CN114693691A - Graph cutting method based on coordinate mapping for double-source double-view angle - Google Patents
Graph cutting method based on coordinate mapping for double-source double-view angle Download PDFInfo
- Publication number
- CN114693691A CN114693691A CN202210288884.XA CN202210288884A CN114693691A CN 114693691 A CN114693691 A CN 114693691A CN 202210288884 A CN202210288884 A CN 202210288884A CN 114693691 A CN114693691 A CN 114693691A
- Authority
- CN
- China
- Prior art keywords
- image
- coordinate
- cutting
- main
- visual angle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013507 mapping Methods 0.000 title claims abstract description 24
- 230000000007 visual effect Effects 0.000 claims abstract description 53
- 238000001514 detection method Methods 0.000 claims description 21
- 238000007689 inspection Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009336 multiple cropping Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a graph cutting method based on coordinate mapping for double-source double-view angles, which comprises the following steps of: s1: obtaining a main visual angle image A and a side visual angle image B according to a main visual angle and a side visual angle which are mutually orthogonal; s2: correcting the main visual angle image A and the side visual angle image B, wherein the corrected main visual angle image A and the side visual angle image B are overlapped at one side; s3: cutting the main view angle image A to obtain a cut image P, wherein the cut image P is a single cut image P0 or a spliced cut image P'; s4: extracting a coordinate T1 of the wrapping image in the cutting image P; s5: acquiring a coordinate T2, wherein the coordinate T2 is a coordinate mapped on the main perspective image A by the coordinate T1; s6: acquiring a coordinate T3, wherein the coordinate T3 is a package image coordinate acquired by the side view angle image B according to the coordinate T2; s7: the lateral view image B is cut based on the coordinate T3.
Description
Technical Field
The invention relates to the technical field of intelligent security inspection, in particular to a graph cutting method based on coordinate mapping and adopting double sources and double view angles.
Background
The security inspection equipment used in airport, railway and road transportation usually mainly uses single X-ray perspective imaging, but because the objects in the luggage to be inspected are often stacked together, only one detector is needed, the imaging graph of the luggage in one direction can be inspected, and because the objects in the luggage are mutually shielded and covered, the objects which have smaller volume and are clamped between the objects with larger volume along the X-ray direction can not be detected, and the phenomenon of missing inspection easily occurs, therefore, in the prior art, the double-source double-view angle security inspection method is usually adopted to reduce the single detection angle to cause the phenomenon of missing inspection of dangerous objects, in the security inspection scene, the video signal of an X-ray machine needs to be converted into pictures, so the video is subjected to the cutting processing, but under the double-source double-view angle, if the two viewing angles both adopt the cutting picture splicing method, the method has the defects of high performance loss and weak real-time performance. Therefore, the method for providing the dual-source dual-view angle coordinate mapping-based map cutting is significant in view of the above problems.
Disclosure of Invention
The present invention is directed to a dual-source dual-view graph cutting method based on coordinate mapping, so as to solve the problems in the background art.
In order to solve the technical problem, the invention adopts the following scheme:
a dual-source dual-view coordinate mapping-based map cutting method comprises the following steps:
s1: obtaining a main visual angle image A and a side visual angle image B according to a main visual angle and a side visual angle which are mutually orthogonal;
s2: correcting the main visual angle image A and the side visual angle image B, wherein the corrected main visual angle image A and the side visual angle image B are overlapped at one side;
s3: cutting the main view angle image A to obtain a cut image P, wherein the cut image P is a single cut image P0 or a spliced cut image P';
s4: extracting a coordinate T1 of a wrapping image in the cutting image P;
s5: acquiring a coordinate T2, wherein the coordinate T2 is a coordinate mapped on the main perspective image A by the coordinate T1;
s6: acquiring a coordinate T3, wherein the coordinate T3 is a parcel image coordinate acquired by the side view angle image B according to the coordinate T2;
s7: the lateral view image B is cut based on the coordinate T3.
Further, the method also comprises the following steps:
s0: and obtaining a main visual angle and a side visual angle which are orthogonal with each other according to the coordinate mapping requirement and the movement direction of the conveyor belt of the security inspection machine.
Further, when S1 is executed: the main viewing angle image A and the side viewing angle image B are obtained at the same time.
Further, when S2 is executed: the main view angle image a and the side view angle image B are corrected based on a feature matrix method.
Further, when S3 is executed: the main view angle is provided with a detection area S and an identification area X, a cutting area Q is formed between the detection area S and the identification area X at an initial position, the detection area S is fixedly arranged, the identification area X moves along with a conveyor belt of the security inspection machine, and when the identification area X is overlapped with the detection area S, a main view angle image A in the cutting area Q is cut to obtain a single cutting image P0;
further, when the recognition area X coincides with the detection area S, the recognition area X will be generated again at the initial position.
Furthermore, the size of the cutting map area Q is m × n, and the size of the detection area S and the size of the identification area X are a × n.
Further, S3 is repeatedly executed to perform multiple cropping on the main perspective image a, resulting in a stitched cropped image P'.
Further, the method also comprises the following steps: step S31: the single cutout image P0 or the stitched cutout image P' is saved in the buffer area W.
Further, when the main view image a is subjected to the first cutout, the cutout image P0 is saved in the buffer area W;
when the main perspective image A is subjected to secondary image cutting, a cutting image P1 is obtained, the cutting image P0 moves m to one side of the motion direction of the security inspection machine conveyor belt, the cutting image P1 is saved until the cutting image P0 is saved at the original position of the buffer area W,
……
when the main visual angle image A is subjected to the nth cutting, a cutting image P (N-1) is obtained, the cutting image P (N-2) moves m to one side of the motion direction of a conveyor belt of the security inspection machine, the cutting image P (N-1) is stored until the cutting image P (N-2) is stored at the original position of a buffer area W,
and the cutting image P0, the cutting images P1 and … … are spliced into a cutting image P (N-2) and a cutting image P (N-1) to obtain a cutting image P'.
The invention has the following beneficial effects:
1. in the invention, under the models of the main visual angle and the side visual angle which are orthogonal with each other, the cutting and jigsaw processing are only carried out on the main visual angle image A, the side visual angle image B can obtain the coordinate of the package image on the side visual angle image B according to the coordinate relation with the main visual angle image A, and the cutting is directly carried out according to the coordinate on the side visual angle image B without jigsaw processing and jigsaw caching, thereby reducing the performance loss and enhancing the real-time property.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic diagram of a model of dual source and dual view;
FIG. 3 is a schematic diagram showing the relationship between the corrected main viewing angle image A and the corrected side viewing angle image B;
FIG. 4 is a schematic flow chart of a main view image A;
fig. 5 is a schematic view of saving the slice pictures in the buffer area W.
Detailed Description
In order to make the technical solutions, technical problems to be solved, and technical effects of the present invention more clearly apparent, the technical solutions of the present invention are described below in detail with reference to specific embodiments. All embodiments that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention are within the protection scope of the present invention.
As shown in fig. 1 and 2, according to the coordinate mapping requirement and the movement direction of the conveyor belt of the security inspection machine, a dual-source dual-view model of a main view angle and a side view angle which are orthogonal to each other is obtained, and a graph cutting method based on the coordinate mapping is as follows: firstly, obtaining a main visual angle image A and a side visual angle image B and correcting the main visual angle image A and the side visual angle image B; secondly, cutting the main visual angle image A to obtain a cut image P; thirdly, acquiring a required coordinate coefficient, including extracting a coordinate T1 of the package image in the cutting image P, a coordinate T2 of the coordinate T1 mapped on the main viewing angle image A, and a package image coordinate T3 of the side viewing angle image B acquired according to the coordinate T2; finally, the lateral perspective image B is cut based on the coordinate T3.
Example one
As shown in fig. 2 and 3, two viewing angles perpendicular to the moving direction are taken along the moving direction of the conveyor belt, and the two viewing angles are orthogonal. In the following drawings, the Z direction is the moving direction of the conveyor belt, the X and Y directions are perpendicular to the Z direction, and the X and Y directions are two viewing angles of a dual-source dual-viewing angle, wherein the X direction and the Y direction are perpendicular, and one of the X direction and the Y direction is assumed as a main viewing angle, and the other is assumed as a side viewing angle. It is assumed here that the X direction is the main viewing angle and the Y direction is the side viewing angle. After the main perspective image a and the side perspective image B are obtained, the main perspective image a and the side perspective image B are corrected, and the main perspective image a and the side perspective image B are corrected by using a characteristic matrix method so that the main perspective image a and the side perspective image B are overlapped on one side when the images are perpendicular to each other, that is, the length of the perspective image a is the same as that of the side perspective image B, that is, w0 is w 1.
As shown in fig. 4, when the main view image a is cut, two regions, namely, a detection region S and an identification region X, are set for the main view, the detection region S is at a fixed position, the identification region X moves along with the conveyor belt of the security inspection machine, the moving direction of the conveyor belt in fig. 4 is from right to left, and when the identification region X coincides with the detection region S, the main view image a located in a cutting region Q is cut to obtain a single cutting image P0, wherein the cutting region Q has a size of m × n, and the detection region S and the identification region X have a size of a × n.
When a finished package image is contained in the scene of single image cutting, extraction of the package image is carried out in the image cutting image P0, the coordinate T1 of the extracted package image is obtained, the coordinate T1 is mapped to the main viewing angle image A to obtain the coordinate T2, the coordinate T3 is obtained according to the relation between the corrected main viewing angle image A and the corrected side viewing angle image B, and the image cutting of the side viewing angle image B is carried out on the basis of the coordinate T3.
Example two
As shown in fig. 2 and 3, two visual angles perpendicular to the moving direction are taken along the moving direction of the conveyor belt, and the two visual angles are orthogonal. In the following drawings, the Z direction is the moving direction of the conveyor belt, the X and Y directions are perpendicular to the Z direction, and the X and Y directions are two viewing angles of a dual-source dual-viewing angle, wherein the X direction and the Y direction are perpendicular, and one of the X direction and the Y direction is assumed as a main viewing angle, and the other is assumed as a side viewing angle. It is assumed here that the X direction is the main viewing angle and the Y direction is the side viewing angle. After the main perspective image a and the side perspective image B are obtained, the main perspective image a and the side perspective image B are corrected, and the main perspective image a and the side perspective image B are corrected by using a characteristic matrix method so that the main perspective image a and the side perspective image B are overlapped on one side when the images are perpendicular to each other, that is, the length of the perspective image a is the same as that of the side perspective image B, that is, w0 is w 1.
As shown in fig. 4, when the main view image a is cut, two regions, a detection region S and an identification region X are set for the main view, the detection region S is a fixed position, the identification region X moves along with the movement of the security inspection machine conveyor belt, the moving direction of the conveyor belt in fig. 4 is from right to left, and when the identification region X coincides with the detection region S, the main view image a located in a cut region Q with a size of m × n is cut to obtain a single cut image P0, wherein the size of the cut region Q is m × n, and the size of the detection region S and the size of the identification region X are a × n.
When a finished parcel image is contained under the scene needing multiple image cutting and splicing, multiple image cutting is carried out on the main visual angle image A to obtain a spliced image cutting image P ', the spliced image cutting image P' is stored in a cache region, and the maximum length of a W cache region W is L
When the main perspective image A is subjected to first image cutting, the image cutting image P0 is stored in the buffer area W; when the main perspective image A is subjected to secondary image cutting, a cut image P1 is obtained, the cut image P0 moves m to one side of the motion direction of the security inspection machine conveyor belt, namely moves m to the left, and the cut image P1 is placed at the rightmost side of the buffer area W, namely the cut image P0 is stored at the original position of the buffer area W;
when the main visual angle image A is subjected to nth image cutting, a cutting image P (N-1) is obtained, the cutting image P (N-2) moves m to one side of the motion direction of a conveyor belt of the security inspection machine, namely moves m leftwards, the cutting image P (N-1) is stored until the cutting image P (N-2) is stored at the original position of a cache area W, namely the cutting image P (N-1) is placed at the rightmost side of the cache area W;
and splicing the cutting image P0, the cutting images P1 and … …, the cutting image P (N-2) and the cutting image P (N-1) to obtain a cutting image P ', wherein the length of the cutting image P' is b, b is less than L, and the dimension of P is b N.
The extraction of the parcel images is carried out in the cutout image P', the coordinates of the extracted parcel images are selected as the upper left vertex t0(x0, y0), the lower right vertex t1(x1, y1) of the parcel images in the embodiment,
the distance from t0, t1 to the right edge of the map-cut image P' is calculated as: d0 ═ b-y0, d1 ═ b-y 1;
mapping the coordinates of the parcel image into the main view image A to obtain:
the upper left vertex t 0', x0 ═ x0, y0 ═ w0-a-d0
Right lower vertex t 1', x1 ═ x1, y1 ═ w0-a-d1
Since the length of the main view angle image a is the same as that of the side view angle image B, that is, w0 is w1, the side view angle image B may be cut with the upper left vertex being (0, y0 ') and the lower right vertex being (h1, y 1'), thereby completing a cut based on the coordinate mapping relationship.
EXAMPLE III
The technical solution of the present embodiment is different from the second embodiment in that a spliced cutout image P 'includes a plurality of parcel images, and the same portions are not described repeatedly, when extraction of a parcel image is performed in the cutout image P', coordinates of the plurality of parcel images are extracted, a parcel image coordinate T1 at this time is a coordinate set including coordinates of the plurality of parcel images, the coordinate set is mapped to a main perspective image a, a coordinate T1 is mapped to the main perspective image a to obtain a coordinate T2, a coordinate T3 is obtained according to a relationship between the corrected main perspective image a and a side perspective image B, and a side perspective image B is cut based on the coordinate T3.
To sum up, the double-source double-view is based on cutting the picture when the coordinate maps, only cut picture puzzle processing to main visual angle image A, and cache main visual angle image A's cut picture P, extract parcel image coordinate in cut picture P, and map it on main visual angle image A, side view angle image B can be according to the coordinate relation with main visual angle image A, acquire the coordinate of parcel image on side view angle image B, according to the direct cutting of coordinate on side view angle image B, side view angle image B need not to carry out puzzle processing again and cache the puzzle, thereby reduce performance loss, reinforcing real-time.
The principle and embodiments of the present invention are described in detail by using specific examples, which are only used to help understanding the core technical content of the present invention, and are not used to limit the protection scope of the present invention, and the technical solution of the present invention is not limited to the specific embodiments described above. Based on the above embodiments of the present invention, those skilled in the art should make any improvements and modifications to the present invention without departing from the principle of the present invention, and therefore, the present invention should fall into the protection scope of the present invention.
Claims (10)
1. A graph cutting method based on coordinate mapping for double sources and double visual angles is characterized by comprising the following steps:
s1: obtaining a main visual angle image A and a side visual angle image B according to a main visual angle and a side visual angle which are orthogonal to each other;
s2: correcting the main visual angle image A and the side visual angle image B, wherein the corrected main visual angle image A and the side visual angle image B are overlapped at one side;
s3: cutting the main view angle image A to obtain a cut image P, wherein the cut image P is a single cut image P0 or a spliced cut image P';
s4: extracting a coordinate T1 of the wrapping image in the cutting image P;
s5: acquiring a coordinate T2, wherein the coordinate T2 is a coordinate mapped on the main perspective image A by the coordinate T1;
s6: acquiring a coordinate T3, wherein the coordinate T3 is a parcel image coordinate acquired by the side view angle image B according to the coordinate T2;
s7: the lateral view image B is cut based on the coordinate T3.
2. The dual-source dual-view coordinate-based mapping method of claim 1, further comprising the steps of:
s0: and obtaining a main visual angle and a side visual angle which are mutually orthogonal according to the coordinate mapping requirement and the movement direction of the conveyor belt of the security inspection machine.
3. The dual-source dual-view coordinate-based mapping method of claim 1, wherein when performing S1: the main viewing angle image A and the side viewing angle image B are obtained at the same time.
4. The dual-source dual-view coordinate-based mapping method of claim 1, wherein when performing S2: the main view angle image a and the side view angle image B are corrected based on a feature matrix method.
5. The dual-source dual-view coordinate-based mapping method of claim 1, wherein when performing S3: the main visual angle is provided with a detection area S and an identification area X, a cutting area Q is formed between the detection area S and the identification area X at the initial position, the detection area S is fixedly arranged, the identification area X moves along with a conveyor belt of the security inspection machine, and when the identification area X is overlapped with the detection area S, a main visual angle image in the cutting area Q is cut to obtain a single cutting image P0.
6. The dual-source dual-view coordinate-mapping-based graph cutting method of claim 5, wherein the identification region X is generated again at an initial position when the identification region X coincides with the detection region S.
7. The dual-source dual-view coordinate-based mapping method of claim 5, wherein the size of the mapping region Q is m X n, and the size of the detection region S and the identification region X is a X n.
8. The dual-source dual-view coordinate-based mapping method of claim 5, wherein S3 is repeatedly performed to perform multiple cuts on the main-view image a to obtain a stitched cut image P'.
9. The dual-source dual-view coordinate-based mapping method of claim 8, further comprising:
step S31: the single cutout image P0 or the stitched cutout image P' is saved in the buffer area W.
10. The dual-source dual-view coordinate-based mapping method of claim 9,
when the main perspective image A is subjected to first image cutting, the image cutting image P0 is stored in the buffer area W;
when the main perspective image A is subjected to secondary image cutting, a cutting image P1 is obtained, the cutting image P0 moves m to one side of the motion direction of the security inspection machine conveyor belt, the cutting image P1 is saved until the cutting image P0 is saved at the original position of the buffer area W,
……
when the main visual angle image A is subjected to the nth cutting, a cutting image P (N-1) is obtained, the cutting image P (N-2) moves m to one side of the motion direction of a conveyor belt of the security inspection machine, the cutting image P (N-1) is stored until the cutting image P (N-2) is stored at the original position of a buffer area W,
the cutting image P0, the cutting images P1 and … … are spliced into the cutting image P (N-2) and the cutting image P (N-1) to obtain a cutting image P'.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210288884.XA CN114693691B (en) | 2022-03-23 | 2022-03-23 | Graph cutting method based on coordinate mapping for double sources and double visual angles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210288884.XA CN114693691B (en) | 2022-03-23 | 2022-03-23 | Graph cutting method based on coordinate mapping for double sources and double visual angles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114693691A true CN114693691A (en) | 2022-07-01 |
| CN114693691B CN114693691B (en) | 2023-05-02 |
Family
ID=82138359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210288884.XA Active CN114693691B (en) | 2022-03-23 | 2022-03-23 | Graph cutting method based on coordinate mapping for double sources and double visual angles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114693691B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471560A (en) * | 2022-11-11 | 2022-12-13 | 成都智元汇信息技术股份有限公司 | Graph cutting method and device based on main view angle and side view angle |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2678460A1 (en) * | 1991-06-27 | 1992-12-31 | Centre Nat Etd Spatiales | METHOD FOR RECORDING AND PROCESSING IMAGE AND VIEWING INSTRUMENT FOR IMPLEMENTING SAID METHOD |
| JP2000155839A (en) * | 1998-11-18 | 2000-06-06 | Nippon Telegr & Teleph Corp <Ntt> | Marked area image extraction method, device therefor and recoding medium recorded with marked area image extracting program |
| US6577760B1 (en) * | 1997-12-18 | 2003-06-10 | Fuji Photo Film Co., Ltd. | Image processing apparatus and method, image synthesizing system and method, image synthesizer and client computer which constitute image synthesizing system, and image separating method |
| US20050073723A1 (en) * | 2003-03-20 | 2005-04-07 | Toshiba Tec Kabushiki Kaisha | Image processing apparatus and image processing method |
| US20050117779A1 (en) * | 2003-11-27 | 2005-06-02 | Konica Minolta Holdings, Inc. | Object detection apparatus, object detection method and computer program product |
| JP2016081425A (en) * | 2014-10-21 | 2016-05-16 | キヤノン株式会社 | Image processing device, and image processing method and program |
| CN107202808A (en) * | 2017-06-14 | 2017-09-26 | 上海英曼尼安全装备有限公司 | A kind of double source double-visual angle safety inspection method and its system |
| TWI619091B (en) * | 2016-12-29 | 2018-03-21 | Beijing Qiyi Century Science & Technology Co Ltd | Panorama image compression method and device |
| CN108230454A (en) * | 2017-12-28 | 2018-06-29 | 瑞庭网络技术（上海）有限公司 | A kind of panoramic pictures cut drawing method, device and storage medium |
-
2022
- 2022-03-23 CN CN202210288884.XA patent/CN114693691B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2678460A1 (en) * | 1991-06-27 | 1992-12-31 | Centre Nat Etd Spatiales | METHOD FOR RECORDING AND PROCESSING IMAGE AND VIEWING INSTRUMENT FOR IMPLEMENTING SAID METHOD |
| US6577760B1 (en) * | 1997-12-18 | 2003-06-10 | Fuji Photo Film Co., Ltd. | Image processing apparatus and method, image synthesizing system and method, image synthesizer and client computer which constitute image synthesizing system, and image separating method |
| JP2000155839A (en) * | 1998-11-18 | 2000-06-06 | Nippon Telegr & Teleph Corp <Ntt> | Marked area image extraction method, device therefor and recoding medium recorded with marked area image extracting program |
| US20050073723A1 (en) * | 2003-03-20 | 2005-04-07 | Toshiba Tec Kabushiki Kaisha | Image processing apparatus and image processing method |
| US20050117779A1 (en) * | 2003-11-27 | 2005-06-02 | Konica Minolta Holdings, Inc. | Object detection apparatus, object detection method and computer program product |
| JP2016081425A (en) * | 2014-10-21 | 2016-05-16 | キヤノン株式会社 | Image processing device, and image processing method and program |
| TWI619091B (en) * | 2016-12-29 | 2018-03-21 | Beijing Qiyi Century Science & Technology Co Ltd | Panorama image compression method and device |
| CN107202808A (en) * | 2017-06-14 | 2017-09-26 | 上海英曼尼安全装备有限公司 | A kind of double source double-visual angle safety inspection method and its system |
| CN108230454A (en) * | 2017-12-28 | 2018-06-29 | 瑞庭网络技术（上海）有限公司 | A kind of panoramic pictures cut drawing method, device and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471560A (en) * | 2022-11-11 | 2022-12-13 | 成都智元汇信息技术股份有限公司 | Graph cutting method and device based on main view angle and side view angle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114693691B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1708138B1 (en) | Image processing method, three-dimensional position measuring method and image processing apparatus | |
| JP5792157B2 (en) | Image processing apparatus, method, program, and recording medium | |
| CN107924571A (en) | Three-dimensional reconstruction is carried out to human ear from a cloud | |
| CN114693691A (en) | Graph cutting method based on coordinate mapping for double-source double-view angle | |
| CN115410167A (en) | Target detection and semantic segmentation method, device, equipment and storage medium | |
| CN114155254B (en) | Image cutting method based on image correction, electronic device and medium | |
| CN113253845A (en) | View display method, device, medium and electronic equipment based on eye tracking | |
| EP2458877A1 (en) | Occlusion layer extension | |
| CN114660097A (en) | Synchronous correction method and system based on double sources and double visual angles | |
| CN115909268A (en) | Dynamic obstacle detection method and device | |
| CN115423683B (en) | Method and device for locally amplifying column data package picture by using drawing board and display | |
| CN115345862B (en) | Method and device for simulating X-ray machine scanning imaging based on column data and display | |
| CN115423684B (en) | Method and device for locally amplifying column wrapping picture by RGB array | |
| CN115086635B (en) | Multi-view video processing method, device and equipment and storage medium | |
| JPH09231370A (en) | Picture information input device | |
| CN115424181A (en) | Target object detection method and device | |
| JP3556319B2 (en) | Distance measuring device | |
| US20060251337A1 (en) | Image object processing | |
| CN113011212B (en) | Image recognition method and device and vehicle | |
| CN115457178B (en) | Method and system for issuing virtual contraband information based on column data | |
| CN115578681B (en) | Method and system for advancing parcel identification based on column data | |
| CN115471560B (en) | Graph cutting method and device based on main view angle and side view angle | |
| CN115690261B (en) | Parking space mapping method based on multi-sensor fusion, vehicle and storage medium | |
| CN111630569A (en) | Binocular matching method, visual imaging device and device with storage function | |
| JPH11248433A (en) | Method and device for recognizing object |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |