CN106846242A - The less efficient image method for registering in overlapping region is directed in a kind of video-splicing - Google Patents
The less efficient image method for registering in overlapping region is directed in a kind of video-splicing Download PDFInfo
- Publication number
- CN106846242A CN106846242A CN201510888018.4A CN201510888018A CN106846242A CN 106846242 A CN106846242 A CN 106846242A CN 201510888018 A CN201510888018 A CN 201510888018A CN 106846242 A CN106846242 A CN 106846242A
- Authority
- CN
- China
- Prior art keywords
- image
- registration
- matching
- characteristic point
- 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 23
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000012544 monitoring process Methods 0.000 description 2
Classifications
-
- G06T3/14—
-
- 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 less efficient image method for registering in overlapping region is directed in a kind of video-splicing, the two field picture for choosing camera to be spliced is initially registered process.Feature point extraction is carried out to image respectively, Feature Points Matching process is shown initial feature point pair matching result;On initial matching display window, the event pressed to left mouse button and lifted is responded, decision block choosing rectangle frame the upper left corner and the coordinate position in the lower right corner, manually select correct matching characteristic point to be distributed comparatively dense region;Using the characteristic point in selected region to as the characteristic point pair after screening, as the input of secondary registration, completing process of image registration;Inside and outside parameter according to camera carries out image co-registration, obtains final image mosaic result.
Description
Technical field
The invention belongs to digital audio-video technical field, and in particular to be directed to the less efficient image method for registering in overlapping region in a kind of video-splicing.
Background technology
The precision of image registration is the key factor for determining video-splicing effect.In video-splicing, general handling process shows for image registration, image co-registration and image.In process of image registration, first to each image zooming-out characteristic point, then the characteristic point to overlapping region is matched, and is finally the parameter that image registration is determined according to the position relationship of the characteristic point pair of matching.But above-mentioned method for registering images registration effect when image includes timestamp to overlapping region in smaller or overlapping region is poor, so as to cause the effect of final video-splicing unsatisfactory.
The content of the invention
The present invention carries out manual intervention to overlapping region by process of image registration, increases the ratio of correct matching double points, improves the precision of image registration.
Technical scheme is as follows:
The less efficient image method for registering in overlapping region is directed in a kind of video-splicing, it is characterised in that:
(1) two field picture for choosing camera to be spliced is initially registered process.Feature point extraction is carried out to image respectively, Feature Points Matching process is shown initial feature point pair matching result;
(2) on initial matching display window, the event pressed to left mouse button and lifted is responded, decision block choosing rectangle frame the upper left corner and the coordinate position in the lower right corner, manually select correct matching characteristic point to be distributed comparatively dense region;
(3) using the characteristic point in selected region to as the characteristic point pair after screening, as the input of secondary registration, completing process of image registration;
(4) inside and outside parameter according to camera carries out image co-registration, obtains final image mosaic result.
The present invention is for overlapping region area is small, characteristic point carries out manual intervention to the initial registration result of few image and chooses the mode that correct registration region realizes secondary registration, the accuracy of registration parameter estimation can be significantly improved, ideal splicing result is finally obtained.
Specific embodiment
Below by taking two video-splicings of monitoring camera as an example, the principle and necessity of simple declaration manual intervention registration.The a certain frame of the video that two monitoring cameras are photographed, registration parameter is calculated with the registration of the image pair.But in the image pair, overlapping region has that area is small, characteristic point to it is few the features such as, simultaneously because two positions of camera, the features such as timestamp is basically identical, camera head monitor region has great similarity, causing to have a certain amount of error hiding pair and pseudo- matching being right.Choose correct matching secondary registration carried out to the region relatively concentrated by artificial in preliminary matches result, can effectively improve correct matching to ratio, so as to realize to the accuracy registration with the image that overlapping region area is small, characteristic point is to the feature such as few.
Implement process as follows:
(1) two field picture for choosing camera to be spliced is initially registered process.Feature point extraction is carried out to image respectively, Feature Points Matching process is shown initial feature point pair matching result;
(2) on initial matching display window, the event pressed to left mouse button and lifted is responded, decision block choosing rectangle frame the upper left corner and the coordinate position in the lower right corner, manually select correct matching characteristic point to be distributed comparatively dense region;
(3) using the characteristic point in selected region to as the characteristic point pair after screening, as the input of secondary registration, completing process of image registration;
(4) inside and outside parameter according to camera carries out image co-registration, obtains final image mosaic result.
Claims (1)
1. the less efficient image method for registering in overlapping region is directed in a kind of video-splicing, it is characterised in that:
(1) two field picture for choosing camera to be spliced is initially registered process.Feature point extraction is carried out to image respectively,
Feature Points Matching process, initial feature point pair matching result is shown;
(2) on initial matching display window, the event pressed to left mouse button and lifted is responded, the square of decision block choosing
The upper left corner of shape frame and the coordinate position in the lower right corner, manually select correct matching characteristic point to being distributed the region of comparatively dense;
(3) using the characteristic point in selected region to as the characteristic point pair after screening, as the input of secondary registration, completing
Process of image registration;
(4) inside and outside parameter according to camera carries out image co-registration, obtains final image mosaic result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510888018.4A CN106846242A (en) | 2015-12-07 | 2015-12-07 | The less efficient image method for registering in overlapping region is directed in a kind of video-splicing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510888018.4A CN106846242A (en) | 2015-12-07 | 2015-12-07 | The less efficient image method for registering in overlapping region is directed in a kind of video-splicing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106846242A true CN106846242A (en) | 2017-06-13 |
Family
ID=59151307
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510888018.4A Pending CN106846242A (en) | 2015-12-07 | 2015-12-07 | The less efficient image method for registering in overlapping region is directed in a kind of video-splicing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106846242A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154476A (en) * | 2017-12-22 | 2018-06-12 | 成都华栖云科技有限公司 | The method of video-splicing correction |
CN109191502A (en) * | 2018-08-14 | 2019-01-11 | 南京工业大学 | A kind of method of automatic identification shell case trace |
CN111932593A (en) * | 2020-07-21 | 2020-11-13 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120274739A1 (en) * | 2009-12-21 | 2012-11-01 | Huawei Device Co.,Ud. | Image splicing method and apparatus |
CN103514625A (en) * | 2012-06-20 | 2014-01-15 | 上海路同信息科技有限公司 | Three-dimensional reconstruction method based on multi-view self-adaptation characteristic registration |
CN103997609A (en) * | 2014-06-12 | 2014-08-20 | 四川川大智胜软件股份有限公司 | Multi-video real-time panoramic fusion splicing method based on CUDA |
CN104376332A (en) * | 2014-12-09 | 2015-02-25 | 深圳市捷顺科技实业股份有限公司 | License plate recognition method and device |
-
2015
- 2015-12-07 CN CN201510888018.4A patent/CN106846242A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120274739A1 (en) * | 2009-12-21 | 2012-11-01 | Huawei Device Co.,Ud. | Image splicing method and apparatus |
CN103514625A (en) * | 2012-06-20 | 2014-01-15 | 上海路同信息科技有限公司 | Three-dimensional reconstruction method based on multi-view self-adaptation characteristic registration |
CN103997609A (en) * | 2014-06-12 | 2014-08-20 | 四川川大智胜软件股份有限公司 | Multi-video real-time panoramic fusion splicing method based on CUDA |
CN104376332A (en) * | 2014-12-09 | 2015-02-25 | 深圳市捷顺科技实业股份有限公司 | License plate recognition method and device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154476A (en) * | 2017-12-22 | 2018-06-12 | 成都华栖云科技有限公司 | The method of video-splicing correction |
CN109191502A (en) * | 2018-08-14 | 2019-01-11 | 南京工业大学 | A kind of method of automatic identification shell case trace |
CN109191502B (en) * | 2018-08-14 | 2021-08-24 | 南京工业大学 | Method for automatically identifying cartridge case trace |
CN111932593A (en) * | 2020-07-21 | 2020-11-13 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
CN111932593B (en) * | 2020-07-21 | 2024-04-09 | 湖南中联重科智能技术有限公司 | Image registration method, system and equipment based on touch screen gesture correction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20180218485A1 (en) | Method and apparatus for fusing plurality of depth images | |
WO2016086754A1 (en) | Large-scale scene video image stitching method | |
US8717405B2 (en) | Method and device for generating 3D panoramic video streams, and videoconference method and device | |
US9241147B2 (en) | External depth map transformation method for conversion of two-dimensional images to stereoscopic images | |
CN106600644B (en) | Parameter correction method and device for panoramic camera | |
CN103986874A (en) | Image acquiring device, method and terminal | |
CN106780330B (en) | A kind of super resolution ratio reconstruction method based on colour with black and white dual camera | |
WO2015082572A3 (en) | User feedback for real-time checking and improving quality of scanned image | |
US11282232B2 (en) | Camera calibration using depth data | |
WO2015165222A1 (en) | Method and device for acquiring panoramic image | |
WO2015015383A3 (en) | Thin multi-aperture imaging system with auto-focus and methods for using same | |
TWI612495B (en) | Process and device for capturing and rendering a panoramic or stereoscopic stream of images | |
WO2015028587A3 (en) | User feedback for real-time checking and improving quality of scanned image | |
WO2010129363A3 (en) | Markerless geometric registration of multiple projectors on extruded surfaces using an uncalibrated camera | |
WO2016155110A1 (en) | Method and system for correcting image perspective distortion | |
CN106846242A (en) | The less efficient image method for registering in overlapping region is directed in a kind of video-splicing | |
CN111223108A (en) | Method and system based on backdrop matting and fusion | |
CN107220955A (en) | A kind of brightness of image equalization methods based on overlapping region characteristic point pair | |
CN108090877A (en) | A kind of RGB-D camera depth image repair methods based on image sequence | |
CN106023170B (en) | A kind of binocular 3D distortion correction methods based on GPU processors | |
TW201409365A (en) | Gesture recognition system and method | |
CN103888674B (en) | Image capture unit and image acquisition method | |
JP2012165147A5 (en) | Image processing apparatus, control method therefor, and imaging apparatus | |
CN106447655B (en) | Method for detecting heterochromatic and slight dent on surface of smooth object | |
CN106131498B (en) | Panoramic video joining method and device |
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: 20170613 |
|
WD01 | Invention patent application deemed withdrawn after publication |