CN110544206A - Image splicing system and image splicing method - Google Patents
Image splicing system and image splicing method Download PDFInfo
- Publication number
- CN110544206A CN110544206A CN201910806265.3A CN201910806265A CN110544206A CN 110544206 A CN110544206 A CN 110544206A CN 201910806265 A CN201910806265 A CN 201910806265A CN 110544206 A CN110544206 A CN 110544206A
- Authority
- CN
- China
- Prior art keywords
- splicing
- camera
- image
- cameras
- industrial
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
Abstract
The invention relates to an image splicing system and an image splicing method, which comprise a front-end acquisition system and a back-end processing system, wherein the front-end processing system comprises 5 industrial cameras which are positioned on the same horizontal plane and distributed in a sector shape, and the industrial cameras are all connected with a gigabit network switch; the back-end processing system is composed of a computer provided with splicing system software, and the splicing system software comprises a camera layer, a splicing layer and a user layer. According to the method, reasonable placing positions and image overlapping ranges of all industrial cameras are obtained through calculation in an image splicing method in a front-end acquisition system, optical centers can be guaranteed to be consistent, the problem of shooting of shot objects with near field depth is solved, the two cameras can be spliced smoothly, image distortion at edges is small, then a gigabit switch is connected with a rear-end processing system, the image overlapping ranges obtained through calculation are input, multi-thread parallel splicing operation is carried out, and high-resolution images are output.
Description
(I) technical field
The invention relates to the field of image processing, in particular to an image splicing system and an image splicing method.
(II) background of the invention
the image splicing technology is mainly used for generating large-format high-definition images, and the collected images are spliced by using a plurality of cameras or a single camera at different angle positions, so that the visual range and the resolution of the images are improved. The ultra-wide viewing angle image has an irreplaceable effect in real life. Although an image with a wide angle of view can be obtained with a wide-angle lens, distortion is generated at the edge of the wide-angle lens, which is difficult to avoid. The image stitching technology is provided for solving the problem that a common camera is limited by a shooting visual angle and cannot shoot a wide visual angle picture at one time.
With the development of computers and image processing technologies, the image stitching technology provides a good solution for obtaining ultra-wide viewing angle images and even panoramic images. The current image splicing main technical scheme is divided into two types: single-camera rotation stitching and multi-view stitching. The single camera rotary splicing has the defect of serious distortion, and the core principle of the single camera rotary splicing is that images acquired by a plurality of common lenses are spliced into an image acquired by a super wide-angle lens, so that the defect of the super wide-angle lens is inherited, the closer to the edge position of the spliced image, the larger the perspective transformation of an angle exists, and the larger the error of the depth of field is, so that the distortion of an object with changed depth of field in shooting cannot be corrected in a later stage to obtain a correct shape; due to the existence of parallax, multi-view stitching cannot correctly register images. Therefore, the shot object is required to be a plane or the distance from the shot object to the shot object is far higher than the change of the depth of field of the shot object, so that the scheme cannot successfully splice the images shot by the object with the depth of field at a short distance into the ultra-wide viewing angle image.
Disclosure of the invention
aiming at the problems in the prior art, the invention provides an image splicing system and an image splicing method.
the invention is realized by the following technical scheme:
an image splicing system comprises a front-end acquisition system and a rear-end processing system, wherein the front-end processing system comprises a plurality of industrial cameras which are positioned on the same horizontal plane and distributed in a fan shape, and the plurality of industrial cameras are all connected with a gigabit network switch; the back-end processing system is composed of a computer provided with splicing system software, and the splicing system software comprises a camera layer, a splicing layer and a user layer.
Preferably, the industrial cameras are provided with high-definition fixed-focus lenses, and the number of the industrial cameras is 5.
An image stitching method comprises the following steps:
s1, determining the position of the industrial camera and the imaging overlapping range through calculation;
S2, the computer controls the front camera to collect the image through the GigE protocol;
S3, splicing the overlapped parts of the two images, firstly searching the best splicing seam, and then fusing the images at the two sides of the splicing seam according to the weight;
and S4, outputting the spliced image at the user layer.
preferably, the determining the position of the industrial camera in S1 includes the following steps:
firstly, determining the length 2X and the object distance Z of a shot object;
Next, the imaging angle 2 θ of the entire system is calculated:
；
And finally, calculating the placing angle of each industrial camera:
The deflection angles of the cameras on the two sides of the middle camera are the deflection angles of the outermost cameras.
Preferably, the calculation formula for determining the imaging overlapping range of the industrial camera in S1 is as follows:
the camera is arranged in the center of the camera, and is arranged in the outermost side of the camera.
the invention has the beneficial effects that:
According to the image splicing system and the image splicing method provided by the invention, through the front-end acquisition system, the arrangement positions and the overlapping ranges of all industrial cameras are calculated by using the method provided by the invention, the optical centers are ensured to be consistent, the shooting problem of a shot object with near distance and depth of field is solved, the parallax between the cameras is small, and the image distortion at the edge is small; and then connecting a back-end processing system through a gigabit switch, splicing the overlapped parts of the two calculated images, searching for the optimal splicing seam, fusing the images on the two sides of the splicing seam according to the weight, and outputting a high-resolution image.
(IV) description of the drawings
the invention will be further described with reference to the accompanying drawings.
FIG. 1 is a schematic diagram of the system of the present invention.
Fig. 2 is a schematic view of an arrangement of industrial cameras according to the present invention.
Fig. 3 is a schematic diagram of the splicing software structure in the present invention.
fig. 4 is a first schematic diagram illustrating the calculation of the placement angle and the overlapping range of the industrial camera according to the present invention.
Fig. 5 is a second schematic diagram illustrating the calculation of the placement angle and the overlapping range of the industrial camera according to the present invention.
fig. 6 is a third schematic diagram illustrating calculation of the placement angle and the overlapping range of the industrial camera according to the present invention.
(V) detailed description of the preferred embodiments
in order to make the technical solution of the present invention better understood, the technical solution of the present invention will be further described with reference to the accompanying drawings.
Referring to fig. 1 to 6, the present invention includes a front-end acquisition system and a back-end processing system, where the front-end processing system includes 5 industrial cameras located on the same horizontal plane and distributed in a sector shape, each of the 5 industrial cameras is equipped with a high-definition fixed-focus lens, and the industrial cameras are connected to a gigabit network switch; the back-end processing system is composed of a computer provided with splicing system software, and the splicing system software comprises a camera layer, a splicing layer and a user layer.
an image stitching method comprises the following steps:
S1, determining the positions of the cameras and the imaging overlapping range through calculation;
S2, the computer controls the front camera to collect the image through the GigE protocol;
s3, splicing the overlapped parts of the two images, firstly searching the best splicing seam, and then fusing the images at the two sides of the splicing seam according to the weight;
And S4, outputting the spliced image at the user layer.
In S1, the step of calculating the precise placement positions of the cameras based on the distances between the objects to be photographed by using the optical center matching includes the steps of:
Firstly, determining the length and the object distance of a shot object:
Referring to fig. 4, 2X is the length of the object, Z is the object distance, and the size after image sensing stitching is 2X', and the equivalent focal length is f.
in this embodiment, the object distance is Z =2m, and the object length is 2X =3.6 m;
secondly, the imaging angle 2 θ of the whole system is calculated, and can be obtained from the relationship in fig. 4:
；
finally, the placing angles of the cameras in the 5 cameras are as follows:
referring to fig. 5, the deflection angles of the cameras on the two sides of the middle camera, that is, the deflection angle of the outermost camera, that is, the relative deflection angle between the cameras, are 17 degrees, and fig. 2 is a schematic view of the placement positions of the cameras.
After the placing angle of the cameras is calculated by using the optical center consistency principle, the size of the area where the imaging ranges of the cameras coincide with each other needs to be calculated, and parameters are provided for subsequent splicing.
referring to fig. 6, an imaging range of one side of the system is shown, wherein a thick solid line is an imaging representation of a center camera, the imaging range is from o to x2 on the x-axis, cameras adjacent to the center position camera are illustrated with a dotted line, the imaging range is from x1 to x4 on the x-axis, the outermost cameras are illustrated with a double-dashed line, and the imaging range is from x3 to x5 on the x-axis.
Assuming that the imaging angle of a single camera is =20 ° and Z =2m in this embodiment, then:
The overlap range of the center camera with the adjacent cameras is:
The overlapping range of the outermost camera and the adjacent camera is as follows:
in S2, that is, the camera layer of the stitching system software, the computer controls the front-end camera to capture images through the GigE protocol, because the optical centers of the cameras are consistent, the parallax between the cameras is small, and the overlapped part between the two cameras can be smoothly stitched.
in S3, that is, the stitching layer of the stitching system software, due to the difference in viewpoint between the cameras, it is necessary to stitch the images together by using the characteristic of high-performance CPU multi-core multi-thread operation, stitching the overlapped parts of the two images (x 2-x1 and x4-x 3), finding the best seam, and fusing the images on both sides of the seam according to the weight.
at S4, that is, the user layer of the stitching system software, is used to display the results of the output stitching and to perform necessary parameter settings such as the portions (x 2-x1 and x4-x 3) where the two images coincide, calculated as described above, and the like.
In the description of the present invention, the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "vertical", "horizontal", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for the purpose of describing the present invention but do not require that the present invention must be constructed or operated in a specific orientation, and thus, should not be construed as limiting the present invention. The terms "connected" and "connected" in the present invention should be interpreted broadly, and may be connected or disconnected, for example; the terms may be directly connected or indirectly connected through intermediate components, and specific meanings of the terms may be understood as specific conditions by those skilled in the art.
The above description is of the preferred embodiment of the present invention, and the description of the specific embodiment is only for better understanding of the idea of the present invention. It will be appreciated by those skilled in the art that various modifications and equivalents may be made in accordance with the principles of the invention and are considered to be within the scope of the invention.
Claims (5)
1. an image stitching system, characterized by: the system comprises a front-end acquisition system and a back-end processing system, wherein the front-end processing system comprises a plurality of industrial cameras which are positioned on the same horizontal plane and distributed in a fan shape, and the industrial cameras are communicated with the back-end processing system through a gigabit network switch; the back-end processing system is composed of a computer provided with splicing system software, and the splicing system software comprises a camera layer, a splicing layer and a user layer.
2. an image stitching system and an image stitching method according to claim 1, characterized in that: the industrial cameras are provided with high-definition fixed-focus lenses, and the number of the industrial cameras is 5.
3. An image stitching method is characterized by comprising the following steps:
S1, determining the position of the industrial camera and the imaging overlapping range through calculation;
s2, the computer controls the front camera to collect the image through the GigE protocol;
s3, splicing the overlapping range of the two images, firstly searching the best splicing seam, and then fusing the images at the two sides of the splicing seam according to the weight;
And S4, outputting the spliced image at the user layer.
4. An image stitching method according to claim 3, characterized in that: determining the industrial camera position in S1 includes the steps of:
firstly, determining the length 2X and the object distance Z of a shot object;
Next, the imaging angle 2 θ of the entire system is calculated:
；
And finally, calculating the placing angle of each industrial camera:
，
The deflection angles of the cameras on the two sides of the middle camera are the deflection angles of the outermost cameras.
5. an image stitching method according to claim 3 or 4, characterized in that: determining the calculation formula of the imaging overlapping range of the industrial camera in S1 as follows:
，
The camera is arranged in the center of the camera, and is arranged in the outermost side of the camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910806265.3A CN110544206A (en) | 2019-08-29 | 2019-08-29 | Image splicing system and image splicing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910806265.3A CN110544206A (en) | 2019-08-29 | 2019-08-29 | Image splicing system and image splicing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110544206A true CN110544206A (en) | 2019-12-06 |
Family
ID=68710754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910806265.3A Pending CN110544206A (en) | 2019-08-29 | 2019-08-29 | Image splicing system and image splicing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110544206A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112637551A (en) * | 2020-11-18 | 2021-04-09 | 合肥市卓迩无人机科技服务有限责任公司 | Panoramic data management software system for multi-path 4K quasi-real-time spliced videos |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102143305A (en) * | 2010-02-02 | 2011-08-03 | 华为终端有限公司 | Image pickup method and system |
| US20150154776A1 (en) * | 2013-12-03 | 2015-06-04 | Huawei Technologies Co., Ltd. | Image splicing method and apparatus |
| CN106886979A (en) * | 2017-03-30 | 2017-06-23 | 深圳市未来媒体技术研究院 | A kind of image splicing device and image split-joint method |
| CN107133925A (en) * | 2017-04-12 | 2017-09-05 | 新疆林业科学院现代林业研究所 | A kind of spectrum image bearing calibration for automatically extracting control point |
-
2019
- 2019-08-29 CN CN201910806265.3A patent/CN110544206A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102143305A (en) * | 2010-02-02 | 2011-08-03 | 华为终端有限公司 | Image pickup method and system |
| US20150154776A1 (en) * | 2013-12-03 | 2015-06-04 | Huawei Technologies Co., Ltd. | Image splicing method and apparatus |
| CN106886979A (en) * | 2017-03-30 | 2017-06-23 | 深圳市未来媒体技术研究院 | A kind of image splicing device and image split-joint method |
| CN107133925A (en) * | 2017-04-12 | 2017-09-05 | 新疆林业科学院现代林业研究所 | A kind of spectrum image bearing calibration for automatically extracting control point |
Non-Patent Citations (1)
| Title |
|---|
| 王一博等: "《基于微相机阵列成像系统的图像拼接研究》", 《红外技术》, vol. 41, no. 4 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112637551A (en) * | 2020-11-18 | 2021-04-09 | 合肥市卓迩无人机科技服务有限责任公司 | Panoramic data management software system for multi-path 4K quasi-real-time spliced videos |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018076154A1 (en) | Spatial positioning calibration of fisheye camera-based panoramic video generating method | |
| CN108600576B (en) | Image processing apparatus, method and system, and computer-readable recording medium | |
| CN106683071B (en) | Image splicing method and device | |
| KR20200030603A (en) | Seamless image stitching | |
| CN106060493A (en) | Multi-source projection seamless edge stitching method and system | |
| CN102722080B (en) | A kind of multi purpose spatial image capture method based on many lens shootings | |
| WO2020228680A1 (en) | Dual camera image-based splicing method and apparatus, and electronic device | |
| CN102222337A (en) | Fisheye image correcting method for image stitching | |
| TWI704404B (en) | Camera module and electronic device | |
| WO2018153254A1 (en) | Multi-view camera device and monitoring system | |
| CN105379264A (en) | System and method for imaging device modelling and calibration | |
| CN101673395A (en) | Image mosaic method and image mosaic device | |
| WO2010118674A1 (en) | Image acquisition equipment | |
| CN106952219B (en) | Image generation method for correcting fisheye camera based on external parameters | |
| CN103501409A (en) | Ultrahigh resolution panorama speed dome AIO (All-In-One) system | |
| JP2006279538A (en) | Imaging apparatus | |
| CN106886976B (en) | Image generation method for correcting fisheye camera based on internal parameters | |
| WO2011095026A1 (en) | Method and system for photography | |
| JP4679293B2 (en) | In-vehicle panoramic camera system | |
| CN111445537A (en) | Calibration method and system of camera | |
| ES2884323T3 (en) | System and method for capturing horizontal disparity stereo panoramic | |
| CN108141519A (en) | Camara module | |
| Chen et al. | Calibration for high-definition camera rigs with marker chessboard | |
| CN105139336A (en) | Method for converting multichannel panorama images into dome-screen fish-eye movie | |
| WO2017203796A1 (en) | Information processing device, information processing method, and program |
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 |