CN110728703B - Registration fusion method for visible light image and solar blind ultraviolet light image - Google Patents
Registration fusion method for visible light image and solar blind ultraviolet light image Download PDFInfo
- Publication number
- CN110728703B CN110728703B CN201910869579.8A CN201910869579A CN110728703B CN 110728703 B CN110728703 B CN 110728703B CN 201910869579 A CN201910869579 A CN 201910869579A CN 110728703 B CN110728703 B CN 110728703B
- Authority
- CN
- China
- Prior art keywords
- image
- coordinate system
- light image
- light source
- visible light
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The invention discloses a registration fusion method of a visible light image and a solar blind ultraviolet light image, which comprises the following steps: obtaining a visible light image and a solar blind ultraviolet image in a scanned range; extracting a laser spot from a visible light image to obtain a light source pixel region of the laser spot in the visible light image; identifying light source position information of an ultraviolet light source in a solar blind ultraviolet light image, and determining a target light source range of the solar blind ultraviolet light image according to the light source position information; respectively converting each pixel point of the target light source range into a first image pixel coordinate system corresponding to the visible light image; and fusing each pixel point of the target light source range after coordinate conversion with each pixel point of the light source pixel region to realize registration fusion of the visible light image and the solar blind ultraviolet light image. By adopting the method, the fusion of the ultraviolet light source information in the visible light image and the ultraviolet light source information in the solar blind ultraviolet light image can be realized, and the fusion efficiency of the ultraviolet light source information and the ultraviolet light source information is improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a registration fusion method of a visible light image and a solar blind ultraviolet light image.
Background
Due to the physical characteristics of the individual light sources themselves and the imaging principle of the single light source image sensor, the effective information of the scene contained in the picture obtained by the single light source image sensor is limited. For example, a single visible light source image sensor can only obtain the position information of a shooting scene, and a single solar blind ultraviolet light source image sensor can only transmit the position and intensity information of a solar blind ultraviolet light source in a detection range. Because of different imaging principles, the heterogeneous images lack a unified reference object, the detection range of the heterogeneous image reaction has larger difference, and the registration and fusion of the heterogeneous images are more difficult. Due to the characteristic of solar blind ultraviolet light, a general object cannot autonomously radiate solar blind ultraviolet light like infrared light, so that the difficulty in extracting available feature operators based on a traditional heterogeneous image registration fusion algorithm for feature detection is high, the process of corresponding image fusion is complex, and the efficiency is low.
Disclosure of Invention
Aiming at the problems, the invention provides a registration fusion method of a visible light image and a solar blind ultraviolet light image.
In order to achieve the purpose of the invention, a registration fusion method of a visible light image and a solar blind ultraviolet light image is provided, which comprises the following steps:
s10, obtaining a visible light image and a solar blind ultraviolet image in a scanned range;
s20, extracting a laser point from the visible light image to obtain a light source pixel area of the laser point in the visible light image;
s30, identifying light source position information of an ultraviolet light source in the solar blind ultraviolet light image, and determining a target light source range of the solar blind ultraviolet light image according to the light source position information;
s40, converting each pixel point of the target light source range into a first image pixel coordinate system corresponding to the visible light image;
and S50, fusing each pixel point of the target light source range after coordinate conversion with each pixel point of the light source pixel region in the visible light image to realize registration fusion of the visible light image and the solar blind ultraviolet light image.
In one embodiment, the converting each pixel point of the target light source range to the first image pixel coordinate system corresponding to the visible light image includes:
converting each pixel point of the target light source range from a second image pixel coordinate system corresponding to the solar blind ultraviolet light image to a second image physical coordinate system;
respectively converting each pixel point of the target light source range in the second image physical coordinate system into a camera coordinate system;
respectively converting each pixel point of a target light source range in the camera coordinate system into a first image physical coordinate system;
and respectively converting each pixel point of the target light source range in the first image physical coordinate system into the first image pixel coordinate system.
In one embodiment, the acquiring the visible light image and the solar blind ultraviolet image within the scanned range includes:
shooting the scanned range through a CCD camera to obtain the visible light image; and shooting the scanned range through solar blind ultraviolet detection equipment to obtain the solar blind ultraviolet image.
As an embodiment, after the capturing the visible light image and the solar blind ultraviolet image in the scanned range, the method further includes:
acquiring a first object distance between a scanned range and a CCD lens of a CCD camera;
acquiring a second object distance between the scanned range and a solar blind ultraviolet detection lens of solar blind ultraviolet detection equipment;
acquiring the distance between a CCD lens and a solar blind ultraviolet detection lens, the first resolution of a visible light image and the second resolution of the solar blind ultraviolet image;
determining a first coordinate conversion relation between a second image pixel coordinate system and a second image physical coordinate system according to the second object distance and the second resolution;
determining a second coordinate conversion relation between a second image physical coordinate system and a camera coordinate system according to the second object distance and the interval;
determining a third coordinate system conversion relation between a camera coordinate system and a first image physical coordinate system according to the first object distance and the distance;
and determining a fourth coordinate conversion relation between the first image physical coordinate system and the first image pixel coordinate system according to the first object distance and the first resolution.
As an embodiment, after the capturing the visible light image and the solar blind ultraviolet image in the scanned range, the method further includes:
converting a scanning starting point in the solar blind ultraviolet image to a first image pixel coordinate system corresponding to the visible light image to obtain a starting point conversion coordinate;
if the difference value between the starting point conversion coordinate and the scanning starting point coordinate in the visible light image is smaller than a difference value threshold, determining that the registration parameter is accurate; the registration parameters include a first object distance, a second object distance, a distance between the CCD lens and the solar blind ultraviolet detection lens, a first resolution, and a second resolution.
As an embodiment, the converting the scanning start point in the solar blind ultraviolet image to the first image pixel coordinate system corresponding to the visible light image includes:
converting a scanning starting point of the second image pixel coordinate system into an image physical coordinate system according to the first coordinate conversion relation;
converting a scanning starting point of the second image physical coordinate system to a camera coordinate system according to the second coordinate conversion relation;
converting a scanning starting point of the camera coordinate system into a first image physical coordinate system according to the third coordinate conversion relation;
and converting the scanning starting point of the first image physical coordinate system into a first image pixel coordinate system according to the fourth coordinate conversion relation.
As an embodiment, after the capturing the visible light image and the solar blind ultraviolet image in the scanned range, the method further includes:
and if the difference value between the starting point conversion coordinate and the scanning starting point coordinate in the visible light image is larger than or equal to a difference value threshold, judging that the registration parameter is wrong.
In one embodiment, the method for registering and fusing the visible light image and the solar blind ultraviolet image further includes:
and detecting light source intensity information of an ultraviolet light source according to the solar blind ultraviolet light image.
In one embodiment, the extracting the laser point from the visible light image to obtain the light source pixel area of the laser point in the visible light image includes:
identifying an indication laser point in the visible light image, and each similar laser point with the indication laser having a similarity greater than a similarity threshold;
determining similar areas corresponding to the similar laser points, and calculating the pixel mean value of the similar areas;
if the pixel mean value is larger than a set threshold value, judging that the corresponding similar laser points are real laser points;
and determining a light source pixel area of the laser point in the visible light image according to the indication laser point and the real laser point.
According to the registration fusion method of the visible light image and the solar blind ultraviolet light image, the visible light image and the solar blind ultraviolet light image in the scanned range can be obtained, laser points are extracted from the visible light image, the light source pixel area of the laser points in the visible light image is obtained, the light source position information of an ultraviolet light source in the solar blind ultraviolet light image is identified, the target light source range of the solar blind ultraviolet light image is determined according to the light source position information, each pixel point of the target light source range is respectively converted into a first image pixel coordinate system corresponding to the visible light image, each pixel point of the target light source range after coordinate conversion is fused with each pixel point of the light source pixel area in the visible light image, the fusion of the ultraviolet light source information in the visible light image and the ultraviolet light source information in the solar blind ultraviolet light image is achieved, the fusion efficiency of the ultraviolet light source information and the ultraviolet light source information is improved, and the corresponding ultraviolet light source detection efficiency is further improved.
Drawings
Fig. 1 is a flowchart of a registration fusion method of a visible light image and a solar blind ultraviolet light image according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Referring to fig. 1, fig. 1 is a flowchart of a registration fusion method of a visible light image and a solar blind ultraviolet light image according to an embodiment, including the following steps:
s10, obtaining a visible light image and a solar blind ultraviolet image in a scanned range;
the scanned range may be a range in which ultraviolet light source detection is required. The visible light image may be an image captured by a CCD camera for the scanned range. The solar blind ultraviolet light image can be an image obtained by shooting a scanning range by solar blind ultraviolet detection equipment (such as a solar blind ultraviolet detection circuit).
S20, extracting a laser point from the visible light image to obtain a light source pixel area of the laser point in the visible light image;
the light source pixel region is a region corresponding to a laser point (ultraviolet light source) in the visible light image.
S30, identifying light source position information of an ultraviolet light source in the solar blind ultraviolet light image, and determining a target light source range of the solar blind ultraviolet light image according to the light source position information;
the step can also detect the light source intensity information from the solar blind ultraviolet light image so as to obtain more perfect light source information.
S40, converting each pixel point of the target light source range into a first image pixel coordinate system corresponding to the visible light image;
specifically, the above steps may convert each pixel point of the target light source range to other intermediate coordinate systems, and then convert each pixel point of the target light source range of the intermediate coordinate system to the first image pixel coordinate system, so as to ensure accuracy in the pixel point conversion process.
And S50, fusing each pixel point of the target light source range after coordinate conversion with each pixel point of the light source pixel region in the visible light image to realize registration fusion of the visible light image and the solar blind ultraviolet light image.
The steps can be used for realizing the fusion of the ultraviolet light source information in the visible light image and the ultraviolet light source information in the solar blind ultraviolet light image, so as to be used for detecting the ultraviolet light source in the corresponding scanned range and improve the accuracy of ultraviolet light source detection.
According to the registration fusion method for the visible light image and the solar blind ultraviolet light image, the visible light image and the solar blind ultraviolet light image in the scanned range can be obtained, laser points are extracted from the visible light image, a light source pixel area of the laser points in the visible light image is obtained, the light source position and the intensity information of an ultraviolet light source in the solar blind ultraviolet light image are identified, the target light source range of the solar blind ultraviolet light image is determined according to the light source position information, each pixel point of the target light source range is respectively converted into a first image pixel coordinate system corresponding to the visible light image, each pixel point of the target light source range after coordinate conversion is fused with each pixel point of the light source pixel area in the visible light image, registration fusion of the ultraviolet light source information in the visible light image and the ultraviolet light source information in the solar blind ultraviolet light image is achieved, fusion efficiency of the ultraviolet light source information and the ultraviolet light source information in the solar blind ultraviolet light image is improved, and corresponding ultraviolet light source detection efficiency is further improved.
In one embodiment, the converting each pixel point of the target light source range to the first image pixel coordinate system corresponding to the visible light image includes:
converting each pixel point of the target light source range from a second image pixel coordinate system corresponding to the solar blind ultraviolet light image to a second image physical coordinate system;
respectively converting each pixel point of the target light source range in the second image physical coordinate system into a camera coordinate system;
respectively converting each pixel point of a target light source range in the camera coordinate system into the first image physical coordinate system;
and respectively converting each pixel point of the target light source range in the first image physical coordinate system into the first image pixel coordinate system.
Specifically, the first image pixel coordinate system and the second image pixel coordinate system are on the corresponding imaging plane, the first pixel point at the upper left corner of the corresponding image is taken as the origin of coordinates, the length-width direction of the image is taken as the direction of the axis of abscissa and ordinate, and the units of the coordinate systems are pixels. The second image physical coordinate system is on the imaging plane, the origin is the focus of the optical axis of the solar blind ultraviolet detection lens and the imaging plane, the midpoint of the imaging plane is usually the midpoint of the imaging plane, the horizontal direction and the vertical direction are the directions of the horizontal axis and the vertical axis, the unit of the coordinate system is the length unit, and the physical unit is the physical unit. The camera coordinate system takes a lens optical center as a coordinate origin, takes the directions from a CCD camera lens to an ultraviolet detection lens and the vertical directions as the directions of the horizontal and vertical coordinate axes, and the unit of the coordinate system is a length unit and belongs to a physical unit. The first image physical coordinate system is on the imaging plane, the origin is the focus of the optical axis of the CCD camera lens and the imaging plane, the midpoint of the imaging plane is usually the midpoint of the imaging plane, the horizontal direction and the vertical direction are the directions of the abscissa axis and the ordinate axis, the unit of the coordinate system is the length unit, and the physical unit is the physical unit.
Specifically, a first object distance between a scanned range and a CCD lens of a CCD camera can be obtained, a second object distance between the scanned range and a solar blind ultraviolet detection lens of solar blind ultraviolet detection equipment is obtained, and a distance between the CCD lens and the solar blind ultraviolet detection lens, a first resolution of a visible light image and a second resolution of a solar blind ultraviolet image are obtained; determining a first coordinate conversion relation between a second image pixel coordinate system and a second image physical coordinate system according to a second object distance and a second resolution, and converting each pixel point of a target light source range from the second image pixel coordinate system corresponding to the solar blind ultraviolet light image to the second image physical coordinate system according to the first coordinate conversion relation; determining a second coordinate conversion relation between a second image physical coordinate system and a camera coordinate system according to the second distance and the interval, and respectively converting each pixel point of the target light source range in the second image physical coordinate system into the camera coordinate system according to the second coordinate conversion relation; determining a third coordinate conversion relation between the camera coordinate system and the first image physical coordinate system according to the first object distance and the distance, and respectively converting each pixel point of the target light source range in the camera coordinate system into the first image physical coordinate system according to the third coordinate conversion relation; determining a fourth coordinate conversion relation between a first image physical coordinate system and a first image pixel coordinate system according to a first object distance and a first resolution, and respectively converting each pixel point of a target light source range in the first image physical coordinate system into the first image pixel coordinate system according to the fourth coordinate conversion relation; and respectively converting each pixel point of the target light source range into a first image pixel coordinate system corresponding to the visible light image, so that the ultraviolet light source in the visible light image and the ultraviolet light source in the solar blind ultraviolet light image are accurately fused.
In one embodiment, the acquiring the visible light image and the solar blind ultraviolet image within the scanned range includes:
shooting the scanned range through a CCD camera to obtain the visible light image; and shooting the scanned range through solar blind ultraviolet detection equipment (such as a solar blind ultraviolet detection circuit) to obtain the solar blind ultraviolet image.
As an embodiment, after the capturing the visible light image and the solar blind ultraviolet image in the scanned range, the method further includes:
acquiring a first object distance between a scanned range and a CCD lens of a CCD camera;
acquiring a second object distance between the scanned range and a solar blind ultraviolet detection lens of solar blind ultraviolet detection equipment;
acquiring the distance between a CCD lens and a solar blind ultraviolet detection lens, the first resolution of a visible light image and the second resolution of the solar blind ultraviolet image;
determining a first coordinate conversion relation between a second image pixel coordinate system and a second image physical coordinate system according to the second resolution;
determining a second coordinate conversion relation between a second image physical coordinate system and a camera coordinate system according to the second object distance and the interval;
determining a third coordinate system conversion relation between a camera coordinate system and a first image physical coordinate system according to the first object distance and the distance;
and determining a fourth coordinate conversion relation between the first image physical coordinate system and the first image pixel coordinate system according to the first resolution.
The registration parameters in the registration fusion process of the visible light image and the solar blind ultraviolet light image comprise parameters such as a first object distance between a scanned range and a CCD lens of the CCD camera, a second object distance between the scanned range and a solar blind ultraviolet detection lens of the solar blind ultraviolet detection device, a distance between the CCD lens and the solar blind ultraviolet detection lens, a first resolution of the visible light image, a second resolution of the solar blind ultraviolet light image and the like, if the registration parameters are accurate, the accuracy of an image fusion result can be effectively ensured, and if the registration parameters are wrong, the corresponding image fusion result is very likely to be wrong.
Further, the image distance of the two lenses (the CCD lens and the solar blind ultraviolet detection lens) and the field angle of the two lenses can be calculated according to the first object distance and the second object distance, and the obtained registration parameters are utilized to register and fuse the visible light image and the solar blind ultraviolet image. And taking the first object distance, the second object distance, the distance and the picture resolution (the first resolution and the second resolution), the image distance and the view angle as registration parameters, and taking the registration parameters into the conversion relations of an image pixel coordinate system (such as a first image pixel coordinate system and a second image pixel coordinate system), an image physical coordinate system (such as a first image physical coordinate system and a second image physical coordinate system) and a camera coordinate system to finish registration and fusion of the visible light image and the solar blind ultraviolet light image.
As an embodiment, after the capturing the visible light image and the solar blind ultraviolet image in the scanned range, the method further includes:
converting a scanning starting point in the solar blind ultraviolet image to a first image pixel coordinate system corresponding to the visible light image to obtain a starting point conversion coordinate;
if the difference value between the starting point conversion coordinate and the scanning starting point coordinate in the visible light image is smaller than a difference value threshold, determining that the registration parameter is accurate; the registration parameters include a first object distance, a second object distance, a distance between the CCD lens and the solar blind ultraviolet detection lens, a first resolution, and a second resolution.
The difference threshold may be set according to the corresponding image fusion accuracy, for example, set to 0.5 equivalent. If the difference between the starting point conversion coordinates and the scanning starting point coordinates in the visible light image is smaller than the difference threshold, the registration parameters adopted in the corresponding image fusion process are accurate, and at the moment, the laser points can be continuously extracted from the visible light image, so that the image fusion process of the laser points in the visible light image such as a light source pixel area and the like is obtained, and the fusion of the ultraviolet light source in the visible light image and the ultraviolet light source in the solar blind ultraviolet light image is realized.
As an embodiment, the converting the scanning start point in the solar blind ultraviolet image to the first image pixel coordinate system corresponding to the visible light image includes:
converting a scanning starting point of the second image pixel coordinate system into a second image physical coordinate system according to the first coordinate conversion relation;
converting a scanning starting point of the image physical coordinate system to a camera coordinate system according to the second coordinate conversion relation;
and converting the scanning starting point of the camera coordinate system into a first image physical coordinate system according to the third coordinate conversion relation.
And converting the scanning starting point in the first image physical coordinate system into a first image pixel coordinate system according to the fourth coordinate system conversion relation.
As an embodiment, after the capturing the visible light image and the solar blind ultraviolet image in the scanned range, the method further includes:
and if the difference value between the starting point conversion coordinate and the scanning starting point coordinate in the visible light image is larger than or equal to a difference value threshold, judging that the registration parameter is wrong.
If the difference between the starting point conversion coordinates and the scanning starting point coordinates in the visible light image is larger than or equal to a difference threshold, indicating that the currently obtained registration parameters have errors such as large errors, the errors can be reported to a user, and the process of acquiring the visible light image and the solar blind ultraviolet light image in the scanned range is carried out in a returning mode, and fusion of the ultraviolet light source in the visible light image and the ultraviolet light source in the solar blind ultraviolet light image is carried out according to the newly acquired visible light image and the newly acquired solar blind ultraviolet light image so as to ensure the accuracy of the obtained fusion result.
In one embodiment, the method for registering and fusing the visible light image and the solar blind ultraviolet image further includes:
and detecting light source intensity information of an ultraviolet light source according to the solar blind ultraviolet light image.
Specifically, the position and intensity information of the ultraviolet light source target can be extracted from the solar blind ultraviolet light image, the image distance of the two lenses is calculated according to the calculation formulas of the object distance (such as the first object distance and the second object distance), the related focal distance and the image distance, the field angle of the CCD lens is calculated according to the object distance and the shooting range, and the field angle of the solar blind ultraviolet detection range is calculated according to the detector specification and the image distance so as to prepare for the detection of the ultraviolet light source in the scanned range.
In one embodiment, the extracting the laser point from the visible light image to obtain the light source pixel area of the laser point in the visible light image includes:
identifying an indication laser point in the visible light image, and each similar laser point with the indication laser having a similarity greater than a similarity threshold;
determining similar areas corresponding to the similar laser points, and calculating the pixel mean value of the similar areas;
if the pixel mean value is larger than a set threshold value, judging that the corresponding similar laser points are real laser points; if the pixel mean value is smaller than or equal to a set threshold value, judging that the corresponding similar laser points are noise points;
and determining a light source pixel area of the laser point in the visible light image according to the indication laser point and the real laser point.
The similar laser points are other pixel points in the visible light image, which have similar RGB components with the indicating laser points. The pixel mean may refer to an RGB component mean corresponding to each pixel point in the similar region.
The similarity threshold may be set to 80% or 90% equivalent. The similarity region may be a 3 row and 3 column light source pixel region centered on the similarity threshold. The set threshold may be set according to the characteristics of the uv light source and the associated accuracy requirements.
The embodiment can identify and detect the similar laser points to further identify the real laser points, reject the noise points and ensure the accuracy of the determined initial image.
The registration fusion method of the visible light image and the solar blind ultraviolet image acquires the visible light image and the solar blind ultraviolet image of the scanned range in real time; then acquiring configuration parameters such as the object distance between the scanned range and each lens, the space between the CCD lens and the solar blind ultraviolet detection lens and the like; and then, the registration and fusion of the visible light image and the solar blind ultraviolet light image are completed by using the acquired registration parameters. In the registration process, the acquired registration parameters are utilized, and the registration is completed through the geometric relationship between the two lenses, so that the operation amount of the registration is greatly reduced. The registration mode is realized through geometric operation, and detection omission or false detection caused by the traditional registration realized through image feature matching is avoided. The speed and the precision of the visible light image and the solar blind ultraviolet light image of the scanned range are improved. The method has the advantages of low requirements on the cleanliness of the detection background, high universality of different detection backgrounds, small calculated amount and more friendliness to handheld equipment.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, and it is understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate to enable embodiments of the present application described herein to be implemented in sequences other than those illustrated or described herein.
The terms "comprising" and "having" and any variations thereof, in embodiments of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, article, or device that comprises a list of steps or modules is not limited to the particular steps or modules listed and may optionally include additional steps or modules not listed or inherent to such process, method, article, or device.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (5)
1. The registration fusion method of the visible light image and the solar blind ultraviolet light image is characterized by comprising the following steps of:
s10, obtaining a visible light image and a solar blind ultraviolet light image in a scanned range, and further comprising:
acquiring a first object distance between a scanned range and a CCD lens of a CCD camera; acquiring a second object distance between the scanned range and a solar blind ultraviolet detection lens of solar blind ultraviolet detection equipment; acquiring the distance between a CCD lens and a solar blind ultraviolet detection lens, the first resolution of a visible light image and the second resolution of the solar blind ultraviolet image; determining a first coordinate conversion relation between a second image pixel coordinate system and a second image physical coordinate system according to the second object distance and the second resolution; determining a second coordinate conversion relation between a second image physical coordinate system and a camera coordinate system according to the second object distance and the interval; determining a third coordinate system conversion relation between a camera coordinate system and a first image physical coordinate system according to the first object distance and the distance; determining a fourth coordinate conversion relation between the first image physical coordinate system and the first image pixel coordinate system according to the first object distance and the first resolution;
converting a scanning starting point in the solar blind ultraviolet image to a first image pixel coordinate system corresponding to the visible light image to obtain a starting point conversion coordinate; if the difference value between the starting point conversion coordinate and the scanning starting point coordinate in the visible light image is smaller than a difference value threshold, determining that the registration parameter is accurate; the registration parameters comprise a first object distance, a second object distance, a distance between the CCD lens and the solar blind ultraviolet detection lens, a first resolution and a second resolution;
s20, extracting a laser point from the visible light image to obtain a light source pixel area of the laser point in the visible light image;
s30, identifying light source position information of an ultraviolet light source in the solar blind ultraviolet light image, and determining a target light source range of the solar blind ultraviolet light image according to the light source position information;
s40, converting each pixel point of the target light source range to a first image pixel coordinate system corresponding to the visible light image, wherein the S40 comprises the following steps:
converting each pixel point of the target light source range from a second image pixel coordinate system corresponding to the solar blind ultraviolet light image to a second image physical coordinate system; respectively converting each pixel point of the target light source range in the second image physical coordinate system into a camera coordinate system; respectively converting each pixel point of a target light source range in the camera coordinate system into a first image physical coordinate system; respectively converting each pixel point of a target light source range in the first image physical coordinate system into the first image pixel coordinate system;
converting a scanning starting point of the second image pixel coordinate system into a second image physical coordinate system according to the first coordinate conversion relation; converting a scanning starting point of the second image physical coordinate system to a camera coordinate system according to the second coordinate conversion relation; converting a scanning starting point of the camera coordinate system into a first image physical coordinate system according to a third coordinate conversion relation; converting the scanning starting point of the first image physical coordinate system into a first image pixel coordinate system according to the fourth coordinate conversion relation;
and S50, fusing each pixel point of the target light source range after coordinate conversion with each pixel point of the light source pixel region in the visible light image to realize registration fusion of the visible light image and the solar blind ultraviolet light image.
2. The method for registering and fusing a visible light image and a solar blind ultraviolet image according to claim 1, wherein the acquiring the visible light image and the solar blind ultraviolet image in the scanned range comprises:
shooting the scanned range through a CCD camera to obtain the visible light image; and shooting the scanned range through solar blind ultraviolet detection equipment to obtain the solar blind ultraviolet image.
3. The registration fusion method of a visible light image and a solar blind ultraviolet light image according to claim 1, wherein after the obtaining of the visible light image and the solar blind ultraviolet light image in the scanned range, the registration fusion method further comprises:
and if the difference value between the starting point conversion coordinate and the scanning starting point coordinate in the visible light image is larger than or equal to a difference value threshold, judging that the registration parameter is wrong.
4. A method of registration fusion of a visible light image and a solar blind ultraviolet light image according to any one of claims 1 to 3, further comprising:
and detecting light source intensity information of an ultraviolet light source according to the solar blind ultraviolet light image.
5. The registration fusion method of a visible light image and a solar blind ultraviolet light image according to any one of claims 1 to 3, wherein extracting a laser point from the visible light image to obtain a light source pixel region of the laser point in the visible light image comprises:
identifying an indication laser point in the visible light image, and each similar laser point with the indication laser having a similarity greater than a similarity threshold;
determining similar areas corresponding to the similar laser points, and calculating the pixel mean value of the similar areas;
if the pixel mean value is larger than a set threshold value, judging that the corresponding similar laser points are real laser points;
and determining a light source pixel area of the laser point in the visible light image according to the indication laser point and the real laser point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910869579.8A CN110728703B (en) | 2019-09-16 | 2019-09-16 | Registration fusion method for visible light image and solar blind ultraviolet light image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910869579.8A CN110728703B (en) | 2019-09-16 | 2019-09-16 | Registration fusion method for visible light image and solar blind ultraviolet light image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110728703A CN110728703A (en) | 2020-01-24 |
| CN110728703B true CN110728703B (en) | 2023-05-12 |
Family
ID=69219043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910869579.8A Active CN110728703B (en) | 2019-09-16 | 2019-09-16 | Registration fusion method for visible light image and solar blind ultraviolet light image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728703B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111413597B (en) * | 2020-03-31 | 2022-02-15 | 北方夜视技术股份有限公司 | Ultraviolet, infrared and visible light integrated high-voltage power transformation equipment detection method |
| CN112200842B (en) * | 2020-09-11 | 2023-12-01 | 深圳市优必选科技股份有限公司 | Image registration method, device, terminal equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111028188B (en) * | 2016-09-19 | 2023-05-02 | 杭州海康威视数字技术股份有限公司 | Light-splitting fusion image acquisition equipment |
| CN106500852B (en) * | 2016-09-28 | 2018-11-13 | 北方夜视技术股份有限公司 | It is infrared with visible light image registration with the System and method for that merges |
| CN107169947B (en) * | 2017-04-26 | 2021-02-12 | 国网上海市电力公司 | Image fusion experimental method based on feature point positioning and edge detection |
| CN108805848B (en) * | 2018-04-04 | 2022-02-22 | 国网浙江省电力有限公司温州供电公司 | Image fusion method for ultraviolet light and visible light imaging |
| CN109727290B (en) * | 2018-12-26 | 2022-09-06 | 南京理工大学 | Zoom camera dynamic calibration method based on monocular vision triangulation distance measurement method |
-
2019
- 2019-09-16 CN CN201910869579.8A patent/CN110728703B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110728703A (en) | 2020-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7924312B2 (en) | Infrared and visible-light image registration | |
| EP1343332B1 (en) | Stereoscopic image characteristics examination system | |
| US9613465B1 (en) | Method for suturing 3D coordinate information and the device using the same | |
| KR20120053275A (en) | Method and apparatus for estimating 3d face position | |
| JP2003244521A (en) | Information processing method and apparatus, and recording medium | |
| CN106056594A (en) | Double-spectrum-based visible light image extraction system and method | |
| CN110728703B (en) | Registration fusion method for visible light image and solar blind ultraviolet light image | |
| US7949244B2 (en) | Method for measuring subject distance | |
| CN114137511B (en) | Airport runway foreign matter fusion detection method based on multi-source heterogeneous sensor | |
| CN107092905B (en) | Method for positioning instrument to be identified of power inspection robot | |
| CN102201058A (en) | Cat eye effect object recognition algorithm of active and passive imaging system sharing same aperture | |
| JP5336325B2 (en) | Image processing method | |
| JP2019036213A (en) | Image processing device | |
| CN112541932A (en) | Multi-source image registration method based on different focal length transformation parameters of dual-optical camera | |
| US10783646B2 (en) | Method for detecting motion in a video sequence | |
| CN102082905A (en) | Method for detecting position of camera optic axis | |
| KR101705330B1 (en) | Keypoints Selection method to Find the Viewing Angle of Objects in a Stereo Camera Image | |
| TWI774543B (en) | Obstacle detection method | |
| KR20170043880A (en) | Face tracking camera module and method | |
| KR20190134426A (en) | Photovoltaic module thermal imaging system with trio imaging device | |
| KR20150009842A (en) | System for testing camera module centering and method for testing camera module centering using the same | |
| JP2012181757A (en) | Optical information reader | |
| KR101599434B1 (en) | Space detecting apparatus for image pickup apparatus using auto focusing and the method thereof | |
| JPH1194527A (en) | Stereo measuring method and device using image processing | |
| CN110726407A (en) | Positioning monitoring 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |