WO2021098080A1 - 基于边缘特征的多光谱相机外参自校正算法 - Google Patents
基于边缘特征的多光谱相机外参自校正算法 Download PDFInfo
- Publication number
- WO2021098080A1 WO2021098080A1 PCT/CN2020/077951 CN2020077951W WO2021098080A1 WO 2021098080 A1 WO2021098080 A1 WO 2021098080A1 CN 2020077951 W CN2020077951 W CN 2020077951W WO 2021098080 A1 WO2021098080 A1 WO 2021098080A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- visible light
- infrared
- camera
- relationship
- Prior art date
Links
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 46
- 238000013519 translation Methods 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 16
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000001559 infrared map Methods 0.000 claims description 4
- 230000000717 retained effect Effects 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000003702 image correction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
- H04N13/122—Improving the 3D impression of stereoscopic images by modifying image signal contents, e.g. by filtering or adding monoscopic depth cues
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
- H04N13/156—Mixing image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/239—Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/246—Calibration of cameras
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/25—Image signal generators using stereoscopic image cameras using two or more image sensors with different characteristics other than in their location or field of view, e.g. having different resolutions or colour pickup characteristics; using image signals from one sensor to control the characteristics of another sensor
-
- 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
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/10024—Color 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
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N2013/0074—Stereoscopic image analysis
- H04N2013/0092—Image segmentation from stereoscopic image signals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Definitions
- the invention belongs to the field of image processing and computer vision, and relates to extracting and matching feature points from captured infrared scene images and visible light scene images, and correcting the positional relationship between the infrared camera and the visible light camera according to the matched feature points, thereby Solve the problem that the external parameters of infrared cameras and visible light cameras change due to temperature and vibration.
- Infrared is an electromagnetic wave with a wavelength between microwave and visible light, and the wavelength is longer than red light. Any substance above absolute zero (-273.15°C) can produce infrared rays. Infrared images are widely used in different fields such as military and national defense, resource exploration, weather forecasting, environmental monitoring, medical diagnosis and treatment, and marine research due to their ability to observe through fog and rain. Infrared can be used to shoot scenes through mist and smoke, and infrared photography can also be carried out at night.
- the advantage of infrared camera imaging is that it can also image in extreme scenes (low light, rain, snow, dense fog, etc.), but the disadvantage is low resolution and blurry image details.
- the advantages of visible light cameras are high resolution and clear image details, but they cannot be imaged in extreme scenes. Therefore, it is of great practical significance to combine the infrared camera and the visible light camera.
- Stereo vision is an important subject in the field of computer vision. Its purpose is to reconstruct the 3D geometric information of the scene. Binocular stereo vision is an important field of stereo vision. In binocular stereo vision, the left and right cameras are used to simulate two eyes. Calculate the depth image by calculating the difference between the binocular images. Binocular stereo vision has the advantages of high efficiency, high accuracy, simple system structure and low cost. Since binocular stereo vision needs to match the same point on the left and right image capture points, the focal length and image capture center of the two lenses of the camera, as well as the positional relationship between the left and right lenses. In order to get the above data, we need to calibrate the camera. Obtaining the positional relationship between the visible light camera and the infrared camera is called joint calibration.
- the two lens parameters and relative position parameters of the camera are obtained, but these parameters are not stable.
- the internal parameters of the camera lens will also change.
- the positional relationship between the two lenses may change. Therefore, every time you use the camera, you must modify the internal and external parameters, which is self-calibration.
- we correct the positional relationship between the infrared lens and the visible light lens by extracting the infrared image characteristics and the visible light image characteristics respectively, that is, the joint self-calibration of the infrared camera and the visible light camera.
- the invention aims to solve the change of the positional relationship between the infrared camera and the visible light camera due to factors such as temperature, humidity, vibration, etc.
- the characteristic points are selected from the matched edges, and the original calibration results are corrected according to these characteristic points.
- Extract and screen out the best matching point pair extract and select the matching point pair that meets the requirements according to the best corresponding position of the infrared image on the visible light image.
- step 1) The specific steps of step 1) are as follows:
- Coordinate System The pixel coordinate system takes the upper left corner of the picture as the origin, and its x-axis and y-axis are parallel to the x-axis and y-axis of the image coordinate system, respectively.
- the unit of the pixel coordinate system is the pixel.
- the relationship between pixel coordinates and normal coordinates is as follows:
- the image radial distortion is the position deviation of the image pixel points along the radial direction with the distortion center as the center point, which causes the image formed in the image to be deformed.
- the general expression of radial distortion is as follows:
- x d x(1+k 1 r 2 + k 2 r 4 + k 3 r 6 )
- y d y(1+k 1 r 2 +k 2 r 4 +k 3 r 6 )
- r 2 x 2 +y 2 , k 1 , k 2 , and k 3 are radial distortion parameters.
- the tangential distortion of the image is caused by the defect in the manufacturing of the camera that makes the lens itself not parallel to the image plane. It can be quantitatively described as:
- x d x+(2p 1 xy+p 2 (r 2 +2x 2 ))
- p 1 and p 2 are tangential distortion coefficients.
- x d x(1+k 1 r 2 + k 2 r 4 + k 3 r 6 )+(2p 1 xy+p 2 (r 2 +2x 2 ))
- y d y(1+k 1 r 2 +k 2 r 4 +k 3 r 6 )+(p 1 (r 2 +2y 2 )+2p 2 xy)
- (x, y) are the normal coordinates in an ideal state
- (x d , y d ) are the actual normal coordinates with distortion.
- X l represents the normal coordinates of the infrared camera
- X r represents the normal coordinates of the visible light camera.
- the step 3) specifically includes the following steps:
- the normalized cross-correlation matching method is used to calculate the correlation coefficient between the visible light edge image and the infrared edge image.
- (u,v) represents the position of the infrared edge image Im IRe relative to the visible light edge image Im Oe
- Im Oeu,v represents the part of Im Oe with (u,v) as the starting point and the same size as Im IRe.
- ⁇ IR respectively represent the standard deviation of the corresponding image.
- a set of points ⁇ (u k ,v k ) ⁇ that maximizes ⁇ (u,v) is selected as the candidate corresponding positions.
- each candidate position multiple times according to an angle range (for example, the range of -10° ⁇ 10° is divided into 200 parts, that is, the position starts from -10° and each rotation is 0.1°), and choose to make ⁇ ( u,v) The maximum corresponding position and rotation angle.
- an angle range for example, the range of -10° ⁇ 10° is divided into 200 parts, that is, the position starts from -10° and each rotation is 0.1°
- the step 4) specifically includes the following steps:
- step 41) Select the best corresponding position of the infrared image on the visible light image. Translate and rotate the infrared image according to the result of step 3). Then perform feature point detection on the visible light image and the translated and rotated infrared image respectively.
- step 4-1 The final matching point pair is Need to follow the inverse process of step 4-1) to restore the infrared image to the coordinates before the rotation and translation.
- the step 6) specifically includes the following steps:
- Random Sampling Consistency (RANSAC) to further screen point pairs.
- K l and K r are the internal parameter matrices of the infrared camera and the visible light camera, respectively.
- the present invention solves the change of the positional relationship between the infrared camera and the visible light camera due to factors such as temperature, humidity, vibration, etc. It has the advantages of fast speed, accurate results, and simple operation.
- Figure 1 is a schematic diagram of the overall process.
- Figure 2 is a schematic diagram of the binocular correction process.
- Figure 3 is a schematic diagram of block matching. Among them, (a) is a schematic diagram of infrared block, (b) is a schematic diagram of visible light block.
- the invention aims to solve the change of the positional relationship between the infrared camera and the visible light camera due to factors such as temperature, humidity, vibration, etc.
- the detailed description is as follows in conjunction with the drawings and embodiments:
- the pixel coordinate system takes the upper left corner of the picture as the origin, and its x-axis and y-axis are parallel to the x-axis and y-axis of the image coordinate system, respectively.
- the unit of the pixel coordinate system is the pixel, which is the basic and indivisible unit of image display.
- the relationship between pixel coordinates and normal coordinates is as follows:
- the image radial distortion is the position deviation of the image pixel points along the radial direction with the distortion center as the center point, which causes the image formed in the image to be deformed.
- the general expression of radial distortion is as follows:
- x d x(1+k 1 r 2 + k 2 r 4 + k 3 r 6 )
- y d y(1+k 1 r 2 +k 2 r 4 +k 3 r 6 )
- r 2 x 2 +y 2 , k 1 , k 2 , and k 3 are radial distortion parameters.
- Tangential distortion is caused by a defect in the camera's manufacturing that makes the lens itself not parallel to the image plane. It can be quantitatively described as:
- x d x+(2p 1 xy+p 2 (r 2 +2x 2 ))
- p 1 and p 2 are tangential distortion coefficients.
- x d x(1+k 1 r 2 + k 2 r 4 + k 3 r 6 )+(2p 1 xy+p 2 (r 2 +2x 2 ))
- y d y(1+k 1 r 2 +k 2 r 4 +k 3 r 6 )+(p 1 (r 2 +2y 2 )+2p 2 xy)
- (x, y) are the normal coordinates in an ideal state
- (x d , y d ) are the actual normal coordinates with distortion.
- X l represents the normal coordinates of the infrared camera
- X r represents the normal coordinates of the visible light camera.
- the normalized cross-correlation matching method is used to calculate the correlation coefficient between the visible light edge image and the infrared edge image.
- (u,v) represents the position of the infrared edge image Im IRe relative to the visible light edge image Im Oe
- Im Oeu,v represents the part of Im Oe with (u,v) as the starting point and the same size as Im IRe.
- ⁇ IR respectively represent the standard deviation of the corresponding image.
- a set of points ⁇ (u k ,v k ) ⁇ that maximizes ⁇ (u,v) is selected as the candidate corresponding positions.
- Extract and screen out the best matching point pair extract and select the matching point pair that meets the requirements according to the best corresponding position of the infrared image on the visible light image.
- step 41) Select the best corresponding position of the infrared image on the visible light image. Translate and rotate the infrared image according to the result of step 3). Then perform feature point detection on the visible light image and the translated and rotated infrared image respectively.
- step 4-1 The final matching point pair is Need to follow the inverse process of step 4-1) to restore the infrared image to the coordinates before the rotation and translation.
- Random Sampling Consistency (RANSAC) to further screen point pairs.
- K l and K r are the internal parameter matrices of the infrared camera and the visible light camera, respectively.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
本发明公开了基于边缘特征的多光谱相机外参自校正算法,属于图像处理和计算机视觉领域。由于可见光相机和红外相机属于不同模态,因此直接提取特征点做匹配得到的满足要求的点对比较少。为了解决这个问题,本方法从边缘特征入手,通过边缘提取和匹配找到红外图像在可见光图像上的最佳对应位置。这样就缩小了搜索范围,增加了满足要求的匹配点对数,从而更加有效的对红外相机和可见光相机进行联合自标定,操作简便,结果精确。
Description
本发明属于图像处理和计算机视觉领域,涉及从拍摄到的红外场景图像和可见光场景图像中提取并匹配特征点,并根据匹配的特征点对红外相机和可见光相机之间的位置关系进行修正,从而解决红外相机和可见光相机因温度和震动导致其外参发生变化的问题。
红外线(Infrared)是波长介于微波与可见光之间的电磁波,波长比红光要长。高于绝对零度(-273.15℃)的物质都可以产生红外线。红外图像由于其具有透过雾、雨等进行观察的能力而被广泛用于军事国防、资源勘探、气象预报、环境监测、医学诊治、海洋研究等不同领域。利用红外线可以隔着薄雾和烟雾拍摄景物,而且在夜间也可以进行红外摄影。红外相机成像的优点是在极端场景(低光、雨雪、浓雾等)也可以成像,缺点是分辨率低、图像细节较模糊。相比之下,可见光相机的优点是分辨率高、图像细节清晰,但是在极端场景下不能成像。因此,将红外相机和可见光相机结合起来具有重大的现实意义。
立体视觉是计算机视觉领域的重要主题。其目的是重建场景的3D几何信息。双目立体视觉是立体视觉的重要领域。在双目立体视觉中,左右摄像头用于模拟两只眼睛。通过计算双目图像之间的差异来计算深度图像。双目立体视觉具有效率高,准确度高,系统结构简单,成本低的优点。由于双目立体视觉需要匹配左右图像捕获点上的相同点,因此相机两个镜头的焦距和图像捕获中心,以及左右两个镜头之间的位置关系。为了得到以上数据,我们需要对相机进行标定。获取可见光相机和红外相机之间的位置关系称为联合标定。
在标定过程中获得了相机的两个镜头参数和相对位置参数,但这些参数不稳定。当温度、湿度等发生变化时,相机镜头的内部参数也会发生变化。另外,由 于意外的相机碰撞,两个镜头之间的位置关系可能会改变。因此,每次使用摄像机时,都必须修改内部和外部参数,这就是自标定。在已知相机内部参数的情况下,我们通过分别提取红外图像特征和可见光图像特征来对红外镜头和可见光镜头的位置关系进行修正,即红外相机与可见光相机的联合自标定。
发明内容
本发明旨在解决由于温湿度、震动等因素造成红外相机和可见光相机位置关系的改变。通过提取红外相机和可见光相机的边缘并匹配,之后从匹配的边缘选取特征点,并根据这些特征点对原有的标定结果进行修正。
本发明的技术方案:
基于边缘特征的多光谱相机外参自校正算法,流程如图1所示,步骤如下:
1)原图校正:将原图根据红外相机和可见光相机各自内参和原来的外参进行去畸变和双目校正。流程如图2所示。
2)场景边缘检测:将红外图像和可见光图像分别做边缘提取。
3)判断红外图像在可见光图像上的最佳对应位置:将红外图像的边缘和可见光图像的边缘做匹配,根据匹配结果确定对应位置。
4)提取并筛选出最佳的匹配点对:根据红外图像在可见光图像上的最佳对应位置提取并选择满足要求的匹配点对。
5)判断特征点覆盖区域:将图像分成m*n个格子,当特征点覆盖到所有格子时,则进行下一步,否则继续拍摄图像,提取特征点。
6)修正标定结果:使用所有特征点的图像坐标来计算校正之后的两相机之间的位置关系,然后与原来的外参相叠加。
所述步骤1)的具体步骤如下:
1-1)计算图像的像素点对应的正规坐标系下的坐标。其中,正规坐标系是相机坐标系在平面Z=1的投影;而相机坐标系是以相机的中心作为图像坐标系的原点,以图片方向为XY轴方向,以垂直于图像为Z轴方向的坐标系。像素坐标 系以图片的左上角为原点,其x轴和y轴分别与图像坐标系的x轴和y轴平行。像素坐标系的单位是像素。像素坐标与正规坐标的关系如下:
u=KX
其中,
表示图像的像素坐标;
表示相机的内参矩阵,f
x和f
y分别表示图像x方向和y方向的焦距,单位是像素,(c
x,c
y)表示相机的主点位置,即相机中心在图像上的对应位置;
是正规坐标系下的坐标。已知图像的像素坐标系以及相机的内参计算出像素点对应的正规坐标系,即X=K
-1u;
1-2)去除图像畸变:由于镜头生产工艺的限制,实际情况下的镜头会存在一些失真现象导致非线性的畸变。因此纯线性模型不能完全准确地描述成像几何关系。非线性畸变可大致分为径向畸变和切向畸变。
图像径向畸变是图像像素点以畸变中心为中心点,沿着径向产生的位置偏差,从而导致图像中所成的像发生形变。径向畸变的大致表述如下:
x
d=x(1+k
1r
2+k
2r
4+k
3r
6)
y
d=y(1+k
1r
2+k
2r
4+k
3r
6)
其中,r
2=x
2+y
2,k
1、k
2、k
3为径向畸变参数。
图像切向畸变是由于摄像机制造上的缺陷使得透镜本身与图像平面不平行而产生的,可定量描述为:
x
d=x+(2p
1xy+p
2(r
2+2x
2))
y
d=y+(p
1(r
2+2y
2)+2p
2xy)
其中,p
1、p
2为切向畸变系数。
综上,畸变前后的坐标关系如下:
x
d=x(1+k
1r
2+k
2r
4+k
3r
6)+(2p
1xy+p
2(r
2+2x
2))
y
d=y(1+k
1r
2+k
2r
4+k
3r
6)+(p
1(r
2+2y
2)+2p
2xy)
其中,(x,y)是理想状态下的正规坐标,(x
d,y
d)是实际带有畸变的正规坐标。
1-3)根据原来两相机的旋转关系将两图转回来:已知原来两个相机之间的旋转矩阵R和平移向量t,使得:
X
r=RX
l+t
其中,X
l表示红外相机的正规坐标,X
r表示可见光相机的正规坐标。将红外图像向R正方向旋转一半的角度,将可见光图像向R反方向旋转一半的角度;
1-4)根据公式u=KX将去畸旋转后的图像还原至像素坐标系。
所述步骤3)具体包括以下步骤:
3-1)使用归一化互相关匹配法来计算可见光边缘图和红外边缘图的互相关系数。
选取使ρ(u,v)最大的一组点{(u
k,v
k)}作为候选的对应位置。
3-2)对每一个侯选位置按照一个角度范围旋转多次(比如-10°~10°范围内分为200份,即从-10°位置开始每次转0.1°),选取使ρ(u,v)最大的对应位置和旋转角度。
所述步骤4)具体包括以下步骤:
4-1)在可见光图像上选取红外图像最佳对应位置。将红外图像按照步骤3)的结果进行平移和旋转。然后分别在可见光图像和平移和旋转后的红外图像上进 行特征点检测。
4-2)将红外图像和可见光图像区域同时分为m×n个块。对于红外图每一个特征点
找到其在红外图对应的块
块
所对应的可见光图搜索范围记为
如图3所示。找到一个能够描述特征点相似程度的变量来评估
和
中任意一点的相似程度,如果相似程度最大值大于阈值t
1,则视为粗匹配点
F(s
first,s
second)≥t
2
则保留该匹配,其中t
2为阈值,F(s
flrst,s
second)用于描述s
first和s
second之间的关系。
所述步骤6)具体包括以下步骤:
6-1)使用随机抽样一致性(RANSAC)对点对做进一步筛选。
6-2)求解基础矩阵F和本质矩阵E:红外和可见光对应像素点对u
l、u
r和基础矩阵F的关系是:
将对应点坐标代入上式,构建齐次线性方程组求解F。
基础矩阵和本质矩阵的关系是:
其中,K
l、K
r分别是红外相机和可见光相机的内参矩阵。
6-3)从本质矩阵分解出旋转和平移关系:本质矩阵E与旋转R和平移t的关系如下:
E=[t]
×R
其中[t]
×表示t的叉乘矩阵。
将E做奇异值分解,得
定义两个矩阵
所以E写成以下两种形式
(1)E=UZU
TUWV
T
令[t]
×=UZU
T,R=UWV
T
(2)E=-UZU
TUW
TV
T
令[t]
×=-UZU
T,R=UW
TV
T
6-4)将分解出的旋转和平移关系叠加到原来的红外相机和可见光相机的位置关系里面。
本发明的有益效果:本发明解决了由于温湿度、震动等因素造成红外相机和可见光相机位置关系的改变。具有速度快、结果精确、操作简单等优点。
图1为整体流程示意图。
图2为双目校正流程示意图。
图3是分块匹配的示意图。其中,(a)为红外分块示意图,(b)为可见光分块示意图。
本发明旨在解决由于温湿度、震动等因素造成红外相机和可见光相机位置关系的改变。结合附图及实施例详细说明如下:
1)原图校正:将原图根据红外相机和可见光相机各自内参和原来的外参进行去畸变和双目校正。流程如图2所示。
1-1)计算图像的像素点对应的正规坐标系下的坐标。像素坐标系以图片的左上角为原点,其x轴和y轴分别与图像坐标系的x轴和y轴平行。像素坐标系的单位是像素,像素是图像显示的基本且不可分割的单位。正规坐标系是相机坐标系在平面Z=1的投影;而相机坐标系是以相机的中心作为图像坐标系的原点,以图片方向为XY轴方向,以垂直于图像为Z轴方向的坐标系。像素坐标与正规坐标的关系如下:
u=KX
其中,
表示图像的像素坐标;
表示相机的内参矩阵,f
x和f
y分别表示图像x方向和y方向的焦距(单位是像素),(c
x,c
y)表示相机的主点位置,即相机中心在图像上的对应位置;
是正规坐标系下的坐标。已知图像的像素坐标系以及相机的内参可以计算出像素点对应的正规坐标系,即
X=K
-1u
1-2)去除图像畸变:由于镜头生产工艺的限制,实际情况下的镜头会存在一些失真现象导致非线性的畸变。因此纯线性模型不能完全准确地描述成像几何 关系。非线性畸变可大致分为径向畸变和切向畸变。
图像径向畸变是图像像素点以畸变中心为中心点,沿着径向产生的位置偏差,从而导致图像中所成的像发生形变。径向畸变的大致表述如下:
x
d=x(1+k
1r
2+k
2r
4+k
3r
6)
y
d=y(1+k
1r
2+k
2r
4+k
3r
6)
其中,r
2=x
2+y
2,k
1、k
2、k
3为径向畸变参数。
切向畸变是由于摄像机制造上的缺陷使得透镜本身与图像平面不平行而产生的,可定量描述为:
x
d=x+(2p
1xy+p
2(r
2+2x
2))
y
d=y+(p
1(r
2+2y
2)+2p
2xy)
其中,p
1、p
2为切向畸变系数。
综上,畸变前后的坐标关系如下:
x
d=x(1+k
1r
2+k
2r
4+k
3r
6)+(2p
1xy+p
2(r
2+2x
2))
y
d=y(1+k
1r
2+k
2r
4+k
3r
6)+(p
1(r
2+2y
2)+2p
2xy)
其中,(x,y)是理想状态下的正规坐标,(x
d,y
d)是实际带有畸变的正规坐标。
1-3)根据原来两相机的旋转关系将两图转回来:已知原来两个相机之间的旋转矩阵R和平移向量t,使得
X
r=RX
l+t
其中,X
l表示红外相机的正规坐标,X
r表示可见光相机的正规坐标。将红外图像向R正方向旋转一半的角度,将可见光图像向R反方向旋转一半的角度;
1-4)根据公式u=KX将去畸旋转后的图像还原至像素坐标系。
2)场景边缘检测:将红外图像和可见光图像分别做边缘提取。
3)判断红外图像在可见光图像上的最佳对应位置:将红外图像的边缘和可见光图像的边缘做匹配,根据匹配结果确定对应位置。
3-1)使用归一化互相关匹配法来计算可见光边缘图和红外边缘图的互相关系数。
选取使ρ(u,v)最大的一组点{(u
k,v
k)}作为候选的对应位置。
3-2)对每一个侯选位置按照一个角度范围旋转多次:-10°~10°范围内分为200份,即从-10°位置开始每次转0.1°,选取使ρ(u,v)最大的对应位置和旋转角度。
4)提取并筛选出最佳的匹配点对:根据红外图像在可见光图像上的最佳对应位置提取并选择满足要求的匹配点对。
4-1)在可见光图像上选取红外图像最佳对应位置。将红外图像按照步骤3)的结果进行平移和旋转。然后分别在可见光图像和平移和旋转后的红外图像上进行特征点检测。
4-2)将红外图像和可见光图像区域同时分为m×n个块。对于红外图每一个特征点
找到其在红外图对应的块
块
所对应的可见光图搜索范围记为
如图3所示。找到一个能够描述特征点相似程度的变量来评估
和
中任意一点的相似程度,如果相似程度最大值大于阈值t
1,则视为粗匹配点
F(s
first,s
second)≥t
2
则保留该匹配,其中t
2为阈值,F(s
first,s
second)用于描述s
first和s
second之间的关系。
5)判断特征点覆盖区域:将图像分成m*n个格子,如果特征点覆盖到所有格子,则进行下一步,否则继续拍摄图像,提取特征点。
6)修正标定结果:使用所有特征点的图像坐标来计算校正之后的两相机之间的位置关系,然后与原来的外参相叠加。
6-1)使用随机抽样一致性(RANSAC)对点对做进一步筛选。
6-2)求解基础矩阵F和本质矩阵E:红外和可见光对应像素点对u
l、u
r和基础矩阵F的关系是:
可以将对应点坐标代入上式,构建齐次线性方程组求解F。
基础矩阵和本质矩阵的关系是:
其中,K
l、K
r分别是红外相机和可见光相机的内参矩阵。
6-3)从本质矩阵分解出旋转和平移关系:本质矩阵E与旋转R和平移t的关系如下:
E=[t]
×R
其中[t]
×表示t的叉乘矩阵。
将E做奇异值分解,得
定义两个矩阵
所以E可以写成以下两种形式
(1)E=UZU
TUWV
T
令[t]
×=UZU
T,R=UWV
T
(2)E=-UZU
TUW
TV
T
令[t]
×=-UZU
T,R=UW
TV
T
6-4)将分解出的旋转和平移关系叠加到原来的红外相机和可见光相机的位置关系里面。
Claims (8)
- 基于边缘特征的多光谱相机外参自校正算法,其特征在于,步骤如下:1)原图校正:将原图根据红外相机和可见光相机各自内参和原来的外参进行去畸变和双目校正;2)场景边缘检测:将红外图像和可见光图像分别做边缘提取;3)判断红外图像在可见光图像上的最佳对应位置:将红外图像的边缘和可见光图像的边缘做匹配,根据匹配结果确定对应位置;4)提取并筛选出最佳的匹配点对:根据红外图像在可见光图像上的最佳对应位置提取并选择满足要求的匹配点对;5)判断特征点覆盖区域:将图像分成m*n个格子,当特征点覆盖到所有格子时,则进行下一步,否则继续拍摄图像,提取特征点;6)修正标定结果:使用所有特征点的图像坐标来计算校正之后的两相机之间的位置关系,然后与原来的外参相叠加。
- 根据权利要求1所述的基于边缘特征的多光谱相机外参自校正算法,其特征在于,所述步骤1)的具体过程如下:1-1)计算图像的像素点对应的正规坐标系下的坐标像素坐标系以图片的左上角为原点,其x轴和y轴分别与图像坐标系的x轴和y轴平行,像素坐标系的单位是像素;正规坐标系是相机坐标系在平面Z=1的投影;而相机坐标系是以相机的中心作为图像坐标系的原点,以图片方向为XY轴方向,以垂直于图像为Z轴方向的坐标系;像素坐标与正规坐标的关系如下:u=KX其中, 表示图像的像素坐标; 表示相机的内参矩阵,f x和f y分别表示图像x方向和y方向的焦距,单位是像素,(c x,c y)表示相机的主 点位置,即相机中心在图像上的对应位置; 是正规坐标系下的坐标;已知图像的像素坐标系以及相机的内参计算出像素点对应的正规坐标系,即X=K -1u;1-2)去除图像畸变图像径向畸变表述如下:x d=x(1+k 1r 2+k 2r 4+k 3r 6)y d=y(1+k 1r 2+k 2r 4+k 3r 6)其中,r 2=x 2+y 2,k 1、k 2、k 3为径向畸变参数;图像切向畸变表述如下:x d=x+(2p 1xy+p 2(r 2+2x 2))y d=y+(p 1(r 2+2y 2)+2p 2xy)其中,p 1、p 2为切向畸变系数;畸变前后的坐标关系如下:x d=x(1+k 1r 2+k 2r 4+k 3r 6)+(2p 1xy+p 2(r 2+2x 2))y d=y(1+k 1r 2+k 2r 4+k 3r 6)+(p 1(r 2+2y 2)+2p 2xy)其中,(x,y)是理想状态下的正规坐标,(x d,y d)是实际带有畸变的正规坐标;1-3)根据原来两相机的旋转关系将两图转回来:已知原来两个相机之间的旋转矩阵R和平移向量t,使得:X r=RX l+t其中,X l表示红外相机的正规坐标,X r表示可见光相机的正规坐标;将红外图像向R正方向旋转一半的角度,将可见光图像向R反方向旋转一半的角度;1-4)根据公式u=KX将去畸旋转后的图像还原至像素坐标系。
- 根据权利要求1或2所述的基于边缘特征的多光谱相机外参自校正算法,其特征在于,所述步骤4)具体包括以下步骤:4-1)在可见光图像上选取红外图像最佳对应位置;将红外图像按照步骤3)的结果进行平移和旋转;然后分别在可见光图像和平移和旋转后的红外图像上进行特征点检测;4-2)将红外图像和可见光图像区域同时分为m×n个块;对于红外图每一个特征点 找到其在红外图对应的块 块 所对应的可见光图搜索范围记为 如图3所示;找到一个能够描述特征点相似程度的变量来评估 和 中任意一点的相似程度,如果相似程度最大值大于阈值t 1,则视为粗匹配点F(s first,s second)≥t 2则保留该匹配,其中t 2为阈值,F(s first,s second)用于描述s first和s second之间的关系;
- 根据权利要求3所述的基于边缘特征的多光谱相机外参自校正算法,其特征在于,所述步骤4)具体包括以下步骤:4-1)在可见光图像上选取红外图像最佳对应位置;将红外图像按照步骤3)的结果进行平移和旋转;然后分别在可见光图像和平移和旋转后的红外图像上进行特征点检测;4-2)将红外图像和可见光图像区域同时分为m×n个块;对于红外图每一个特征点 找到其在红外图对应的块 块 所对应的可见光图搜索范围记为 如图3所示;找到一个能够描述特征点相似程度的变量来评估 和 中任意一点的相似程度,如果相似程度最大值大于阈值t 1,则视为粗匹配点F(s first,s second)≥t 2则保留该匹配,其中t 2为阈值,F(s first,s second)用于描述s first和s second之间的关系;
- 根据权利要求1、2或5所述的基于边缘特征的多光谱相机外参自校正算法,其特征在于,所述步骤6)具体包括以下步骤:6-1)使用随机抽样一致性对点对做进一步筛选;6-2)求解基础矩阵F和本质矩阵E:红外和可见光对应像素点对u l、u r和基础矩阵F的关系是:将对应点坐标代入上式,构建齐次线性方程组求解F;基础矩阵和本质矩阵的关系是:其中,K l、K r分别是红外相机和可见光相机的内参矩阵;6-3)从本质矩阵分解出旋转和平移关系:本质矩阵E与旋转R和平移t的关系如下:E=[t] ×R其中[t] ×表示t的叉乘矩阵;将E做奇异值分解,得定义两个矩阵所以E写成以下两种形式(1)E=UZU TUWV T令[t] ×=UZU T,R=UWV T(2)E=-UZU TUW TV T令[t] ×=-UZU T,R=UW TV T6-4)将分解出的旋转和平移关系叠加到原来的红外相机和可见光相机的位置关系里面。
- 根据权利要求3所述的基于边缘特征的多光谱相机外参自校正算法,其特征在于,所述步骤6)具体包括以下步骤:6-1)使用随机抽样一致性对点对做进一步筛选;6-2)求解基础矩阵F和本质矩阵E:红外和可见光对应像素点对u l、u r和基础矩阵F的关系是:将对应点坐标代入上式,构建齐次线性方程组求解F;基础矩阵和本质矩阵的关系是:其中,K l、K r分别是红外相机和可见光相机的内参矩阵;6-3)从本质矩阵分解出旋转和平移关系:本质矩阵E与旋转R和平移t的关系如下:E=[t] ×R其中[t] ×表示t的叉乘矩阵;将E做奇异值分解,得定义两个矩阵所以E写成以下两种形式(1)E=UZU TUWV T令[t] ×=UZU T,R=UWV T(2)E=-UZU TUW TV T令[t] ×=-UZU T,R=UW TV T6-4)将分解出的旋转和平移关系叠加到原来的红外相机和可见光相机的位置关系里面。
- 根据权利要求4所述的基于边缘特征的多光谱相机外参自校正算法,其特征在于,所述步骤6)具体包括以下步骤:6-1)使用随机抽样一致性对点对做进一步筛选;6-2)求解基础矩阵F和本质矩阵E:红外和可见光对应像素点对u l、u r和基础矩阵F的关系是:将对应点坐标代入上式,构建齐次线性方程组求解F;基础矩阵和本质矩阵的关系是:其中,K l、K r分别是红外相机和可见光相机的内参矩阵;6-3)从本质矩阵分解出旋转和平移关系:本质矩阵E与旋转R和平移t的关系如下:E=[t] ×R其中[t] ×表示t的叉乘矩阵;将E做奇异值分解,得定义两个矩阵所以E写成以下两种形式(1)E=UZU TUWV T令[t] ×=UZU T,R=UWV T(2)E=-UZU TUW TV T令[t] ×=-UZU T,R=UW TV T6-4)将分解出的旋转和平移关系叠加到原来的红外相机和可见光相机的位置关系里面。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/279,461 US11398053B2 (en) | 2019-11-22 | 2020-03-05 | Multispectral camera external parameter self-calibration algorithm based on edge features |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911152421.5 | 2019-11-22 | ||
CN201911152421.5A CN110969667B (zh) | 2019-11-22 | 2019-11-22 | 基于边缘特征的多光谱相机外参自校正算法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021098080A1 true WO2021098080A1 (zh) | 2021-05-27 |
Family
ID=70031191
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/077951 WO2021098080A1 (zh) | 2019-11-22 | 2020-03-05 | 基于边缘特征的多光谱相机外参自校正算法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US11398053B2 (zh) |
CN (1) | CN110969667B (zh) |
WO (1) | WO2021098080A1 (zh) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113327290A (zh) * | 2021-06-07 | 2021-08-31 | 深圳市商汤科技有限公司 | 双目模组标定方法、装置、存储介质及电子设备 |
CN113628261A (zh) * | 2021-08-04 | 2021-11-09 | 国网福建省电力有限公司泉州供电公司 | 一种电力巡检场景下的红外与可见光图像配准方法 |
CN113744349A (zh) * | 2021-08-31 | 2021-12-03 | 湖南航天远望科技有限公司 | 一种红外光谱图像测量对准方法、装置及介质 |
CN114255197A (zh) * | 2021-12-27 | 2022-03-29 | 西安交通大学 | 一种红外与可见光图像自适应融合对齐方法及系统 |
CN117474953A (zh) * | 2023-11-16 | 2024-01-30 | 玩出梦想(上海)科技有限公司 | 一种描述子匹配方法及存储介质 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112729558B (zh) * | 2020-12-25 | 2022-04-22 | 武汉高德智感科技有限公司 | 一种红外热成像装置的测试调整系统及方法 |
CN112986312B (zh) * | 2021-02-05 | 2023-02-03 | 郑州大学 | 一种利用二维数字图像技术测量注塑制品热应力的方法 |
CN112907680B (zh) * | 2021-02-22 | 2022-06-14 | 上海数川数据科技有限公司 | 一种可见光与红外双光相机旋转矩阵自动校准方法 |
CN112819901B (zh) * | 2021-02-26 | 2024-05-14 | 中国人民解放军93114部队 | 基于图像边缘信息的红外相机自标定方法 |
CN116385502B (zh) * | 2023-03-09 | 2024-04-19 | 武汉大学 | 一种基于几何约束下区域搜索的图像配准方法 |
CN118212591B (zh) * | 2024-05-16 | 2024-08-06 | 杭州巨岩欣成科技有限公司 | 多映射坐标自动对应方法、装置、计算机设备及存储介质 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100302366A1 (en) * | 2009-05-29 | 2010-12-02 | Zhao Bingyan | Calibration method and calibration device |
CN105701827A (zh) * | 2016-01-15 | 2016-06-22 | 中林信达(北京)科技信息有限责任公司 | 可见光相机与红外相机的参数联合标定方法及装置 |
KR101806045B1 (ko) * | 2016-10-17 | 2017-12-07 | 한국기초과학지원연구원 | 적외선 및 가시광 카메라의 실시간 이미지 합성 장치 및 그 제어 방법 |
CN108492335A (zh) * | 2018-03-27 | 2018-09-04 | 长春理工大学 | 一种双相机透视畸变校正方法及系统 |
CN109146930A (zh) * | 2018-09-20 | 2019-01-04 | 河海大学常州校区 | 一种电力机房设备红外与可见光图像配准方法 |
CN109389630A (zh) * | 2018-09-30 | 2019-02-26 | 北京精密机电控制设备研究所 | 可见光图像与红外图像特征点集确定、配准方法及装置 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750697B (zh) * | 2012-06-08 | 2014-08-20 | 华为技术有限公司 | 一种参数标定方法及装置 |
DE112017007685B4 (de) * | 2017-07-24 | 2021-07-15 | Mitsubishi Electric Corporation | Anzeigesteuervorrichtung, Anzeigesystem und Anzeigesteuerverfahren |
CN109523583B (zh) * | 2018-10-09 | 2021-07-13 | 河海大学常州校区 | 一种基于反馈机制的电力设备红外与可见光图像配准方法 |
-
2019
- 2019-11-22 CN CN201911152421.5A patent/CN110969667B/zh active Active
-
2020
- 2020-03-05 WO PCT/CN2020/077951 patent/WO2021098080A1/zh active Application Filing
- 2020-03-05 US US17/279,461 patent/US11398053B2/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100302366A1 (en) * | 2009-05-29 | 2010-12-02 | Zhao Bingyan | Calibration method and calibration device |
CN105701827A (zh) * | 2016-01-15 | 2016-06-22 | 中林信达(北京)科技信息有限责任公司 | 可见光相机与红外相机的参数联合标定方法及装置 |
KR101806045B1 (ko) * | 2016-10-17 | 2017-12-07 | 한국기초과학지원연구원 | 적외선 및 가시광 카메라의 실시간 이미지 합성 장치 및 그 제어 방법 |
CN108492335A (zh) * | 2018-03-27 | 2018-09-04 | 长春理工大学 | 一种双相机透视畸变校正方法及系统 |
CN109146930A (zh) * | 2018-09-20 | 2019-01-04 | 河海大学常州校区 | 一种电力机房设备红外与可见光图像配准方法 |
CN109389630A (zh) * | 2018-09-30 | 2019-02-26 | 北京精密机电控制设备研究所 | 可见光图像与红外图像特征点集确定、配准方法及装置 |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113327290A (zh) * | 2021-06-07 | 2021-08-31 | 深圳市商汤科技有限公司 | 双目模组标定方法、装置、存储介质及电子设备 |
CN113327290B (zh) * | 2021-06-07 | 2022-11-11 | 深圳市商汤科技有限公司 | 双目模组标定方法、装置、存储介质及电子设备 |
CN113628261A (zh) * | 2021-08-04 | 2021-11-09 | 国网福建省电力有限公司泉州供电公司 | 一种电力巡检场景下的红外与可见光图像配准方法 |
CN113628261B (zh) * | 2021-08-04 | 2023-09-22 | 国网福建省电力有限公司泉州供电公司 | 一种电力巡检场景下的红外与可见光图像配准方法 |
CN113744349A (zh) * | 2021-08-31 | 2021-12-03 | 湖南航天远望科技有限公司 | 一种红外光谱图像测量对准方法、装置及介质 |
CN114255197A (zh) * | 2021-12-27 | 2022-03-29 | 西安交通大学 | 一种红外与可见光图像自适应融合对齐方法及系统 |
CN114255197B (zh) * | 2021-12-27 | 2024-04-05 | 西安交通大学 | 一种红外与可见光图像自适应融合对齐方法及系统 |
CN117474953A (zh) * | 2023-11-16 | 2024-01-30 | 玩出梦想(上海)科技有限公司 | 一种描述子匹配方法及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
US11398053B2 (en) | 2022-07-26 |
CN110969667B (zh) | 2023-04-28 |
US20220036589A1 (en) | 2022-02-03 |
CN110969667A (zh) | 2020-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021098080A1 (zh) | 基于边缘特征的多光谱相机外参自校正算法 | |
WO2021098081A1 (zh) | 基于轨迹特征配准的多光谱立体相机自标定算法 | |
WO2021098083A1 (zh) | 基于显著特征的多光谱相机动态立体标定算法 | |
CN110969668B (zh) | 一种长焦双目相机的立体标定算法 | |
CN110956661B (zh) | 基于双向单应矩阵的可见光与红外相机动态位姿计算方法 | |
WO2021139176A1 (zh) | 基于双目摄像机标定的行人轨迹跟踪方法、装置、计算机设备及存储介质 | |
CN110969669B (zh) | 基于互信息配准的可见光与红外相机联合标定方法 | |
CN110992409B (zh) | 基于傅里叶变换配准的多光谱立体相机动态配准方法 | |
CN111243033B (zh) | 一种优化双目相机外参数的方法 | |
CN110910456B (zh) | 基于Harris角点互信息匹配的立体相机动态标定方法 | |
CN110880191B (zh) | 基于直方图均衡化的红外立体相机动态外参计算方法 | |
CN112470192A (zh) | 双摄像头标定方法、电子设备、计算机可读存储介质 | |
CN115222785A (zh) | 一种基于双目标定的红外与可见光图像配准方法 | |
CN110910457B (zh) | 基于角点特征的多光谱立体相机外参计算方法 | |
CN111127353A (zh) | 一种基于块配准和匹配的高动态图像去鬼影方法 | |
Zhang et al. | Building a stereo and wide-view hybrid RGB/FIR imaging system for autonomous vehicle | |
CN111833384B (zh) | 一种可见光和红外图像快速配准方法及装置 | |
CN108805937B (zh) | 一种单相机偏振信息预测方法 | |
CN112396687B (zh) | 基于红外微偏振片阵列的双目立体视觉三维重建系统及方法 | |
Mo et al. | A Robust Infrared and Visible Image Registration Method for Dual Sensor UAV System | |
Lu et al. | A Digital Orthophoto Map Generation Method Based on a Small Amount of Low Overlap Unmanned Aerial Vehicle Images | |
CN116958216B (zh) | 一种基于特征点距离估计的多光谱图像通道间配准方法 | |
CN115115689B (zh) | 一种多波段光谱的深度估计方法 | |
CN116030106A (zh) | 基于相位特征与边缘特征的红外与可见光图像配准方法 | |
Ma et al. | Image Dehazing With Polarization Boundary Constraints of Transmission |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20890840 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20890840 Country of ref document: EP Kind code of ref document: A1 |