CN106023073A - Image splicing system - Google Patents
Image splicing system Download PDFInfo
- Publication number
- CN106023073A CN106023073A CN201610305058.6A CN201610305058A CN106023073A CN 106023073 A CN106023073 A CN 106023073A CN 201610305058 A CN201610305058 A CN 201610305058A CN 106023073 A CN106023073 A CN 106023073A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- coordinate system
- mosaic
- average
- 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
- 238000003707 image sharpening Methods 0.000 claims abstract description 10
- 230000007704 transition Effects 0.000 claims abstract description 9
- 238000002485 combustion reaction Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
Classifications
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image splicing system comprising an image obtaining module, an image splicing module, a mean value calculation module, an image coverage module, an image fuzzy module, an image sharpening module, and an image storage module. According to the invention, the mean value calculation module and the image coverage module carry out mean value processing on an overlapped part in a spliced image and particularly transition for splicing of images shot by two adjacent cameras is realized by the mean value image, so that a problem that a spliced image can not be watched properly and comfortably because of pixel hopping of images shot by two cameras due to different angles and light can be solved.
Description
Technical field
The present invention relates to image mosaic technology field, particularly relate to a kind of image mosaic system.
Background technology
Along with the development of electronic imaging technology, various video image demonstration equipments in the life of people without
Hole does not enters.Video image demonstration equipment is used for demonstration video or image, and the essence of video is image
Dynamic play, so, video image demonstration in, image be basis be also core.
In image processing process, a requisite processing mode is exactly image mosaic, i.e. by edge weight
Folded image mosaic is piece image.At present, during image mosaic, it is all simple by edge portions phase
Overlapping image mutually covers.The image that this mode is spliced, smoothness is low, and transition is unnatural, easily makes
Become the discomfort that vision is viewed and admired.
Summary of the invention
The technical problem existed based on background technology, the present invention proposes a kind of image mosaic system.
A kind of image mosaic system that the present invention proposes, including:
Image collection module, it includes multiple photographic head, two photographic head that any two camera watch region is adjacent
Shooting local area portion overlapping；
Image mosaic module, its connection image collection module obtains the image of each photographic head shooting in real time, and will
The image of each camera collection of synchronization splices, the overlapping region in the image of adjacent camera shooting
Mutually cover；Image mosaic module also will shoot in image with adjacent camera in each photographic head shooting image
Overlapping region extracts；
Mean value computation module, its internal preset has the first coordinate system, the second coordinate system and HCCI combustion system, its
Connect image mosaic module, and by the overlapping region that extracts in image mosaic module according to its adjacent two width figures
Correspondence image in Xiang is respectively mapped to the first coordinate system and second in the case of pixel coordinate is corresponding and sits
In mark system, then calculate the average of pixel corresponding in the first coordinate system and the second coordinate system and be mapped to
HCCI combustion system obtains average pixel coordinate；It is right that mean value computation module generates according to the conversion of average pixel coordinate
Should the average image of each overlapping region；
Image overlay module connects image mosaic module and mean value computation module respectively, and it is from image mosaic module
Middle acquisition stitching image, and from mean value computation module, obtain corresponding equal in overlapping region each with stitching image
Value image, is then covered each by stitching image the overlapping region of correspondence, it is thus achieved that average mistake by average image
Cross stitching image.
Preferably, the coordinate of corresponding in the first coordinate system, the second coordinate system and HCCI combustion system pixel
Identical.
Preferably, in mean value computation module, the corresponding multiple overlapping regions of the first coordinate system are divided into multiple corresponding
Coordinates regional, the correspondence image on the piece image wherein of each overlapping region is respectively mapped in the first coordinate system
In corresponding coordinates regional；Each overlapping region correspondence image on another piece image is at pixel coordinate and
One coordinate system is respectively mapped in the second coordinate system in the case of keeping unanimously.
Preferably, also include that image blurring module and image sharpening module, image blurring module cover with image
Module connects, and it obtains average transition stitching image and it is carried out Fuzzy Processing；Image sharpening module and figure
As obfuscation module connects, it obtains the average transition stitching image after Fuzzy Processing and it is sharpened acquisition
Final stitching image.
Preferably, also including image storage module, it is connected with image sharpening module, and it obtains final splicing
Its correlation time is also stored by image.
The image mosaic system that the present invention provides, first passes through and arranges multiple photographic head, and any two shooting
The shooting local area portion of two photographic head that region is adjacent is overlapping, so, can be shot bigger field by subregion
Scape carries out pan-shot, is then obtained the panoramic picture of actual scene by image mosaic.
In the present invention, by mean value computation module and image overlay module to the overlapping portion in spliced image
Divide and carry out average value processing, be equivalent to the splicing by average image shoots image to adjacent two photographic head and enter
Row transition, solves the image of two photographic head shootings due to the different pixel jump occurred such as angle, light
Cause the problem that spliced image views and admires discomfort.
In the present invention, mean value computation module, carry out average value processing by converting images into pixel coordinate, make
Image equalization from abstract become having as, be conducive to improving the precision of image average value processing and efficiency.And,
The overlapping region of different images is both mapped in the first coordinate system and the second coordinate system by the present invention, simplifies
The foundation of coordinate system, and by the first coordinate system and the second coordinate system, each overlapping region is unifiedly calculated, carry
High mean value computation efficiency.
Accompanying drawing explanation
Fig. 1 is a kind of image mosaic system structure schematic diagram that the present invention proposes.
Detailed description of the invention
Reference Fig. 1, a kind of image mosaic system that the present invention proposes, including: image collection module, image are spelled
Connection module, mean value computation module, image overlay module, image blurring module, image sharpening module and image
Memory module.
Image collection module includes multiple photographic head, the bat of two photographic head that any two camera watch region is adjacent
Take the photograph local area portion overlapping.In present embodiment, by arranging multiple photographic head, relatively large scene can be carried out point
Region shoots, and overcomes the problem that single photographic head shooting area is limited.
Image mosaic module connects image collection module and obtains the image of each photographic head shooting in real time, and by same
The moment image of each camera collection splices, and the overlapping region in the image of adjacent camera shooting is mutual
Cover.In present embodiment, the shooting local area portion weight of two photographic head that any two camera watch region is adjacent
Folded, so, by overlapping region, the shooting image mosaic of two photographic head is got up, thus can obtain
Whole scene capture image.
Image mosaic module also will shoot the overlay region in image with adjacent camera in each photographic head shooting image
Territory extracts.
Mean value computation inside modules is preset with the first coordinate system, the second coordinate system and HCCI combustion system.Average meter
Calculate module and connect image mosaic module, and by adjacent according to it for the overlapping region that extracts in image mosaic module
Correspondence image in two width images be respectively mapped in the case of pixel coordinate is corresponding first coordinate system and
In second coordinate system, then calculate the average of pixel corresponding in the first coordinate system and the second coordinate system also
It is mapped in HCCI combustion system acquisition average pixel coordinate.
That is, shooting image with some photographic head is the first image, and adjacent camera shooting image is the second figure
Picture, the first image and the second image section are overlapping, and in the first image, overlapping region is the first overlay chart picture,
In second image, overlapping region is the second overlay chart picture.Mean value computation module is by the first overlay chart picture and the second weight
Folded image is respectively mapped in the first coordinate system and the second coordinate system, and the first overlay chart picture and the second overlay chart
Pixel corresponding in Xiang is identical with the coordinate position in the second coordinate system in the first coordinate system.HCCI combustion
In coordinate points in system and the first coordinate system and the second coordinate system in coordinate points one_to_one corresponding, and HCCI combustion system
The pixel that pixel value is pixel corresponding in the first coordinate system and the second coordinate system corresponding to each coordinate points
Average, i.e. T(X,Y)=(T1(X,Y)+T2(X,Y))/2, (X, Y) is pixel coordinate, T(X,Y)For pixel (X, Y) in average
Pixel value in coordinate system, T1(X,Y)For the pixel (X, Y) pixel value in the first coordinate system, T2(X,Y)For picture
The vegetarian refreshments (X, Y) pixel value in the second coordinate system.
Mean value computation module generates the average image of corresponding each overlapping region according to the conversion of average pixel coordinate.All
Value image be the first overlay chart picture and the second overlay chart as the image after average value processing, it combines the first image
Acquisition characteristics such as light, angle etc. with the second image.
In present embodiment, in the first coordinate system of mean value computation module, corresponding multiple overlapping regions are divided into multiple
Corresponding coordinates regional, the correspondence image on the piece image wherein of each overlapping region is respectively mapped to first
In coordinates regional corresponding in coordinate system；Each overlapping region correspondence image on another piece image is at pixel
Coordinate and the first coordinate system are respectively mapped in the second coordinate system in the case of keeping unanimously.Then, by all
Value calculates, and the pixel average of each overlapping region is mapped in HCCI combustion.
In present embodiment, the overlapping region of different images is both mapped to the first coordinate system and the second coordinate system
In, simplify the foundation of coordinate system, and by the first coordinate system and the second coordinate system, is united in each overlapping region
One calculates, and improves mean value computation efficiency.
Image overlay module connects image mosaic module and mean value computation module respectively, and it is from image mosaic module
Middle acquisition stitching image, and from mean value computation module, obtain corresponding equal in overlapping region each with stitching image
Value image, is then covered each by stitching image the overlapping region of correspondence, it is thus achieved that average mistake by average image
Cross stitching image.
In present embodiment, be equivalent to after the first image and the second image mosaic, in image after splicing
First overlay chart picture and the second overlay chart picture carry out the smoothness of image after average value processing splices with raising, thus
The problem that in spliced image, pixel jump occurs in the transitional region of the first image to the second image.
Image blurring module is connected with image overlay module, and it obtains average transition stitching image and carries out it
Fuzzy Processing, with the smoothness of image after further raising splicing.Image sharpening module and image blurring module
Connecting, it obtains the average transition stitching image after Fuzzy Processing and it is sharpened the final spliced map of acquisition
Picture.Edge contrast can solve the unsharp problem of profile that Fuzzy Processing is brought.
Image storage module is connected with image sharpening module, and it obtains final stitching image and by its correlation time
Store.
The above, the only present invention preferably detailed description of the invention, but protection scope of the present invention not office
Being limited to this, any those familiar with the art is in the technical scope that the invention discloses, according to this
The technical scheme of invention and inventive concept thereof in addition equivalent or change, all should contain the protection in the present invention
Within the scope of.
Claims (5)
1. an image mosaic system, it is characterised in that including:
Image collection module, it includes multiple photographic head, two photographic head that any two camera watch region is adjacent
Shooting local area portion overlapping；
Image mosaic module, its connection image collection module obtains the image of each photographic head shooting in real time, and will
The image of each camera collection of synchronization splices, the overlapping region in the image of adjacent camera shooting
Mutually cover；Image mosaic module also will shoot in image with adjacent camera in each photographic head shooting image
Overlapping region extracts；
Mean value computation module, its internal preset has the first coordinate system, the second coordinate system and HCCI combustion system, its
Connect image mosaic module, and by the overlapping region that extracts in image mosaic module according to its adjacent two width figures
Correspondence image in Xiang is respectively mapped to the first coordinate system and second in the case of pixel coordinate is corresponding and sits
In mark system, then calculate the average of pixel corresponding in the first coordinate system and the second coordinate system and be mapped to
HCCI combustion system obtains average pixel coordinate；It is right that mean value computation module generates according to the conversion of average pixel coordinate
Should the average image of each overlapping region；
Image overlay module connects image mosaic module and mean value computation module respectively, and it is from image mosaic module
Middle acquisition stitching image, and from mean value computation module, obtain corresponding equal in overlapping region each with stitching image
Value image, is then covered each by stitching image the overlapping region of correspondence, it is thus achieved that average mistake by average image
Cross stitching image.
2. image mosaic system as claimed in claim 1, it is characterised in that the first coordinate system, the second seat
The coordinate of the pixel that mark system is corresponding with in HCCI combustion system is identical.
3. image mosaic system as claimed in claim 2, it is characterised in that in mean value computation module first
The corresponding multiple overlapping regions of coordinate system are divided into multiple corresponding coordinates regional, each overlapping region width wherein
Correspondence image on image is respectively mapped in the first coordinate system in the coordinates regional of correspondence；Each overlapping region exists
Correspondence image on another piece image is reflected in the case of pixel coordinate and the first coordinate system keep unanimously respectively
It is mapped in the second coordinate system.
4. image mosaic system as claimed in claim 1, it is characterised in that also include image blurring module
With image sharpening module, image blurring module is connected with image overlay module, and it obtains average transition spliced map
Picture also carries out Fuzzy Processing to it；Image sharpening module is connected with image blurring module, and it obtains Fuzzy Processing
After average transition stitching image and to its be sharpened acquisition final stitching image.
5. image mosaic system as claimed in claim 4, it is characterised in that also include image storage module,
It is connected with image sharpening module, and it obtains final stitching image and is stored its correlation time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610305058.6A CN106023073A (en) | 2016-05-06 | 2016-05-06 | Image splicing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610305058.6A CN106023073A (en) | 2016-05-06 | 2016-05-06 | Image splicing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106023073A true CN106023073A (en) | 2016-10-12 |
Family
ID=57099347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610305058.6A Pending CN106023073A (en) | 2016-05-06 | 2016-05-06 | Image splicing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106023073A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651755A (en) * | 2016-11-17 | 2017-05-10 | 宇龙计算机通信科技(深圳)有限公司 | Panoramic image processing method and device for terminal and terminal |
| CN106846407A (en) * | 2016-11-25 | 2017-06-13 | 努比亚技术有限公司 | A kind of method and apparatus for realizing image rectification |
| CN106846408A (en) * | 2016-11-25 | 2017-06-13 | 努比亚技术有限公司 | A kind of method and apparatus for obtaining correction parameter |
| CN107273402A (en) * | 2017-04-24 | 2017-10-20 | 广东小天才科技有限公司 | Method and device for searching test questions by using double cameras |
| CN110169044A (en) * | 2017-01-06 | 2019-08-23 | 富士胶片株式会社 | Image processing apparatus, image processing method and program |
| CN110288639A (en) * | 2019-06-21 | 2019-09-27 | 深圳职业技术学院 | A computer-aided virtual mosaic system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090231447A1 (en) * | 2008-03-12 | 2009-09-17 | Chung-Ang University Industry-Academic Cooperation Foundation | Apparatus and method for generating panorama images and apparatus and method for object-tracking using the same |
| CN101621634A (en) * | 2009-07-24 | 2010-01-06 | 北京工业大学 | Method for splicing large-scale video with separated dynamic foreground |
| US20100194851A1 (en) * | 2009-02-03 | 2010-08-05 | Aricent Inc. | Panorama image stitching |
| CN102342092A (en) * | 2009-03-05 | 2012-02-01 | 韩国科亚电子股份有限公司 | Apparatus and method of generating panoramic image and computer-readable recording medium storing program for executing the method |
| EP1587031A3 (en) * | 2004-04-16 | 2012-09-26 | Sony Corporation | Image pickup apparatus and image pickup method |
| CN103390267A (en) * | 2013-07-11 | 2013-11-13 | 华为技术有限公司 | Image processing method and device |
| CN104318517A (en) * | 2014-11-19 | 2015-01-28 | 北京奇虎科技有限公司 | Image splicing method and device and client terminal |
| CN105530425A (en) * | 2014-10-23 | 2016-04-27 | 西安三维通信有限责任公司 | Automatic continuous shooting system |
| CN105550981A (en) * | 2015-11-27 | 2016-05-04 | 中山大学 | Image registration and splicing method on the basis of Lucas-Kanade algorithm |
-
2016
- 2016-05-06 CN CN201610305058.6A patent/CN106023073A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1587031A3 (en) * | 2004-04-16 | 2012-09-26 | Sony Corporation | Image pickup apparatus and image pickup method |
| US20090231447A1 (en) * | 2008-03-12 | 2009-09-17 | Chung-Ang University Industry-Academic Cooperation Foundation | Apparatus and method for generating panorama images and apparatus and method for object-tracking using the same |
| US20100194851A1 (en) * | 2009-02-03 | 2010-08-05 | Aricent Inc. | Panorama image stitching |
| CN102342092A (en) * | 2009-03-05 | 2012-02-01 | 韩国科亚电子股份有限公司 | Apparatus and method of generating panoramic image and computer-readable recording medium storing program for executing the method |
| CN101621634A (en) * | 2009-07-24 | 2010-01-06 | 北京工业大学 | Method for splicing large-scale video with separated dynamic foreground |
| CN103390267A (en) * | 2013-07-11 | 2013-11-13 | 华为技术有限公司 | Image processing method and device |
| CN105530425A (en) * | 2014-10-23 | 2016-04-27 | 西安三维通信有限责任公司 | Automatic continuous shooting system |
| CN104318517A (en) * | 2014-11-19 | 2015-01-28 | 北京奇虎科技有限公司 | Image splicing method and device and client terminal |
| CN105550981A (en) * | 2015-11-27 | 2016-05-04 | 中山大学 | Image registration and splicing method on the basis of Lucas-Kanade algorithm |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651755A (en) * | 2016-11-17 | 2017-05-10 | 宇龙计算机通信科技(深圳)有限公司 | Panoramic image processing method and device for terminal and terminal |
| WO2018090455A1 (en) * | 2016-11-17 | 2018-05-24 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for processing panoramic image of terminal, and terminal |
| CN106846407A (en) * | 2016-11-25 | 2017-06-13 | 努比亚技术有限公司 | A kind of method and apparatus for realizing image rectification |
| CN106846408A (en) * | 2016-11-25 | 2017-06-13 | 努比亚技术有限公司 | A kind of method and apparatus for obtaining correction parameter |
| CN106846407B (en) * | 2016-11-25 | 2019-12-20 | 深圳智荟物联技术有限公司 | Method and device for realizing image correction |
| CN106846408B (en) * | 2016-11-25 | 2020-05-19 | 瑞安市辉煌网络科技有限公司 | Method and device for acquiring correction parameters |
| CN110169044A (en) * | 2017-01-06 | 2019-08-23 | 富士胶片株式会社 | Image processing apparatus, image processing method and program |
| CN107273402A (en) * | 2017-04-24 | 2017-10-20 | 广东小天才科技有限公司 | Method and device for searching test questions by using double cameras |
| CN110288639A (en) * | 2019-06-21 | 2019-09-27 | 深圳职业技术学院 | A computer-aided virtual mosaic system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10609282B2 (en) | Wide-area image acquiring method and apparatus | |
| CN106023073A (en) | Image splicing system | |
| CN110351494B (en) | Panoramic video synthesis method and device and electronic equipment | |
| KR102013978B1 (en) | Method and apparatus for fusion of images | |
| US10425638B2 (en) | Equipment and method for promptly performing calibration and verification of intrinsic and extrinsic parameters of a plurality of image capturing elements installed on electronic device | |
| EP2328125B1 (en) | Image splicing method and device | |
| CN107925751B (en) | System and method for multi-view noise reduction and high dynamic range | |
| CN103150715B (en) | Image mosaic processing method and processing device | |
| US10560633B2 (en) | Apparatus and methods for rolling shutter compensation for multi-camera systems | |
| CN102722080B (en) | A kind of multi purpose spatial image capture method based on many lens shootings | |
| CN106157304A (en) | A kind of Panoramagram montage method based on multiple cameras and system | |
| CN105072314A (en) | Virtual studio implementation method capable of automatically tracking objects | |
| CN105488766B (en) | Fisheye image bearing calibration and device | |
| CN105450931B (en) | A kind of imaging method based on array camera, device and electronic equipment | |
| JPH0380676A (en) | Electronic pan focus device | |
| CN111866523B (en) | Panoramic video synthesis method and device, electronic equipment and computer storage medium | |
| CN103295231A (en) | Method for geometrically correcting vertically mapped images of fisheye lenses in fisheye image mosaic | |
| CN110519528A (en) | A kind of panoramic video synthetic method, device and electronic equipment | |
| CN101540822A (en) | Device and method for high-resolution large-viewing-field aerial image forming | |
| CN104184935A (en) | Image shooting device and method | |
| CN107578450A (en) | A kind of method and system for the demarcation of panorama camera rigging error | |
| JP7300895B2 (en) | Image processing device, image processing method, program, and storage medium | |
| CN108269234A (en) | A kind of lens of panoramic camera Attitude estimation method and panorama camera | |
| BR112021008558A2 (en) | apparatus, disparity estimation method, and computer program product | |
| CN109428987A (en) | A kind of 360 degree of stereo photographic devices of wear-type panorama and image pickup processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |