CN108074216A - Video-splicing method based on manual planning splicing seams algorithm - Google Patents
Video-splicing method based on manual planning splicing seams algorithm Download PDFInfo
- Publication number
- CN108074216A CN108074216A CN201611001987.4A CN201611001987A CN108074216A CN 108074216 A CN108074216 A CN 108074216A CN 201611001987 A CN201611001987 A CN 201611001987A CN 108074216 A CN108074216 A CN 108074216A
- Authority
- CN
- China
- Prior art keywords
- splicing
- image
- video
- splicing seams
- overlapping region
- 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
- 238000000034 method Methods 0.000 title claims abstract description 7
- 230000001235 sensitizing effect Effects 0.000 claims abstract description 17
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000007796 conventional method Methods 0.000 claims description 3
- 239000000155 melt Substances 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation 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
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of video-splicing method based on manual planning splicing seams algorithm, after video-splicing image registration early period, obtains overlapping region;Before a splice, the trend of splicing seams is marked in advance in the overlapping region of extraction;4 points are chosen successively according to the trend of splicing seams on overlapping region, according to 4 dot sequencies of selection, connect one curved broken line of composition successively so that this curved broken line can avoid sensitizing range;The above-mentioned splicing seams chosen manually are introduced into de-militarized zone, then carry out image co-registration, so as to which the bad splicing effect that the image co-registration based on optimal stitching line is brought is introduced into de-militarized zone, so that final video-splicing has good visual effect.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of individual by several with certain overlapping region
Picture synthesizes the picture of a large scene, so as to expand the method in the scene visual field and content of single picture.
Background technology
As the rapid development and people of science and technology are to shooting the demand in the broader visual field, image mosaic technology is increasingly heavier
It will.Image mosaic is exactly several single pictures with certain overlapping region to be synthesized the picture of a large scene, so as to
Expand the scene visual field and the content of single picture.For application of the image mosaic in video monitoring, can have multiple
The scene of the monitoring camera shooting of certain overlapping region is spliced in real time, is finally spliced into the reality of entire monitoring area
When monitoring image, so as to expand monitoring visual zone.General video-splicing is broadly divided into three key steps:Characteristics of image carries
It takes, images match, image co-registration, as shown in Figure 1.
Image characteristics extraction is mainly to extract becoming to Affine distortion, 3D view transformations, noise, illumination in image to be spliced
Change has the angle point of certain robustness as feature;Images match is that the corner feature based on extraction goes to calculate in video camera
Outer parameter, so as to obtain the overlapping region of stitching image;Image co-registration is the overlay region to stitching image according to registering result
Domain carries out last fusion.
Overlapping region between stitching image is divided into sensitizing range and de-militarized zone.In monitor video, for
Sensitizing range and de-militarized zone can be defined as follows:
The region that user is concerned about is arranged to sensitizing range, the region that user is less concerned about is arranged to de-militarized zone;
The more region of moving target is arranged to sensitizing range, the less region of moving target is arranged to non-sensitive
Region.
The image fusion technology of mainstream is the image co-registration of the optimal stitching line based on max-flow min-cut algorithm at present,
The thought of core minimizes (i.e. minimal cut problem) by energy function, and in overlapping region, News Search goes out a cut-off rule, i.e.,
So-called splicing seams.But the trend of the splicing seams of its News Search out is uncontrollable, by largely testing, is found
The splicing seams of max-flow method minimal cut planning inevitably all can be by sensitizing range.
Although improving the accuracy of registration parameter by many measures during video-splicing, error is difficult in institute
Exempt from, it is difficult to obtain complete free from error registration parameter.Consequence caused by so is exactly can exist centainly at splicing seams below
Image misalignment, ghost and the aliasing and crenellated phenomena of degree leave segmentation trace in stitching portion, and max-flow is minimum
Cutting the splicing seams of planning, be inevitable all can be by sensitizing range, so that the visual effect that sensitizing range is finally spliced
It is very undesirable.
The content of the invention
It is an object of the invention to provide a kind of planning splicing seams algorithms manually, eliminate since max-flow min-cut dynamic is searched
Rope come out splicing seams trend be it is uncontrollable and cause splicing seams by sensitizing range cause sensitizing range splicing vision effect
The phenomenon that fruit is bad so that last stitching image reaches good visual effect.
Technical scheme is as follows:
A kind of video-splicing method based on manual planning splicing seams algorithm, which is characterized in that comprise the following steps:
(1) after video-splicing image registration early period, overlapping region is obtained;
(2) planning stitching direction manually is determined:Before a splice, walking for splicing seams is marked in advance in the overlapping region of extraction
To;
(3) splicing seams are chosen manually:4 points are chosen successively according to the trend of splicing seams on overlapping region, according to selection
4 dot sequencies, connect one curved broken line of composition successively so that this curved broken line can avoid sensitizing range
Domain;
(4) image co-registration:The above-mentioned splicing seams chosen manually are introduced into de-militarized zone, then carry out figure according to a conventional method
As fusion, so that the bad splicing effect that the image co-registration based on optimal stitching line is brought is introduced into de-militarized zone, so as to
So that final video-splicing has good visual effect.
The present invention can get around image by the manual planning splicing seams of realization, the path of artificial cabling planning splicing seams
In sensitizing range so that last splicing seams are by de-militarized zone, by early period, registration error was brought to splicing effect
Influence be introduced into de-militarized zone, thereby realizing sensitizing range has preferable splicing visual effect.
Description of the drawings
Fig. 1 is general video-splicing flow chart;
Fig. 2 is the video-splicing flow chart of the present invention.
Specific embodiment
As shown in Fig. 2, the present invention after video-splicing image registration early period, obtains overlapping region.Based on overlapping region
The flow of planning splicing seams is as follows manually:
1st, planning stitching direction manually is determined:
In video monitoring system, since the monitoring camera level angle of erection is different, cause in video-splicing
When occur it is misaligned in the horizontal direction of image to be spliced.Assuming that there is left and right two images, there are following two misaligned
Situation:
(1) one, left side image to be spliced is lower than the one image level angle of inclination to be spliced in the right;
(2) one, left side image to be spliced is higher than the one image level angle of inclination to be spliced in the right.
Otherwise the trend of the splicing seams of two kinds of situations above equally can cannot influence splicing effect.If the
A kind of trend of situation splicing seams should be tilted down from left to right, if the second situation is then to turn left to dip down from the right side
Tiltedly.The present invention before a splice, the trend of splicing seams is marked in the overlapping region of extraction in advance.
2nd, splicing seams are chosen manually:
Obtaining walking backward for splicing seams, be known that splicing seams be turn left from the right side tilt down or from left to right to
Then lower inclination chooses 4 points successively on overlapping region according to the trend of splicing seams, according to 4 dot sequencies of selection, successively will
It, which is connected, forms a curved broken line so that this curved broken line can avoid sensitizing range.This curved folding
Line is exactly to cook up the splicing seams come manually, and this curved broken line (splicing seams) is shown in overlapping region, to illustrate to spell
Whether the trend of seam is correct.
3rd, image co-registration:
According to the splicing seams obtained manually so that splicing seams can avoid sensitizing range.Above-mentioned splicing seams are introduced into non-
Sensitizing range, then image co-registration is carried out according to a conventional method, so as to the bad spelling that the image co-registration based on optimal stitching line is brought
It connects effect and is introduced into de-militarized zone, so that final video-splicing has good visual effect.
Claims (1)
- A kind of 1. video-splicing method based on manual planning splicing seams algorithm, which is characterized in that comprise the following steps:(1) after video-splicing image registration early period, overlapping region is obtained;(2) planning stitching direction manually is determined:Before a splice, the trend of splicing seams is marked in advance in the overlapping region of extraction;(3) splicing seams are chosen manually:4 points are chosen successively according to the trend of splicing seams on overlapping region, according to the 4 of selection points Sequentially, one curved broken line of composition is connected successively so that this curved broken line can avoid sensitizing range;(4) image co-registration:The above-mentioned splicing seams chosen manually are introduced into de-militarized zone, then carries out image according to a conventional method and melts It closes, so as to which the bad splicing effect that the image co-registration based on optimal stitching line is brought is introduced into de-militarized zone, so that Final video-splicing has good visual effect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611001987.4A CN108074216A (en) | 2016-11-14 | 2016-11-14 | Video-splicing method based on manual planning splicing seams algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611001987.4A CN108074216A (en) | 2016-11-14 | 2016-11-14 | Video-splicing method based on manual planning splicing seams algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108074216A true CN108074216A (en) | 2018-05-25 |
Family
ID=62161933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611001987.4A Pending CN108074216A (en) | 2016-11-14 | 2016-11-14 | Video-splicing method based on manual planning splicing seams algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108074216A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112184541A (en) * | 2019-07-05 | 2021-01-05 | 杭州海康威视数字技术股份有限公司 | Image splicing method, device and equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101945223A (en) * | 2010-09-06 | 2011-01-12 | 浙江大学 | Video consistent fusion processing method |
CN103501415A (en) * | 2013-10-01 | 2014-01-08 | 中国人民解放军国防科学技术大学 | Overlap structural deformation-based video real-time stitching method |
CN104299215A (en) * | 2014-10-11 | 2015-01-21 | 中国兵器工业第二O二研究所 | Feature point calibrating and matching image splicing method |
CN104794701A (en) * | 2014-01-21 | 2015-07-22 | 富士通株式会社 | Image splicing device, method and image processing equipment |
-
2016
- 2016-11-14 CN CN201611001987.4A patent/CN108074216A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101945223A (en) * | 2010-09-06 | 2011-01-12 | 浙江大学 | Video consistent fusion processing method |
CN103501415A (en) * | 2013-10-01 | 2014-01-08 | 中国人民解放军国防科学技术大学 | Overlap structural deformation-based video real-time stitching method |
CN104794701A (en) * | 2014-01-21 | 2015-07-22 | 富士通株式会社 | Image splicing device, method and image processing equipment |
CN104299215A (en) * | 2014-10-11 | 2015-01-21 | 中国兵器工业第二O二研究所 | Feature point calibrating and matching image splicing method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112184541A (en) * | 2019-07-05 | 2021-01-05 | 杭州海康威视数字技术股份有限公司 | Image splicing method, device and equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102027897B1 (en) | Switch between binocular and monocular vision | |
US10205889B2 (en) | Method of replacing objects in a video stream and computer program | |
KR101475895B1 (en) | Image processing system recognizing point and auto-correcting for image update | |
KR101483955B1 (en) | System for processing reflection image by adjusting a 3d position in the reflection image | |
CN106462944A (en) | Mapping multiple high-resolution images onto a low-resolution 360-degree image to produce a high-resolution panorama without ghosting | |
WO2013008653A1 (en) | Object display device, object display method, and object display program | |
CN105931188A (en) | Method for image stitching based on mean value duplication removal | |
CN105023260A (en) | Panorama image fusion method and fusion apparatus | |
KR101983586B1 (en) | Method of stitching depth maps for stereo images | |
CN109194888B (en) | DIBR free viewpoint synthesis method for low-quality depth map | |
CN108074216A (en) | Video-splicing method based on manual planning splicing seams algorithm | |
JP2005123823A (en) | Distance information attaching apparatus, attached video image generating apparatus, attached video information generating method, and distance information attaching program | |
JP2013206431A (en) | Image processing device, image processing method and image processing program | |
CN106023074A (en) | Splicing method for video images from different areas | |
KR101781158B1 (en) | Apparatus for image matting using multi camera, and method for generating alpha map | |
JP6392739B2 (en) | Image processing apparatus, image processing method, and image processing program | |
WO2021197016A1 (en) | System and method for enhancing subjects in videos | |
KR101718309B1 (en) | The method of auto stitching and panoramic image genertation using color histogram | |
CN113763545A (en) | Image determination method, image determination device, electronic equipment and computer-readable storage medium | |
TWI516120B (en) | Method for generating panoramic image and image capturing device thereof | |
JP2010272093A (en) | Image connecting method, device and program | |
KR101893142B1 (en) | Object extraction method and apparatus | |
JP2010033246A (en) | Device, method, and program for combining image | |
JP6450306B2 (en) | Image processing apparatus, image processing method, and image processing program | |
Scollar et al. | Georeferenced orthophotos and DTMs from multiple oblique images |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180525 |
|
WD01 | Invention patent application deemed withdrawn after publication |