CN113052833A - Non-vision field imaging method based on infrared thermal radiation - Google Patents
Non-vision field imaging method based on infrared thermal radiation Download PDFInfo
- Publication number
- CN113052833A CN113052833A CN202110421383.XA CN202110421383A CN113052833A CN 113052833 A CN113052833 A CN 113052833A CN 202110421383 A CN202110421383 A CN 202110421383A CN 113052833 A CN113052833 A CN 113052833A
- Authority
- CN
- China
- Prior art keywords
- image
- operator
- diffuse reflection
- thermal radiation
- point
- 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
- 238000003384 imaging method Methods 0.000 title claims abstract description 35
- 230000005855 radiation Effects 0.000 title claims abstract description 25
- 238000001931 thermography Methods 0.000 claims abstract description 37
- 230000000007 visual effect Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 7
- 230000001629 suppression Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a non-vision field imaging method based on infrared thermal radiation, which utilizes the far infrared thermal radiation characteristic of a hidden object, collects mirror reflection information generated by the far infrared thermal radiation on a wall by a thermal imaging camera and images by a thermosensitive infrared CCD. Firstly, converting a thermal imaging picture into a gray-scale image, then carrying out edge recognition on the gray-scale image by using an improved Canny algorithm, and finally recognizing the shape information of the hidden object to realize non-visual field imaging. The passive non-visual field imaging method has great cost advantage compared with active non-visual field imaging, fully utilizes the specular reflection component, optimizes the imaging result by utilizing the image processing technology, and has good application effect in some scenes.
Description
Technical Field
The invention relates to the technical field of non-visual field imaging, in particular to a non-visual field imaging method based on infrared thermal radiation.
Background
Non-field of view imaging techniques refer to techniques that image a scene that is outside the field of view of the imaging device. The two categories can be mainly classified into active non-visual field imaging and passive non-visual field imaging. The start is earlier abroad, and various colleges and universities and research institutes in China also have certain investment successively. Non-visual field imaging has great application potential in medical treatment, military affairs, disaster relief and the like, so the research in recent years is more and more popular.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a non-visual field imaging method based on infrared thermal radiation, which is a passive non-visual field imaging method based on infrared thermal radiation imaging, has a great cost advantage compared with active non-visual field imaging, fully utilizes a specular reflection component, and optimizes an imaging result by using an image processing technique, and thus, can have a good application effect in some scenes.
In order to achieve the purpose, the invention adopts the following technical scheme:
a non-visual field imaging method based on infrared thermal radiation comprises the following steps:
step S1, acquiring a first image, wherein the first image is a thermal imaging image of the diffuse reflection surface;
step S2, acquiring a second image, wherein the second image is a thermal imaging image of the object to be detected after the diffuse reflection of the diffuse reflection surface;
step S3, performing a difference between the second image and the first image, and performing a gray scale process on the obtained difference image to obtain a gray scale image of the image, so as to reduce the interference caused by the background to a great extent and improve the accuracy of non-visual field imaging;
step S4, carrying out self-adaptive median filtering processing on the gray image to obtain a third image, wherein the third image is an image with noise removed, and compared with the traditional Gaussian filtering, the self-adaptive median filtering does not need to artificially set filtering parameters and has stronger self-adaptability;
step S5, calculating the gradient of the third image by utilizing sobel operators in four directions, performing convolution calculation on the noise-removed picture by utilizing the operators in the four directions when calculating the gradient, wherein the final result is that the four directions are integrated, and the stability and the anti-interference performance are improved;
s6, performing non-maximum suppression on the gradient amplitude value obtained in the S5 to obtain possible edge points of the image to be detected;
s7, screening the possible edge points obtained in the S6 through a double-threshold method, reserving the final edge points, and finally obtaining the edge shape of the image to be detected; when the double-threshold screening is carried out, the high threshold is adaptively selected by adopting a method of maximum inter-class variance, and the low threshold is half of the high threshold, so that the problem caused by manually setting the threshold is avoided.
Further, the step S1 specifically includes: by arranging the diffuse reflection surface, the diffuse reflection surface comprises a wall surface;
and arranging a thermal imaging camera on one side of the diffuse reflection surface, and acquiring a thermal imaging image of the diffuse reflection surface through the thermal imaging camera. The roughness of the wall is small, so that the intensity of the specular reflection component is increased, the intensity of the diffuse reflection component is reduced, and the acquisition of specular information is facilitated.
Further, the step S2 specifically includes: arranging the object to be detected on one side of the diffuse reflection surface close to the thermal imaging camera, and arranging a shelter between the object to be detected and the thermal imaging camera;
and the far infrared light wave of the object to be detected is subjected to diffuse reflection of the diffuse reflection surface and then is imaged by the thermal imaging camera.
The overall temperature of the object to be measured is uniform, and the real world object may have local temperature differences, but the temperature should be uniform as a whole.
Further, the sobel operators in the four directions specifically include: the operator of horizontal direction, the operator of vertical direction, the operator of 45 orientation and the operator of 135 orientation, the expression is:
in the formula group (1), f0Operator, expressed as horizontal direction, f45Operator, f, expressed as a 45 ° orientation90Operator, expressed as vertical direction, f135Represented as an operator in the 135 direction.
Further, the step S5 specifically includes: performing convolution operation on the third image through the sobel operators in the four directions to obtain first-order gradient components in the four directions, and calculating the amplitude M (x, y) and the angle theta (x, y) of the gradient through the first-order gradient components in the four directions, wherein the expression is as follows:
in formula (2) and formula (3), G0Expressed as operators in the horizontal direction, G45Operator, G, expressed as a 45 ° orientation90Operator, G, expressed as vertical135Represented as an operator in the 135 direction.
Further, the step S6 specifically includes: comparing the gradient magnitude M (x, y) point by point through a 3 × 3 neighborhood, and regarding a point of the gradient magnitude M (x, y) satisfying a condition as the possible edge point, where the condition is: the magnitude of the point in the center of the neighborhood is larger than the magnitude of both adjacent points along the gradient direction.
Further, the step S7 specifically includes:
step S701, determining a high threshold value through a maximum inter-class variance method, and taking half of the high threshold value as a low threshold value;
step S702, then reserving the points higher than the high threshold value in the possible edge points as strong edge points, and removing the points lower than the low threshold value;
step 703, regarding a point between the high threshold and the low threshold as a weak edge point;
step S704, a neighborhood is taken from the weak edge point, if the neighborhood has a strong edge point, the weak edge point is reserved, otherwise, the weak edge point is removed.
The invention has the beneficial effects that:
1. the invention utilizes the far infrared thermal radiation characteristic of the hidden object, collects the specular reflection information generated by the far infrared thermal radiation on the wall through the thermal imaging camera and images the specular reflection information by the thermosensitive infrared CCD, and then makes the difference value between the thermal imaging picture of the hidden object and the background thermal imaging picture, thereby reducing the interference caused by the background to a great extent and improving the accuracy of non-vision field imaging.
2. The method adopts an improved Canny algorithm to carry out edge identification, carries out convolution calculation on the noise-removed picture by using operators in four directions when calculating the gradient, and finally has the comprehensive result of the four directions, thereby improving the stability and the anti-interference performance.
3. When the double-threshold screening is carried out, the method of maximum inter-class variance is adopted to adaptively select the high threshold, and the low threshold is half of the high threshold, so that the problem caused by manually setting the threshold is avoided.
Drawings
Fig. 1 is a schematic view of an apparatus for implementing the non-visual field imaging method in embodiment 1.
Fig. 2 is a schematic flowchart of the non-visual field imaging method provided in embodiment 1.
Fig. 3 is a flow diagram of the improved Canny algorithm provided in example 1.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1 to 3, the present embodiment 1 provides a non-visual field imaging method based on infrared thermal radiation, including the steps of:
and step S1, acquiring a first image, wherein the first image is a thermal imaging image of the diffuse reflection surface.
And step S2, acquiring a second image, wherein the second image is a thermal imaging image of the object to be detected after the object to be detected is subjected to diffuse reflection by the diffuse reflection surface.
Specifically, in this embodiment, referring to fig. 1, the diffuse reflection surface adopts a wall with a small roughness, so that the intensity of the specular reflection component is increased and the intensity of the diffuse reflection component is decreased, which is beneficial to the acquisition of specular information.
A thermal imaging camera is arranged on one side of the wall, and a thermal imaging image of the wall is obtained by the camera, namely the first image.
Then, an object to be detected (namely, a hidden object) and a shielding object are arranged on one side of the wall, and the shielding object is blocked between the object to be detected and the thermal imaging camera, so that the thermal imaging camera cannot directly shoot the object to be detected, and only far infrared light waves emitted by the object to be detected are subjected to diffuse reflection through the wall and then are imaged by the thermal imaging camera, and the image is a second image. It should be noted that the overall temperature of the hidden object is uniform, and the real-world object may have local temperature differences, but the temperature should be uniform as a whole.
More specifically, any object has radiation, the higher the temperature of the object, the longer the wavelength of the radiation, and the lower the temperature, the shorter the wavelength. All objects in the real world can be considered as a source of radiation in the far infrared band. Therefore, in the above-mentioned scenario, the object to be measured also radiates far infrared waves. Compared with the visible light band, the far infrared band has great advantages in reflection performance. For walls, a beam of monochromatic light is reflected at its surface, where the intensity of the diffuse reflection is as follows:
in the formula (1), RdIndicating the intensity of diffuse reflection，R0Representing the intensity of reflection at which specular reflection occurs on a smooth wall, m is a constant for a certain wall, σ is the roughness of the wall, and is also a constant for a certain wall. As can be seen from the formula (1), the intensity of the diffuse reflection is 1/lambda4The form of the image is decreased, so that the diffuse reflection component is greatly reduced by utilizing the far infrared band imaging, and the proportion of the specular reflection component is increased.
The thermal imaging camera used in this embodiment is equipped with an infrared thermal CCD, and can recognize objects at different temperatures by using different imaging colors. The wall is made of a material with low roughness, and the radiation wavelength of a hidden object is long, so that the proportion of the specular reflection component in the reflected information is large, and the thermal imaging picture can restore the object in the scene.
And step S3, performing difference on the second image and the first image, and performing gray scale processing on the obtained difference image to obtain a gray scale image of the image.
Specifically, in this embodiment, in order to improve the accuracy of scene restoration and reduce the interference caused by the background, a difference is made between the obtained thermal imaging picture containing the hidden object and the original background thermal imaging picture, and the difference thermal imaging picture is subjected to subsequent processing.
After obtaining the difference thermal imaging picture, in order to facilitate the subsequent processing, the thermal imaging picture (RGB) needs to be converted into a gray scale image, and the conversion formula is as follows:
Gray＝R×0.299+G×0.587+B×0.114 (2)
after obtaining the gray level picture, identifying the edge of the gray level picture by using an improved Canny algorithm, wherein the improved Canny algorithm specifically comprises the following steps:
step S4, performing adaptive median filtering on the grayscale image to obtain a third image, where the third image is an image after removing noise, and in this embodiment, the adaptive median filtering is adopted, and compared with the conventional gaussian filtering, the adaptive median filtering does not need to manually set filtering parameters, and is more adaptive.
Specifically, the traditional Canny algorithm uses a gaussian filter for filtering. Not only is the calculation more complex, but also the smoothing parameter sigma of the filter needs to be set artificially, the size of sigma has a great influence on whether the filtering is good or not, and finding a more accurate sigma value in practical application is a difficult point, so the effect of sigma in edge detection is limited.
The self-adaptive median filtering algorithm not only has the detail protection capability of a small window, but also has the noise removal capability of a large window on a high-density noise image, and different operations can be selected and executed according to the specific situation of a local neighborhood. Noise points can be effectively removed without affecting information at the edges.
And step S5, calculating the gradient of the third image by using the sobel operators in four directions.
Specifically, an operator for calculating the gray gradient amplitude by the conventional Canny algorithm is as shown in the following formula (3), and the interference resistance is weak because only 2 × 2 neighborhoods are selected.
In this embodiment, a 3 × 3 Sobel operator is adopted, and is extended to four directions, i.e., horizontal, vertical, 45 ° and 135 °, where the operators in the four directions are:
in the formula group (4), f0Operator, expressed as horizontal direction, f45Operator, f, expressed as a 45 ° orientation90Operator, expressed as vertical direction, f135Represented as an operator in the 135 direction.
The four operators are respectively convolved with the image after the noise is removed, so that first-order gradient components in four directions can be obtained, and are respectively expressed as G0(x,y)，G45(x,y)，G90(x,y)，G135(x, y). Calculating the magnitude M (x) of the gradientY) and the angle θ (x, y) are then integrated into the values of these four directions, and the calculation formula is as follows:
formula (5) and formula (6), G0Expressed as operators in the horizontal direction, G45Operator, G, expressed as a 45 ° orientation90Operator, G, expressed as vertical135Represented as an operator in the 135 direction.
More specifically, the embodiment uses the first-order components of the gradient in 4 directions when calculating the magnitude and direction of the gradient, and has higher accuracy and stronger interference resistance than the conventional horizontal and vertical directions.
And S6, performing non-maximum suppression on the gradient amplitude obtained in the step S5 to obtain possible edge points of the image to be detected. In particular, the regions of gradient change are usually concentrated, so that there may be a problem of gradient direction inconsistency in a local range. Therefore, it is necessary to perform non-maximum suppression on the gradient amplitude, that is, within the range of gradient change, the gradient change is stored maximally, and the rest is not stored, so that a large part of points can be eliminated, and the edge can be refined.
More specifically, the method adopted in this embodiment is: comparing the gradient amplitude array M (x, y) point by using a 3 x 3 neighborhood, wherein the amplitude of a point in the center of the neighborhood is required to be ensured to be larger than the amplitudes of two adjacent points in the gradient direction, if the condition is met, the point is judged to be a possible edge point, and if the condition is not met, the gradient amplitude of the point is set to be 0, namely, the point is judged to be a non-edge point.
And S7, screening the possible edge points obtained in the step S6 by a double-threshold method, reserving the final edge points, and finally obtaining the edge shape of the image to be detected. In particular, a dual thresholdThe value algorithm uses high and low threshold values to screen the image after the non-maximum value inhibition, wherein the points higher than the high threshold value are reserved as strong edge points, the points lower than the low threshold value are removed, and the points between the high and low threshold values belong to weak edge points and need further judgment. The specific method is to take a neighborhood of the weak edge point, if there is a strong edge point in the neighborhood, the point is reserved, otherwise, the point is removed. The key to the dual threshold method is the choice of the high threshold, since the low threshold is typically half of the high threshold. In this embodiment, an Otsu algorithm, i.e., a maximum inter-class variance method, is used to perform threshold value screening. More specifically, the maximum inter-class variance method needs to determine the number of gray level levels M according to the gray level range of the picture, and the number of pixel points corresponding to each gray level is niThe gray value corresponding to each gray level is giAnd the total number of the pixel points is N, then the method comprises the following steps:
where pi represents the probability of the ith gray level. Selecting a threshold k satisfying 1<k<M, its corresponding gray value is denoted gkThen the gray scale value is less than gkProbability P of1And the corresponding average gray value G1Comprises the following steps:
for the same reason, greater than gkProbability P of2And the corresponding average gray value G2Comprises the following steps:
average gray value G of whole picturegComprises the following steps:
the inter-class variance can be obtained by the above formula
Comprises the following steps:
the high threshold is g when the inter-class variance is maximumkValue, g, provided that the maximum between-class variance corresponds tokMore than one value, then all g's are usedkAverage value of (a). After the high threshold is obtained, the low threshold is half of the high threshold.
The application of the maximum inter-class variance method enables the high and low thresholds not to be manually set, but can be automatically defined according to a specific gradient amplitude image, so that the applicability and the feasibility of the dual-threshold algorithm are greatly improved. After double-threshold screening, the shape information of the hidden object can be obtained.
To sum up, this embodiment utilizes the far infrared thermal radiation characteristic of hiding the object, and the mirror reflection information that the far infrared thermal radiation produced in wall department is gathered and is imaged by heat-sensitive infrared CCD by thermal imaging camera. Firstly, converting a thermal imaging picture into a gray-scale image, then carrying out edge recognition on the gray-scale image by using an improved Canny algorithm, and finally recognizing the shape information of the hidden object to realize non-visual field imaging.
The invention is not described in detail, but is well known to those skilled in the art. The foregoing detailed description of the preferred embodiments of the invention has been presented. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the above teachings without undue experimentation. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (7)
1. A non-vision field imaging method based on infrared thermal radiation, characterized by comprising the steps of:
step S1, acquiring a first image, wherein the first image is a thermal imaging image of the diffuse reflection surface;
step S2, acquiring a second image, wherein the second image is a thermal imaging image of the object to be detected after the diffuse reflection of the diffuse reflection surface;
step S3, making a difference value between the second image and the first image, and making gray scale processing on the obtained difference value image to obtain a gray scale image of the image;
step S4, carrying out self-adaptive median filtering processing on the gray-scale image to obtain a third image, wherein the third image is an image with noise removed;
step S5, calculating the gradient of the third image by utilizing a sobel operator in four directions;
s6, performing non-maximum suppression on the gradient amplitude value obtained in the S5 to obtain possible edge points of the image to be detected;
and S7, screening the possible edge points obtained in the step S6 by a double-threshold method, reserving the final edge points, and finally obtaining the edge shape of the image to be detected.
2. The infrared thermal radiation-based non-viewing area imaging method according to claim 1, wherein said step S1 specifically comprises: by arranging the diffuse reflection surface, the diffuse reflection surface comprises a wall surface;
and arranging a thermal imaging camera on one side of the diffuse reflection surface, and acquiring a thermal imaging image of the diffuse reflection surface through the thermal imaging camera.
3. The infrared thermal radiation-based non-visual-field imaging method as claimed in claim 2, wherein said step S2 specifically includes: arranging the object to be detected on one side of the diffuse reflection surface close to the thermal imaging camera, and arranging a shelter between the object to be detected and the thermal imaging camera;
and the far infrared light wave of the object to be detected is subjected to diffuse reflection of the diffuse reflection surface and then is imaged by the thermal imaging camera.
4. The infrared thermal radiation-based non-visual field imaging method as claimed in claim 3, wherein said four-directional sobel operators specifically comprise: the operator of horizontal direction, the operator of vertical direction, the operator of 45 orientation and the operator of 135 orientation, the expression is:
in the formula group (1), f0Operator, expressed as horizontal direction, f45Operator, f, expressed as a 45 ° orientation90Operator, expressed as vertical direction, f135Represented as an operator in the 135 direction.
5. The infrared thermal radiation-based non-viewing area imaging method according to claim 4, wherein said step S5 specifically comprises: performing convolution operation on the third image through the sobel operators in the four directions to obtain first-order gradient components in the four directions, and calculating the amplitude M (x, y) and the angle theta (x, y) of the gradient through the first-order gradient components in the four directions, wherein the expression is as follows:
in formula (2) and formula (3), G0Expressed as operators in the horizontal direction, G45Operator, G, expressed as a 45 ° orientation90Operator, G, expressed as vertical135Represented as an operator in the 135 direction.
6. The infrared thermal radiation-based non-viewing area imaging method according to claim 5, wherein said step S6 specifically comprises: comparing the gradient magnitude M (x, y) point by point through a 3 × 3 neighborhood, and regarding a point of the gradient magnitude M (x, y) satisfying a condition as the possible edge point, where the condition is: the magnitude of the point in the center of the neighborhood is larger than the magnitude of both adjacent points along the gradient direction.
7. The infrared thermal radiation-based non-visual field imaging method as set forth in claim 6, wherein: the step S7 specifically includes:
step S701, determining a high threshold value through a maximum inter-class variance method, and taking half of the high threshold value as a low threshold value;
step S702, then reserving the points higher than the high threshold value in the possible edge points as strong edge points, and removing the points lower than the low threshold value;
step 703, regarding a point between the high threshold and the low threshold as a weak edge point;
step S704, a neighborhood is taken from the weak edge point, if the neighborhood has a strong edge point, the weak edge point is reserved, otherwise, the weak edge point is removed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421383.XA CN113052833A (en) | 2021-04-20 | 2021-04-20 | Non-vision field imaging method based on infrared thermal radiation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421383.XA CN113052833A (en) | 2021-04-20 | 2021-04-20 | Non-vision field imaging method based on infrared thermal radiation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113052833A true CN113052833A (en) | 2021-06-29 |
Family
ID=76519684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110421383.XA Pending CN113052833A (en) | 2021-04-20 | 2021-04-20 | Non-vision field imaging method based on infrared thermal radiation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052833A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837217A (en) * | 2021-07-02 | 2021-12-24 | 中国空间技术研究院 | Passive non-visual field image identification method and device based on deep learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377469A (en) * | 2018-11-07 | 2019-02-22 | 永州市诺方舟电子科技有限公司 | A kind of processing method, system and the storage medium of thermal imaging fusion visible images |
| CN111340929A (en) * | 2020-02-20 | 2020-06-26 | 东南大学 | Non-vision field imaging method based on ray tracing algorithm |
| CN111476897A (en) * | 2020-03-24 | 2020-07-31 | 清华大学 | Non-visual field dynamic imaging method and device based on synchronous scanning stripe camera |
| CN111487648A (en) * | 2020-04-16 | 2020-08-04 | 北京深测科技有限公司 | Non-visual field imaging method and system based on flight time |
| CN112669286A (en) * | 2020-12-29 | 2021-04-16 | 北京建筑材料检验研究院有限公司 | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall |
-
2021
- 2021-04-20 CN CN202110421383.XA patent/CN113052833A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377469A (en) * | 2018-11-07 | 2019-02-22 | 永州市诺方舟电子科技有限公司 | A kind of processing method, system and the storage medium of thermal imaging fusion visible images |
| CN111340929A (en) * | 2020-02-20 | 2020-06-26 | 东南大学 | Non-vision field imaging method based on ray tracing algorithm |
| CN111476897A (en) * | 2020-03-24 | 2020-07-31 | 清华大学 | Non-visual field dynamic imaging method and device based on synchronous scanning stripe camera |
| CN111487648A (en) * | 2020-04-16 | 2020-08-04 | 北京深测科技有限公司 | Non-visual field imaging method and system based on flight time |
| CN112669286A (en) * | 2020-12-29 | 2021-04-16 | 北京建筑材料检验研究院有限公司 | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall |
Non-Patent Citations (2)
| Title |
|---|
| TOMOHIRO MAEDA 等: "Thermal Non-Line-of-Sight Imaging", 《IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL PHOTOGRAPHY》, 27 June 2019 (2019-06-27), pages 1 - 11 * |
| 王威 等: "基于红外热成像的槽罐车内壁裂纹检测方法的研究", 《科技通报》, vol. 35, no. 9, 29 September 2019 (2019-09-29), pages 162 - 167 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837217A (en) * | 2021-07-02 | 2021-12-24 | 中国空间技术研究院 | Passive non-visual field image identification method and device based on deep learning |
| CN113837217B (en) * | 2021-07-02 | 2024-05-07 | 中国空间技术研究院 | Passive non-visual field image recognition method and recognition device based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
| KR100872253B1 (en) | Method for eliminating noise of image generated by image sensor | |
| CN112819772B (en) | High-precision rapid pattern detection and recognition method | |
| US20070098260A1 (en) | Detecting and correcting peteye | |
| WO2011151821A1 (en) | Inspection of region of interest | |
| CN112529800B (en) | Near-infrared vein image processing method for filtering hair noise | |
| CN112883824A (en) | Finger vein feature recognition device for intelligent blood sampling and recognition method thereof | |
| CN117649357B (en) | Ultrasonic image processing method based on image enhancement | |
| CN113052833A (en) | Non-vision field imaging method based on infrared thermal radiation | |
| CN114943744A (en) | Edge detection method based on local Otsu thresholding | |
| CN110717935A (en) | Image matching method, device and system based on image characteristic information | |
| CN111192280A (en) | Method for detecting optic disc edge based on local feature | |
| CN116205939A (en) | Line extraction method, line extraction apparatus, and computer storage medium | |
| CN115661110A (en) | Method for identifying and positioning transparent workpiece | |
| CN114841907A (en) | Method for generating countermeasure fusion network in multiple scales facing infrared and visible light images | |
| RU2405200C2 (en) | Method and device for fast noise filtration in digital images | |
| CN110647843B (en) | Face image processing method | |
| CN109934190B (en) | Self-adaptive highlight face image texture recovery method based on deformed Gaussian kernel function | |
| Lupu | Development of optimal filters obtained through convolution methods, used for fingerprint image enhancement and restoration | |
| AKINTOYE et al. | COMPOSITE MEDIAN WIENER FILTER BASED TECHNIQUE FOR IMAGE ENHANCEMENT. | |
| CN117115174B (en) | Automatic detection method and system for appearance of pliers | |
| JP2003141550A (en) | Position detection method | |
| CN109949245A (en) | Cross laser detects localization method, device, storage medium and computer equipment | |
| CN112862708B (en) | Adaptive recognition method of image noise, sensor chip and electronic equipment | |
| CN114863139A (en) | Method for enhancing extraction of textural features and application of textural features in acanthosis nigricans |
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 |