CN106780525A - Optical remote sensing image ship direction feature extraction method based on coordinate rotation minimum circumscribed rectangle - Google Patents
Optical remote sensing image ship direction feature extraction method based on coordinate rotation minimum circumscribed rectangle Download PDFInfo
- Publication number
- CN106780525A CN106780525A CN201611016618.2A CN201611016618A CN106780525A CN 106780525 A CN106780525 A CN 106780525A CN 201611016618 A CN201611016618 A CN 201611016618A CN 106780525 A CN106780525 A CN 106780525A
- Authority
- CN
- China
- Prior art keywords
- target
- rectangle
- ship
- hull
- point
- 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
- 238000000605 extraction Methods 0.000 title abstract description 11
- 230000003287 optical effect Effects 0.000 title abstract 3
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 claims description 2
- 238000011160 research Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
Landscapes
- Image Analysis (AREA)
Abstract
And (4) ship direction feature extraction of the optical remote sensing image based on the minimum circumscribed rectangle of coordinate rotation. The research provides the ship direction feature extraction of the optical remote sensing image based on the coordinate rotation minimum circumscribed rectangle, and the ship direction feature extraction method adopts a method of rotating a coordinate axis and efficiently and accurately obtains the direction features of the orientation, the length, the width and the like of a target by extracting the minimum circumscribed rectangle of the ship. Firstly, image preprocessing is carried out to obtain a single-pixel edge of a target, and the single-pixel edge is used as an effective reference area for extracting target direction features. Secondly, aiming at the obtained edge contour image, carrying out initial judgment on the target orientation by adopting a quadrant division strategy, wherein the step aims to limit the search range of the minimum circumscribed rectangle and improve the algorithm efficiency; and thirdly, under the limitation of the target initial judgment range in the previous step, searching for a minimum circumscribed rectangle in the range, and performing initial judgment on the heading of the ship based on the minimum circumscribed rectangle. And finally, extracting ship direction related features such as the length, the width, the orientation and the like of the target by using the extracted minimum circumscribed rectangle.
Description
Technical field
The remote sensing image vessel orientation feature extracting method of minimum enclosed rectangle is rotated the present invention relates to be based on coordinate.
Background technology
In recent years, with the fast development of empty day carrying platform technology, space remote sensing technology also in constantly improve and progress,
The research and technology exploitation for carrying out ship detection and monitoring using acquired remote sensing images obtains more next in ocean remote sensing field
More attention.
Remote sensing image vessel orientation feature extraction refers to, based on remote sensing image data, using image procossing
Method extracts the feature about vessel orientation, and the technology can coordinate Automatic Measurement Technique to realize remotely-sensed data sea ship information
It is automatic effectively to extract.It is applied on civil area, can support shipping monitoring, sea fishery supervision, water transportation control etc..
Apply and then can be used in military field：Ship foreign countries naval port dynamic surveillance, the departure from port early warning of emphasis ship target etc..
In sea ship remote sensing features are extracted, the direction of ship is the crucial letter of remotely-sensed data ship target automatic interpretation
Breath.The technology that current relevant vessel orientation is extracted mostly is by traveling through target area, finding the method for long and short axle to obtain ship
Direction.This kind of conventionally employed calculating connected region major axis, short axle obtain the mode of vessel orientation feature, easily by connected domain
The interference of a small amount of false-alarm point of integrality and target periphery for calculating is marked, and major and minor axis are found using traversal target area and obtained
The method operand in direction is big, and efficiency is low.
This programme proposes the side of the remote sensing image vessel orientation feature extraction based on coordinate rotation minimum enclosed rectangle
Method, it is considered to the globality of target periphery, can effectively overcome what conventional method connected component labeling integrality and all domain false-alarm points were disturbed
Problem.Additionally, this method employs the strategy of rotatable coordinate axis, and by target fore direction just sentence, will after just sentencing
The angle of rotation traversal scope is limited in [0,45 °], and complexity and the calculating time of calculating is greatly reduced, and improves efficiency.
The content of the invention
According to an aspect of the invention, there is provided a kind of remote sensing images ship that minimum enclosed rectangle is rotated based on coordinate
Directional feature extraction method, the direction character for extracting ship, comprises the following steps：
A image preprocessing) is carried out, including：
Section to target carries out the binary map that adaptive threshold fuzziness obtains gray scale input picture；
Medium filtering is carried out to bianry image, the interference noise point in all domains of target hull is removed, noise pair graph is prevented
As the severe jamming for the treatment of；
Two-value corrosion and two-value expansion are carried out to the image after filtering to reach the purpose of holes filling to target hull,
Then, carry out two-value expansive working and the two-value region of target hull is extended out into a circle, prepared to extract edge；
Using binary morphology method, the bianry image of the target hull extended out with edge subtracts the region two of target hull
Value image, obtains the Single pixel edge contour images of target hull；
B) for the edge image for obtaining, the two-value connected region based on target hull of the statistics in 4 quadrants of reference axis
Sentence at the beginning of the method for domain Single pixel edge profile, the quick initial angle for determining coordinate, the direction for carrying out target hull；
C) in step B) target hull direction at the beginning of under the limitation of result sentenced, do the minimum enclosed rectangle of hunting zone
And vessel orientation is calculated based on minimum enclosed rectangle；
D the vessel orientation correlated characteristic of the length and width including ship, direction) is extracted using the minimum enclosed rectangle for obtaining.
Brief description of the drawings
Fig. 1 is the general flow chart of the remote sensing images vessel orientation feature extraction based on coordinate rotation minimum enclosed rectangle.
Fig. 2 is the flow chart of quick obtaining minimum enclosed rectangle.
Fig. 3 (a) is that target direction just sentences schematic diagram to 3 (c).
Fig. 4 is to sentence quadrantization point of explanatory diagram at the beginning of rectangle.
Fig. 5 be limited search scope minimum enclosed rectangle confirm and fore at the beginning of sentence schematic diagram.
Specific embodiment
Shortcoming it is an object of the invention to be directed to above-mentioned prior art, proposes based on coordinate rotation minimum enclosed rectangle
Remote sensing image vessel orientation feature extracting method, efficiently and accurately obtains the directional correlation information of ship in remote sensing images.
The present invention is directed to situation described above, using the remote sensing image ship based on coordinate rotation minimum enclosed rectangle
The extracting method of direction character.Not yet there is the report of such method at present.
The present invention proposes carrying for the ship remote sensing image vessel orientation feature based on coordinate rotation minimum enclosed rectangle
Take method.Comprise the following steps that：
The first step：Image preprocessing
The binary map that adaptive threshold fuzziness obtains gray scale input picture is carried out to target slice, two are carried out to this binary map
Value medium filtering, the scattered interference noise point in removal target image.Then carry out holes filling and expand edge, and use two
Value morphological method obtains the Single pixel edge profile of target two-value connected region.
Second step：Sentence at the beginning of the vessel orientation divided based on quadrant
First to target towards just sentence, by counting the target two-value connected region list picture in 4 quadrants of reference axis
Plain edge contour (previous step is obtained), carrys out the quick initial angle for determining coordinate, shortens subsequent searches scope.Then, pass through
Judge two regional aims of forward andor aft points number tentatively judge target direction.
3rd step：Just sentence the ship minimum enclosed rectangle quick obtaining in the range of limitation
After sentencing at the beginning of previous step direction, it is rotated in by coordinate and minimum enclosed rectangle is determined in the range of limited search, from
Initial angle starts 1 ° of each rotating coordinate system, scans 45 times altogether, and finds out the wherein minimum boundary rectangle of area and record this
When the anglec of rotation, the anglec of rotation now is the vessel orientation of our needs.Fig. 2 is that quick minimum enclosed rectangle is obtained
Flow chart.
4th step：Directional feature extraction based on minimum enclosed rectangle
The minimum enclosed rectangle obtained to target hull Single pixel edge by previous step, by the main shaft of minimum enclosed rectangle
Direction can determine the course of ship；Length and width based on the minimum enclosed rectangle obtained, can directly determine the length and width of ship.
It is described below how the method that the specific implementation present invention is provided, Fig. 1 is side according to an embodiment of the invention
The FB(flow block) of method, the method includes：
The first step：Image preprocessing
(1.1st) step adaptive threshold fuzziness：Adaptive threshold fuzziness is carried out to gray level image first and obtains bianry image,
It is convenient that target hull edge contour is extracted and prepared.
(1.2nd) step medium filtering：Medium filtering is carried out to bianry image, the interference noise point in all domains of removal target is prevented
Only severe jamming of the noise spot to image procossing.
(1.3rd) step holes filling and expansion edge：Image after filtering is carried out two-value corrosion and two-value expansion with
Hull areas are reached with the purpose of holes filling；Then, carry out two-value expansive working and the two-value region of target hull is extended out one
Circle, prepares to extract edge contour.
(1.4th) step edge extracting：Using binary morphology method, the target bianry image extended out with edge subtracts target
Region bianry image, obtains the Single pixel edge contour images of target hull.
Second step：Sentence at the beginning of the vessel orientation divided based on quadrant
(2.1st) step target direction is just sentenced：Quadrant division is carried out to objective contour image：With the pixel that abscissa value is maximum
Point subtracts the width that the minimum pixel of abscissa obtains rectangle, while subtracting ordinate most with the maximum pixel of ordinate value
Small pixel obtains the height of rectangle.This boundary rectangle is divided into four regions by boundary of center line.Divided based on quadrant
The preliminary direction of target can be counted：Point of the statistics objective contour in quadrant, if the point fallen in quadrant area 1,3 is more than quadrant
Region 2,4, then, towards the right side, otherwise towards a left side, such as Fig. 3 (a) -3 (c) is shown for hull.Vice versa.
(2.2nd) step initial angle quickly determines：Center line with above-mentioned boundary rectangle as coordinate system, four from upper right
Quadrant makees the ray with origin as starting point according to first, second, third and fourth quadrant is respectively clockwise to each quadrant,
Each quadrant is divided into the region that two sizes are 45 °, four quadrants are divided into 8 an equal amount of regions, set abscissa
Region above axle is respectively tetra- regions of a, b, c, d from right to left.If drawing target hull towards the right side by upper step, 1 region is counted
Objective contour pixel value is 1 point, if the points fallen in region b are more than a, initial angle is 0, is otherwise 45 °；If ship court
A left side, the points fallen in region c are 0 more than d, then initial angle, are otherwise 45 °.As shown in Figure 4.
3rd step：Just sentence the ship minimum enclosed rectangle quick obtaining in the range of limitation
(3.1st) step is rotated in by coordinate and minimum enclosed rectangle is determined in the range of limited search：Mesh is obtained in previous step
After target initial angle scope, 1 ° of each rotating coordinate system since initial angle, if target hull towards the right side if turn clockwise,
Otherwise rotate counterclockwise.Scan 45 times altogether, obtain the boundary rectangle after scanning every time.And find out the wherein minimum external square of area
Shape and the record anglec of rotation now.The anglec of rotation now is the vessel orientation of our needs, because working as boundary rectangle most
Hour, its center line coincides with the axis of target hull, and boundary rectangle is tangent with target hull edge.
(3.2nd) step fore direction is just sentenced：Two parallel sides long are made two by the minimum enclosed rectangle that above step draws
Bar vertical line section, so as to minimum enclosed rectangle is divided into three regions, will target hull be divided into fore, stern and pars intermedia
Point, by number that the pixel for counting two edge contour of hull 1 and 3 is 1 number the direction of fore is sentenced come at the beginning of, i.e., picture
Vegetarian refreshments number is the side that side where 1 less region is defined as fore.As shown in Figure 5.
4th step：Directional feature extraction based on minimum enclosed rectangle
(4.1st) step fore direction character is obtained：Ship is obtained by the direction calculated in minimum enclosed rectangle acquisition process
The direction of head, during boundary rectangle is obtained, the boundary rectangle for obtaining each time can all correspond to corresponding angle, relatively outer
Connect the size of rectangle, record the angle of the minimum enclosed rectangle while boundary rectangle for finding out minimum, that is, fore side
To angle.And the determination for further providing ship course is sentenced by the first of fore.
(4.2nd) step：Boat lengths and width characteristics are obtained：The side long of minimum enclosed rectangle and the length of short side are exactly ship
Length and width only.
It is of the invention that there is advantages below compared with existing detection method:
(1) extracted using object edge profile travel direction.Objective contour is to measure the most essential image spy of target direction
Property, this method, can direct correlation directional information with extracting object edge profile come instead of directly carrying out extracted region to target
Essence, reduces the influence that is produced to direction estimation of hole that segmentation is produced, it is to avoid because area information segmentation is forbidden and caused by direction
That estimates is inaccurate, is conducive to more accurately extracting the direction character information of target.
(2) strategy is estimated using the target direction of minimum enclosed rectangle.Consider the configuration of target, it is to avoid traversal mesh
In mark extracting method because it is contemplated that local message and easily there is the shortcoming of error, such as because of the original such as interference of details irregularity
Result error caused by, can be with the direction character of the extraction target of high accuracy.
(3) using sentencing raising efficiency of algorithm at the beginning of direction.Sentence method at the beginning of proposing a kind of target direction divided based on quadrant,
Before rotatable coordinate axis determine minimum enclosed rectangle, sentence at the beginning of the quadrant that fore is carried out first, the method reduce the scope of search,
Computationally intensive shortcoming when being searched for by full angle is avoided, computational efficiency is effectively improved.
(4) directional correlation feature is directly asked for by minimum enclosed rectangle.Directly by the side long of minimum enclosed rectangle and
Short side can direct access target major axis and short axle, it is to avoid ship length was individually obtained by the method for full figure traversal in the past
The complex process of axle；The major and minor axis of ship are extracted using minimum enclosed rectangle simultaneously, the orthogonal of major and minor axis has been effectively ensured and has been hung down
Directly, it is to avoid conventional method because noise and the reason such as segmentation is imperfect are to obtaining the influence that major and minor axis are extracted, with Shandong higher
Rod.
Claims (4)
1. it is a kind of based on coordinate rotate minimum enclosed rectangle remote sensing images vessel orientation feature extracting method, for extracting ship
Direction character, comprise the following steps：
A image preprocessing) is carried out, including：
Section to target carries out the binary map that adaptive threshold fuzziness obtains gray scale input picture,
Carry out medium filtering to bianry image, remove the interference noise point in all domains of target hull, prevent noise spot to image at
The severe jamming of reason,
Two-value corrosion and two-value expansion are carried out to the image after filtering to reach the purpose of holes filling to target hull, is connect
, carry out two-value expansive working and the two-value region of target hull is extended out into a circle, prepared to extract edge,
Using binary morphology method, the bianry image of the target hull extended out with edge subtracts the region binary map of target hull
Picture, obtains the Single pixel edge contour images of target hull,
B) for the edge image for obtaining, the two-value connected region list based on target hull of the statistics in 4 quadrants of reference axis
Sentence at the beginning of the method for pixel edge profile, the quick initial angle for determining coordinate, the direction for carrying out target hull；
C) in step B) target hull direction at the beginning of under the limitation of result sentenced, do the minimum enclosed rectangle and base of hunting zone
Vessel orientation is calculated in minimum enclosed rectangle；
D the vessel orientation correlated characteristic of the length and width including ship, direction) is extracted using the minimum enclosed rectangle for obtaining.
2. method according to claim 1, it is characterised in that the step B) include：
B1 quadrant division) is carried out to the edge image for obtaining, including：It is minimum abscissa to be subtracted with the maximum pixel of abscissa value
Pixel so as to obtain the width of boundary rectangle；With the maximum pixel of ordinate value subtract the minimum pixel of ordinate from
And obtain the height of boundary rectangle；This boundary rectangle is divided into four regions by boundary of its center line；Based on quadrant division come
Count the preliminary direction of target hull：Pixel of the edge contour of target hull in quadrant is counted, if falling in quadrant area
1st, the point in 3 is more than the point fallen in quadrant area 2,4, then target hull is towards the right side；Otherwise, if falling in quadrant area 2,4
Point is more than the point that falls in quadrant area 1,3, then target hull is towards a left side,
B2) center line with above-mentioned boundary rectangle is as coordinate system, from upper right four quadrants according to being respectively first counterclockwise, the
2nd, the third and fourth quadrant, the ray with origin as starting point is made to each quadrant, and each quadrant is divided into two sizes for 45 °
Region, four quadrants are divided into 8 an equal amount of regions, and four regions of the first and second quadrants are respectively from right to left
Region a, b, c, d, the pixel value of the edge contour of target hull is 1 point in statistics quadrant area a, if falling in the b of region
The number of point is more than the number of the point in a of region that falls, it is determined that initial angle is 0, otherwise determines that initial angle is 45 °；When
Step B1) draw ship a towards left side, and the number of the point in the c of region that falls is when being more than the number of the point in the d of region that falls, it is determined that
Initial angle is 0, otherwise determines that initial angle is 45 °.
3. method according to claim 2, it is characterised in that the step C) include：
C1) in step B) obtain target hull initial angle scope after, 1 ° of each rotating coordinate system since initial angle, if
Hull then turns clockwise towards the right side, otherwise rotate counterclockwise, scans 45 times altogether, obtains the boundary rectangle after scanning every time, and look for
Go out the wherein minimum boundary rectangle of area and the record anglec of rotation now, the anglec of rotation now is required ship side
To, wherein when boundary rectangle is minimum enclosed rectangle, its center line coincides with the axis of target hull, and outside the minimum
The four edges for connecing rectangle are tangent with the edge of target hull,
C2) by step C1) longer sides of the minimum enclosed rectangle that draw are defined, and two vertical lines are made to two parallel sides long
Section, minimum enclosed rectangle is divided into three regions, while by hull be divided into along its longitudinal direction two heads and positioned at this two
The center section of the centre of individual head, the pixel value by the edge for counting the two heads is 1 point, by comparing the two
Head edge profile value is that the number of 1 pixel judges fore and stern, i.e., the less institute that pixel is 1
Side be defined as the side of fore.
4. method according to claim 3, it is characterised in that the step D) include：
D1) direction by being calculated in minimum enclosed rectangle acquisition process obtains the direction of fore, wherein, obtained in boundary rectangle
During, using C1) step obtain each time boundary rectangle when the corresponding angle that obtains, it is determined that minimum enclosed rectangle
The angle of the minimum enclosed rectangle is recorded simultaneously, using the angle as the direction of ship, and combines step C2) the middle fore court for determining
To the direction for determining fore,
D2) side long of minimum enclosed rectangle and the length of short side are identified as the length and width of ship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611016618.2A CN106780525B (en) | 2016-11-18 | 2016-11-18 | Optical remote sensing image ship direction feature extraction method based on coordinate rotation minimum circumscribed rectangle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611016618.2A CN106780525B (en) | 2016-11-18 | 2016-11-18 | Optical remote sensing image ship direction feature extraction method based on coordinate rotation minimum circumscribed rectangle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106780525A true CN106780525A (en) | 2017-05-31 |
| CN106780525B CN106780525B (en) | 2020-08-14 |
Family
ID=58969044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611016618.2A Active CN106780525B (en) | 2016-11-18 | 2016-11-18 | Optical remote sensing image ship direction feature extraction method based on coordinate rotation minimum circumscribed rectangle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106780525B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460367A (en) * | 2018-03-28 | 2018-08-28 | 北方工业大学 | Target detection method based on prejudgment mechanism |
| CN108596223A (en) * | 2018-04-11 | 2018-09-28 | 珠海博明视觉科技有限公司 | A method of automatically generating object data set |
| CN108830862A (en) * | 2018-06-08 | 2018-11-16 | 江南大学 | Based on the crab of image segmentation towards recognition methods |
| CN109034173A (en) * | 2017-06-08 | 2018-12-18 | 北京君正集成电路股份有限公司 | Target object choosing method and device |
| CN109034153A (en) * | 2018-07-20 | 2018-12-18 | 泰康保险集团股份有限公司 | A kind of method and device of the image fidelity applied to image rotation |
| CN109657713A (en) * | 2018-12-11 | 2019-04-19 | 武汉大学 | A kind of multiple-factor road network method and system based on crowd-sourced road net data |
| CN110223302A (en) * | 2019-05-08 | 2019-09-10 | 华中科技大学 | A kind of naval vessel multi-target detection method extracted based on rotary area |
| CN112184744A (en) * | 2020-11-29 | 2021-01-05 | 惠州高视科技有限公司 | Display screen edge defect detection method and device |
| CN113534795A (en) * | 2021-06-30 | 2021-10-22 | 深圳市银星智能科技股份有限公司 | Equipment searching method and self-moving equipment |
| CN114047865A (en) * | 2021-11-11 | 2022-02-15 | 四川长虹教育科技有限公司 | Graphic control method |
| CN114281076A (en) * | 2021-12-13 | 2022-04-05 | 烟台杰瑞石油服务集团股份有限公司 | Robot covering and moving operation method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001357401A (en) * | 2000-06-12 | 2001-12-26 | Matsushita Electric Works Ltd | Picture processing method |
| US20050175239A1 (en) * | 2004-02-10 | 2005-08-11 | Tadashi Araki | Correcting image distortion caused by scanning |
| CN102496018A (en) * | 2011-12-08 | 2012-06-13 | 方正国际软件有限公司 | Document skew detection method and system |
| CN104077777A (en) * | 2014-07-04 | 2014-10-01 | 中国科学院大学 | Sea surface vessel target detection method |
| CN104484883A (en) * | 2014-12-24 | 2015-04-01 | 河海大学常州校区 | Video-based three-dimensional virtual ship positioning and track simulation method |
| CN105809705A (en) * | 2016-03-30 | 2016-07-27 | 广东工业大学 | Patch element positioning identification method based on minimum enclosing rectangle |
-
2016
- 2016-11-18 CN CN201611016618.2A patent/CN106780525B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001357401A (en) * | 2000-06-12 | 2001-12-26 | Matsushita Electric Works Ltd | Picture processing method |
| US20050175239A1 (en) * | 2004-02-10 | 2005-08-11 | Tadashi Araki | Correcting image distortion caused by scanning |
| CN102496018A (en) * | 2011-12-08 | 2012-06-13 | 方正国际软件有限公司 | Document skew detection method and system |
| CN104077777A (en) * | 2014-07-04 | 2014-10-01 | 中国科学院大学 | Sea surface vessel target detection method |
| CN104484883A (en) * | 2014-12-24 | 2015-04-01 | 河海大学常州校区 | Video-based three-dimensional virtual ship positioning and track simulation method |
| CN105809705A (en) * | 2016-03-30 | 2016-07-27 | 广东工业大学 | Patch element positioning identification method based on minimum enclosing rectangle |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034173A (en) * | 2017-06-08 | 2018-12-18 | 北京君正集成电路股份有限公司 | Target object choosing method and device |
| CN108460367A (en) * | 2018-03-28 | 2018-08-28 | 北方工业大学 | Target detection method based on prejudgment mechanism |
| CN108596223A (en) * | 2018-04-11 | 2018-09-28 | 珠海博明视觉科技有限公司 | A method of automatically generating object data set |
| CN108830862A (en) * | 2018-06-08 | 2018-11-16 | 江南大学 | Based on the crab of image segmentation towards recognition methods |
| CN108830862B (en) * | 2018-06-08 | 2021-11-30 | 江南大学 | Crab orientation identification method based on image segmentation |
| CN109034153A (en) * | 2018-07-20 | 2018-12-18 | 泰康保险集团股份有限公司 | A kind of method and device of the image fidelity applied to image rotation |
| CN109034153B (en) * | 2018-07-20 | 2022-04-26 | 泰康保险集团股份有限公司 | Image fidelity method and device applied to image rotation |
| CN109657713A (en) * | 2018-12-11 | 2019-04-19 | 武汉大学 | A kind of multiple-factor road network method and system based on crowd-sourced road net data |
| CN110223302B (en) * | 2019-05-08 | 2021-11-19 | 华中科技大学 | Ship multi-target detection method based on rotation region extraction |
| CN110223302A (en) * | 2019-05-08 | 2019-09-10 | 华中科技大学 | A kind of naval vessel multi-target detection method extracted based on rotary area |
| CN112184744B (en) * | 2020-11-29 | 2021-03-30 | 惠州高视科技有限公司 | Display screen edge defect detection method and device |
| CN112184744A (en) * | 2020-11-29 | 2021-01-05 | 惠州高视科技有限公司 | Display screen edge defect detection method and device |
| CN113534795A (en) * | 2021-06-30 | 2021-10-22 | 深圳市银星智能科技股份有限公司 | Equipment searching method and self-moving equipment |
| CN114047865A (en) * | 2021-11-11 | 2022-02-15 | 四川长虹教育科技有限公司 | Graphic control method |
| CN114047865B (en) * | 2021-11-11 | 2023-04-25 | 四川长虹教育科技有限公司 | Graphic control method |
| CN114281076A (en) * | 2021-12-13 | 2022-04-05 | 烟台杰瑞石油服务集团股份有限公司 | Robot covering and moving operation method |
| CN114281076B (en) * | 2021-12-13 | 2024-02-09 | 烟台杰瑞石油服务集团股份有限公司 | Covering and moving operation method of robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106780525B (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106780525A (en) | Optical remote sensing image ship direction feature extraction method based on coordinate rotation minimum circumscribed rectangle | |
| CN108805904B (en) | Moving ship detection and tracking method based on satellite sequence image | |
| CN106651880B (en) | Offshore moving target detection method based on multi-feature fusion thermal infrared remote sensing image | |
| CN111476120B (en) | Unmanned aerial vehicle intelligent ship water gauge identification method and device | |
| CN101609504A (en) | A kind of method for detecting, distinguishing and locating infrared imagery sea-surface target | |
| CN109117802A (en) | Ship Detection towards large scene high score remote sensing image | |
| CN103020975A (en) | Wharf and ship segmentation method combining multi-source remote sensing image characteristics | |
| CN108229342A (en) | A kind of surface vessel target automatic testing method | |
| CN108846844B (en) | Sea surface target detection method based on sea antenna | |
| CN110428425B (en) | Sea-land separation method of SAR image based on coastline vector data | |
| CN107909002B (en) | Sea-land segmentation method of infrared remote sensing image based on coastline matching | |
| CN104992172B (en) | Port remote sensing image shore ship detection method based on coastal outburst and different area scanning | |
| CN115456970B (en) | Method for identifying carrier line of topside-cut ship based on dimension-reduction regression | |
| CN108229433A (en) | A kind of Inshore ship detection method based on line segment detection and shape feature | |
| CN108288268B (en) | Method for detecting ship landing in high-resolution remote sensing image based on projection analysis | |
| CN110210428A (en) | A kind of smog root node detection method under remote complex environment based on MSER | |
| CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
| CN107169412B (en) | Remote sensing image harbor-berthing ship detection method based on mixed model decision | |
| CN109961065A (en) | A kind of surface vessel object detection method | |
| CN111428573A (en) | Infrared weak and small target detection false alarm suppression method under complex background | |
| CN113781523B (en) | Football detection tracking method and device, electronic equipment and storage medium | |
| CN113888456B (en) | Corner detection method based on contour | |
| CN113723314A (en) | Sugarcane stem node identification method based on YOLOv3 algorithm | |
| CN117115193A (en) | Infrared ship positioning method based on line inhibition | |
| CN109918968B (en) | Ship target detection method |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Bi Fukun Inventor after: Han Jianhong Inventor after: Zhang Xu Inventor after: Chen Jing Inventor after: Ge Xianjun Inventor after: Ma Xiao Inventor before: Bi Fukun Inventor before: Zhang Xu Inventor before: Chen Jing Inventor before: Ge Xianjun Inventor before: Ma Xiao |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |