CN108961155B - High-fidelity fisheye lens distortion correction method - Google Patents
High-fidelity fisheye lens distortion correction method Download PDFInfo
- Publication number
- CN108961155B CN108961155B CN201810769358.9A CN201810769358A CN108961155B CN 108961155 B CN108961155 B CN 108961155B CN 201810769358 A CN201810769358 A CN 201810769358A CN 108961155 B CN108961155 B CN 108961155B
- Authority
- CN
- China
- Prior art keywords
- image
- feature points
- fidelity
- fisheye lens
- correction method
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012937 correction Methods 0.000 title claims abstract description 15
- 238000003702 image correction Methods 0.000 claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G06T3/047—
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Abstract
The invention relates to the field of image processing, and discloses a high-fidelity fisheye lens distortion correction method, which comprises the following steps: collecting images by using a fish-eye lens; detecting feature points in the image, counting position information of the feature points, and dividing the image into different view angle areas according to the positions of the feature points; establishing a segmentation curve model of each field angle region, and acquiring image correction parameters of each field angle region; and carrying each image correction parameter into the corresponding piecewise curve model to correct the image. By adopting the technical scheme, the real information of the object can be highly maintained, the gestures of the object in different view angles can be restored, the correction method has strong adaptability, the algorithm complexity is low, and the method is easy to realize.
Description
Technical Field
The invention relates to the field of image processing, in particular to a high-fidelity fisheye lens distortion correction method.
Background
The vehicle-mounted fisheye lens has the remarkable advantages that the visual angle blind area is small, the visual angle range can contain the content of a plurality of lenses, the image contains large and abundant information, and the vehicle-mounted fisheye lens is widely applied to vehicle-mounted intelligent traffic and other systems. However, the ultra-wide field angle of the fish-eye lens also brings about obvious defects, and the photographed image has serious distortion, so that a real object is distorted. If special effects of ultra-wide angles are not required, but rather information of the image's ultra-wide angle of view is to be utilized, these distorted images need to be unfolded into a true perspective projection image. Therefore, in order to make full use of information in the fisheye image, it is very important to correct the fisheye image to restore such distortion to a real object in the vehicle-mounted intelligent system.
The existing fisheye distortion correction algorithm defines a fisheye lens imaging model as a polynomial of an incident angle about the distance between an imaging point and an optical axis, simultaneously introduces collinear constraint, parallel constraint and orthogonal constraint, minimizes parameters of a solving model through characteristic values, and finally corrects the fisheye image by using the obtained correction model. The corrected image has true effect of correcting the content on the ground in the area with small view angle in the middle of the image, but the stereo object above the ground is severely stretched and distorted, and the edge area with large view angle is blurred and deformed.
Disclosure of Invention
In view of the above problems, an object of the embodiments of the present invention is to provide a high-fidelity fisheye lens distortion correction method, which can highly maintain real information of an object, restore the posture of the object in different viewing angle areas, and has strong adaptability, low algorithm complexity and easy implementation.
The embodiment of the invention provides a high-fidelity fisheye lens distortion correction method, which comprises the following steps:
1) Collecting images by using a fish-eye lens;
2) Detecting feature points in the image, counting position information of the feature points, and dividing the image into different view angle areas according to the positions of the feature points;
3) Establishing a segmentation curve model of each field angle region, and acquiring image correction parameters of each field angle region;
4) And carrying each image correction parameter into the corresponding piecewise curve model to correct the image.
Alternatively, feature points in the image are detected by using a SIFT algorithm, and the image is segmented into different view angle areas according to the positions of the feature points.
Optionally, the image correction parameters of each view angle area are obtained according to the statistical information of the image by utilizing a least square algorithm.
Optionally, acquiring the image correction parameters of each view angle area according to the detected feature point angular point coordinate statistic value in the image.
Optionally, image preprocessing is also included after the acquisition of the image.
Optionally, the image preprocessing includes removing noise from the acquired image using a bilateral filtering algorithm, and then graying the image.
From the above, by applying the technical scheme of the embodiment, as the sectional curve model is adopted, different view angle areas are brought into different sectional curve models by adopting different parameters to correct images, the corrected images can highly keep the real information of the object, the posture of the object in the different view angle areas is restored, and the correction method has strong adaptability, low algorithm complexity and easy realization.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flowchart of a high-fidelity fisheye lens distortion correction method provided by the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples:
the embodiment provides a high-fidelity fisheye lens distortion correction method, as shown in fig. 1, including:
1) The fisheye lens is used to collect an image, and the collected image is subjected to image preprocessing, which can include, but is not limited to, removing noise of the collected image by using a bilateral filtering algorithm, and then graying the image.
2) Detecting feature points in the image, counting position information of the feature points, and dividing the image into different view angle areas according to the positions of the feature points; feature points in an image may be detected using, but not limited to, SIFT algorithms, and the image may be segmented into different field angle regions according to the location of the feature points. In image processing, feature points refer to points where the gray value of an image changes drastically or points where the curvature is large on the edge of an image (i.e., the intersection of two edges). The image feature points play a very important role in the feature point-based image matching algorithm. The image feature points can reflect the essential features of the image and can identify the target object in the image. The characteristic points of the image have vivid characteristics and can effectively reflect the points of the image essential characteristics, which can identify the target object in the image, and the characteristic points-based image matching algorithm has very important roles, can reflect the image essential characteristics and can identify the target object in the image. Matching of images can be completed through matching of feature points. The image feature point extraction algorithm commonly used in the current scientific research includes a SIFT algorithm, a SURF algorithm and the like.
3) And establishing a segmentation curve model of each field angle area, and acquiring image correction parameters of each field angle area. According to different areas of the image, different curve models are adopted, a quadratic curve model is adopted near the middle part of the image, a polynomial curve model is adopted at the part which is outside the middle part of the image but is not at the edge of the image, and a polynomial curve model with a high power is adopted at the outermost periphery.
The image correction parameters of each of the field angle regions may be obtained from statistical information of the image using, but not limited to, a least squares algorithm. Specifically, image correction parameters of all the view angle areas are obtained according to the detected characteristic point angular point coordinate statistical values in the images.
4) And carrying each image correction parameter into the corresponding piecewise curve model to correct the image.
Therefore, the sectional curve model is adopted, different view angle areas are brought into different sectional curve models by different parameters to correct images, the corrected images can highly keep the real information of the object, the posture of the object in the different view angle areas is restored, the correction method is high in adaptability, low in algorithm complexity and easy to realize.
The above-described embodiments do not limit the scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the above embodiments should be included in the scope of the present invention.
Claims (6)
1. A high-fidelity fisheye lens distortion correction method is characterized by comprising the following steps:
1) Collecting images by using a fish-eye lens;
2) Detecting feature points in the image, counting position information of the feature points, and dividing the image into different view angle areas according to the positions of the feature points; the feature points are used for identifying target objects in the image;
3) Establishing a segmentation curve model of each field angle region, and acquiring image correction parameters of each field angle region;
4) And carrying each image correction parameter into the corresponding piecewise curve model to correct the image.
2. The method of claim 1, wherein the SIFT algorithm is used to detect feature points in the image, and the image is segmented into different angular regions according to the location of the feature points.
3. The method of claim 2, wherein the image correction parameters of each of the angle areas are obtained according to statistical information of the image using a least squares algorithm.
4. A high-fidelity fisheye lens distortion correction method as set forth in claim 3 wherein the image correction parameters for each of said field angle regions are obtained based on the feature point corner coordinate statistics detected in the image.
5. The method of claim 4, further comprising preprocessing the image after capturing the image.
6. The method of claim 5, wherein the image preprocessing includes removing noise from the captured image using a bilateral filtering algorithm, and then graying the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810769358.9A CN108961155B (en) | 2018-07-13 | 2018-07-13 | High-fidelity fisheye lens distortion correction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810769358.9A CN108961155B (en) | 2018-07-13 | 2018-07-13 | High-fidelity fisheye lens distortion correction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108961155A CN108961155A (en) | 2018-12-07 |
CN108961155B true CN108961155B (en) | 2023-06-27 |
Family
ID=64483188
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810769358.9A Active CN108961155B (en) | 2018-07-13 | 2018-07-13 | High-fidelity fisheye lens distortion correction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108961155B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189269B (en) * | 2019-05-23 | 2023-06-09 | Oppo广东移动通信有限公司 | Correction method, device, terminal and storage medium for 3D distortion of wide-angle lens |
CN111080544B (en) * | 2019-12-09 | 2023-09-22 | Oppo广东移动通信有限公司 | Face distortion correction method and device based on image and electronic equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005258953A (en) * | 2004-03-12 | 2005-09-22 | Ntt Docomo Inc | Fish eye camera and calibration method in the fish eye camera |
JP2008287426A (en) * | 2007-05-16 | 2008-11-27 | Mitsubishi Electric Corp | Distortion correction device and program |
CN102667854A (en) * | 2009-11-12 | 2012-09-12 | 佳能株式会社 | Three-dimensional measurement method |
CN103258328A (en) * | 2013-04-27 | 2013-08-21 | 浙江大学 | Method for locating distorted center of wide-field lens |
CN104079808A (en) * | 2014-07-13 | 2014-10-01 | 西安电子科技大学 | Ultrahigh resolution wide-field imaging system |
CN105550670A (en) * | 2016-01-27 | 2016-05-04 | 兰州理工大学 | Target object dynamic tracking and measurement positioning method |
KR101705333B1 (en) * | 2015-09-30 | 2017-02-09 | 인하대학교 산학협력단 | Estimation Method of Depth Vatiation around SIFT Features using a Stereo Camera |
CN106886976A (en) * | 2017-03-14 | 2017-06-23 | 成都通甲优博科技有限责任公司 | A kind of image generating method based on intrinsic parameter amendment flake camera |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008187564A (en) * | 2007-01-31 | 2008-08-14 | Sanyo Electric Co Ltd | Camera calibration apparatus and method, and vehicle |
WO2009000906A1 (en) * | 2007-06-26 | 2008-12-31 | Dublin City University | A method for high precision lens distortion calibration and removal |
US20130201326A1 (en) * | 2012-01-23 | 2013-08-08 | Hiroshi Tsujii | Single camera image processing apparatus, method, and program |
US10198865B2 (en) * | 2014-07-10 | 2019-02-05 | Seiko Epson Corporation | HMD calibration with direct geometric modeling |
CN104537616A (en) * | 2014-12-20 | 2015-04-22 | 中国科学院西安光学精密机械研究所 | Correction method for fisheye image distortion |
US9950669B2 (en) * | 2015-11-12 | 2018-04-24 | Robert Bosch Gmbh | Vehicle camera system with multiple-camera alignment |
EP3387506B1 (en) * | 2015-12-09 | 2021-01-13 | SZ DJI Technology Co., Ltd. | Systems and methods for auto-return |
CN107707821B (en) * | 2017-09-30 | 2020-11-06 | 努比亚技术有限公司 | Distortion parameter modeling method and device, correction method, terminal and storage medium |
-
2018
- 2018-07-13 CN CN201810769358.9A patent/CN108961155B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005258953A (en) * | 2004-03-12 | 2005-09-22 | Ntt Docomo Inc | Fish eye camera and calibration method in the fish eye camera |
JP2008287426A (en) * | 2007-05-16 | 2008-11-27 | Mitsubishi Electric Corp | Distortion correction device and program |
CN102667854A (en) * | 2009-11-12 | 2012-09-12 | 佳能株式会社 | Three-dimensional measurement method |
CN103258328A (en) * | 2013-04-27 | 2013-08-21 | 浙江大学 | Method for locating distorted center of wide-field lens |
CN104079808A (en) * | 2014-07-13 | 2014-10-01 | 西安电子科技大学 | Ultrahigh resolution wide-field imaging system |
KR101705333B1 (en) * | 2015-09-30 | 2017-02-09 | 인하대학교 산학협력단 | Estimation Method of Depth Vatiation around SIFT Features using a Stereo Camera |
CN105550670A (en) * | 2016-01-27 | 2016-05-04 | 兰州理工大学 | Target object dynamic tracking and measurement positioning method |
CN106886976A (en) * | 2017-03-14 | 2017-06-23 | 成都通甲优博科技有限责任公司 | A kind of image generating method based on intrinsic parameter amendment flake camera |
Also Published As
Publication number | Publication date |
---|---|
CN108961155A (en) | 2018-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103517041B (en) | Based on real time panoramic method for supervising and the device of polyphaser rotation sweep | |
WO2021120406A1 (en) | Infrared and visible light fusion method based on saliency map enhancement | |
CN109003311B (en) | Calibration method of fisheye lens | |
CN109785291B (en) | Lane line self-adaptive detection method | |
JP5542889B2 (en) | Image processing device | |
Rengarajan et al. | From bows to arrows: Rolling shutter rectification of urban scenes | |
CN105046657B (en) | A kind of image stretch distortion self-adapting correction method | |
CN108510451B (en) | Method for reconstructing license plate based on double-layer convolutional neural network | |
CN110414308B (en) | Target identification method for dynamic foreign matters on power transmission line | |
KR20130030220A (en) | Fast obstacle detection | |
CN112184604B (en) | Color image enhancement method based on image fusion | |
CN109544635B (en) | Camera automatic calibration method based on enumeration heuristic | |
CN109214288B (en) | Inter-frame scene matching method and device based on multi-rotor unmanned aerial vehicle aerial video | |
CN108961155B (en) | High-fidelity fisheye lens distortion correction method | |
CN111243034A (en) | Panoramic auxiliary parking calibration method, device, equipment and storage medium | |
CN111429533A (en) | Camera lens distortion parameter estimation device and method | |
KR20100091383A (en) | Correction method of radial distortion based on a line-fitting | |
CN114898353B (en) | License plate recognition method based on video sequence image characteristics and information | |
CN115239820A (en) | Split type flying vehicle aerial view real-time splicing and parking space detection method | |
CN114037970A (en) | Sliding window-based lane line detection method, system, terminal and readable storage medium | |
CN114693760A (en) | Image correction method, device and system and electronic equipment | |
CN110490886A (en) | A kind of method for automatically correcting and system for certificate image under oblique viewing angle | |
CN110827375B (en) | Infrared image true color coloring method and system based on low-light-level image | |
CN111428538B (en) | Lane line extraction method, device and equipment | |
KR20140038749A (en) | Apparatus and method for correcting image distortion |
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 |