CN104504684A - Edge extraction method and device - Google Patents
Edge extraction method and device Download PDFInfo
- Publication number
- CN104504684A CN104504684A CN201410724960.2A CN201410724960A CN104504684A CN 104504684 A CN104504684 A CN 104504684A CN 201410724960 A CN201410724960 A CN 201410724960A CN 104504684 A CN104504684 A CN 104504684A
- Authority
- CN
- China
- Prior art keywords
- edge
- line
- line segment
- eigenwert
- straight line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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 about edge extracting method and device.
Background technology
Along with the development of infotech, three-dimensional model building rebuilds the important means having become and obtained fabric structure information, all has a wide range of applications in fields such as city planning, communications facility construction and digital city construction.And in order to carry out three-dimensional model building reconstruction, need the edge first extracting buildings.
When extracting the edge of buildings, first can obtain the image of buildings, denoising being carried out to image, obtains gray level image, utilizing the edge of the operator extraction gray level images such as Sobel (Sobel) or Canny, as the edge of buildings.
Realizing in process of the present invention, inventor finds correlation technique existing defects, such as: the edge adopting said method to extract is mostly short line segment, is difficult to the profile forming complete closure, and short line segment comprising much tiny fluctuation, the accuracy of edge extracting is very poor.When carrying out reconstructing three-dimensional model according to these short line segments, rebuild poor effect.
Summary of the invention
In order to solve Problems existing in correlation technique, present disclose provides a kind of edge extracting method and device.Described technical scheme is as follows:
According to the first aspect of disclosure embodiment, provide a kind of edge extracting method, described method comprises:
Obtain the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
From described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines;
Extend described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
For the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
When the eigenwert of described straight line is greater than predetermined threshold value, described straight line is defined as the edge line of described object.
In another embodiment, described from described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines and comprise:
From described many candidate edge lines, extract the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or,
From described many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or,
From described many candidate edge lines, extract length and belong to described preset length scope and angle belongs to the candidate edge lines of described predetermined angle scope, as the first candidate edge lines.
In another embodiment, described for the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, the eigenwert calculating described straight line comprises:
For the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine the eigenwert of described line segment;
For the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, calculate the eigenwert of described straight line.
In another embodiment, described for the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine that the eigenwert of described line segment comprises:
When the pixel value of described line segment is identical with the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as first and presets eigenwert; Or,
When the pixel value of described line segment is different from the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as second and presets eigenwert.
In another embodiment, described for the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, the eigenwert calculating described straight line comprises:
Using the eigenwert of the eigenwert sum of bar line segment every on described straight line as described straight line; Or,
Using the eigenwert of the mean value of the eigenwert of bar line segment every on described straight line as described straight line; Or,
Using the eigenwert of the variance of the eigenwert of bar line segment every on described straight line as described straight line.
In another embodiment, described method also comprises:
For every two edge lines in fixed many edge lines, when the angle of described two edge lines is identical, and when the distance between described two edge lines is less than predeterminable range, described two edge lines are merged.
According to the second aspect of disclosure embodiment, provide a kind of edge extraction device, described device comprises:
Image collection module, for obtaining the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
Extraction module, for from described many candidate edge lines, extracts many and meets the first pre-conditioned candidate edge lines;
Extension of module, for extending described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
Characteristic value calculating module, for for the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
Edge line determination module, for when the eigenwert of described straight line is greater than predetermined threshold value, is defined as the edge line of described object by described straight line.
In another embodiment, described extraction module is used for from described many candidate edge lines, extracts the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or, from described many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or, from described many candidate edge lines, extract length and belong to described preset length scope and angle belongs to the candidate edge lines of described predetermined angle scope, as the first candidate edge lines.
In another embodiment, described characteristic value calculating module is used for for the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine the eigenwert of described line segment; For the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, calculate the eigenwert of described straight line.
In another embodiment, described characteristic value calculating module is used for when the pixel value of described line segment is identical with the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as first and presets eigenwert; Or, when the pixel value of described line segment is different from the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as second and presets eigenwert.
In another embodiment, described characteristic value calculating module is for using the eigenwert of the eigenwert sum of bar line segment every on described straight line as described straight line; Or, using the eigenwert of the mean value of the eigenwert of bar line segment every on described straight line as described straight line; Or, using the eigenwert of the variance of the eigenwert of bar line segment every on described straight line as described straight line.
In another embodiment, described device also comprises:
Merge module, for for every two edge lines in fixed many edge lines, when the angle of described two edge lines is identical, and when the distance between described two edge lines is less than predeterminable range, described two edge lines are merged.
According to the third aspect of disclosure embodiment, provide a kind of edge extraction device, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Obtain the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
From described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines;
Extend described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
For the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
When the eigenwert of described straight line is greater than predetermined threshold value, described straight line is defined as the edge line of described object.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:
The method and apparatus that the present embodiment provides, by filtering candidate edge lines and extending, line segment in this edge line grid and the line segment in former edge image are compared, therefrom determine multiple edge lines of this object, improve the accuracy rate of edge extracting, and the multiple edge lines determined can form closed profile, when carrying out reconstructing three-dimensional model according to the plurality of edge line, reconstruction effect can be improved.
Should be understood that, it is only exemplary that above general description and details hereinafter describe, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows embodiment according to the invention, and is used from instructions one and explains principle of the present invention.
Fig. 1 is the process flow diagram of a kind of edge extracting method according to an exemplary embodiment;
Fig. 2 is the process flow diagram of a kind of edge extracting method according to an exemplary embodiment;
Fig. 3 A is the object image schematic diagram according to an exemplary embodiment;
Fig. 3 B is the edge image schematic diagram according to an exemplary embodiment;
Fig. 3 C is the edge line schematic diagram according to an exemplary embodiment;
Fig. 4 A is the block diagram of a kind of edge extraction device according to an exemplary embodiment;
Fig. 4 B is the block diagram of a kind of edge extraction device according to an exemplary embodiment;
Fig. 5 is the block diagram of a kind of device for edge extracting according to an exemplary embodiment.
Embodiment
For making object of the present disclosure, technical scheme and advantage clearly understand, below in conjunction with embodiment and accompanying drawing, the disclosure is described in further details.At this, exemplary embodiment of the present disclosure and illustrating for explaining the disclosure, but not as to restriction of the present disclosure.
Disclosure embodiment provides a kind of edge extracting method and device, is described in detail to the disclosure below in conjunction with accompanying drawing.
Fig. 1 is the process flow diagram of a kind of edge extracting method according to an exemplary embodiment, and as shown in Figure 1, this edge extracting method is used for, in image processing apparatus, comprising the following steps:
In a step 101, obtain the edge image of object, this edge image comprises many candidate edge lines that this object extracts.
Wherein, this object can be window, card etc. on buildings, buildings, and this image processing apparatus has the function of process image, and can be mobile phone, computing machine or server etc., the present embodiment limit this.This image processing apparatus can receive this edge image that other equipment sends, and also can carry out edge extracting process to the image of this object, obtain this edge image, this edge image can be binary image, and the present embodiment does not also limit this.
In a step 102, from these many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines.
Wherein, at least one item in this pre-conditioned length for specifying edge line and angle or other conditions, the present embodiment does not limit this.Accordingly, this pre-conditioned at least one item that can comprise in preset length scope and predetermined angle scope.This preset length scope and this predetermined angle scope can comprise continuous print numerical range, and also can comprise discrete multiple numerical value, such as, this predetermined angle scope can be { 0 °, 90 ° }.And this preset length scope and this predetermined angle scope can be determined according to the size of this object in the image of this edge image before edge extracting process and angle in advance respectively by this image processing apparatus, the present embodiment does not limit this.
In step 103, extend, obtain edge line grid to these many first candidate edge lines, this edge line grid comprises many straight lines, and every bar straight line comprises many line segments.
At step 104, for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and be in the pixel value of the line segment of same position with every bar line segment on this straight line in this edge image, calculate the eigenwert of this straight line.
For the every bar line segment in this edge line grid, when position identical with this line segment in this edge image also comprises line segment, represent this line segment probably on this object edge line, and position identical with this line segment in this edge image is not when comprising line segment, represent that this line segment may not on the edge line of this object.And for the every bar straight line in this edge line grid, in many line segments of this straight line, may line segment on the edge line of this object more, this straight line is that the possibility of the edge line of this object is higher, and may line segment on the edge line of this object fewer, this straight line is that the possibility of the edge line of this object is lower.For this reason, for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and the pixel value of the line segment of same position can be in every bar line segment on this straight line in this edge image, calculate the eigenwert of this straight line.So, when the eigenwert of this straight line is larger, to represent on this straight line may line segment on the edge line of this object more, this straight line is that the possibility of the edge line of this object is higher, when this straight line eigenwert more hour, represent on this straight line that the line segment on the edge line that may be this object is more, this straight line is that the possibility of the edge line of this object is lower.
In step 105, when the eigenwert of this straight line is greater than predetermined threshold value, this straight line is defined as the edge line of this object.
In the method that the present embodiment provides, when extracting many candidate edge lines of object, from these many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines, edge line grid is obtained after extension, for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and the pixel value of the line segment of same position is in every bar line segment on this straight line in this edge image, calculate the eigenwert of this straight line, when the eigenwert of this straight line is greater than predetermined threshold value, this straight line is defined as the edge line of this object.By filtering candidate edge lines and extending, line segment in this edge line grid and the line segment in former edge image are compared, therefrom determine multiple edge lines of this object, improve the accuracy rate of edge extracting, and the multiple edge lines determined can form closed profile, when carrying out reconstructing three-dimensional model according to the plurality of edge line, reconstruction effect can be improved.
In another embodiment, should from these many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines and comprise:
From these many candidate edge lines, extract the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or,
From these many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or,
From these many candidate edge lines, extract length and belong to this preset length scope and angle belongs to the candidate edge lines of this predetermined angle scope, as the first candidate edge lines.
In another embodiment, should for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and be in the pixel value of the line segment of same position with every bar line segment on this straight line in this edge image, the eigenwert calculating this straight line comprises:
For the every bar line segment in this edge line grid, according to the pixel value of this line segment and the pixel value of line segment being in same position in this edge image with this line segment, determine the eigenwert of this line segment;
For the every bar straight line in this edge line grid, according to the eigenwert of bar line segment every on this straight line, calculate the eigenwert of this straight line.
In another embodiment, should for the every bar line segment in this edge line grid, according to the pixel value of this line segment and the pixel value of line segment being in same position in this edge image with this line segment, determine that the eigenwert of this line segment comprises:
When the pixel value of this line segment is identical with the pixel value being in the line segment of same position in this edge image with this line segment, the eigenwert of this line segment is defined as first and presets eigenwert; Or,
When the pixel value of this line segment is different from the pixel value being in the line segment of same position in this edge image with this line segment, the eigenwert of this line segment is defined as second and presets eigenwert.
In another embodiment, should for the every bar straight line in this edge line grid, according to the eigenwert of bar line segment every on this straight line, the eigenwert calculating this straight line comprises:
Using the eigenwert of the eigenwert sum of bar line segment every on this straight line as this straight line; Or,
Using the eigenwert of the mean value of the eigenwert of bar line segment every on this straight line as this straight line; Or,
Using the eigenwert of the variance of the eigenwert of bar line segment every on this straight line as this straight line.
In another embodiment, the method also comprises:
For every two edge lines in fixed many edge lines, when the angle of these two edge lines is identical, and when the distance between these two edge lines is less than predeterminable range, these two edge lines are merged.
Above-mentioned all alternatives, can adopt and combine arbitrarily formation optional embodiment of the present invention, this is no longer going to repeat them.
Fig. 2 is the process flow diagram of a kind of edge extracting method according to an exemplary embodiment, and as shown in Figure 2, this edge extracting method is used for, in image processing apparatus, comprising the following steps:
In step 201, this image processing apparatus obtains the edge image of object, and this edge image comprises many candidate edge lines that this object extracts.
In actual applications, many the candidate edge lines that this edge image comprises are mostly short line segment, short line segment comprise tiny fluctuation, and these many short line segments can not form the profile of complete closure, when carrying out reconstructing three-dimensional model according to these short line segments, rebuild poor effect.In order to improve reconstruction effect, this image processing apparatus can process this edge image, obtains this object edge line more clearly.
In addition, for the ease of extracting edge line, this image processing apparatus can also first expand to this edge image, and these many candidate edge lines of overstriking, in subsequent process, this image processing apparatus processes the image after this expansion.
In step 202., this image processing apparatus, from these many candidate edge lines, extracts many and meets the first pre-conditioned candidate edge lines.
This image processing apparatus first according to pre-conditioned, can filter these many candidate edge lines, therefrom extracts the first candidate edge lines of the edge line being likely this object, can not be that the candidate edge lines of the edge line of this object filters out.
Wherein, at least one item in this pre-conditioned length for specifying edge line and angle or other conditions, accordingly, this pre-conditioned at least one item that can comprise in preset length scope and predetermined angle scope.When this is pre-conditioned comprise this preset length scope time, this image processing apparatus is from these many candidate edge lines, extract the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines, length can also not belonged to the candidate edge lines of this preset length scope as the second candidate edge lines.Or, when this is pre-conditioned comprise this predetermined angle scope time, this image processing apparatus is from these many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines, angle can also not belonged to the candidate edge lines of this predetermined angle scope as the second candidate edge lines.Or, when this is pre-conditioned comprise this preset length scope and this predetermined angle scope time, this image processing apparatus is from these many candidate edge lines, extract length and belong to this preset length scope and angle belongs to the candidate edge lines of this predetermined angle scope, as the first candidate edge lines, length can also not belonged to this preset length scope or angle does not belong to the candidate edge lines of this predetermined angle scope as the second candidate edge lines.
When this image processing apparatus extracts this many first candidate edge lines, the pixel value of each pixel in undrawn second candidate edge lines can be adjusted to 0, to filter this second candidate edge lines.
In actual applications, this image processing apparatus can carry out Hough transformation to this edge image, by these many candidate edge lines from the former coordinate system transformation of this edge image to hough space, a point in the corresponding hough space of a candidate edge lines in this former coordinate system, then this image processing apparatus is according to this predetermined angle scope and preset length scope, multiple points in hough space are filtered, carry out Hough inverse transformation again, by filtering rear remaining point transformation in hough space to former coordinate system, obtain many first candidate edge lines.
In step 203, this image processing apparatus extends these many first candidate edge lines, obtains edge line grid, and this edge line grid comprises many straight lines, and every bar straight line comprises many line segments.
This image processing apparatus can extend these many first candidate edge lines, by these many first candidate edge lines along the prolongation two ends, direction pointed to separately, till the edge extending to image, then the straight line of many first candidate edge lines intersects mutually, form edge line grid, this edge line grid comprises many straight lines, and every bar straight line is become many line segments by other line segmentation again.
In step 204, for the every bar line segment in this edge line grid, this image processing apparatus, according to the pixel value of this line segment and the pixel value of line segment being in same position in this edge image with this line segment, determines the eigenwert of this line segment.
For the every bar line segment in this edge line grid, when position identical with this line segment in this edge image also comprises line segment, represent this line segment probably on this object edge line, and position identical with this line segment in this edge image is not when comprising line segment, represent that this line segment may not on the edge line of this object.And for the every bar straight line in this edge line grid, in many line segments of this straight line, may line segment on the edge line of this object more, this straight line is that the possibility of the edge line of this object is higher, and may line segment on the edge line of this object fewer, this straight line is that the possibility of the edge line of this object is lower.
Based on These characteristics, for the every bar straight line in this edge line grid, this image processing apparatus according to the pixel value of bar line segment every on this straight line, and can be in the pixel value of the line segment of same position with every bar line segment on this straight line in this edge image, calculates the eigenwert of this straight line.
For the every bar line segment in this edge line grid, this image processing apparatus can obtain the pixel value of this line segment, and in this edge image, the pixel value of line segment of same position is in this line segment, according to the pixel value of this line segment and the pixel value of line segment being in same position in this edge image with this line segment, determine the eigenwert of this line segment.This image processing apparatus can judge that whether the pixel value of this line segment is identical with the pixel value being in the line segment of same position in this edge image with this line segment, if identical, the eigenwert of this line segment is defined as first and presets eigenwert by this image processing apparatus, if different, the eigenwert of this line segment is defined as second and presets eigenwert by this image processing apparatus, and this second default eigenwert is less than this first default eigenwert.Wherein, this first default eigenwert and this second default eigenwert can be pre-determined by this image processing apparatus, and this first default eigenwert can be 1, and this second default eigenwert can be 0, and the present embodiment does not limit this.
For this edge image for binary image, in this edge line grid, the pixel value of every bar line segment is 1, for the every bar line segment in this edge line grid, when the pixel value being in the line segment of same position in this edge image with this line segment is 1, determine that the eigenwert of this line segment is 1, when the pixel value being in the line segment of same position in this edge image with this line segment is 0, determine that the eigenwert of this line segment is 0.
During practical application, the image obtained after extending these many first candidate edge lines is specified image as first, then this image processing apparatus can carry out and computing this edge image and this first appointment image, obtain the second appointment image, this second specify image comprise pixel value be 1 line segment and pixel value be the line segment of 0, second pixel value in image is specified to be the line segment of 1 for this, represent in this edge image and this first appointment image, the position identical with this line segment present position also comprises line segment, then the eigenwert being in the line segment of same position in this first appointment image with this line segment is defined as this first default eigenwert.Second pixel value in image is specified to be the line segment of 0 for this, represent in this edge image or this first appointment image, the position identical with this line segment present position does not comprise line segment, then the eigenwert being in the line segment of same position in this first appointment image with this line segment is defined as this second default eigenwert.
In addition, if this image processing apparatus extends these many first candidate edge lines after expanding to this edge image again, then can first specify image to carry out and computing the image after this expansion and this, not repeat them here.
In step 205, for the every bar straight line in this edge line grid, this image processing apparatus, according to the eigenwert of bar line segment every on this straight line, calculates the eigenwert of this straight line.
For the every bar straight line in this edge line grid, when this image processing apparatus determines the eigenwert of every bar line segment on this straight line, can add up the eigenwert of these many line segments, obtain the eigenwert of this straight line.
This image processing apparatus can using the eigenwert of the eigenwert sum of bar line segment every on this straight line as this straight line; Or, using the eigenwert of the mean value of the eigenwert of bar line segment every on this straight line as this straight line; Or using the eigenwert of the variance of the eigenwert of bar line segment every on this straight line as this straight line, or using the eigenwert of other statistical values of the eigenwert of bar line segment every on this straight line as this straight line, the present embodiment does not limit this.
In step 206, when the eigenwert of this straight line is greater than predetermined threshold value, this straight line is defined as the edge line of this object by this image processing apparatus.
For the every bar straight line in this edge line grid, when the eigenwert of this straight line is larger, to represent on this straight line may line segment on the edge line of this object more, this straight line is that the possibility of the edge line of this object is higher, when this straight line eigenwert more hour, represent on this straight line that the line segment on the edge line that may be this object is more, this straight line is that the possibility of the edge line of this object is lower.For this reason, this image processing apparatus can pre-determine predetermined threshold value, for every bar straight line, when the eigenwert of this straight line is greater than this predetermined threshold value, can think that this straight line is the edge line of this object, then this straight line is defined as the edge line of this object by this image processing apparatus.And when the eigenwert of this straight line is not more than this predetermined threshold value, can think that this straight line is not the edge line of this object, then this straight line filters out by this image processing apparatus.
Wherein, this predetermined threshold value can according to this, first presets eigenwert, this second statistical value type presetting the eigenwert of every bar line segment on eigenwert and straight line is determined in advance by this image processing apparatus, and the present embodiment does not limit this.
In step 207, for every two edge lines in fixed many edge lines, when the angle of these two edge lines is identical, and when the distance between these two edge lines is less than predeterminable range, these two edge lines merge by this image processing apparatus.
In actual applications, many line segments in this edge image on the same edge line of this object owing to there is the reason such as fluctuation, distortion, and may be extended into two straight lines in this edge line grid, make finally correspondingly to determine two edge lines.In order to prevent edge line repeat determine, when this image processing apparatus has determined many edge lines of this object, for every two edge lines in these many edge lines, this image processing apparatus can judge that whether the angle of these two edge lines is identical, if the angle of these two edge lines is identical, this image processing apparatus calculates the distance between these two edge lines, judge whether this distance is less than predeterminable range, when this distance is less than this predeterminable range, represent that these two edge lines are same edge line, then these two edge lines are merged.This image processing apparatus can by the wherein deletion in these two edge lines, using a remaining edge line as this object, also an edge line parallel with this two edge lines can be generated in these two edge line centre positions, these two edge lines are deleted, using the edge line of newly-generated edge line as this object, the present embodiment does not limit the mode that this image processing apparatus merges.
Fig. 3 A is the object image schematic diagram according to an exemplary embodiment, and this image processing apparatus can carry out edge extracting according to this Fig. 3 A, obtains the edge image shown in Fig. 3 B.See Fig. 3 B, this edge image comprises many tiny, bending line segments, and these line segments are distributed in this edge image dispersedly, and this image processing apparatus can apply the method that the present embodiment provides, and to this Fig. 3 B process, obtain the image shown in Fig. 3 C.See Fig. 3 C, this image comprises many straight lines clearly, and these many straight lines have constituted closed profile.
When the method that this image processing apparatus application the present embodiment provides, when obtaining the sharp edge line of this object, can will comprise the Image Saving of this sharp edge line in a database, so that according to the edge line of the object in this image in subsequent process, carry out reconstructing three-dimensional model.Such as, when this object is buildings, according to the image comprising this buildings edge line, the three-dimensional model of this buildings can be set up, this three-dimensional model may be used for generating city three-dimensional map, or the communications facility on this buildings auxiliary is arranged, or for construction work teaching etc., the present embodiment does not limit this.
In the method that the present embodiment provides, when extracting many candidate edge lines of object, from these many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines, edge line grid is obtained after extension, for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and the pixel value of the line segment of same position is in every bar line segment on this straight line in this edge image, calculate the eigenwert of this straight line, when the eigenwert of this straight line is greater than predetermined threshold value, this straight line is defined as the edge line of this object.By filtering candidate edge lines and extending, line segment in this edge line grid and the line segment in former edge image are compared, therefrom determine multiple edge lines of this object, improve the accuracy rate of edge extracting, and the multiple edge lines determined can form closed profile, when carrying out reconstructing three-dimensional model according to the plurality of edge line, reconstruction effect can be improved.
Fig. 4 A is the block diagram of a kind of edge extraction device according to an exemplary embodiment, and see Fig. 4 A, this device comprises image collection module 401, extraction module 402, extension of module 403, characteristic value calculating module 404 and edge line determination module 405.
Image collection module 401 is configured to the edge image for obtaining object, and this edge image comprises many candidate edge lines that this object extracts;
Extraction module 402 is configured to, for from these many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines;
Extension of module 403 is configured to, for extending these many first candidate edge lines, obtain edge line grid, and this edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
Characteristic value calculating module 404 is configured to for for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and the pixel value of the line segment of same position is in every bar line segment on this straight line in this edge image, calculate the eigenwert of this straight line;
Edge line determination module 405 is configured to, for when the eigenwert of this straight line is greater than predetermined threshold value, this straight line is defined as the edge line of this object.
In the device that the present embodiment provides, when extracting many candidate edge lines of object, from these many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines, edge line grid is obtained after extension, for the every bar straight line in this edge line grid, according to the pixel value of bar line segment every on this straight line, and the pixel value of the line segment of same position is in every bar line segment on this straight line in this edge image, calculate the eigenwert of this straight line, when the eigenwert of this straight line is greater than predetermined threshold value, this straight line is defined as the edge line of this object.By filtering candidate edge lines and extending, line segment in this edge line grid and the line segment in former edge image are compared, therefrom determine multiple edge lines of this object, improve the accuracy rate of edge extracting, and the multiple edge lines determined can form closed profile, when carrying out reconstructing three-dimensional model according to the plurality of edge line, reconstruction effect can be improved.
In another embodiment, this extraction module 402 is configured to, for from these many candidate edge lines, extract the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or, from these many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or, from these many candidate edge lines, extract length and belong to this preset length scope and angle belongs to the candidate edge lines of this predetermined angle scope, as the first candidate edge lines.
In another embodiment, this characteristic value calculating module 404 is configured to for for the every bar line segment in this edge line grid, according to the pixel value of this line segment and the pixel value of line segment being in same position in this edge image with this line segment, determine the eigenwert of this line segment; For the every bar straight line in this edge line grid, according to the eigenwert of bar line segment every on this straight line, calculate the eigenwert of this straight line.
In another embodiment, this characteristic value calculating module 404 is configured to for when the pixel value of this line segment is identical with the pixel value being in the line segment of same position in this edge image with this line segment, the eigenwert of this line segment is defined as first and presets eigenwert; Or, when the pixel value of this line segment is different from the pixel value being in the line segment of same position in this edge image with this line segment, the eigenwert of this line segment is defined as second and presets eigenwert.
In another embodiment, this characteristic value calculating module 404 is configured to for using the eigenwert of the eigenwert sum of bar line segment every on this straight line as this straight line; Or, using the eigenwert of the mean value of the eigenwert of bar line segment every on this straight line as this straight line; Or, using the eigenwert of the variance of the eigenwert of bar line segment every on this straight line as this straight line.
See Fig. 4 B, in another embodiment, this device also comprises:
Merging module 406 is configured to for for every two edge lines in fixed many edge lines, when the angle of these two edge lines is identical, and when the distance between these two edge lines is less than predeterminable range, is merged by these two edge lines.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
It should be noted that: the edge extraction device that above-described embodiment provides is when extracting edge, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by image processing apparatus is divided into different functional modules, to complete all or part of function described above.In addition, the edge extraction device that above-described embodiment provides and edge extracting method embodiment belong to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
Fig. 5 is the block diagram of a kind of device 500 for edge extracting according to an exemplary embodiment.Such as, device 500 can be mobile phone, computing machine, digital broadcast terminal, messaging devices, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Fig. 5, device 500 can comprise following one or more assembly: processing components 502, storer 504, power supply module 506, multimedia groupware 508, audio-frequency assembly 510, the interface 512 of I/O (I/O), sensor module 514, and communications component 516.
The integrated operation of the usual control device 500 of processing components 502, such as with display, call, data communication, camera operation and record operate the operation be associated.Treatment element 502 can comprise one or more processor 520 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 502 can comprise one or more module, and what be convenient between processing components 502 and other assemblies is mutual.Such as, processing element 502 can comprise multi-media module, mutual with what facilitate between multimedia groupware 508 and processing components 502.
Storer 504 is configured to store various types of data to be supported in the operation of equipment 500.The example of these data comprises the instruction of any application program for operating on device 500 or method, contact data, telephone book data, message, picture, video etc.Storer 504 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.
The various assemblies that electric power assembly 506 is device 500 provide electric power.Electric power assembly 506 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for device 500 and be associated.
Multimedia groupware 508 is included in the screen providing an output interface between described device 500 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 508 comprises a front-facing camera and/or post-positioned pick-up head.When equipment 500 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 510 is configured to export and/or input audio signal.Such as, audio-frequency assembly 510 comprises a microphone (MIC), and when device 500 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal received can be stored in storer 504 further or be sent via communications component 516.In certain embodiments, audio-frequency assembly 510 also comprises a loudspeaker, for output audio signal.
I/O interface 512 is for providing interface between processing components 502 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 514 comprises one or more sensor, for providing the state estimation of various aspects for device 500.Such as, sensor module 514 can detect the opening/closing state of equipment 500, the relative positioning of assembly, such as described assembly is display and the keypad of device 500, the position of all right pick-up unit 500 of sensor module 514 or device 500 1 assemblies changes, the presence or absence that user contacts with device 500, the temperature variation of device 500 orientation or acceleration/deceleration and device 500.Sensor module 514 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 514 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 514 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 516 is configured to the communication being convenient to wired or wireless mode between device 500 and other equipment.Device 500 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communication component 516 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communication component 516 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, device 500 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the storer 504 of instruction, above-mentioned instruction can perform said method by the processor 520 of device 500.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of image processing apparatus, make image processing apparatus can perform a kind of edge extracting method, described method comprises:
Obtain the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
From described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines;
Extend described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
For the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
When the eigenwert of described straight line is greater than predetermined threshold value, described straight line is defined as the edge line of described object.
In another embodiment, described from described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines and comprise:
From described many candidate edge lines, extract the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or,
From described many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or,
From described many candidate edge lines, extract length and belong to described preset length scope and angle belongs to the candidate edge lines of described predetermined angle scope, as the first candidate edge lines.
In another embodiment, described for the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, the eigenwert calculating described straight line comprises:
For the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine the eigenwert of described line segment;
For the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, calculate the eigenwert of described straight line.
In another embodiment, described for the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine that the eigenwert of described line segment comprises:
When the pixel value of described line segment is identical with the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as first and presets eigenwert; Or,
When the pixel value of described line segment is different from the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as second and presets eigenwert.
In another embodiment, described for the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, the eigenwert calculating described straight line comprises:
Using the eigenwert of the eigenwert sum of bar line segment every on described straight line as described straight line; Or,
Using the eigenwert of the mean value of the eigenwert of bar line segment every on described straight line as described straight line; Or,
Using the eigenwert of the variance of the eigenwert of bar line segment every on described straight line as described straight line.
In another embodiment, described method also comprises:
For every two edge lines in fixed many edge lines, when the angle of described two edge lines is identical, and when the distance between described two edge lines is less than predeterminable range, described two edge lines are merged.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.
Claims (13)
1. an edge extracting method, is characterized in that, described method comprises:
Obtain the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
From described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines;
Extend described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
For the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
When the eigenwert of described straight line is greater than predetermined threshold value, described straight line is defined as the edge line of described object.
2. method according to claim 1, is characterized in that, described from described many candidate edge lines, extracts many and meets the first pre-conditioned candidate edge lines and comprise:
From described many candidate edge lines, extract the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or,
From described many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or,
From described many candidate edge lines, extract length and belong to described preset length scope and angle belongs to the candidate edge lines of described predetermined angle scope, as the first candidate edge lines.
3. method according to claim 1, it is characterized in that, described for the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and the pixel value of the line segment of same position is in every bar line segment on described straight line in described edge image, the eigenwert calculating described straight line comprises:
For the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine the eigenwert of described line segment;
For the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, calculate the eigenwert of described straight line.
4. method according to claim 3, it is characterized in that, described for the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine that the eigenwert of described line segment comprises:
When the pixel value of described line segment is identical with the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as first and presets eigenwert; Or,
When the pixel value of described line segment is different from the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as second and presets eigenwert.
5. method according to claim 3, is characterized in that, described for the every bar straight line in described edge line grid, and according to the eigenwert of bar line segment every on described straight line, the eigenwert calculating described straight line comprises:
Using the eigenwert of the eigenwert sum of bar line segment every on described straight line as described straight line; Or,
Using the eigenwert of the mean value of the eigenwert of bar line segment every on described straight line as described straight line; Or,
Using the eigenwert of the variance of the eigenwert of bar line segment every on described straight line as described straight line.
6. method according to claim 1, is characterized in that, described method also comprises:
For every two edge lines in fixed many edge lines, when the angle of described two edge lines is identical, and when the distance between described two edge lines is less than predeterminable range, described two edge lines are merged.
7. an edge extraction device, is characterized in that, described device comprises:
Image collection module, for obtaining the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
Extraction module, for from described many candidate edge lines, extracts many and meets the first pre-conditioned candidate edge lines;
Extension of module, for extending described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
Characteristic value calculating module, for for the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
Edge line determination module, for when the eigenwert of described straight line is greater than predetermined threshold value, is defined as the edge line of described object by described straight line.
8. device according to claim 7, is characterized in that, described extraction module is used for from described many candidate edge lines, extracts the candidate edge lines that length belongs to preset length scope, as the first candidate edge lines; Or, from described many candidate edge lines, extract the candidate edge lines that angle belongs to predetermined angle scope, as the first candidate edge lines; Or, from described many candidate edge lines, extract length and belong to described preset length scope and angle belongs to the candidate edge lines of described predetermined angle scope, as the first candidate edge lines.
9. device according to claim 7, it is characterized in that, described characteristic value calculating module is used for for the every bar line segment in described edge line grid, according to the pixel value of described line segment and the pixel value of line segment being in same position in described edge image with described line segment, determine the eigenwert of described line segment; For the every bar straight line in described edge line grid, according to the eigenwert of bar line segment every on described straight line, calculate the eigenwert of described straight line.
10. device according to claim 9, it is characterized in that, described characteristic value calculating module is used for when the pixel value of described line segment is identical with the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as first and presets eigenwert; Or, when the pixel value of described line segment is different from the pixel value being in the line segment of same position in described edge image with described line segment, the eigenwert of described line segment is defined as second and presets eigenwert.
11. devices according to claim 9, is characterized in that, described characteristic value calculating module is for using the eigenwert of the eigenwert sum of bar line segment every on described straight line as described straight line; Or, using the eigenwert of the mean value of the eigenwert of bar line segment every on described straight line as described straight line; Or, using the eigenwert of the variance of the eigenwert of bar line segment every on described straight line as described straight line.
12. devices according to claim 7, is characterized in that, described device also comprises:
Merge module, for for every two edge lines in fixed many edge lines, when the angle of described two edge lines is identical, and when the distance between described two edge lines is less than predeterminable range, described two edge lines are merged.
13. 1 kinds of edge extraction device, is characterized in that, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Obtain the edge image of object, described edge image comprises many candidate edge lines that described object extracts;
From described many candidate edge lines, extract many and meet the first pre-conditioned candidate edge lines;
Extend described many first candidate edge lines, obtain edge line grid, described edge line grid comprises many straight lines, and every bar straight line comprises many line segments;
For the every bar straight line in described edge line grid, according to the pixel value of bar line segment every on described straight line, and be in the pixel value of the line segment of same position with every bar line segment on described straight line in described edge image, calculate the eigenwert of described straight line;
When the eigenwert of described straight line is greater than predetermined threshold value, described straight line is defined as the edge line of described 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 true CN104504684A (en) | 2015-04-08 |
| CN104504684B 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) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127679A (en) * | 2016-06-24 | 2016-11-16 | 厦门中控生物识别信息技术有限公司 | The conversion method of a kind of fingerprint image and device |
| CN106951898A (en) * | 2017-03-15 | 2017-07-14 | 纵目科技（上海）股份有限公司 | Recommend method and system, electronic equipment in a kind of vehicle candidate region |
| CN105046260B (en) * | 2015-07-31 | 2019-01-04 | 小米科技有限责任公司 | Image pre-processing method and device |
| WO2019062426A1 (en) * | 2017-09-26 | 2019-04-04 | 腾讯科技（深圳）有限公司 | Border detection method, server 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 |
| CN110148221A (en) * | 2018-08-30 | 2019-08-20 | 杭州维聚科技有限公司 | A kind of method of lines fitting when image reconstruction |
| CN111562877A (en) * | 2020-04-30 | 2020-08-21 | 联想(北京)有限公司 | Image processing method and device |
| CN112509139A (en) * | 2020-12-14 | 2021-03-16 | 盈嘉互联（北京）科技有限公司 | BIM model pipeline center line extraction method and device |
| CN112651983A (en) * | 2020-12-15 | 2021-04-13 | 北京百度网讯科技有限公司 | Mosaic image identification method and device, electronic equipment and storage medium |
| CN112734783A (en) * | 2020-02-14 | 2021-04-30 | 牧今科技 | Method and computing system for processing candidate edges |
| CN113160389A (en) * | 2021-04-25 | 2021-07-23 | 上海方联技术服务有限公司 | Image reconstruction method and device based on characteristic line matching and storage medium |
| CN113313052A (en) * | 2021-06-15 | 2021-08-27 | 杭州萤石软件有限公司 | Cliff area detection and mobile robot control method and device and mobile robot |
| US11403764B2 (en) * | 2020-02-14 | 2022-08-02 | Mujin, Inc. | Method and computing system for processing candidate edges |
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 |
|---|
| CUNEYT AKINLAR ET AL: "Edlines： Real-time line segment detection by Edge Drawing (ED)", 《18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING》 * |
| 吕同富 等: "图像边缘提取的简单方法及应用", 《计算机仿真》 * |
Cited By (20)
| 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 |
| CN106127679A (en) * | 2016-06-24 | 2016-11-16 | 厦门中控生物识别信息技术有限公司 | The conversion method of a kind of fingerprint image 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 |
| CN106951898A (en) * | 2017-03-15 | 2017-07-14 | 纵目科技（上海）股份有限公司 | Recommend method and system, electronic equipment in a kind of vehicle candidate region |
| WO2019062426A1 (en) * | 2017-09-26 | 2019-04-04 | 腾讯科技（深圳）有限公司 | Border detection method, server and storage medium |
| US11328427B2 (en) | 2017-09-26 | 2022-05-10 | Tencent Technology (Shenzhen) Company Ltd | Border detection method, server 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 |
| CN110148221A (en) * | 2018-08-30 | 2019-08-20 | 杭州维聚科技有限公司 | A kind of method of lines fitting when image reconstruction |
| CN110148221B (en) * | 2018-08-30 | 2023-09-01 | 杭州维聚科技有限公司 | Line fitting method during image reconstruction |
| CN112734783A (en) * | 2020-02-14 | 2021-04-30 | 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 |
| US20220351389A1 (en) * | 2020-02-14 | 2022-11-03 | 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 |
| CN112509139A (en) * | 2020-12-14 | 2021-03-16 | 盈嘉互联（北京）科技有限公司 | BIM model pipeline center line extraction 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 |
| CN112651983A (en) * | 2020-12-15 | 2021-04-13 | 北京百度网讯科技有限公司 | Mosaic image identification method and device, electronic equipment and storage medium |
| 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 |
| CN113160389A (en) * | 2021-04-25 | 2021-07-23 | 上海方联技术服务有限公司 | Image reconstruction method and device based on characteristic line matching and storage medium |
| CN113313052A (en) * | 2021-06-15 | 2021-08-27 | 杭州萤石软件有限公司 | Cliff area detection and mobile robot control method and device and mobile robot |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104504684B (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104504684A (en) | Edge extraction method and device | |
| CN105069786A (en) | Straight line detection method and straight line detection device | |
| CN104378570A (en) | Sound recording method and device | |
| CN104484871A (en) | Method and device for extracting edges | |
| CN105224195A (en) | Terminal operation method and device | |
| CN105528600A (en) | Region identification method and device | |
| CN105095881A (en) | Method, apparatus and terminal for face identification | |
| CN104850852A (en) | Feature vector calculation method and device | |
| CN105046231A (en) | Face detection method and device | |
| CN104238912A (en) | Application control method and application control device | |
| CN105488511A (en) | Image identification method and device | |
| CN104503681A (en) | Interface icon movement control method and device | |
| CN105469356A (en) | Human face image processing method and apparatus thereof | |
| CN105046260A (en) | Image pre-processing method and apparatus | |
| CN104731688A (en) | Method and device for prompting reading schedule | |
| CN105354560A (en) | Fingerprint identification method and device | |
| CN104361558A (en) | Image processing method, device and equipment | |
| CN104537380A (en) | Clustering method and device | |
| CN105139378A (en) | Card boundary detection method and apparatus | |
| CN105354793A (en) | Facial image processing method and device | |
| CN104484858A (en) | Figure image processing method and device | |
| CN105205494A (en) | Similar picture identification method and device | |
| CN104268864A (en) | Card edge extracting method and device | |
| CN104598534A (en) | Picture folding method and device | |
| CN105095860A (en) | Method and device for character segmentation |
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 |