CN115034992A - Long-wave infrared image denoising method - Google Patents
Long-wave infrared image denoising method Download PDFInfo
- Publication number
- CN115034992A CN115034992A CN202210673122.1A CN202210673122A CN115034992A CN 115034992 A CN115034992 A CN 115034992A CN 202210673122 A CN202210673122 A CN 202210673122A CN 115034992 A CN115034992 A CN 115034992A
- Authority
- CN
- China
- Prior art keywords
- image
- long
- wave infrared
- singular
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000011159 matrix material Substances 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 17
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 8
- 230000003247 decreasing effect Effects 0.000 claims description 6
- 230000017105 transposition Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 5
- 238000005286 illumination Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 101150049349 setA gene Proteins 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention discloses a long-wave infrared image denoising method, which comprises the following steps: decomposing a long-wave infrared image with high noise and low contrast acquired by long-wave infrared by using a singular value decomposition algorithm through SVD (singular value decomposition), zeroing the maximum singular value of a characteristic value matrix obtained by decomposition, calculating an average singular value, replacing the rest singular values except the head singular value with the average singular value, giving sequentially descending weight to each position of the singular value according to the position, reconstructing the characteristic value matrix, reconstructing the long-wave infrared image matrix, and finally, further denoising the reconstructed long-wave infrared image by using a median filtering algorithm. In the aspect of image processing, the invention overcomes the defects of noise and low contrast of the long-wave infrared image per se; in the aspect of feature processing, the method overcomes the problems of feature mis-tracking and the like caused by the self defects of the long-wave infrared image, and provides a feasible scheme for the subsequent SLAM method to operate in a low-light environment.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a long-wave infrared image denoising method.
Background
The vision-based Simultaneous Localization and Mapping (SLAM) system is used for estimating current pose information of a carrier by utilizing environmental information acquired by a camera and simultaneously constructing a map model of an explored area. With the development of the fields of mechanical hardware, computer vision and the like, the types of cameras are increasing continuously, wherein the visible light camera is widely applied to the SLAM system by virtue of the advantages of low cost, light weight and the like. Currently, the study of visible light SLAM has achieved good results. Under the condition of a stable light source, the SLAM system based on the visible light camera has good performance, but when the environment has non-ideal environmental conditions such as illumination change, no light source or fog and the like, the positioning and mapping accuracy of the SLAM system designed based on the visible light camera is seriously influenced, so that the synchronous positioning and mapping tasks cannot be completed.
Compared with a visible light camera, the long-wave infrared imaging device can sense infrared information in the environment to image, the imaging result reflects the temperature distribution of the surrounding environment, can image even in the environment without illumination at night, and is less influenced by illumination change and severe weather. Therefore, the SLAM based on the long-wave infrared can effectively solve the problem that the system robustness of the visible light camera is poor under the conditions of no light, heavy fog and the like. However, due to the influence of the long-wave infrared imaging principle, the imaging result has the problems of low signal-to-noise ratio, texture loss, low contrast and the like, so that the characteristics of the SLAM front end are extracted wrongly and tracked wrongly, and the performance of the SLAM system based on the long-wave infrared is directly influenced.
Therefore, in order to reduce the influence of the long-wave infrared on the performance of the SLAM system caused by the defects, the invention provides the long-wave infrared image denoising method, the SVD method is used for decomposing the long-wave infrared collected image, the characteristic value matrix obtained by decomposition is processed, the noise influence is reduced, the image contrast is enhanced, the image characteristic extraction and tracking accuracy is improved, reliable data correlation is provided for a subsequent SLAM system, and the positioning accuracy and the robustness are improved.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a long-wave infrared image denoising method, which can process long-wave infrared data with high noise and low contrast in a weak illumination environment and provide a data association basis for subsequent synchronous positioning and image building functions.
The purpose of the invention is realized by the following technical scheme: a long-wave infrared image denoising method comprises the following steps:
step (1): under the weak light environment, a long-wave infrared camera C with a calibrated internal reference is arranged, and at t 0 Constantly acquiring long-wave infrared image I with noise interference 0 Image I 0 The size is M N, M and N are the height and width of the image respectively;
step (2): decomposition of long-wave infrared images I using SVD method 0 Obtaining a corresponding characteristic value matrix sigma, processing the characteristic value matrix sigma based on the definition of SVD decomposition, and processing the long-wave infrared image I 0 Reconstructing to obtain a reconstructed long-wave infrared image I 1 ；
And (3): processing a reconstructed image I using a median filtering method 1 Obtaining a de-noised long-wave infrared image I 2 。
Further, the process of processing the eigenvalue matrix Σ in step (2) is: setting the maximum singular value of the eigenvalue matrix sigma to zero, calculating the average singular value, replacing the singular values except the first singular value with the average singular value, and giving sequentially decreasing weight to each singular value according to the position to form a new eigenvalue matrix.
Further, the process of processing the eigenvalue matrix Σ in step (2) is:
decomposition of long-wave infrared images I using SVD method 0 Obtaining:
wherein, the matrix U is M × M, and is composed of Left Singular Vector (LSV) U i Composition is carried out; the matrix V has a size of NxN and is composed of Right Singular Vectors (RSV) V i Composition is carried out; the matrix sigma is of size M × N, and its diagonal elements represent singular values s of the image i ，s i Arranging the characteristic value matrixes from large to small on a diagonal line of a sigma of the characteristic value matrix according to a descending order, wherein T represents transposition operation; singular values s from the perspective of the image matrix i Representing the brightness, singularity, of the image as a wholeQuantity u i 、v i Representing texture features in the image, wherein the maximum singular value can reflect feature information with high proportion in the image, and the rest singular values can reflect feature information with low proportion in the image;
processing the eigenvalue matrix sigma obtained by decomposition to make the maximum singular value s 1 0 and calculating the mean singular value s avg
Replacing all singular values except the first singular value in the eigenvalue matrix sigma with average singular values, and giving sequentially decreasing weights according to positions to obtain singular values s' i Constructed new eigenvalue matrix sigma'
Using the new characteristic value matrix sigma' to reconstruct an image matrix to obtain a reconstructed long-wave infrared image I 1
I 1 ＝[U][Σ′][V] T 。 (4)
Further, the image I is processed by median filtering in the step (3) 1 The process comprises the following steps:
with a sliding window of size K x K, which is arranged in the image I 1 Up-sliding, in-window processed pixel value p i ' is
Wherein, set
As an image I 1 Original pixel value, Median function is to take Median in the set; the window is slid on the whole image according to columns, the pixel values in the window are processed by the median value to obtain a processed image I 2 。
The invention has the beneficial effects that: according to the method, a singular value decomposition algorithm is utilized, a long-wave infrared image with high noise and low contrast acquired by long-wave infrared is decomposed through SVD, the maximum singular value of a characteristic value matrix obtained through decomposition is set to be zero, an average singular value is calculated, the singular values except the first singular value are replaced by the average singular value, each singular value is given with sequentially descending weight according to the position, the characteristic value matrix is reconstructed, then the long-wave infrared image matrix is reconstructed, and finally the reconstructed long-wave infrared image is denoised through a median filtering algorithm. In the aspect of image processing, the invention overcomes the defects of self height noise and low contrast of the long-wave infrared image; in the aspect of feature processing, the method overcomes the problems of feature mis-tracking and the like caused by the self defects of the long-wave infrared image, and provides a feasible scheme for the subsequent SLAM method to operate in a low-light environment.
Drawings
In order to more clearly explain the technical solution of the present invention, the drawings needed in the embodiments will be briefly described below, and it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope of the present invention. Like components are numbered similarly in the various figures.
FIG. 1 is a flow chart of a long-wave infrared image denoising method;
FIG. 2 is a flowchart of a specific algorithm for reconstructing a long-wave infrared image by SVD in the using process of a long-wave infrared image denoising method;
FIG. 3 is a flowchart of a specific algorithm of median filtering in the process of using the denoising method for a long-wave infrared image;
FIG. 4 is a diagram of optical flow tracking effect of an original long-wave infrared image;
FIG. 5 is a diagram showing the optical flow tracking effect of the reconstructed long-wave infrared image.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Various embodiments of the present disclosure will be described more fully hereinafter. The present disclosure is capable of various embodiments and of modifications and variations therein. However, it should be understood that: there is no intention to limit the various embodiments of the disclosure to the specific embodiments disclosed herein, but rather, the disclosure is to cover all modifications, equivalents, and/or alternatives falling within the spirit and scope of the various embodiments of the disclosure.
Hereinafter, the terms "including", "having", and their derivatives, which may be used in various embodiments of the present invention, are only intended to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be construed as first excluding the existence of, or adding to, one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.
Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as those defined in commonly used dictionaries) should be interpreted as having a meaning that is consistent with their contextual meaning in the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in various embodiments of the present invention.
The invention provides a long-wave infrared image denoising method, which is further described in detail below with reference to embodiments in order to make the purpose, technical scheme and advantages of the invention more clear. Fig. 1 is a schematic flowchart of a method for denoising a long-wave infrared image in an embodiment, where the method includes:
step 110: under the severe environment of weak light such as fog, a long-wave infrared camera C with calibrated internal reference is arranged at t 0 Constantly acquiring long-wave infrared image I with noise interference 0 Image I 0 The size is 240 × 640;
step 120: decomposition of long-wave infrared images I using SVD method 0 Obtaining a corresponding characteristic value matrix sigma, processing the characteristic value matrix sigma based on the definition of SVD decomposition, and processing the long-wave infrared image I 0 Reconstructing to obtain a reconstructed long-wave infrared image I 1 ；
Step 130: processing a reconstructed image I using a median filtering method 1 Obtaining a denoised long-wave infrared image I 2 。
Further, in step 120, the maximum singular value of the eigenvalue matrix Σ is set to zero, the average singular value is calculated, the remaining singular values except the first singular value are replaced with the average singular value, and each singular value is given a sequentially decreasing weight according to the position to form a new eigenvalue matrix, which specifically includes the following sub-steps as shown in fig. 2:
step 121, decomposing the long-wave infrared image I by using an SVD method 0 Obtaining:
wherein, the matrix U is 240 × 240, and is composed of Left Singular Vector (LSV) U i Composition is carried out; the size of matrix V is 320 × 320, and is composed of Right Singular Vector (RSV) V i Composition is carried out; the matrix Σ has a size of 240 × 320, and its diagonal elements represent the singular values s of the image i ，s i And arranging the characteristic value matrixes from large to small on a diagonal line of the characteristic value matrix sigma in a descending order. Singular values s from the perspective of the image matrix i Representing the brightness of the image as a whole, singular vectors u i 、 v i The texture features in the image are represented, meanwhile, the maximum singular value can reflect the feature information with higher proportion in the image, and the rest singular values can reflect the feature information with lower proportion in the image.
Step 122, processing the eigenvalue matrix sigma obtained by decomposition to make the maximum singular value s of the matrix sigma 1 ＝0。
Step 123, calculating the average singular value s avg
Step 124, replacing all singular values except the first singular value in the eigenvalue matrix sigma with the average singular value, and giving successively decreasing weights according to the positions to obtain the singular value s i 'New eigenvalue matrix of composition'
Step 125, reconstructing an image matrix by using the new eigenvalue matrix Σ', so as to obtain a reconstructed long-wave infrared image I 1
I 1 ＝[U][Σ′][V] T (4)
Further, in step 130, the median filter processes the image I 1 As shown in fig. 3, includes:
step 131, create a sliding window of size 3 × 3, the window being listed in image I 1 And sliding upwards to traverse the image.
At step 132, the processed pixel value p 'within the window is computed' i
p′ i ＝Median{p 1 ,...,p 9 },i＝1,...,9 (5)
Wherein, the set { p 1 ,...,p 9 Is an image I in the window 1 The original pixel value, the Median function, is to take the Median of the set.
Step 133, the window slides across the entire image in columns, the median processes the pixel values in the window, and exits after the traversal is completed to obtain processed image I 2 。
To further illustrate the effectiveness of the present invention in denoising, an original image I is processed 0 And reconstructed image I 2 At the same time, the optical flow tracking between the original image and the rotated image is performed by rotating the original image clockwise by 10 °, using the lk (lucas kanade) optical flow method, and the results are shown in fig. 4 and 5. The error of the tracking point is calculated using the root mean square error RMSE, and the results are shown in the following table:
| image(s) | Tracking point error/pixel |
| I 0 | 50.1044 |
| I 2 | 3.2068 |
Original long-wave infrared image I 0 The long-wave infrared image I processed by the method has large error in characteristic tracking due to the problems of noise interference and low contrast 2 The method has the advantages of smaller error in the aspect of feature tracking, high precision and system robustness, capability of providing basic data association for realizing the positioning and mapping functions of subsequent automatic driving and verification of the effectiveness of the method.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (4)
1. A long-wave infrared image denoising method is characterized by comprising the following steps:
step (1): under the weak light environment, a long-wave infrared camera C with a calibrated internal reference is arranged, and at t 0 Constantly acquiring long-wave infrared image I with noise interference 0 Picture I 0 The size is M N, M and N are the height and width of the image respectively;
step (2): decomposition of long-wave infrared images I using SVD method 0 Obtaining a corresponding characteristic value matrix sigma, processing the characteristic value matrix sigma based on the definition of SVD decomposition, and processing the long-wave infrared image I 0 Reconstructing to obtain a reconstructed long-wave infrared image I 1 ；
And (3): processing a reconstructed image I using a median filtering method 1 Obtaining a de-noised long-wave infrared image I 2 。
2. The method of claim 1, wherein the processing of the eigenvalue matrix Σ in step (2) is: setting the maximum singular value of the eigenvalue matrix sigma to zero, calculating the average singular value, replacing the singular values except the first singular value with the average singular value, and giving sequentially decreasing weight to each singular value according to the position to form a new eigenvalue matrix.
3. The method of claim 2, wherein the processing of the eigenvalue matrix Σ in step (2) is:
decomposition of long-wave infrared images I using SVD method 0 Obtaining:
wherein,the matrix U has a size of M × M and is composed of left singular vectors U i Composition is carried out; the matrix V is NXN in size and is composed of right singular vectors V i Composition is carried out; the matrix Σ has a size mxn and diagonal elements representing the singular values s of the image i ，s i Arranging the characteristic value matrixes sigma diagonal in sequence from large to small according to a descending order, wherein T represents transposition operation; from the perspective of the image matrix, singular values s i Representing the brightness of the image as a whole, singular vectors u i 、v i Representing texture features in the image, wherein the maximum singular value can reflect feature information with high ratio in the image, and the rest singular values can reflect feature information with low ratio in the image;
processing the eigenvalue matrix sigma obtained by decomposition to make the maximum singular value s 1 0 and calculating the mean singular value s avg
Replacing all singular values except the first singular value in the eigenvalue matrix sigma with the average singular value, and giving sequentially decreasing weights according to the positions to obtain singular values s' i Constructed new eigenvalue matrix sigma'
Using the new characteristic value matrix sigma' to reconstruct an image matrix to obtain a reconstructed long-wave infrared image I 1
I 1 ＝[U][Σ′][V] T 。 (4)
4. The method of claim 1, wherein the image I is median filtered in step (3) 1 The process comprises the following steps:
with a sliding window of size K x K, which is arranged in the image I 1 Up-sliding, in-window processed pixel value p' i Is composed of
Wherein, aggregate
As an image I 1 Original pixel value, Median function is to take Median in the set; the window is slid on the whole image according to columns, the pixel values in the window are processed by the median value to obtain a processed image I 2 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210673122.1A CN115034992A (en) | 2022-06-14 | 2022-06-14 | Long-wave infrared image denoising method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210673122.1A CN115034992A (en) | 2022-06-14 | 2022-06-14 | Long-wave infrared image denoising method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115034992A true CN115034992A (en) | 2022-09-09 |
Family
ID=83124510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210673122.1A Pending CN115034992A (en) | 2022-06-14 | 2022-06-14 | Long-wave infrared image denoising method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115034992A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601232A (en) * | 2022-12-14 | 2023-01-13 | 华东交通大学（Cn） | Color image decoloring method and system based on singular value decomposition |
-
2022
- 2022-06-14 CN CN202210673122.1A patent/CN115034992A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601232A (en) * | 2022-12-14 | 2023-01-13 | 华东交通大学（Cn） | Color image decoloring method and system based on singular value decomposition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110108258B (en) | Monocular vision odometer positioning method | |
| CN108615027B (en) | Method for counting video crowd based on long-term and short-term memory-weighted neural network | |
| Chatterjee et al. | Is denoising dead? | |
| CN108288270B (en) | Target detection method based on channel pruning and full convolution deep learning | |
| CN105976330B (en) | A kind of embedded greasy weather real time video image stabilization | |
| WO2021098083A1 (en) | Multispectral camera dynamic stereo calibration algorithm based on salient feature | |
| CN107507135B (en) | Image reconstruction method based on coding aperture and target | |
| CN111914698B (en) | Human body segmentation method, segmentation system, electronic equipment and storage medium in image | |
| CN110163818A (en) | A kind of low illumination level video image enhancement for maritime affairs unmanned plane | |
| CN111160229B (en) | SSD network-based video target detection method and device | |
| CN105654440B (en) | Quick single image defogging algorithm based on regression model and system | |
| CN110825900A (en) | Training method of feature reconstruction layer, reconstruction method of image features and related device | |
| CN109685045A (en) | A kind of Moving Targets Based on Video Streams tracking and system | |
| CN113724379B (en) | Three-dimensional reconstruction method and device for fusing image and laser point cloud | |
| CN102170526A (en) | Method for calculation of defocus fuzzy core and sharp processing of defocus fuzzy image of defocus fuzzy core | |
| Liang et al. | Deep bilateral retinex for low-light image enhancement | |
| CN107392211B (en) | Salient target detection method based on visual sparse cognition | |
| CN116310095A (en) | Multi-view three-dimensional reconstruction method based on deep learning | |
| CN115034992A (en) | Long-wave infrared image denoising method | |
| CN107845120B (en) | PET image reconstruction method, system, terminal and readable storage medium | |
| Ye et al. | Optical and SAR image fusion based on complementary feature decomposition and visual saliency features | |
| Kumari et al. | A new fast and efficient dehazing and defogging algorithm for single remote sensing images | |
| CN115358962B (en) | End-to-end visual odometer method and device | |
| CN102129687B (en) | Self-adapting target tracking method based on local background subtraction under dynamic scene | |
| CN110895790A (en) | Scene image super-resolution method based on posterior degradation information estimation |
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 |