CN104504684B - Edge extraction method and device - Google Patents
Edge extraction method and device Download PDFInfo
- Publication number
- CN104504684B CN104504684B CN201410724960.2A CN201410724960A CN104504684B CN 104504684 B CN104504684 B CN 104504684B CN 201410724960 A CN201410724960 A CN 201410724960A CN 104504684 B CN104504684 B CN 104504684B
- Authority
- CN
- China
- Prior art keywords
- edge
- line segment
- line
- straight line
- characteristic value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The disclosure relates to an edge extraction method and device, and belongs to the field of image processing. The method comprises the steps that an edge image of a target object is acquired, and the edge image comprises multiple candidate edge lines; a first candidate edge line meeting the preset conditions is extracted from the multiple candidate edge lines; the first candidate edge line is extended so that an edge line grid is acquired; as for all the straight lines in the edge line grid, the characteristic values of the straight lines are calculated according to the pixel value of each line segment on the straight lines and the pixel value of the line segment arranged in the same position with each line segment on the straight lines in the edge image; and when the characteristic values of the straight lines are greater than a preset threshold value, the straight lines are confirmed to be the edge lines of the target object. Accuracy of edge extraction is enhanced, and an enclosed contour can be formed by the multiple confirmed edge lines. When three-dimensional model reconstruction is performed according to the multiple edge lines, the reconstruction effect can be enhanced.
Description
Technical field
The disclosure is directed to image processing field, specifically on edge extracting method and device.
Background technology
With the development of information technology, three-dimensional model building rebuilds the important hand for having turned into and having obtained fabric structure information
Section, all has a wide range of applications in fields such as urban planning, communications facility construction and digital urban construction.And in order to be built
Thing reconstructing three-dimensional model is, it is necessary to first extract the edge of building.
When the edge of building is extracted, the image of building can be first obtained, denoising is carried out to image, obtain ash
Degree image, using the edge of the operator extraction gray level images such as Sobel (Sobel) or Canny, as the edge of building.
Realize it is of the invention during, inventor find correlation technique existing defects, for example：Carried using the above method
The edge got is mostly short-term section, it is difficult to constitute the profile of complete closure, and includes many tiny fluctuations, side in short-term section
The degree of accuracy that edge is extracted is very poor.When carrying out reconstructing three-dimensional model according to these short-terms section, poor effect is rebuild.
The content of the invention
In order to solve problem present in correlation technique, present disclose provides a kind of edge extracting method and device.It is described
Technical scheme is as follows：
According to the first aspect of the embodiment of the present disclosure, there is provided a kind of edge extracting method, methods described includes：
The edge image of object is obtained, the edge image includes a plurality of candidate edge that the object is extracted
Line；
From a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate edge lines；
A plurality of first candidate edge lines are extended, edge wire grid is obtained, the edge wire grid includes
A plurality of straight line, every straight line includes a plurality of line segment；
For every straight line in the edge wire grid, according to every pixel value of line segment, Yi Ji on the straight line
With the pixel value of line segment of the every line segment in same position on the straight line in the edge image, the spy of the straight line is calculated
Value indicative；
When the characteristic value of the straight line is more than predetermined threshold value, the straight line is defined as the edge line of the object.
In another embodiment, described from a plurality of candidate edge lines, extraction is a plurality of to meet pre-conditioned first
Candidate edge lines include：
From a plurality of candidate edge lines, the candidate edge lines that length belongs to preset length scope are extracted, as first
Candidate edge lines；Or,
From a plurality of candidate edge lines, the candidate edge lines that angle belongs to predetermined angle scope are extracted, as first
Candidate edge lines；Or,
From a plurality of candidate edge lines, extraction length belongs to the preset length scope and angle belongs to described default
The candidate edge lines of angular range, as the first candidate edge lines.
In another embodiment, every straight line in the edge wire grid, according to every on the straight line
The pixel value of line segment, and the pixel in the edge image with line segment of the every line segment in same position on the straight line
Value, the characteristic value for calculating the straight line includes：
For every line segment in the edge wire grid, the pixel value of every line segment in the edge wire grid
And in the edge image with the edge wire grid in every line segment be in same position line segment pixel value, really
The characteristic value of every line segment in the fixed edge wire grid；
For every straight line in the edge wire grid, according to every characteristic value of line segment on the straight line, institute is calculated
State the characteristic value of straight line.
In another embodiment, every line segment in each of the edges wire grid in the edge wire grid,
The pixel value of every line segment in the edge wire grid and in the edge image with the line segment be in it is identical
The pixel value of the line segment of position, determining the characteristic value of every line segment in the edge wire grid includes：
When any bar line segment in the edge wire grid pixel value with the edge image with any bar
When the pixel value of line segment of the line segment in same position is identical, the characteristic value of any bar line segment is defined as the first default spy
Value indicative；Or,
When any bar line segment in the edge wire grid pixel value with the edge image with any bar
When line segment is in the pixel value difference of the line segment of same position, the characteristic value of any bar line segment is defined as the second default spy
Value indicative.
In another embodiment, every straight line in the edge wire grid, according to every on the straight line
The characteristic value of line segment, the characteristic value for calculating the straight line includes：
Using characteristic value of the every characteristic value sum of line segment as the straight line on the straight line；Or,
Using characteristic value of the every average value of the characteristic value of line segment as the straight line on the straight line；Or,
Using characteristic value of the every variance of the characteristic value of line segment as the straight line on the straight line.
In another embodiment, methods described also includes：
Every two edge lines in for fixed a plurality of edge line, when the angle of two edge lines is identical, and
When the distance between described two edge lines are less than predeterminable range, two edge lines are merged.
According to the second aspect of the embodiment of the present disclosure, there is provided a kind of edge extraction device, described device includes：
Image collection module, the edge image for obtaining object, the edge image includes that the object is carried
The a plurality of candidate edge lines got；
Extraction module, the first pre-conditioned candidate side is met for from a plurality of candidate edge lines, extraction to be a plurality of
Edge line；
Extension of module, for extending to a plurality of first candidate edge lines, obtains edge wire grid, the edge
Wire grid includes a plurality of straight line, and every straight line includes a plurality of line segment；
Characteristic value calculating module, for for every straight line in the edge wire grid, according to every on the straight line
The pixel value of line segment, and the pixel in the edge image with line segment of the every line segment in same position on the straight line
Value, calculates the characteristic value of the straight line；
Edge line determining module, for when the characteristic value of the straight line is more than predetermined threshold value, the straight line being defined as
The edge line of the object.
In another embodiment, the extraction module is used for from a plurality of candidate edge lines, extracts length and belongs to pre-
If the candidate edge lines of length range, as the first candidate edge lines；Or, from a plurality of candidate edge lines, extract angle
Degree belongs to the candidate edge lines of predetermined angle scope, used as the first candidate edge lines；Or, from a plurality of candidate edge lines
In, extract length and belong to the preset length scope and angle belongs to the candidate edge lines of the predetermined angle scope, as the
One candidate edge lines.
In another embodiment, the characteristic value calculating module is used for for every line segment in the edge wire grid,
The pixel value of every line segment in the edge wire grid and in the edge image with the edge wire grid in
Every line segment be in same position line segment pixel value, determine the characteristic value of every line segment in the edge wire grid；
For every straight line in the edge wire grid, according to every characteristic value of line segment on the straight line, the straight line is calculated
Characteristic value.
In another embodiment, the characteristic value calculating module is used for when any bar line segment in the edge wire grid
When pixel value is identical with the pixel value with line segment of any bar line segment in same position in the edge image, by institute
The characteristic value for stating any bar line segment is defined as the first default characteristic value；Or, any bar line segment in the edge wire grid
Pixel value from the edge image with any bar line segment be in same position line segment pixel value it is different when, general
The characteristic value of any bar line segment is defined as the second default characteristic value.
In another embodiment, the characteristic value calculating module is used for every characteristic value sum of line segment on the straight line
As the characteristic value of the straight line；Or, using every average value of the characteristic value of line segment on the straight line as the straight line
Characteristic value；Or, using characteristic value of the every variance of the characteristic value of line segment as the straight line on the straight line.
In another embodiment, described device also includes：
Merging module, for every two edge lines in for fixed a plurality of edge line, when two edge lines
Angle it is identical, and the distance between two edge lines less than predeterminable range when, will two edge lines merging.
According to the third aspect of the embodiment of the present disclosure, there is provided a kind of edge extraction device, including：
Processor；
Memory for storing processor-executable instruction；
Wherein, the processor is configured as：
The edge image of object is obtained, the edge image includes a plurality of candidate edge that the object is extracted
Line；
From a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate edge lines；
A plurality of first candidate edge lines are extended, edge wire grid is obtained, the edge wire grid includes
A plurality of straight line, every straight line includes a plurality of line segment；
For every straight line in the edge wire grid, according to every pixel value of line segment, Yi Ji on the straight line
With the pixel value of line segment of the every line segment in same position on the straight line in the edge image, the spy of the straight line is calculated
Value indicative；
When the characteristic value of the straight line is more than predetermined threshold value, the straight line is defined as the edge line of the object.
The technical scheme provided by this disclosed embodiment can include the following benefits：
The method and apparatus that the present embodiment is provided, are filtered and are extended, by the edge gauze by candidate edge lines
Line segment in lattice is compared with the line segment in former edge image, therefrom determines multiple edge lines of the object, improves side
The accuracy rate that edge is extracted, and the multiple edge lines for determining may be constructed the profile of closing, when carrying out three according to the plurality of edge line
When dimension module is rebuild, reconstruction effect can be improved.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary, this can not be limited
It is open.
Brief description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows and meets implementation of the invention
Example, and be used to explain principle of the invention together with specification.
Fig. 1 is a kind of flow chart of the edge extracting method according to an exemplary embodiment；
Fig. 2 is a kind of flow chart of the edge extracting method according to an exemplary embodiment；
Fig. 3 A are the target object image schematic diagrames according to an exemplary embodiment；
Fig. 3 B are the edge image schematic diagrames according to an exemplary embodiment；
Fig. 3 C are the edge line schematic diagrames according to an exemplary embodiment；
Fig. 4 A are a kind of block diagrams of the edge extraction device according to an exemplary embodiment；
Fig. 4 B are a kind of block diagrams of the edge extraction device according to an exemplary embodiment；
Fig. 5 is a kind of block diagram of the device for edge extracting according to an exemplary embodiment.
Specific embodiment
It is right with reference to implementation method and accompanying drawing for the purpose, technical scheme and advantage for making the disclosure become more apparent
The disclosure is described in further details.Here, the exemplary embodiment of the disclosure and its illustrating for explaining the disclosure, but simultaneously
Not as restriction of this disclosure.
The embodiment of the present disclosure provides a kind of edge extracting method and device, and the disclosure is carried out specifically below in conjunction with accompanying drawing
It is bright.
Fig. 1 is a kind of flow chart of the edge extracting method according to an exemplary embodiment, as shown in figure 1, the side
Edge extracting method is used in image processing apparatus, comprises the following steps：
In a step 101, the edge image of object is obtained, it is a plurality of that the edge image includes that the object is extracted
Candidate edge lines.
Wherein, the object can be window, card on building, building etc., and the image processing apparatus have place
The function of image is managed, can be mobile phone, computer or server etc., the present embodiment is not limited this.The image procossing is filled
Put the edge image that can receive other equipment transmission, it is also possible to which the image to the object carries out edge extracting treatment, obtains
To the edge image, the edge image can be binary image, and the present embodiment is not also limited this.
In a step 102, from a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate edge
Line.
Wherein, at least one in the pre-conditioned length and angle for specifying edge line or other conditions, this
Embodiment is not limited this.Accordingly, this pre-conditioned can include in preset length scope and predetermined angle scope extremely
One item missing.The preset length scope and the predetermined angle scope can include continuous number range, it is also possible to including discrete
Multiple numerical value, for example, the predetermined angle may range from { 0 °, 90 ° }.And the preset length scope and the predetermined angle scope can
With by the image processing apparatus previously according to the object in the image before the edge image is processed by edge extracting
Size and angle determine that the present embodiment is not limited this respectively.
In step 103, a plurality of first candidate edge lines are extended, obtains edge wire grid, the edge gauze
Lattice include a plurality of straight line, and every straight line includes a plurality of line segment.
At step 104, for every straight line in the edge wire grid, according to every pixel of line segment on the straight line
Value, and the pixel value in the edge image with line segment of the every line segment in same position on the straight line, calculate the straight line
Characteristic value.
For every line segment in the edge wire grid, when in the edge image with the line segment identical position
During including line segment, represent that the line segment is likely on the object edge line, and in the edge image with the line segment identical
When position does not include line segment, represent that the line segment may not be on the edge line of the object.And in the edge wire grid
For every straight line, in a plurality of line segment of the straight line, may be more in the line segment on the edge line of the object, the straight line is this
The possibility of the edge line of object is higher, and may be fewer in the line segment on the edge line of the object, and the straight line is the mesh
The possibility for marking the edge line of thing is lower.Therefore, for every straight line in the edge wire grid, can be according to every on the straight line
The pixel value of bar line segment, and the pixel in the edge image with line segment of the every line segment in same position on the straight line
Value, calculates the characteristic value of the straight line.So, when the characteristic value of the straight line is bigger, representing may be in the object on the straight line
Edge line on line segment it is more, the straight line is that the possibility of the edge line of the object is higher, when the characteristic value of the straight line is got over
Hour, representing on the straight line that the line segment on the edge line for being probably the object is more, the straight line is the edge line of the object
Possibility it is lower.
In step 105, when the characteristic value of the straight line is more than predetermined threshold value, the straight line is defined as the side of the object
Edge line.
In the method that the present embodiment is provided, when a plurality of candidate edge lines of object are extracted, from a plurality of candidate side
In edge line, extraction is a plurality of to meet the first pre-conditioned candidate edge lines, edge wire grid is obtained after extension, for the edge line
Every straight line in grid, according to every pixel value of line segment on the straight line, and in the edge image it is every with the straight line
Bar line segment is in the pixel value of the line segment of same position, calculates the characteristic value of the straight line, when the characteristic value of the straight line is more than default
During threshold value, the straight line is defined as the edge line of the object.Filtered and extended by candidate edge lines, by the edge
Line segment in wire grid is compared with the line segment in former edge image, therefrom determines multiple edge lines of the object, improves
The accuracy rate of edge extracting, and the multiple edge lines for determining may be constructed the profile of closing, enter when according to the plurality of edge line
During row reconstructing three-dimensional model, reconstruction effect can be improved.
In another embodiment, should be from a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate
Edge line includes：
From a plurality of candidate edge lines, the candidate edge lines that length belongs to preset length scope are extracted, waited as first
Select edge line；Or,
From a plurality of candidate edge lines, the candidate edge lines that angle belongs to predetermined angle scope are extracted, waited as first
Select edge line；Or,
From a plurality of candidate edge lines, extraction length belongs to the preset length scope and angle belongs to the predetermined angle model
The candidate edge lines enclosed, as the first candidate edge lines.
In another embodiment, should be for every straight line in the edge wire grid, according to every line segment on the straight line
Pixel value, and the pixel value in the edge image with line segment of the every line segment in same position on the straight line, calculating should
The characteristic value of straight line includes：
For every line segment in the edge wire grid, pixel value according to the line segment and in the edge image with should
Line segment is in the pixel value of the line segment of same position, determines the characteristic value of the line segment；
For every straight line in the edge wire grid, according to every characteristic value of line segment on the straight line, the straight line is calculated
Characteristic value.
In another embodiment, should for every line segment in the edge wire grid, pixel value according to the line segment and
The pixel value of the line segment of same position is in the line segment in the edge image, determining the characteristic value of the line segment includes：
When the pixel value and the pixel value phase in the edge image with line segment of the line segment in same position of the line segment
Meanwhile, the characteristic value of the line segment is defined as the first default characteristic value；Or,
The pixel value for being in the line segment of same position with the line segment when the pixel value of the line segment and in the edge image is not
Meanwhile, the characteristic value of the line segment is defined as the second default characteristic value.
In another embodiment, should be for every straight line in the edge wire grid, according to every line segment on the straight line
Characteristic value, the characteristic value for calculating the straight line includes：
Using characteristic value of the every characteristic value sum of line segment as the straight line on the straight line；Or,
Using characteristic value of the every average value of the characteristic value of line segment as the straight line on the straight line；Or,
Using characteristic value of the every variance of the characteristic value of line segment as the straight line on the straight line.
In another embodiment, the method also includes：
Every two edge lines in for fixed a plurality of edge line, when the angle of two edge lines is identical, and should
When the distance between two edge lines are less than predeterminable range, two edge lines are merged.
Above-mentioned all optional technical schemes, can form alternative embodiment of the invention, herein no longer using any combination
Repeat one by one.
Fig. 2 is a kind of flow chart of the edge extracting method according to an exemplary embodiment, as shown in Fig. 2 the side
Edge extracting method is used in image processing apparatus, comprises the following steps：
In step 201, the image processing apparatus obtain the edge image of object, and the edge image includes the target
The a plurality of candidate edge lines that thing is extracted.
In actual applications, a plurality of candidate edge lines that the edge image includes are mostly short-term section, are wrapped in short-term section
Tiny fluctuation is included, and a plurality of short-term section can not constitute the profile of complete closure, when carrying out three-dimensional mould according to these short-terms section
When type is rebuild, poor effect is rebuild.In order to improve reconstruction effect, the image processing apparatus can be to the edge image at
Reason, obtains the edge line that the object becomes apparent from.
In addition, for the ease of extracting edge line, the image processing apparatus first can also expand to the edge image, plus
The thick a plurality of candidate edge lines, in subsequent process, the image processing apparatus are processed the image after the expansion.
In step 202., from a plurality of candidate edge lines, extraction is a plurality of to meet pre-conditioned to the image processing apparatus
First candidate edge lines.
The image processing apparatus first according to pre-conditioned can be filtered to a plurality of candidate edge lines, therefrom be extracted
Go out to be likely to be the first candidate edge lines of the edge line of the object, on the contrary it will not be possible to be the candidate side of the edge line of the object
Edge line is filtered out.
Wherein, at least one in the pre-conditioned length and angle for specifying edge line or other conditions, phase
Answer, this it is pre-conditioned can include preset length scope and predetermined angle scope at least one.When the pre-conditioned bag
When including the preset length scope, the image processing apparatus extract length and belong to preset length model from a plurality of candidate edge lines
The candidate edge lines enclosed, as the first candidate edge lines, length can also be not belonging to the candidate edge of the preset length scope
Line is used as the second candidate edge lines.Or, when this it is pre-conditioned including the predetermined angle scope when, the image processing apparatus from this
In a plurality of candidate edge lines, the candidate edge lines that angle belongs to predetermined angle scope are extracted, as the first candidate edge lines, may be used also
So that angle to be not belonging to the candidate edge lines of the predetermined angle scope as the second candidate edge lines.Or, when this is pre-conditioned
During including the preset length scope with the predetermined angle scope, the image processing apparatus are extracted from a plurality of candidate edge lines
Length belongs to the preset length scope and angle belongs to the candidate edge lines of the predetermined angle scope, used as the first candidate edge
Line, by length can also be not belonging to the preset length scope or angle is not belonging to the candidate edge lines of the predetermined angle scope and makees
It is the second candidate edge lines.
When the image processing apparatus extract a plurality of first candidate edge lines, can be by undrawn second candidate side
The pixel value of each pixel is adjusted to 0 on edge line, to filter second candidate edge lines.
In actual applications, the image processing apparatus can carry out Hough transformation to the edge image, by a plurality of candidate
, from the former coordinate system transformation of the edge image to hough space, the candidate edge lines correspondence in the former coordinate system is suddenly for edge line
A point in husband space, then the image processing apparatus are according to the predetermined angle scope and preset length scope, to hough space
In multiple points filtered, then carry out Hough inverse transformation, after being filtered in hough space remaining point transformation to former coordinate system,
Obtain a plurality of first candidate edge lines.
In step 203, the image processing apparatus extend to a plurality of first candidate edge lines, obtain edge gauze
Lattice, the edge wire grid includes a plurality of straight line, and every straight line includes a plurality of line segment.
The image processing apparatus can extend to a plurality of first candidate edge lines, will a plurality of first candidate side
Edge line extends two ends along the respective direction pointed to, untill the edge for extending to image, then a plurality of first candidate edge lines
Straight line intersect, form edge wire grid, the edge wire grid includes a plurality of straight line, and every straight line and other
Line segmentation is into a plurality of line segment.
In step 204, for every line segment in the edge wire grid, picture of the image processing apparatus according to the line segment
Element is worth and is in the line segment in the edge image pixel value of the line segment of same position, determines the characteristic value of the line segment.
For every line segment in the edge wire grid, when in the edge image with the line segment identical position
During including line segment, represent that the line segment is likely on the object edge line, and in the edge image with the line segment identical
When position does not include line segment, represent that the line segment may not be on the edge line of the object.And in the edge wire grid
For every straight line, in a plurality of line segment of the straight line, may be more in the line segment on the edge line of the object, the straight line is this
The possibility of the edge line of object is higher, and may be fewer in the line segment on the edge line of the object, and the straight line is the mesh
The possibility for marking the edge line of thing is lower.
Based on These characteristics, for every straight line in the edge wire grid, the image processing apparatus can be straight according to this
Every pixel value of line segment on line, and the line segment of same position is in every line segment on the straight line in the edge image
Pixel value, calculates the characteristic value of the straight line.
For every line segment in the edge wire grid, the image processing apparatus can obtain the pixel value of the line segment, with
And it is in the pixel value of the line segment of same position with the line segment in the edge image, pixel value according to the line segment and at this
The pixel value of the line segment of same position is in edge image with the line segment, the characteristic value of the line segment is determined.The image procossing is filled
Put may determine that the line segment for being in same position in the pixel value of the line segment and the edge image with the line segment pixel value whether
Identical, if identical, the characteristic value of the line segment is defined as the first default characteristic value by the image processing apparatus, if it is different, should
The characteristic value of the line segment is defined as the second default characteristic value by image processing apparatus, and the second default characteristic value is first pre- less than this
If characteristic value.Wherein, the first default characteristic value and the second default characteristic value can be predefined by the image processing apparatus,
The first default characteristic value can be 1, and the second default characteristic value can be 0, and the present embodiment is not limited this.
So that the edge image is as binary image as an example, the pixel value of every line segment is 1 in the edge wire grid, for
For every line segment in the edge wire grid, when the pixel value of the line segment for being in same position in the edge image with the line segment
For 1 when, determine that the characteristic value of the line segment is 1, when the pixel value of the line segment for being in same position in the edge image with the line segment
For 0 when, determine the line segment characteristic value be 0.
During practical application, the image obtained after extending to a plurality of first candidate edge lines specifies figure as first
Picture, then the image processing apparatus can to the edge image and this first specify image carry out and computing, obtain second specify figure
Picture, the second specified image includes the line segment that pixel value is 1 and the line segment that pixel value is 0, for the second specified image
For middle pixel value is 1 line segment, represent the edge image and this first specify image, it is identical with the line segment present position
Position also include line segment, then first specify the characteristic value of line segment for being in same position with the line segment in image be defined as this
The first default characteristic value.For this second specify image in for pixel value is 0 line segment, represent in the edge image or
This first specify image in, with the line segment present position identical position not include line segment, then by this first specify image in
The characteristic value that the line segment is in the line segment of same position is defined as the second default characteristic value.
In addition, if the image processing apparatus edge image is expanded after again to a plurality of first candidate edge lines
Extended, then can by the image after expanding and this first specify image carry out with computing, will not be repeated here.
In step 205, for every straight line in the edge wire grid, the image processing apparatus are according to every on the straight line
The characteristic value of bar line segment, calculates the characteristic value of the straight line.
For every straight line in the edge wire grid, when the image processing apparatus determine on the straight line every line segment
During characteristic value, the characteristic value of a plurality of line segment can be counted, obtain the characteristic value of the straight line.
The image processing apparatus can be using characteristic value of the every characteristic value sum of line segment as the straight line on the straight line；Or
Person, using characteristic value of the every average value of the characteristic value of line segment as the straight line on the straight line；Or, by every line on the straight line
The variance of the characteristic value of section as the straight line characteristic value, or by every other statistical values of the characteristic value of line segment on the straight line
Used as the characteristic value of the straight line, the present embodiment is not limited this.
In step 206, when the characteristic value of the straight line is more than predetermined threshold value, the image processing apparatus determine the straight line
It is the edge line of the object.
For every straight line in the edge wire grid, when the characteristic value of the straight line is bigger, represent on the straight line
May be more in the line segment on the edge line of the object, the straight line is that the possibility of the edge line of the object is higher, when this
The characteristic value of straight line gets over hour, represents on the straight line that the line segment on the edge line for being probably the object is more, and the straight line is this
The possibility of the edge line of object is lower.Therefore, the image processing apparatus can predefine predetermined threshold value, it is straight for every
For line, when the characteristic value of the straight line is more than the predetermined threshold value, it is believed that the straight line is the edge line of the object, then should
The straight line is defined as image processing apparatus the edge line of the object.And the characteristic value for working as the straight line is not more than the predetermined threshold value
When, it is believed that the straight line is not the edge line of the object, then the image processing apparatus filter out the straight line.
Wherein, the predetermined threshold value can by the image processing apparatus previously according to the first default characteristic value, this is second pre-
If every statistics Value Types of the characteristic value of line segment determine that the present embodiment is not limited this on characteristic value and straight line.
In step 207, for fixed a plurality of edge line in every two edge lines, when two angles of edge line
Degree is identical, and the distance between two edge lines less than predeterminable range when, the image processing apparatus close two edge lines
And.
In actual applications, a plurality of line segment in the edge image on the same edge line of the object may be due to
In the presence of reasons such as fluctuation, distortions, and two straight lines in the edge wire grid have been extended into it so that be finally accordingly determined two
Bar edge line.In order to the repetition for preventing edge line determines, when the image processing apparatus have determined that a plurality of edge line of the object
When, for a plurality of edge line in every two edge lines, the image processing apparatus may determine that two angles of edge line
Whether identical, if the angle of two edge lines is identical, the image processing apparatus calculate the distance between two edge lines,
Judge that whether the distance, less than predeterminable range, when the distance is less than the predeterminable range, represents that two edge lines are same one side
Edge line, then merge two edge lines.The image processing apparatus can delete wherein in two edge lines, will
A remaining edge line as the object, it is also possible to generate one with two sides in two edge line centre positions
The parallel edge line of edge line, two edge lines are deleted, using newly-generated edge line as the object edge line, this reality
Example is applied not limit the mode that the image processing apparatus merge.
Fig. 3 A are the target object image schematic diagrames according to an exemplary embodiment, and the image processing apparatus can basis
Fig. 3 A carry out edge extracting, obtain the edge image shown in Fig. 3 B.Referring to Fig. 3 B, the edge image include it is a plurality of it is tiny,
The line segment of bending, these line segments are dispersedly distributed in the edge image, and the image processing apparatus can be carried using the present embodiment
The method of confession, to Fig. 3 B treatment, obtains the image shown in Fig. 3 C.Referring to Fig. 3 C, the image include it is a plurality of clearly
Straight line, a plurality of straight line constitutes the profile for completing closing.
When the method that the image processing apparatus application the present embodiment is provided, when obtaining the sharp edge line of the object, can
It is stored in database with the image that will include the sharp edge line, in order to the object in subsequent process in the image
Edge line, carry out reconstructing three-dimensional model.For example, when the object is building, according to the figure comprising the building edge line
Picture, can set up the threedimensional model of the building, and the threedimensional model can be used for generating city three-dimensional map, or for aiding in
Communications facility arrangement on the building, or for architectural engineering teaching etc., the present embodiment is not limited this.
In the method that the present embodiment is provided, when a plurality of candidate edge lines of object are extracted, from a plurality of candidate side
In edge line, extraction is a plurality of to meet the first pre-conditioned candidate edge lines, edge wire grid is obtained after extension, for the edge line
Every straight line in grid, according to every pixel value of line segment on the straight line, and in the edge image it is every with the straight line
Bar line segment is in the pixel value of the line segment of same position, calculates the characteristic value of the straight line, when the characteristic value of the straight line is more than default
During threshold value, the straight line is defined as the edge line of the object.Filtered and extended by candidate edge lines, by the edge
Line segment in wire grid is compared with the line segment in former edge image, therefrom determines multiple edge lines of the object, improves
The accuracy rate of edge extracting, and the multiple edge lines for determining may be constructed the profile of closing, enter when according to the plurality of edge line
During row reconstructing three-dimensional model, reconstruction effect can be improved.
Fig. 4 A are a kind of block diagrams of the edge extraction device according to an exemplary embodiment, referring to Fig. 4 A, the device
Including image collection module 401, extraction module 402, extension of module 403, characteristic value calculating module 404 and edge line determining module
405。
Image collection module 401 is configurable for obtaining the edge image of object, and the edge image includes the mesh
The a plurality of candidate edge lines that mark thing is extracted；
Extraction module 402 is configurable for from a plurality of candidate edge lines, is extracted and a plurality of is met pre-conditioned the
One candidate edge lines；
Extension of module 403 is configurable for extending a plurality of first candidate edge lines, obtains edge wire grid,
The edge wire grid includes a plurality of straight line, and every straight line includes a plurality of line segment；
Characteristic value calculating module 404 is configurable for for every straight line in the edge wire grid, according to the straight line
The pixel value of upper every line segment, and the picture in the edge image with line segment of the every line segment in same position on the straight line
Element value, calculates the characteristic value of the straight line；
Edge line determining module 405 is configurable for when the characteristic value of the straight line is more than predetermined threshold value, by the straight line
It is defined as the edge line of the object.
In the device that the present embodiment is provided, when a plurality of candidate edge lines of object are extracted, from a plurality of candidate side
In edge line, extraction is a plurality of to meet the first pre-conditioned candidate edge lines, edge wire grid is obtained after extension, for the edge line
Every straight line in grid, according to every pixel value of line segment on the straight line, and in the edge image it is every with the straight line
Bar line segment is in the pixel value of the line segment of same position, calculates the characteristic value of the straight line, when the characteristic value of the straight line is more than default
During threshold value, the straight line is defined as the edge line of the object.Filtered and extended by candidate edge lines, by the edge
Line segment in wire grid is compared with the line segment in former edge image, therefrom determines multiple edge lines of the object, improves
The accuracy rate of edge extracting, and the multiple edge lines for determining may be constructed the profile of closing, enter when according to the plurality of edge line
During row reconstructing three-dimensional model, reconstruction effect can be improved.
In another embodiment, the extraction module 402 is configurable for from a plurality of candidate edge lines, extracts length
Belong to the candidate edge lines of preset length scope, as the first candidate edge lines；Or, from a plurality of candidate edge lines, carry
The candidate edge lines that angle belongs to predetermined angle scope are taken, as the first candidate edge lines；Or, from a plurality of candidate edge lines
In, extraction length belongs to the preset length scope and angle belongs to the candidate edge lines of the predetermined angle scope, is waited as first
Select edge line.
In another embodiment, this feature value computing module 404 is configurable for for every in the edge wire grid
Bar line segment, pixel value according to the line segment and be in the line segment in the edge image same position line segment pixel
Value, determines the characteristic value of the line segment；For every straight line in the edge wire grid, according to every feature of line segment on the straight line
Value, calculates the characteristic value of the straight line.
In another embodiment, this feature value computing module 404 is configurable for when the pixel value of the line segment and at this
When identical with the pixel value that the line segment is in the line segment of same position in edge image, the characteristic value of the line segment is defined as first
Default characteristic value；Or, when the pixel value of the line segment is in the line segment of same position with the edge image with the line segment
When pixel value is different, the characteristic value of the line segment is defined as the second default characteristic value.
In another embodiment, this feature value computing module 404 is configurable for every spy of line segment on the straight line
Value indicative sum as the straight line characteristic value；Or, using every average value of the characteristic value of line segment on the straight line as the straight line
Characteristic value；Or, using characteristic value of the every variance of the characteristic value of line segment as the straight line on the straight line.
Referring to Fig. 4 B, in another embodiment, the device also includes：
Merging module 406 be configurable for for fixed a plurality of edge line in every two edge lines, when this two
The angle of bar edge line is identical, and the distance between two edge lines less than predeterminable range when, two edge lines are merged.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant the method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
It should be noted that：Above-described embodiment provide edge extraction device extract edge when, only with above-mentioned each function
The division of module is carried out for example, in practical application, as needed can distribute by different function moulds above-mentioned functions
Block is completed, will the internal structure of image processing apparatus be divided into different functional modules, with complete it is described above whole or
Person's partial function.In addition, the edge extraction device that above-described embodiment is provided belongs to same design with edge extracting method embodiment,
It implements process and refers to embodiment of the method, repeats no more here.
Fig. 5 is a kind of block diagram of the device 500 for edge extracting according to an exemplary embodiment.For example, dress
It can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, medical treatment to put 500
Equipment, body-building equipment, personal digital assistant etc..
Reference picture 5, device 500 can include following one or more assemblies：Processing assembly 502, memory 504, power supply
Component 506, multimedia groupware 508, audio-frequency assembly 510, the interface 512 of input/output (I/O), sensor cluster 514, and
Communication component 516.
The integrated operation of the usual control device 500 of processing assembly 502, such as with display, call, data communication, phase
Machine is operated and the associated operation of record operation.Treatment element 502 can refer to including one or more processors 520 to perform
Order, to complete all or part of step of above-mentioned method.Additionally, processing assembly 502 can include one or more modules, just
Interaction between processing assembly 502 and other assemblies.For example, processing component 502 can include multi-media module, it is many to facilitate
Interaction between media component 508 and processing assembly 502.
Memory 504 is configured as storing various types of data supporting the operation in equipment 500.These data are shown
Example includes the instruction for any application program or method for operating on device 500, and contact data, telephone book data disappears
Breath, picture, video etc..Memory 504 can be by any kind of volatibility or non-volatile memory device or their group
Close and realize, such as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM) is erasable to compile
Journey read-only storage (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash
Device, disk or CD.
Electric power assembly 506 provides electric power for the various assemblies of device 500.Electric power assembly 506 can include power management system
System, one or more power supplys, and other generate, manage and distribute the component that electric power is associated with for device 500.
Multimedia groupware 508 is included in one screen of output interface of offer between described device 500 and user.One
In a little embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch-screen, to receive the input signal from user.Touch panel includes one or more touch sensings
Device is with the gesture on sensing touch, slip and touch panel.The touch sensor can not only sensing touch or sliding action
Border, but also detection and the touch or slide related duration and pressure.In certain embodiments, many matchmakers
Body component 508 includes a front camera and/or rear camera.When equipment 500 be in operator scheme, such as screening-mode or
During video mode, front camera and/or rear camera can receive outside multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or with focusing and optical zoom capabilities.
Audio-frequency assembly 510 is configured as output and/or input audio signal.For example, audio-frequency assembly 510 includes a Mike
Wind (MIC), when device 500 is in operator scheme, such as call model, logging mode and speech recognition mode, microphone is matched somebody with somebody
It is set to reception external audio signal.The audio signal for being received can be further stored in memory 504 or via communication set
Part 516 sends.In certain embodiments, audio-frequency assembly 510 also includes a loudspeaker, for exports audio signal.
, to provide interface between processing assembly 502 and peripheral interface module, above-mentioned peripheral interface module can for I/O interfaces 512
To be keyboard, click wheel, button etc..These buttons may include but be not limited to：Home button, volume button, start button and lock
Determine button.
Sensor cluster 514 includes one or more sensors, and the state for providing various aspects for device 500 is commented
Estimate.For example, sensor cluster 514 can detect the opening/closed mode of equipment 500, the relative positioning of component is for example described
Component is the display and keypad of device 500, and sensor cluster 514 can be with 500 1 components of detection means 500 or device
Position change, user is presence or absence of with what device 500 was contacted, the orientation of device 500 or acceleration/deceleration and device 500
Temperature change.Sensor cluster 514 can include proximity transducer, be configured to be detected when without any physical contact
The presence of neighbouring object.Sensor cluster 514 can also include optical sensor, such as CMOS or ccd image sensor, for into
As being used in application.In certain embodiments, the sensor cluster 514 can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 516 is configured to facilitate the communication of wired or wireless way between device 500 and other equipment.Device
500 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.In an exemplary implementation
In example, communication component 516 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 516 also includes near-field communication (NFC) module, to promote junction service.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 500 can be by one or more application specific integrated circuits (ASIC), numeral letter
Number processor (DSP), digital signal processing appts (DSPD), PLD (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components realization, for performing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided
Such as include the memory 504 of instruction, above-mentioned instruction can be performed to complete the above method by the processor 520 of device 500.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by image processing apparatus
During computing device so that image processing apparatus are able to carry out a kind of edge extracting method, methods described includes：
The edge image of object is obtained, the edge image includes a plurality of candidate edge that the object is extracted
Line；
From a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate edge lines；
A plurality of first candidate edge lines are extended, edge wire grid is obtained, the edge wire grid includes
A plurality of straight line, every straight line includes a plurality of line segment；
For every straight line in the edge wire grid, according to every pixel value of line segment, Yi Ji on the straight line
With the pixel value of line segment of the every line segment in same position on the straight line in the edge image, the spy of the straight line is calculated
Value indicative；
When the characteristic value of the straight line is more than predetermined threshold value, the straight line is defined as the edge line of the object.
In another embodiment, described from a plurality of candidate edge lines, extraction is a plurality of to meet pre-conditioned first
Candidate edge lines include：
From a plurality of candidate edge lines, the candidate edge lines that length belongs to preset length scope are extracted, as first
Candidate edge lines；Or,
From a plurality of candidate edge lines, the candidate edge lines that angle belongs to predetermined angle scope are extracted, as first
Candidate edge lines；Or,
From a plurality of candidate edge lines, extraction length belongs to the preset length scope and angle belongs to described default
The candidate edge lines of angular range, as the first candidate edge lines.
In another embodiment, every straight line in the edge wire grid, according to every on the straight line
The pixel value of line segment, and the pixel in the edge image with line segment of the every line segment in same position on the straight line
Value, the characteristic value for calculating the straight line includes：
For every line segment in the edge wire grid, pixel value according to the line segment and in the edge image
In with the line segment be in same position line segment pixel value, determine the characteristic value of the line segment；
For every straight line in the edge wire grid, according to every characteristic value of line segment on the straight line, institute is calculated
State the characteristic value of straight line.
In another embodiment, every line segment in the edge wire grid, according to the pixel of the line segment
Value and in the edge image with the line segment be in same position line segment pixel value, determine the feature of the line segment
Value includes：
When the pixel value and the picture in the edge image with line segment of the line segment in same position of the line segment
When element value is identical, the characteristic value of the line segment is defined as the first default characteristic value；Or,
When the pixel value and the picture in the edge image with line segment of the line segment in same position of the line segment
When element value is different, the characteristic value of the line segment is defined as the second default characteristic value.
In another embodiment, every straight line in the edge wire grid, according to every on the straight line
The characteristic value of line segment, the characteristic value for calculating the straight line includes：
Using characteristic value of the every characteristic value sum of line segment as the straight line on the straight line；Or,
Using characteristic value of the every average value of the characteristic value of line segment as the straight line on the straight line；Or,
Using characteristic value of the every variance of the characteristic value of line segment as the straight line on the straight line.
In another embodiment, methods described also includes：
Every two edge lines in for fixed a plurality of edge line, when the angle of two edge lines is identical, and
When the distance between described two edge lines are less than predeterminable range, two edge lines are merged.
Those skilled in the art considering specification and after putting into practice invention disclosed herein, will readily occur to it is of the invention its
Its embodiment.The application is intended to any modification of the invention, purposes or adaptations, these modifications, purposes or
Person's adaptations follow general principle of the invention and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be appreciated that the invention is not limited in the precision architecture being described above and be shown in the drawings, and
And can without departing from the scope carry out various modifications and changes.The scope of the present invention is only limited by appended claim.
Claims (13)
1. a kind of edge extracting method, it is characterised in that methods described includes：
The edge image of object is obtained, the edge image includes a plurality of candidate edge lines that the object is extracted；
From a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate edge lines；
A plurality of first candidate edge lines are extended, edge wire grid is obtained, the edge wire grid includes a plurality of
Straight line, every straight line includes a plurality of line segment；
For every straight line in the edge wire grid, according to every pixel value of line segment on the straight line, and described
With the pixel value of line segment of the every line segment in same position on the straight line in edge image, the feature of the straight line is calculated
Value；
When the characteristic value of the straight line is more than predetermined threshold value, the straight line is defined as the edge line of the object.
2. method according to claim 1, it is characterised in that described from a plurality of candidate edge lines, extracts a plurality of
Meeting the first pre-conditioned candidate edge lines includes：
From a plurality of candidate edge lines, the candidate edge lines that length belongs to preset length scope are extracted, as the first candidate
Edge line；Or,
From a plurality of candidate edge lines, the candidate edge lines that angle belongs to predetermined angle scope are extracted, as the first candidate
Edge line；Or,
From a plurality of candidate edge lines, extraction length belongs to the preset length scope and angle belongs to the predetermined angle
The candidate edge lines of scope, as the first candidate edge lines.
3. method according to claim 1, it is characterised in that every straight line in the edge wire grid,
According to every pixel value of line segment on the straight line, and phase is in every line segment on the straight line in the edge image
With the pixel value of the line segment of position, the characteristic value for calculating the straight line includes：
For every line segment in the edge wire grid, the pixel value of every line segment in the edge wire grid and
In the edge image with the edge wire grid in every line segment be in same position line segment pixel value, determine institute
State the characteristic value of every line segment in edge wire grid；
For every straight line in the edge wire grid, according to every characteristic value of line segment on the straight line, calculate described straight
The characteristic value of line.
4. method according to claim 3, it is characterised in that every line segment in the edge wire grid,
The pixel value of every line segment in the edge wire grid and in the edge image with the edge wire grid in
Every line segment be in same position line segment pixel value, determine the characteristic value bag of every line segment in the edge wire grid
Include：
When any bar line segment in the edge wire grid pixel value with the edge image with any bar line segment
When the pixel value of the line segment in same position is identical, the characteristic value of any bar line segment is defined as the first default feature
Value；Or,
When any bar line segment in the edge wire grid pixel value with the edge image with any bar line segment
When the pixel value of the line segment in same position is different, the characteristic value of any bar line segment is defined as the second default feature
Value.
5. method according to claim 3, it is characterised in that every straight line in the edge wire grid,
According to every characteristic value of line segment on the straight line, the characteristic value for calculating the straight line includes：
Using characteristic value of the every characteristic value sum of line segment as the straight line on the straight line；Or,
Using characteristic value of the every average value of the characteristic value of line segment as the straight line on the straight line；Or,
Using characteristic value of the every variance of the characteristic value of line segment as the straight line on the straight line.
6. method according to claim 1, it is characterised in that methods described also includes：
Every two edge lines in for fixed a plurality of edge line, when the angle of two edge lines is identical and described
When the distance between two edge lines are less than predeterminable range, will two edge lines merging.
7. a kind of edge extraction device, it is characterised in that described device includes：
Image collection module, the edge image for obtaining object, the edge image includes that the object is extracted
A plurality of candidate edge lines；
Extraction module, the first pre-conditioned candidate edge lines are met for from a plurality of candidate edge lines, extraction to be a plurality of；
Extension of module, for extending to a plurality of first candidate edge lines, obtains edge wire grid, the edge gauze
Lattice include a plurality of straight line, and every straight line includes a plurality of line segment；
Characteristic value calculating module, for for every straight line in the edge wire grid, according to every line segment on the straight line
Pixel value, and the pixel value of the line segment of same position is in the edge image with every line segment on the straight line,
Calculate the characteristic value of the straight line；
Edge line determining module, for when the characteristic value of the straight line is more than predetermined threshold value, the straight line being defined as described
The edge line of object.
8. device according to claim 7, it is characterised in that the extraction module is used for from a plurality of candidate edge lines
In, the candidate edge lines that length belongs to preset length scope are extracted, as the first candidate edge lines；Or, from a plurality of time
Select in edge line, the candidate edge lines that angle belongs to predetermined angle scope are extracted, as the first candidate edge lines；Or, from institute
State in a plurality of candidate edge lines, extraction length belongs to the preset length scope and angle belongs to the time of the predetermined angle scope
Edge line is selected, as the first candidate edge lines.
9. device according to claim 7, it is characterised in that the characteristic value calculating module is used for for the edge line
Every line segment in grid, the pixel value of every line segment in the edge wire grid and in the edge image with
Every line segment in the edge wire grid is in the pixel value of the line segment of same position, determines every in the edge wire grid
The characteristic value of bar line segment；For every straight line in the edge wire grid, according to every characteristic value of line segment on the straight line,
Calculate the characteristic value of the straight line.
10. device according to claim 9, it is characterised in that the characteristic value calculating module is used to work as the edge line
The pixel value of any bar line segment in grid and the line for being in same position with any bar line segment in the edge image
When the pixel value of section is identical, the characteristic value of any bar line segment is defined as the first default characteristic value；Or, when the edge
The pixel value of any bar line segment in wire grid is in same position with the edge image with any bar line segment
When the pixel value of line segment is different, the characteristic value of any bar line segment is defined as the second default characteristic value.
11. devices according to claim 9, it is characterised in that the characteristic value calculating module is used for the straight line
Every characteristic value sum of line segment as the straight line characteristic value；Or, by every characteristic value of line segment on the straight line
Average value as the straight line characteristic value；Or, using every variance of the characteristic value of line segment on the straight line as described straight
The characteristic value of line.
12. devices according to claim 7, it is characterised in that described device also includes：
Merging module, for every two edge lines in for fixed a plurality of edge line, when the angle of two edge lines
Degree is identical, and the distance between two edge lines less than predeterminable range when, will two edge lines merging.
A kind of 13. edge extraction devices, it is characterised in that including：
Processor；
Memory for storing processor-executable instruction；
Wherein, the processor is configured as：
The edge image of object is obtained, the edge image includes a plurality of candidate edge lines that the object is extracted；
From a plurality of candidate edge lines, extraction is a plurality of to meet the first pre-conditioned candidate edge lines；
A plurality of first candidate edge lines are extended, edge wire grid is obtained, the edge wire grid includes a plurality of
Straight line, every straight line includes a plurality of line segment；
For every straight line in the edge wire grid, according to every pixel value of line segment on the straight line, and described
With the pixel value of line segment of the every line segment in same position on the straight line in edge image, the feature of the straight line is calculated
Value；
When the characteristic value of the straight line is more than predetermined threshold value, the straight line is defined as the edge line of the object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410724960.2A CN104504684B (en) | 2014-12-03 | 2014-12-03 | Edge extraction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410724960.2A CN104504684B (en) | 2014-12-03 | 2014-12-03 | Edge extraction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104504684A CN104504684A (en) | 2015-04-08 |
| CN104504684B true CN104504684B (en) | 2017-05-24 |
Family
ID=52946078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410724960.2A Active CN104504684B (en) | 2014-12-03 | 2014-12-03 | Edge extraction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104504684B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046260B (en) * | 2015-07-31 | 2019-01-04 | 小米科技有限责任公司 | Image pre-processing method and device |
| CN106127679B (en) * | 2016-06-24 | 2020-04-28 | 厦门中控智慧信息技术有限公司 | Fingerprint image conversion method and device |
| CN106951898B (en) * | 2017-03-15 | 2021-06-04 | 纵目科技（上海）股份有限公司 | Vehicle candidate area recommendation method and system and electronic equipment |
| CN109559344B (en) * | 2017-09-26 | 2023-10-13 | 腾讯科技（上海）有限公司 | Frame detection method, device and storage medium |
| CN109960979A (en) * | 2017-12-25 | 2019-07-02 | 大连楼兰科技股份有限公司 | Vehicle checking method based on image layered technology |
| CN110148221B (en) * | 2018-08-30 | 2023-09-01 | 杭州维聚科技有限公司 | Line fitting method during image reconstruction |
| CN111696124A (en) * | 2020-02-14 | 2020-09-22 | 牧今科技 | Method and computing system for processing candidate edges |
| US11403764B2 (en) * | 2020-02-14 | 2022-08-02 | Mujin, Inc. | Method and computing system for processing candidate edges |
| CN111562877A (en) * | 2020-04-30 | 2020-08-21 | 联想(北京)有限公司 | Image processing method and device |
| CN112509139B (en) * | 2020-12-14 | 2024-05-28 | 盈嘉互联（北京）科技有限公司 | BIM model pipeline center line extraction method and device |
| CN112651983B (en) * | 2020-12-15 | 2023-08-01 | 北京百度网讯科技有限公司 | Splice graph identification method and device, electronic equipment and storage medium |
| CN113160389B (en) * | 2021-04-25 | 2024-06-18 | 上海方联技术服务有限公司 | Image reconstruction method, device and storage medium based on characteristic line matching |
| CN113313052B (en) * | 2021-06-15 | 2024-05-03 | 杭州萤石软件有限公司 | Cliff area detection and mobile robot control method and device and mobile robot |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914830A (en) * | 2014-02-22 | 2014-07-09 | 小米科技有限责任公司 | Straight line detection method and device |
| EP2779025A2 (en) * | 2013-03-11 | 2014-09-17 | Ricoh Company, Ltd. | Method and system for detecting road edge |
-
2014
- 2014-12-03 CN CN201410724960.2A patent/CN104504684B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2779025A2 (en) * | 2013-03-11 | 2014-09-17 | Ricoh Company, Ltd. | Method and system for detecting road edge |
| CN103914830A (en) * | 2014-02-22 | 2014-07-09 | 小米科技有限责任公司 | Straight line detection method and device |
Non-Patent Citations (2)
| Title |
|---|
| Edlines： Real-time line segment detection by Edge Drawing (ED);Cuneyt Akinlar et al;《18th IEEE International Conference on Image Processing》;20111231;2837-2840 * |
| 图像边缘提取的简单方法及应用;吕同富 等;《计算机仿真》;20030430;第20卷(第4期);99-101 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104504684A (en) | 2015-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104504684B (en) | Edge extraction method and device | |
| CN104484871B (en) | edge extracting method and device | |
| CN105069786B (en) | Line detection method and device | |
| CN105809704A (en) | Method and device for identifying image definition | |
| CN106295515B (en) | Determine the method and device of the human face region in image | |
| CN104284240B (en) | Video browsing approach and device | |
| CN104036240B (en) | The localization method and device of human face characteristic point | |
| CN107169493A (en) | information identifying method and device | |
| CN106778773A (en) | The localization method and device of object in picture | |
| CN107145904A (en) | Determination method, device and the storage medium of image category | |
| CN106980840A (en) | Shape of face matching process, device and storage medium | |
| CN107492115A (en) | The detection method and device of destination object | |
| CN105095860B (en) | character segmentation method and device | |
| CN107944447A (en) | Image classification method and device | |
| CN107832741A (en) | The method, apparatus and computer-readable recording medium of facial modeling | |
| CN106778531A (en) | Face detection method and device | |
| CN107992848A (en) | Obtain the method, apparatus and computer-readable recording medium of depth image | |
| CN106228158A (en) | The method and apparatus of picture detection | |
| CN104933700B (en) | A kind of method and apparatus carrying out picture material identification | |
| CN107563994A (en) | The conspicuousness detection method and device of image | |
| CN107729880A (en) | Method for detecting human face and device | |
| CN104268864A (en) | Card edge extracting method and device | |
| CN108171225A (en) | Lane detection method, device, terminal and storage medium | |
| CN107992811A (en) | Face identification method and device | |
| CN105260743A (en) | Pattern classification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |