342A (en) * | 2017-12-18 | 2018-06-29 | 西南技术物理研究所 | A kind of surface vessel target automatic testing method |
CN108334865A (en) * | 2018-03-12 | 2018-07-27 | 王艳 | big data analysis platform based on image |
CN109188421A (en) * | 2018-07-25 | 2019-01-11 | 江苏科技大学 | A kind of maritime search and rescue system and method for unmanned rescue boat |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101976439A (en) * | 2010-11-02 | 2011-02-16 | 上海海事大学 | Visual attention model with combination of motion information in visual system of maritime search and rescue machine |
CN102087744A (en) * | 2010-02-25 | 2011-06-08 | 上海海事大学 | Structure tensor method for quick detection of small video target under dynamic ocean background |
CN102156881A (en) * | 2011-04-13 | 2011-08-17 | 上海海事大学 | Method for detecting salvage target based on multi-scale image phase information |
-
2012
- 2012-06-21 CN CN201210207271.5A patent/CN102800086B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102087744A (en) * | 2010-02-25 | 2011-06-08 | 上海海事大学 | Structure tensor method for quick detection of small video target under dynamic ocean background |
CN101976439A (en) * | 2010-11-02 | 2011-02-16 | 上海海事大学 | Visual attention model with combination of motion information in visual system of maritime search and rescue machine |
CN102156881A (en) * | 2011-04-13 | 2011-08-17 | 上海海事大学 | Method for detecting salvage target based on multi-scale image phase information |
Non-Patent Citations (2)
Title |
---|
LEI REN: "TARGET DETECTION IN MARITIME SEARCH AND RESCUE USING SVD AND FREQUENCY DOMAIN CHARACTERISTICS", 《PROCEEDINGS OF THE 2011 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS》, 13 July 2011 (2011-07-13), pages 556 - 560, XP031966282, DOI: doi:10.1109/ICMLC.2011.6016763 * |
任蕾: "应用改进频率调谐的海上小目标检测方法", 《中国图象图形学报》, vol. 17, no. 3, 31 March 2012 (2012-03-31), pages 365 - 369 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103020965A (en) * | 2012-11-29 | 2013-04-03 | 奇瑞汽车股份有限公司 | Foreground segmentation method based on significance detection |
CN103020965B (en) * | 2012-11-29 | 2016-12-21 | 奇瑞汽车股份有限公司 | A kind of foreground segmentation method based on significance detection |
CN103268586A (en) * | 2013-04-27 | 2013-08-28 | 电子科技大学 | Window fusion method based on heat diffusion theory |
CN103268586B (en) * | 2013-04-27 | 2015-11-18 | 电子科技大学 | A kind of window fusion method based on diffusion theory |
CN103337075A (en) * | 2013-06-20 | 2013-10-02 | 浙江大学 | Image significant degree calculation method based on isolux curve |
CN103337075B (en) * | 2013-06-20 | 2016-04-27 | 浙江大学 | A kind of image significance computing method based on isophote |
CN103413320A (en) * | 2013-08-30 | 2013-11-27 | 上海海事大学 | Port contaminant saliency detection method |
CN103413320B (en) * | 2013-08-30 | 2016-12-28 | 上海海事大学 | A kind of port contaminant saliency detection method |
CN103413127A (en) * | 2013-09-10 | 2013-11-27 | 上海海事大学 | Marine target significance detection method based on spectrum singular value decomposition |
CN103413127B (en) * | 2013-09-10 | 2016-06-08 | 上海海事大学 | Marine target significance detection method based on spectrum singular value decomposition |
CN104050674B (en) * | 2014-06-27 | 2017-01-25 | 中国科学院自动化研究所 | Salient region detection method and device |
CN106991682A (en) * | 2016-01-21 | 2017-07-28 | 深圳中兴力维技术有限公司 | The extracting method and device of automatic harbour freighter |
CN106991682B (en) * | 2016-01-21 | 2019-12-20 | 深圳力维智联技术有限公司 | Automatic port cargo ship extraction method and device |
CN105893957B (en) * | 2016-03-30 | 2019-03-22 | 上海交通大学 | View-based access control model lake surface ship detection recognition and tracking method |
CN105893957A (en) * | 2016-03-30 | 2016-08-24 | 上海交通大学 | Method for recognizing and tracking ships on lake surface on the basis of vision |
CN107169516A (en) * | 2017-05-11 | 2017-09-15 | 上海海事大学 | The marine Small object conspicuousness detection method converted based on K L |
CN107169516B (en) * | 2017-05-11 | 2020-10-23 | 上海海事大学 | Marine small target significance detection method based on K-L transformation |
CN107886533A (en) * | 2017-10-26 | 2018-04-06 | 深圳大学 | Vision significance detection method, device, equipment and the storage medium of stereo-picture |
CN107862262A (en) * | 2017-10-27 | 2018-03-30 | 中国航空无线电电子研究所 | A kind of quick visible images Ship Detection suitable for high altitude surveillance |
CN108009984A (en) * | 2017-11-21 | 2018-05-08 | 中国地质大学(武汉) | A kind of detection method of water surface salient region towards monitoring water environment |
CN108009984B (en) * | 2017-11-21 | 2020-07-07 | 中国地质大学(武汉) | Water environment monitoring-oriented water surface saliency area detection method |
CN107967474A (en) * | 2017-11-24 | 2018-04-27 | 上海海事大学 | A kind of sea-surface target conspicuousness detection method based on convolutional neural networks |
CN108229342A (en) * | 2017-12-18 | 2018-06-29 | 西南技术物理研究所 | A kind of surface vessel target automatic testing method |
CN108229342B (en) * | 2017-12-18 | 2021-10-26 | 西南技术物理研究所 | Automatic sea surface ship target detection method |
CN108334865A (en) * | 2018-03-12 | 2018-07-27 | 王艳 | big data analysis platform based on image |
CN109188421A (en) * | 2018-07-25 | 2019-01-11 | 江苏科技大学 | A kind of maritime search and rescue system and method for unmanned rescue boat |
CN109188421B (en) * | 2018-07-25 | 2023-07-04 | 江苏科技大学 | Maritime search and rescue system and method for unmanned search and rescue boat |
Also Published As
Publication number | Publication date |
---|---|
CN102800086B (en) | 2015-02-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102800086B (en) | Offshore scene significance detection method | |
Dong et al. | RRSGAN: Reference-based super-resolution for remote sensing image | |
CN101673396B (en) | Image fusion method based on dynamic object detection | |
CN103413127B (en) | Marine target significance detection method based on spectrum singular value decomposition | |
CN104504652A (en) | Image denoising method capable of quickly and effectively retaining edge and directional characteristics | |
CN106846289A (en) | A kind of infrared light intensity and polarization image fusion method based on conspicuousness migration with details classification | |
CN102156881B (en) | Method for detecting salvage target based on multi-scale image phase information | |
Zhang et al. | Single image dehazing based on fast wavelet transform with weighted image fusion | |
Feng et al. | Infrared target detection and location for visual surveillance using fusion scheme of visible and infrared images | |
Liu et al. | Haze removal for a single inland waterway image using sky segmentation and dark channel prior | |
Xu et al. | COCO-Net: A dual-supervised network with unified ROI-loss for low-resolution ship detection from optical satellite image sequences | |
Wei et al. | An image fusion dehazing algorithm based on dark channel prior and retinex | |
Chen et al. | Moving vehicle detection based on union of three-frame difference | |
CN117079117B (en) | Underwater image processing and target identification method and device, storage medium and electronic equipment | |
CN103106647B (en) | Based on the Multi-focal-point image fusion method of quaternion wavelet and region segmentation | |
CN110874599A (en) | Ship detection method based on image recognition | |
CN112184572B (en) | Novel rain removing method and system for dynamic vision sensor event stream | |
Ma et al. | Video image clarity algorithm research of USV visual system under the sea fog | |
Yang et al. | Sea-sky-line Detection Based on Improved YOLOv5 Algorithm | |
Hu et al. | Maritime video defogging based on spatial-temporal information fusion and an improved dark channel prior | |
Shi et al. | Ship targets detection based on visual attention | |
Jia et al. | A two-step approach to see-through bad weather for surveillance video quality enhancement | |
CN109685825A (en) | Local auto-adaptive feature extracting method, system and storage medium for thermal infrared target tracking | |
Zhenbo et al. | A Survey of Preprocessing Methods for Marine Ship Target Detection Based on Video Surveillance | |
Deng et al. | Image fusion method for infrared and visible light images based on SWT and regional gradient |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150204 Termination date: 20180621 |