CN101833750A - Active contour method based on shape constraint and direction field, and system thereof - Google Patents
Active contour method based on shape constraint and direction field, and system thereof Download PDFInfo
- Publication number
- CN101833750A CN101833750A CN 201010149361 CN201010149361A CN101833750A CN 101833750 A CN101833750 A CN 101833750A CN 201010149361 CN201010149361 CN 201010149361 CN 201010149361 A CN201010149361 A CN 201010149361A CN 101833750 A CN101833750 A CN 101833750A
- Authority
- CN
- China
- Prior art keywords
- energy field
- shape
- initial profile
- bit
- field
- 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.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an active contour method based on shape constraint and direction field, and a system thereof. The method comprises the following steps of: S1, inputting the initial contour of a target object in image, and establishing the energy field relating to the shape distance of the initial contour according to the shape priori knowledge of the initial contour; S2, establishing the gradient intensity energy field by calculating the gradient intensity values extracted from all points of the edge of the target object; S3, establishing the gradient direction energy field by calculating the consistency between the tangential direction of each point in the initial contour and the tangential direction of each point extracted from the edge of the target object; and S4, overlapping the three energy fields established in S1-S3 to obtain a new energy field, carrying out global optimization, and obtaining an accurate contour of the target object. The invention gives more accurate and complete expression of target image contour under the condition of target image geometrical information in the known image, thus not only completely maintaining the geometrical characteristics of the target image, but also enriching the contour details.
Description
Technical field
The invention belongs to technical field of image processing, particularly a kind of driving wheel contour method and system thereof based on the shape constraining and the field of direction.
Background technology
In recent years, along with popularizing of the development of computer hardware and software engineering and great amount of images, video equipment, computer vision technique becomes the hot fields of computer research.Wherein, detection, extraction and processing to special object in image, the video data have higher utility and technical meaning.The object detection method that present vision technique provides, normally at texture and provincial characteristics, as the Haar characterization method of people's face detection, the signal processing method that flame detects etc., this often can only offer one of the processor guestimate at special object position and zone, and can't estimate comparatively accurately and extract the edge of special object.So in order to solve the problem of edge extracting, the method for traditional driving wheel contour method (Active contour) is arisen at the historic moment.The main thought of traditional driving wheel contour method is, at first import an initial profile, then by extraneous energy field (energy calculates with gradient or other features) information of importing, by the mode of optimizing, seek the optimum position of each point, thereby find border more accurately.In order to improve traditional method, the driving wheel contour method (Active contour with shape prior) of shape prior had appearred having afterwards, can on the basis that keeps original shape, seek optimum border.Yet this method is for the image actual information---each primitive boundary information in the especially significant image---utilizes insufficiently, causes losing of edge details easily.
Therefore, driving wheel contour method technology should be towards can extracting object bounds more accurately, and the direction that can satisfy the needs of some constraint conditions simultaneously develops.
Summary of the invention
(1) technical matters that will solve
The technical problem to be solved in the present invention is how to extract edge of image exactly under the situation that satisfies the shape constraining condition, and does not cause losing of edge details.
(2) technical scheme
For addressing the above problem, the invention provides a kind of driving wheel contour method based on the shape constraining and the field of direction, may further comprise the steps:
S1, the initial profile of destination object in the input picture according to the shape prior knowledge of this initial profile, is set up the relevant energy field of shape distance with this initial profile;
S2, the value of the gradient intensity of the every bit by calculating the edge that is extracted in the destination object is set up the gradient intensity energy field;
S3, the consistance of the tangential direction of the every bit at the edge that is extracted in tangential direction by calculating every bit in the initial profile and the destination object is set up the gradient direction energy field;
S4, three energy field stacks that step S1～S3 is set up obtain new energy field, then it are carried out global optimization, obtain the accurate profile of destination object in the image.
Wherein, geometric configuration, present position and the occupied general area that the shape prior knowledge of this initial profile can the indicating target object.
Wherein, in step S1, set up with the shape of this initial profile step and be specially: according to the position of each point of initial profile apart from relevant energy field, calculate the distance of every bit and this corresponding point on the initial profile normal direction, go out normalized energy according to this distance calculation then, obtain the value of the energy field relevant with the original-shape distance of initial profile.
Wherein, in step S3, the gradient direction of the every bit by calculating the edge that is extracted in the destination object obtains the tangential direction of the every bit at the edge that extracted in the described destination object.
Wherein, in step S4,, utilize process of iteration to seek on the initial profile each optimal location in self neighborhood scope,, obtain the accurate profile of destination object until algorithm convergence according to the elasticity coefficient and the hard lineal number of each point on the initial profile.
Wherein, in step S3, after the normalization of the vector of the tangential direction of the every bit at the edge that is extracted in the vector of the tangential direction of every bit in the initial profile and destination object difference, as described conforming tolerance, this dot product is the value of described gradient direction energy field with the two dot product.
The present invention also provides a kind of active profile system based on the shape constraining and the field of direction, comprising:
With the relevant energy field computing unit of original-shape distance, be used for the initial profile of input picture destination object, according to the shape prior knowledge of this initial profile, set up the relevant energy field of shape distance with this initial profile;
Gradient intensity energy field computing unit, the value that is used for the gradient intensity of the every bit by calculating the edge that destination object extracted is set up the gradient intensity energy field;
Gradient direction energy field computing unit is used for the consistance of tangential direction of the every bit at the edge that extracted in tangential direction by calculating the initial profile every bit and the destination object, sets up the gradient direction energy field;
The global optimization unit, three energy field stacks that are used for above three unit are set up obtain new energy field, then it are carried out global optimization, obtain the accurate profile of destination object in the image.
(3) beneficial effect
Technical scheme of the present invention had both considered that shape prior knowledge was for the constraint of profile as a result, information (be embodied in and set up gradient intensity energy field and gradient direction energy field) that again can the direction of passage field makes profile more approach original visible edge, thereby makes that the profile that extracts is more accurate.In a word, this method can be in known image under the situation of target image geological information, provides more accurate, the more complete expression of target image profile, not only complete reservation the geometric properties of this target image, enriched its profile details again.
Description of drawings
Fig. 1 is the method flow diagram of the embodiment of the invention;
Fig. 2 is three kinds of energygrams that the method for the enforcement embodiment of the invention obtains;
Fig. 3 is the figure as a result that implements the method for the embodiment of the invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples are used to illustrate the present invention, but are not used for limiting the scope of the invention.
Fig. 1 is the method flow diagram of the embodiment of the invention.As shown in Figure 1, at first import an initial profile of target image, this profile is the geometric configuration of indicating target image correctly, and can indicate residing position of target image and occupied general area.Respectively press clockwise storage on the initial profile, and each point is designated as { X
i, simultaneously, calculate the tangential direction at initial profile every bit place, be designated as { dX
i.
Need to set up three kinds of energygrams (as shown in Figure 2) below:
At first according to the position of each point on the initial profile, find out which point correspondence on the profile normal direction of correspondence and profile of every bit on the image, calculate its distance [D (V)
i], obtaining and the relevant energy field (being the shape prior energy field) of original-shape distance, its energy value (value of the energy field relevant with the original-shape distance) is:
E
shape，i＝N((1+D(V)
i)
-1
Wherein, N has represented normalized function, makes this energy value be between 0～1.With this energy as the influence mode of the shape constraining among the present invention for profile variations.Can see that the closer to original position, energy is big more, the confidence level of coupling is considered to higher.
Then, image is carried out edge extracting.The present invention adopts the method for compute gradient to extract the edge, and the intensity level at edge promptly as the value of said gradient intensity energy field, do by note:
E
strength，i＝S(V
i)
Simultaneously, according to the edge gradient direction that extracts, calculate the edge tangential direction at every bit place, according to the corresponding relation that finds previously, after direction vector normalization with the point of correspondence and the point on the image, both dot products as the conforming tolerance of its direction, that is:
E
direction，i＝N(<dV
i，dX
i>)
At last, above-mentioned three energy values that superpose obtain adjusting among the present invention the required optimization energy field of profile:
E
i＝αE
shape，i+βE
direction，i+γE
strength，i
Coefficient when above-mentioned energy superposes need satisfy
And the value of α, β, γ can be selected according to the difference of the destination object character that will extract: if destination object is blocked seriously, then get α and be the value greater than 0.5; If initial profile and destination object are more approaching, then α is the value less than 0.5; And generally get β=γ.
Set up optimize energy field after, for flatness and the continuity that guarantees profile, introduce elasticity coefficient and hard lineal number---represent in the first order derivative and the second derivative at this some place with the initial profile curve respectively, every bit is all sought optimal location in the neighborhood scope of oneself, iteration is until algorithm convergence.The result that obtain this moment thinks the accurate profile of target image.Result when as shown in Figure 3, solid outline line has shown algorithm convergence.
The present invention also provides a kind of active profile system based on the shape constraining and the field of direction, comprising:
With the relevant energy field computing unit of original-shape distance, be used for the initial profile of input picture destination object, according to the shape prior knowledge of this initial profile, set up the relevant energy field of shape distance with this initial profile;
Gradient intensity energy field computing unit, the value that is used for the gradient intensity of the every bit by calculating the edge that destination object extracted is set up the gradient intensity energy field;
Gradient direction energy field computing unit is used for the consistance of tangential direction of the every bit at the edge that extracted in tangential direction by calculating the initial profile every bit and the destination object, sets up the gradient direction energy field;
The global optimization unit, three energy field stacks that are used for above three unit are set up obtain new energy field, then it are carried out global optimization, obtain the accurate profile of destination object in the image.
As can be seen from the above embodiments, this technical scheme had both considered that shape prior knowledge was for the constraint of profile as a result, information (be embodied in and set up gradient intensity energy field and gradient direction energy field) that again can the direction of passage field makes profile more approach original visible edge, thereby makes that the profile that extracts is more accurate.In a word, this method can be in known image under the situation of target image geological information, provides more accurate, the more complete expression of target image profile, not only complete reservation the geometric properties of this target image, enriched its profile details again.
The above only is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the technology of the present invention principle; can also make some improvement and modification, these improve and modification also should be considered as protection scope of the present invention.
Claims (7)
1. the driving wheel contour method based on the shape constraining and the field of direction is characterized in that, may further comprise the steps:
S1, the initial profile of destination object in the input picture according to the shape prior knowledge of this initial profile, is set up the relevant energy field of shape distance with this initial profile;
S2, the value of the gradient intensity of the every bit by calculating the edge that is extracted in the destination object is set up the gradient intensity energy field;
S3, the consistance of the tangential direction of the every bit at the edge that is extracted in tangential direction by calculating every bit in the initial profile and the destination object is set up the gradient direction energy field;
S4, three energy field stacks that step S1～S3 is set up obtain new energy field, then it are carried out global optimization, obtain the accurate profile of destination object in the image.
2. the driving wheel contour method based on the shape constraining and the field of direction as claimed in claim 1 is characterized in that, geometric configuration, present position and occupied general area that the shape prior knowledge of this initial profile can the indicating target object.
3. the driving wheel contour method based on the shape constraining and the field of direction as claimed in claim 2, it is characterized in that, in step S1, set up with the shape of this initial profile step and be specially: according to the position of each point of initial profile apart from relevant energy field, calculate the distance of every bit and this corresponding point on the initial profile normal direction, go out normalized energy according to this distance calculation then, obtain the value of the energy field relevant with the original-shape distance of initial profile.
4. the driving wheel contour method based on the shape constraining and the field of direction as claimed in claim 2, it is characterized in that, in step S3, the gradient direction of the every bit by calculating the edge that is extracted in the destination object obtains the tangential direction of the every bit at the edge that extracted in the described destination object.
5. the driving wheel contour method based on the shape constraining and the field of direction as claimed in claim 2, it is characterized in that, in step S4, elasticity coefficient and hard lineal number according to each point on the initial profile, utilize process of iteration to seek on the initial profile each optimal location in self neighborhood scope, until algorithm convergence, obtain the accurate profile of destination object.
6. as claim 2 or 4 described driving wheel contour methods based on the shape constraining and the field of direction, it is characterized in that, in step S3, after the normalization of the vector of the tangential direction of the every bit at the edge that is extracted in the vector of the tangential direction of every bit in the initial profile and destination object difference, as described conforming tolerance, this dot product is the value of described gradient direction energy field with the two dot product.
7. the active profile system based on the shape constraining and the field of direction is characterized in that, comprising:
With the relevant energy field computing unit of original-shape distance, be used for the initial profile of input picture destination object, according to the shape prior knowledge of this initial profile, set up the relevant energy field of shape distance with this initial profile;
Gradient intensity energy field computing unit, the value that is used for the gradient intensity of the every bit by calculating the edge that destination object extracted is set up the gradient intensity energy field;
Gradient direction energy field computing unit is used for the consistance of tangential direction of the every bit at the edge that extracted in tangential direction by calculating the initial profile every bit and the destination object, sets up the gradient direction energy field;
The global optimization unit, three energy field stacks that are used for above three unit are set up obtain new energy field, then it are carried out global optimization, obtain the accurate profile of destination object in the image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010149361 CN101833750A (en) | 2010-04-15 | 2010-04-15 | Active contour method based on shape constraint and direction field, and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010149361 CN101833750A (en) | 2010-04-15 | 2010-04-15 | Active contour method based on shape constraint and direction field, and system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101833750A true CN101833750A (en) | 2010-09-15 |
Family
ID=42717811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010149361 Pending CN101833750A (en) | 2010-04-15 | 2010-04-15 | Active contour method based on shape constraint and direction field, and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101833750A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964112A (en) * | 2010-10-29 | 2011-02-02 | 上海交通大学 | Adaptive prior shape-based image segmentation method |
| CN103049735A (en) * | 2011-10-14 | 2013-04-17 | 株式会社理光 | Method for detecting particular object in image and equipment for detecting particular object in image |
| CN103473537A (en) * | 2013-09-17 | 2013-12-25 | 湖北工程学院 | Method and device for representing contour feature of target image |
| CN110414595A (en) * | 2019-07-25 | 2019-11-05 | 广西科技大学 | The orientation estimate method of texture image with orientation consistency |
| US20200013171A1 (en) * | 2012-02-14 | 2020-01-09 | Koninklijke Philips N.V. | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms |
| CN113537231A (en) * | 2020-04-17 | 2021-10-22 | 西安邮电大学 | Contour point cloud matching method combining gradient and random information |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101126811A (en) * | 2007-09-29 | 2008-02-20 | 北京交通大学 | Method for detecting lakeshore and extracting lake profile from SAR image |
| CN101202916A (en) * | 2007-12-04 | 2008-06-18 | 南京邮电大学 | Method for sequence image segmentation based on movement forecast and three-dimensional constraining |
-
2010
- 2010-04-15 CN CN 201010149361 patent/CN101833750A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101126811A (en) * | 2007-09-29 | 2008-02-20 | 北京交通大学 | Method for detecting lakeshore and extracting lake profile from SAR image |
| CN101202916A (en) * | 2007-12-04 | 2008-06-18 | 南京邮电大学 | Method for sequence image segmentation based on movement forecast and three-dimensional constraining |
Non-Patent Citations (6)
| Title |
|---|
| 《ACIVS 2008》 20081024 Rami Ben-Ari et al Geodesic Active Contours with Combined Shape and Appearance Priors 第494－499页1－3节 1－7 , 2 * |
| 《ECCV 2002》 20021231 Mikael Rousson et al Shape Priors for Level Set Representations 第84－85页4.1节 3 , 2 * |
| 《IEEE Transactions on Pattern Analysis and Machine Intelligence》 20070131 Hua Li et al Local or Global Minima: Flexible Dual-Front Active Contours 1－14 1－7 第29卷, 第1期 2 * |
| 《International Journal of Computer Vision》 19970331 Vicent Caselles et al Geodesic Active Contours 61－79 1－7 第22卷, 第1期 2 * |
| 《International Journal of Computer Vision》 20030831 R. Kimmel et al Regularized Laplacian Zero Crossings as Optimal Edge Integrators 225－243 1－7 第53卷, 第3期 2 * |
| 《ISVC 2007》 20071128 Wei Wang et al The Multiplicative Path Toward Prior-Shape Guided Active Contour for Object Detection 第541页2.1节第一段 5 , 2 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964112A (en) * | 2010-10-29 | 2011-02-02 | 上海交通大学 | Adaptive prior shape-based image segmentation method |
| CN103049735A (en) * | 2011-10-14 | 2013-04-17 | 株式会社理光 | Method for detecting particular object in image and equipment for detecting particular object in image |
| CN103049735B (en) * | 2011-10-14 | 2016-02-03 | 株式会社理光 | The equipment of certain objects in the method for certain objects and detected image in detected image |
| US20200013171A1 (en) * | 2012-02-14 | 2020-01-09 | Koninklijke Philips N.V. | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms |
| CN103473537A (en) * | 2013-09-17 | 2013-12-25 | 湖北工程学院 | Method and device for representing contour feature of target image |
| CN110414595A (en) * | 2019-07-25 | 2019-11-05 | 广西科技大学 | The orientation estimate method of texture image with orientation consistency |
| CN110414595B (en) * | 2019-07-25 | 2022-04-08 | 广西科技大学 | Method for estimating direction field of texture image with direction consistency |
| CN113537231A (en) * | 2020-04-17 | 2021-10-22 | 西安邮电大学 | Contour point cloud matching method combining gradient and random information |
| CN113537231B (en) * | 2020-04-17 | 2024-02-13 | 西安邮电大学 | Contour point cloud matching method combining gradient and random information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101833750A (en) | Active contour method based on shape constraint and direction field, and system thereof | |
| CN103455991B (en) | A kind of multi-focus image fusing method | |
| CN103208115B (en) | Based on the saliency method for detecting area of geodesic line distance | |
| CN102509099B (en) | Detection method for image salient region | |
| CN104463914A (en) | Improved Camshift target tracking method | |
| Zhao-Yi et al. | Real-time facial expression recognition based on adaptive canny operator edge detection | |
| CN102938066A (en) | Method for reconstructing outer outline polygon of building based on multivariate data | |
| CN104966286A (en) | 3D video saliency detection method | |
| CN103700113A (en) | Method for detecting dim small moving target under downward-looking complicated background | |
| CN102999926B (en) | A kind of image vision significance computational methods merged based on low-level image feature | |
| CN104463870A (en) | Image salient region detection method | |
| CN103065325B (en) | A kind of method for tracking target based on the polymerization of color Distance geometry Iamge Segmentation | |
| CN103679743A (en) | Target tracking device and method as well as camera | |
| CN102831427A (en) | Texture feature extraction method fused with visual significance and gray level co-occurrence matrix (GLCM) | |
| CN103226824B (en) | Maintain the video Redirectional system of vision significance | |
| CN105160686A (en) | Improved scale invariant feature transformation (SIFT) operator based low altitude multi-view remote-sensing image matching method | |
| CN103824305A (en) | Improved Meanshift target tracking method | |
| CN104537342A (en) | Quick lane line detection method combined with ridge boundary detection and Hough transformation | |
| CN107909085A (en) | A kind of characteristics of image Angular Point Extracting Method based on Harris operators | |
| CN105118051A (en) | Saliency detecting method applied to static image human segmentation | |
| CN107610148B (en) | Foreground segmentation method based on binocular stereo vision system | |
| CN102074000A (en) | Tracking method for adaptively adjusting window width by utilizing optimal solution of variance rate | |
| CN103390160A (en) | License plate character segmentation algorithm based on connected domain and template | |
| CN103914829A (en) | Method for detecting edge of noisy image | |
| CN113450412B (en) | Visual SLAM method based on linear features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20100915 |