CN112163587A - Feature extraction method and device of target object and computer readable medium - Google Patents
Feature extraction method and device of target object and computer readable medium Download PDFInfo
- Publication number
- CN112163587A CN112163587A CN202011065455.3A CN202011065455A CN112163587A CN 112163587 A CN112163587 A CN 112163587A CN 202011065455 A CN202011065455 A CN 202011065455A CN 112163587 A CN112163587 A CN 112163587A
- Authority
- CN
- China
- Prior art keywords
- image
- polarization
- target object
- polarization information
- pixel
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method, a device and a computer readable medium for extracting the characteristics of a target object, wherein the method comprises the following steps: obtaining a Stokes parameter map according to the infrared radiation image of the target object; obtaining a polarization information image of the surface of the target object through a Stokes parameter map, wherein the polarization information image is used for representing the polarization degree value of the surface of the target object; and performing feature extraction on the polarization information image by using a Canny operator to obtain a polarization information feature image, wherein the polarization information feature image represents the outline of the target object. The method and the device can improve the accuracy of feature extraction of the target object.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and an apparatus for extracting features of a target object, and a computer-readable medium.
Background
Optical detection is an important technical means for detecting and identifying a space target, and compared with the traditional orbit determination measurement, the spectral detection provides wavelength-dimensional distinguishable information, greatly improves the discrimination capability of target characteristics, and has great application potential. However, with the development of scientific technology, the requirements for detecting and identifying targets become higher and higher, especially in the military field, which is related to national defense strength of the country, so the requirements for detecting and identifying target objects are more severe.
In the detection and identification of the target object, the feature extraction of the target object is the basis, and the accuracy of the subsequent detection and identification of the target object through the extracted target feature is directly influenced by the quality of the target feature extraction. For example, the traditional target feature extraction method often ignores the detail features such as the contour and the edge of the detected target, so that the accuracy of detecting and identifying the target object is not high.
Therefore, it is desirable to provide a method for detecting and identifying a target object to solve the above-mentioned problems.
Disclosure of Invention
The technical problem to be solved by the invention is that the traditional target feature extraction method has low accuracy in extracting detail features such as the contour and the edge of a target object to be detected when feature extraction is carried out, so that the accuracy of feature extraction on the target object is low. Therefore, the invention provides a method, a device and a computer readable medium for extracting the features of a target object, which can improve the accuracy of feature extraction of the target object.
In a first aspect, an embodiment of the present invention provides a method for extracting features of a target object, including:
obtaining a Stokes parameter map according to the infrared radiation image of the target object;
obtaining a polarization information image of the surface of the target object through the Stokes parameter map, wherein the polarization information image is used for representing the polarization degree value of the surface of the target object;
and performing feature extraction on the polarization information image by using a Canny operator to obtain a polarization information feature image, wherein the polarization information feature image represents the outline of the target object.
Optionally, the obtaining a Stokes reference map according to the infrared radiation image of the target object includes:
respectively collecting infrared radiation images I of the target objects0°、I45°、I90°And I135°Wherein the infrared radiation image I0°、I45°、I90°And I135°Obtained at polarization directions of 0 °, 45 °, 90 ° and 135 °, respectively;
calculating the Stokes parameters of the infrared radiation image according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPFor characterizing the right-hand circular polarization of the infrared radiation image, ILCPFor characterizing the left-hand circular polarization of the infrared radiation image.
Optionally, the obtaining, through the Stokes parameter map, a polarization information image of the target object surface includes:
calculating and obtaining a polarization information image of the surface of the target object according to the following formula by using the Stokes parameter map:
wherein p is used for characterizing the polarization degree of the polarization information image, and α is used for characterizing the polarization angle of the polarization information image.
Optionally, the performing feature extraction on the polarization information image by using a Canny operator to obtain a polarization information feature image includes:
performing Gaussian filtering on the polarization information image to obtain a first characteristic image, wherein the first characteristic image is used for representing the image of the polarization information image after removing noise points;
determining at least one first gradient amplitude of the first characteristic image by utilizing finite difference calculation, wherein the first gradient amplitude is the amplitude of a partial derivative of the first characteristic image along the coordinate axis direction, and each first gradient amplitude corresponds to one pixel position;
acquiring a second gradient amplitude from the first gradient amplitude, wherein the second gradient amplitude is an amplitude image without non-edge pixels;
and determining a polarization information characteristic image from the second gradient amplitude by using a preset double-threshold algorithm.
Optionally, the determining a polarization information feature image from the second gradient magnitude by using a preset dual-threshold algorithm includes:
determining a first threshold value and a second threshold value according to the polarization degree of the polarization information image, wherein the second threshold value is larger than the first threshold value;
for each pixel in the polarization information image, performing:
if the second gradient amplitude corresponding to the pixel is larger than or equal to the second threshold value, determining the pixel as an edge pixel of the target object;
if the second gradient amplitude corresponding to the pixel is larger than the first threshold and smaller than the second threshold, and the second gradient amplitude corresponding to at least one pixel adjacent to the pixel in the polarization information image is larger than or equal to the second threshold, determining the pixel as an edge pixel of the target object;
and connecting the edge pixels to obtain the polarization information characteristic image.
In a second aspect, an embodiment of the present invention further provides a device for extracting features of a target object, including: the device comprises a first determining module, a second determining module and a third determining module;
the first determination module is used for obtaining a Stokes parameter map according to the infrared radiation image of the target object;
the second determining module is configured to obtain a polarization information image of the target object surface through the Stokes parameter map determined by the first determining module, where the polarization information image is used to characterize a polarization degree value of the target object surface;
the third determining module is configured to perform feature extraction on the polarization information image determined by the second determining module by using a Canny operator to obtain a polarization information feature image, where the polarization information feature image represents a contour of the target object.
Optionally, the first determining module is configured to perform the following operations:
respectively collecting infrared radiation images I of the target objects0°、I45°、I90°And I135°Wherein the infrared radiation image I0°、I45°、I90°And I135°Obtained at polarization directions of 0 °, 45 °, 90 ° and 135 °, respectively;
calculating the Stokes parameters of the infrared radiation image according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPFor characterizing the right-hand circular polarization of the infrared radiation image, ILCPFor characterizing the left-hand circular polarization of the infrared radiation image.
Optionally, the second determining module is configured to perform the following operations:
calculating and obtaining a polarization information image of the surface of the target object according to the following formula by using the Stokes parameter map:
wherein p is used for characterizing the polarization degree of the polarization information image, and α is used for characterizing the polarization angle of the polarization information image.
In a third aspect, another embodiment of the present invention further provides a feature extraction apparatus for a target object, including at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform the method of any of the above first aspects.
In a fourth aspect, the present invention also provides a computer-readable medium, on which computer instructions are stored, and when executed by a processor, the computer instructions cause the processor to execute the method of any one of the first aspect.
The method, the device and the computer readable medium for extracting the features of the target object have the following beneficial effects:
for a target object needing feature extraction, firstly, an infrared radiation image of the target object is obtained through a polarization device, then a Stokes parameter map of the infrared radiation image is obtained according to a Stokes formula, further, a polarization information image of the Stokes parameter map is obtained through a polarization degree and polarization angle formula, and finally, a Canny operator is used for feature extraction on the polarization information image to obtain a polarization information feature image. Therefore, the method and the device adopt the modes of the polarization information image and the Canny operator in sequence to extract the characteristics of the target object. The polarization information image has an advantage in highlighting edge details of the target object, and the Canny operator has an advantage in identifying dark target areas, so that the Canny operator is used for extracting the features of the polarization information image, namely, the polarization information image and the Canny operator are combined to facilitate the extraction of the outline and the edge details of the dark target areas in the polarization information image, and the accuracy of feature extraction of the target object is improved.
Drawings
Fig. 1 is a flowchart of a feature extraction method for a target object according to an embodiment of the present invention;
fig. 2 is a flowchart of a feature extraction method for a target object according to another embodiment of the present invention;
fig. 3 is a schematic diagram of a device where a feature extraction apparatus of a target object is located according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a feature extraction apparatus for a target object according to an embodiment of the present invention;
fig. 5 is a schematic diagram of another feature extraction apparatus for a target object according to an embodiment of the present invention.
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 obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for extracting features of a target object, where the method may include the following steps:
step 101: obtaining a Stokes parameter map according to the infrared radiation image of the target object;
step 102: obtaining a polarization information image of the surface of the target object through a Stokes parameter map, wherein the polarization information image is used for representing the polarization degree value of the surface of the target object;
step 103: and performing feature extraction on the polarization information image by using a Canny operator to obtain a polarization information feature image, wherein the polarization information feature image represents the outline of the target object.
In the embodiment of the invention, for a target object which needs to be subjected to feature extraction, an infrared radiation image of the target object is obtained through a polarization device, then a Stokes parameter map of the infrared radiation image is obtained according to a Stokes formula, a polarization information image of the Stokes parameter map is obtained through a polarization degree and polarization angle formula, and finally a Canny operator is utilized to perform feature extraction on the polarization information image to obtain a polarization information feature image. Therefore, the method and the device adopt the modes of the polarization information image and the Canny operator in sequence to extract the characteristics of the target object. The polarization information image has an advantage in highlighting edge details of the target object, and the Canny operator has an advantage in identifying dark target areas, so that the Canny operator is used for extracting the features of the polarization information image, namely, the polarization information image and the Canny operator are combined to facilitate the extraction of the outline and the edge details of the dark target areas in the polarization information image, and the accuracy of feature extraction of the target object is improved.
Optionally, according to the feature extraction method of the target object shown in fig. 1, in the embodiment of the present invention, when the Stokes reference map is obtained according to the infrared radiation image of the target object, the Stokes reference map may be obtained specifically by the following method:
respectively collecting infrared radiation images I of target objects0°、I45°、I90°And I135°Wherein, an infrared radiation image I0°、I45°、I90°And I135°Obtained at polarization directions of 0 °, 45 °, 90 ° and 135 °, respectively;
calculating the Stokes parameters of the infrared radiation image according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPRight-handed circular polarization, I, for characterizing infrared radiation imagesLCPFor characterizing the left-hand circular polarization of the infrared radiation image.
In the embodiment of the invention, infrared radiation images with the polarization directions of 0 degrees, 45 degrees, 90 degrees and 135 degrees are collected by rotating the polaroid, and the Stokes parameter graph is determined according to the infrared radiation images. In the scheme, the light intensity information of each polarization direction is measured and acquired by rotating the polarizing film, and the Stokes parameter is represented by the light intensity, so that the polarization state of the infrared radiation image is described by adopting the Stokes parameter, and the method not only has the advantages of directly measuring and acquiring the light intensity and being simple and convenient to calculate, but also is the basis for acquiring the polarization information image subsequently.
Alternatively, according to the feature extraction method of the target object shown in fig. 1, when the polarization information image of the surface of the target object is obtained through the Stokes parameter map, the polarization information image is obtained by calculating the polarization degree and the polarization angle, and specifically, the method can be obtained as follows:
and calculating and obtaining a polarization information image of the surface of the target object according to the following formula by using the Stokes parameter map:
wherein p is used to characterize the degree of polarization of the target object and α is used to characterize the angle of polarization of the target object.
In the embodiment of the invention, the polarization information image is obtained by substituting the obtained Stokes parameters into the polarization degree and polarization angle formula. After the electromagnetic waves are reflected and radiated by the surface of the object, the polarization state of the electromagnetic waves can be changed according to the structure and the texture of the surface and the incident angle of the electromagnetic waves on the surface, so that some information of the surface of the object can be enhanced, and therefore, some information which is difficult to characterize through intensity measurement can be represented through a polarization information image formed by the polarization degree and the polarization angle. Therefore, the polarization information image is obtained by calculating the polarization degree and the polarization angle of the target object, and some feature information such as the outline and the structure of the target object can be obtained, so that feature extraction of the target object is realized.
Optionally, according to the feature extraction method of the target object shown in fig. 1, in the embodiment of the present invention, feature extraction is performed on the polarization information image by using a Canny operator, and when the polarization information image is obtained, the processes of filtering, difference calculation, non-maximum suppression, dual-threshold detection, and the like may be mainly performed, and specifically, the following processes may be implemented:
performing Gaussian filtering on the polarization information image to obtain a first characteristic image, wherein the first characteristic image is used for representing the image of the polarization information image after noise points are removed;
determining at least one first gradient amplitude of the first characteristic image by utilizing finite difference calculation, wherein the first gradient amplitude is the amplitude of a partial derivative of the first characteristic image along the coordinate axis direction, and each first gradient amplitude corresponds to one pixel position;
acquiring a second gradient amplitude from the first gradient amplitude, wherein the second gradient amplitude is an amplitude image without non-edge pixels;
and determining a polarization information characteristic image from the second gradient amplitude by using a preset double-threshold algorithm.
In the embodiment of the invention, when the polarization information characteristic image is obtained by extracting the characteristics of the polarization image, firstly, a proper filter needs to be selected, the polarization information image is filtered by using a filtering algorithm, some pixel points generated due to noise are removed, then, a first gradient amplitude of each pixel position in the filtered image is determined by using a finite difference calculation mode, a second gradient amplitude is further determined from the first gradient amplitude by using a non-maximum suppression method to remove non-edge pixel points in the image, and finally, the polarization characteristic image is determined by setting a dual-threshold algorithm of a high threshold and a low threshold. Therefore, according to the scheme, the noise influence is removed in a filtering mode, and whether the calculated pixel point amplitude corresponds to the edge pixel of the target object outline or not is judged in sequence, so that the edge pixel is continuously screened, and the accuracy of feature extraction on the target object is improved.
Optionally, according to the manner provided by the foregoing embodiment, when determining the polarization information feature image from the second gradient amplitude by using a preset dual-threshold algorithm, the determination is mainly performed by using a magnitude relationship between the second gradient amplitude corresponding to each pixel and two thresholds, and specifically may be implemented by:
determining a first threshold value and a second threshold value according to the polarization degree of the polarization information image, wherein the second threshold value is larger than the first threshold value;
for each pixel in the polarization information image, performing:
if the second gradient amplitude corresponding to the pixel is larger than or equal to a second threshold value, determining the pixel as an edge pixel of the target object;
if the second gradient amplitude corresponding to the pixel is larger than the first threshold and smaller than the second threshold, and the second gradient amplitude corresponding to at least one pixel adjacent to the pixel in the polarization information image is larger than or equal to the second threshold, determining the pixel as an edge pixel of the target object;
and connecting the edge pixels to obtain a polarization information characteristic image.
Since the pixel with the higher second gradient magnitude is more likely to be an edge pixel, there is no exact value to define how many edge pixels or less than how many non-edge pixels the second gradient magnitude reaches. Therefore, in the embodiment of the present invention, by setting a high threshold and a low threshold, not only the pixel points whose second gradient amplitude is greater than the high threshold can be determined as edge pixel points, but also the non-edge pixel points generated by noise can be further removed by determining whether the pixel points whose second gradient amplitude is greater than the first threshold and less than the second threshold can be combined with the pixel points of the high threshold to form a curve, so that the accuracy of extracting the edge contour features of the target object is ensured.
As shown in fig. 2, another embodiment of the present invention further provides a method for extracting features of a target object, which may include the following steps:
step 201: an infrared radiation image of the target object is acquired.
In the embodiment of the invention, the transmission light intensity I of the target object with the polarization directions of 0 degree, 45 degrees, 90 degrees and 135 degrees is obtained by rotating the polaroid by using the polarization imaging measuring device0°、I45°、I90°And I135°. In the infrared polarization imaging measurement process, factors such as difference of used equipment or generation of moving polarization in the imaging process can causeThe infrared polarization information produces an offset in the image representation and therefore requires registration of the infrared polarized radiation image. In view of the characteristic that the infrared radiation image can highlight the contour features of the target edge, the infrared radiation image is registered in an image feature anchoring mode.
The polarization imaging measurement device may include a polarizer, an imaging lens, a CCD imaging detector, a computer, etc., and when an infrared radiation image is acquired, the image may be subjected to preliminary processing by software such as Matlab.
Step 202: and calculating the Stokes parameters of the infrared radiation images.
In the embodiment of the invention, after the infrared radiation image is obtained by the polarization imaging measuring device, the Stokes parameter can be obtained by calculating according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPRight-handed circular polarization, I, for characterizing infrared radiation imagesLCPFor characterizing the left-hand circular polarization of the infrared radiation image.
As known from the above calculation formula of Stokes, the Stokes parameter can be directly expressed by the collected light intensities with different polarization directions, wherein S0Can be approximated to represent the incident light intensity, S1、S2And S3Respectively, to represent the difference in light intensity in two mutually orthogonal directions.
The mueller matrix is a matrix for describing the action of the polarizing devices, and the mueller matrices corresponding to different polarizing devices are different. Therefore, in the embodiment of the present invention, the vector change process corresponding to the process of obtaining the emergent light after the incident light passes through the polarizer is that the incident stokes vector obtains the emergent stokes vector after passing through the miller matrix. For example, the change in the stokes vector for an incident light after passing through a polarizer can be represented by the following relationship:
therefore, in the embodiment of the present invention, the Mueller matrix M of the known polarizing plate and the Stokes vector S of the incident light can be usedinTo obtain the Stokes vector S of the emergent lightout。
Step 203: a polarization information image of the target object surface is determined.
In the embodiment of the invention, after the Stokes parameter map is obtained through the Stokes formula, the polarization degree and the polarization angle can be calculated by utilizing the Stokes parameter, so that the polarization information image of the surface of the target object is obtained. Specifically, calculating the degree of polarization and the polarization angle may be performed by the following equations:
wherein p is used for characterizing the polarization degree of the polarization information image, and α is used for characterizing the polarization angle of the polarization information image.
It is known from fresnel's law that when unpolarized light is incident on the surface of a target object medium and reflected, the polarization state of the incident light changes to generate partially polarized light, and radiation light generated by thermal radiation of an object also exhibits a polarization effect, so that the polarization states of the radiation light waves reflected by different objects or different states of the same object are significantly different. Usually, the characteristic quantities characterizing the target polarization state information mainly include a polarization degree, a polarization angle and the like, wherein the polarization degree refers to a ratio of light intensity of a polarized part in a light beam to the whole light intensity, and is a dimensionless number with a value range within a [0,1] interval. Therefore, in the embodiment of the invention, by representing the polarization information image of the target object by using the information of the polarization degree and the polarization angle, the advantages of the polarization image in the aspects of highlighting the target contour, improving the contrast of the disguised target and the like can be utilized to extract the contour features of the target object, so that the accuracy of feature extraction on the target object is improved.
Here, since the circularly polarized component is very weak in the polarization effect of the natural atmospheric background and the target object on the solar incidence, the circularly polarized component S is not expressed in the above calculation formulas of the degree of polarization and the polarization angle3Among others, are considered.
Step 204: and performing Gaussian filtering on the polarization information image.
Any edge detection algorithm cannot be well processed on unprocessed original data, so in the embodiment of the invention, a proper Gaussian filter is selected firstly, namely a filter function is determined, and the polarization information image is filtered, so that pixel points generated by noise in the polarization information image are removed. Specifically, the data of the polarized image is first convolved with a gaussian smoothing template, and the resulting image is slightly blurred compared to the original image. Thus, the noise of a single pixel becomes almost unaffected on the gaussian-smoothed image.
The image is subjected to Gaussian filtering, which can be realized by weighting two one-dimensional Gaussian kernels twice respectively, namely, one-dimensional convolution in the X direction is performed first, and the obtained result is subjected to one-dimensional convolution in the Y direction. Of course, it can also be realized by one convolution directly through a two-dimensional Gaussian kernel, that is, a two-dimensional convolution template. For example, in the process of implementing gaussian filtering by a two-dimensional convolution template, assume that the two-dimensional gaussian function is:
the gaussian coefficient of each point in the template can be calculated by the above formula, and it is necessary to normalize, that is, the coefficient of each point is divided by the sum of all coefficients, so that the final two-dimensional gaussian template is obtained. After the template is obtained through calculation, the polarization image and the template are convolved, wherein the convolution means that the size area of the template near a pixel point in the image is multiplied by the Gaussian template area, and the obtained result is the result after the point is convolved. The core meaning of convolution is the property of acquiring the template features of the target image in the original image. For example, the expression of the gaussian-filtered image G (x, y) obtained by convolving the polarization information image F (x, y) with the above-described gaussian template H (x, y) can be expressed as follows:
step 205: a first gradient magnitude is determined using a difference calculation.
In an embodiment of the invention, at least one first gradient magnitude is determined using finite difference calculations, wherein the first gradient magnitude is the amplitude of the partial derivative along the coordinate axis, each first gradient magnitude corresponding to a pixel position. When gradient calculation is carried out, because the gradient of the gray value of the image can be approximated by a first-order difference, a Canny operator mainly obtains a gradient operator by solving partial derivatives of the polarization information image in the x direction and the y direction;
when the gradient and the gradient direction are calculated, the four masks of horizontal, vertical, right diagonal and anti diagonal are used for detecting the edge. And storing the convolution of the original image and the four masks, wherein the gradient amplitude of each pixel point is the maximum value of the gradient amplitudes in the four directions, and the direction is the direction corresponding to the maximum value of the amplitude, so that the gradient and the gradient direction of each pixel point in the image can be calculated.
Step 206: a second gradient magnitude is obtained from the first gradient magnitude.
In embodiments of the present invention, non-maxima suppression of gradient amplitudes is required. The larger the element in the image gradient magnitude matrix, the larger the gradient value of the point in the image, but it does not indicate that the point is an edge. The non-maximum suppression is to eliminate non-edge pixels, thin ridge bands in the amplitude image and only reserve points with the maximum local amplitude change, so that the characteristics of edges, contours and the like can be determined.
Step 207: edge detection is performed using a dual threshold algorithm.
In the embodiment of the invention, whether the pixel point corresponding to the second gradient amplitude is the edge pixel point is determined by judging the magnitude relation between the second gradient amplitude and the preset double threshold value. Specifically, this can be achieved by:
determining a first threshold value and a second threshold value according to the polarization degree of the polarization information image, wherein the second threshold value is larger than the first threshold value;
for each pixel in the polarization information image, performing:
if the second gradient amplitude corresponding to the pixel is larger than or equal to a second threshold value, determining the pixel as an edge pixel of the target object;
if the second gradient amplitude corresponding to the pixel is larger than the first threshold and smaller than the second threshold, and the second gradient amplitude corresponding to at least one pixel adjacent to the pixel in the polarization information image is larger than or equal to the second threshold, determining the pixel as an edge pixel of the target object;
it can be seen that if the second gradient magnitude at a certain pixel location exceeds the second threshold, the pixel will be determined to be an edge pixel. If the second gradient magnitude at a pixel location is less than the first threshold, the pixel will be determined to be a non-edge pixel and thus excluded. If the second amplitude of a pixel location is between two thresholds, the pixel is determined to be an edge pixel only if it can be connected to a pixel for which the second gradient amplitude is greater than the second threshold. When the first threshold and the second threshold are determined, the value range of the double thresholds can be set according to the value range of the target edge polarization degree in the linear polarization information image, and then the target edge profile is effectively extracted.
For example, when determining an edge, a pixel having a larger gradient magnitude may be an edge, but there is no certain value that can determine how large a gradient magnitude corresponding pixel is an edge pixel. The Canny algorithm employs a hysteresis threshold strategy, using a high threshold (second threshold) and a low threshold (first threshold) for edge pixel detection. With these two thresholds, three edge images N can be obtainedH(x,y)、NL(x, y) and NM(x, y) wherein NH(x, y) is obtained by being greater than a high threshold, which is relatively disturbed by noiseSmall, which is also closer to the true edge, so that the second gradient magnitude can be directly made larger than the high threshold NHAnd determining the pixel point of (x, y) as an edge pixel. In contrast, NL(x, y) is derived from less than the low threshold, which is clearly very unlikely to be an edge pixel, thereby excluding this pixel. N is a radical ofM(x, y) is a pixel point where the second gradient amplitude is between the high threshold and the low threshold, and it is obvious that the pixel point may be an edge pixel point or a non-edge pixel point, that is, only N is presentH(x,y)、NLThe (x, y) edge image is inevitably interrupted or not closed, and the dual-threshold algorithm judges NMWhether the (x, y) pixel points can find the contour edge which can be connected with the (x, y) pixel points in the eight surrounding pixel points or not is determined, so that whether the pixel points are edge pixels or not is determined, and therefore when the feature extraction of the target object is carried out, the polarization information feature image with the complete contour can be obtained.
As shown in fig. 3 and 4, the embodiment of the present invention provides an apparatus in which the feature extraction device of the target object is located and a feature extraction device of the target object. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware level, as shown in fig. 3, a hardware structure diagram of a device in which a feature extraction apparatus of a target object is located is provided for an embodiment of the present invention, and in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 3, the device in which the apparatus is located in the embodiment may also include other hardware, such as a forwarding chip responsible for processing a packet, in general. Taking a software implementation as an example, as shown in fig. 4, as a logical apparatus, the apparatus is formed by reading a corresponding computer program instruction in a non-volatile memory into a memory by a CPU of a device in which the apparatus is located and running the computer program instruction. As shown in fig. 4, an embodiment of the present invention provides a target object feature extraction apparatus, including: a first determining module 401, a second determining module 402 and a third determining module 403;
a first determining module 401, configured to obtain a Stokes parameter map according to an infrared radiation image of a target object;
a second determining module 402, configured to obtain a polarization information image of the surface of the target object through the Stokes parameter map determined by the first determining module 401, where the polarization information image is used to represent a polarization degree value of the surface of the target object;
a third determining module 403, configured to perform feature extraction on the polarization information image determined by the second determining module 402 by using a Canny operator to obtain a polarization information feature image, where the polarization information feature image represents a contour of the target object.
Optionally, as shown in fig. 4, the first determining module 401 is configured to perform the following operations:
respectively collecting infrared radiation images I of target objects0°、I45°、I90°And I135°Wherein, an infrared radiation image I0°、I45°、I90°And I135°Obtained at polarization directions of 0 °, 45 °, 90 ° and 135 °, respectively;
calculating the Stokes parameters of the infrared radiation image according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPRight-handed circular polarization, I, for characterizing infrared radiation imagesLCPFor characterizing the left-hand circular polarization of the infrared radiation image.
Optionally, according to the above-described feature extraction apparatus of a target object, the second determining module 402 is configured to perform the following operations:
and calculating and obtaining a polarization information image of the surface of the target object according to the following formula by using the Stokes parameter map:
wherein p is used for characterizing the polarization degree of the polarization information image, and α is used for characterizing the polarization angle of the polarization information image.
Alternatively, based on the feature extraction apparatus of a target object in fig. 4, as shown in fig. 5, the third determining module 403 includes: a filtering unit 4031, a calculating unit 4032, an acquiring unit 4033 and a determining unit 4034;
a filtering unit 4031, configured to perform gaussian filtering on the polarization information image to obtain a first feature image, where the first feature image is used to represent an image of the polarization information image after removing noise points;
a calculating unit 4032, configured to determine at least one first gradient amplitude of the first feature image filtered by the filtering unit 4031 by using finite difference calculation, where the first gradient amplitude is an amplitude of a partial derivative of the first feature image along the coordinate axis direction, and each first gradient amplitude corresponds to a pixel position;
an obtaining unit 4033, configured to obtain a second gradient amplitude from the first gradient amplitude determined by the calculating unit 4032, where the second gradient amplitude is an amplitude image from which non-edge pixels are removed;
a determining unit 4034, configured to determine, by using a preset dual-threshold algorithm, a polarization information feature image from the second gradient amplitude acquired by the acquiring unit 4033.
Alternatively, as shown in fig. 5, the determining unit 4034 is configured to perform the following operations:
determining a first threshold value and a second threshold value according to the polarization degree of the target surface, wherein the second threshold value is larger than the first threshold value;
for each pixel in the polarization information image, performing:
if the second gradient amplitude corresponding to the pixel is larger than or equal to a second threshold value, determining the pixel as an edge pixel of the target object;
if the second gradient amplitude corresponding to the pixel is larger than the first threshold and smaller than the second threshold, and the second gradient amplitude corresponding to at least one pixel adjacent to the pixel in the polarization information image is larger than or equal to the second threshold, determining the pixel as an edge pixel of the target object;
and connecting the edge pixels to obtain a polarization information characteristic image.
The embodiment of the present invention further provides a device for extracting features of a target object, which is characterized by including: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform the feature extraction method for the target object in any embodiment of the present invention.
Embodiments of the present invention further provide a storage medium, where the storage medium stores computer instructions, and the computer instructions, when executed by a processor, cause the processor to execute the feature extraction method for a target object in any embodiment of the present invention. Specifically, a method or an apparatus equipped with a storage medium on which a software program code that realizes the functions of any of the above-described embodiments is stored may be provided, and a computer (or a CPU or MPU) of the method or the apparatus is caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments can be implemented not only by executing the program code read out by the computer, but also by performing a part or all of the actual operations by an operation method or the like operating on the computer based on instructions of the program code.
In summary, the method, the apparatus and the computer-readable medium for extracting features of a target object provided in the embodiments of the present invention at least have the following advantages:
1. in the embodiment of the invention, for a target object which needs to be subjected to feature extraction, an infrared radiation image of the target object is obtained through a polarization device, then a Stokes parameter map of the infrared radiation image is obtained according to a Stokes formula, a polarization information image of the Stokes parameter map is obtained through a polarization degree and polarization angle formula, and finally a Canny operator is utilized to perform feature extraction on the polarization information image to obtain a polarization information feature image. Therefore, the method and the device adopt the modes of the polarization information image and the Canny operator in sequence to extract the characteristics of the target object. The polarization information image has an advantage in highlighting edge details of the target object, and the Canny operator has an advantage in identifying dark target areas, so that the Canny operator is used for extracting the features of the polarization information image, namely, the polarization information image and the Canny operator are combined to facilitate the extraction of the outline and the edge details of the dark target areas in the polarization information image, and the accuracy of feature extraction of the target object is improved.
2. In the embodiment of the invention, infrared radiation images with the polarization directions of 0 degrees, 45 degrees, 90 degrees and 135 degrees are collected by rotating the polaroid, and the Stokes parameter graph is determined according to the infrared radiation images. In the scheme, the light intensity information of each polarization direction is measured and acquired by rotating the polarizing film, and the Stokes parameter is represented by the light intensity, so that the polarization state of the infrared radiation image is described by adopting the Stokes parameter, and the method not only has the advantages of directly measuring and acquiring the light intensity and being simple and convenient to calculate, but also is the basis for acquiring the polarization information image subsequently.
3. In the embodiment of the invention, the polarization information image is obtained by substituting the obtained Stokes parameters into the polarization degree and polarization angle formula. After the electromagnetic waves are reflected and radiated by the surface of the object, the polarization state of the electromagnetic waves can be changed according to the structure and the texture of the surface and the incident angle of the electromagnetic waves on the surface, so that some information of the surface of the object can be enhanced, and therefore, some information which is difficult to characterize through intensity measurement can be represented through a polarization information image formed by the polarization degree and the polarization angle. Therefore, the polarization information image is obtained by calculating the polarization degree and the polarization angle of the target object, and some feature information such as the outline and the structure of the target object can be obtained, so that feature extraction of the target object is realized.
4. In the embodiment of the invention, when the polarization information characteristic image is obtained by extracting the characteristics of the polarization image, firstly, a proper filter needs to be selected, the polarization information image is filtered by using a filtering algorithm, some pixel points generated due to noise are removed, then, a first gradient amplitude of each pixel position in the filtered image is determined by using a finite difference calculation mode, a second gradient amplitude is further determined from the first gradient amplitude by using a non-maximum suppression method to remove non-edge pixel points in the image, and finally, the polarization characteristic image is determined by setting a dual-threshold algorithm of a high threshold and a low threshold. Therefore, according to the scheme, the noise influence is removed in a filtering mode, and whether the calculated pixel point amplitude corresponds to the edge pixel of the target object outline or not is judged in sequence, so that the edge pixel is continuously screened, and the accuracy of feature extraction on the target object is improved.
5. Since the pixel with the higher second gradient magnitude is more likely to be an edge pixel, there is no exact value to define how many edge pixels or less than how many non-edge pixels the second gradient magnitude reaches. Therefore, in the embodiment of the present invention, by setting a high threshold and a low threshold, not only the pixel points whose second gradient amplitude is greater than the high threshold can be determined as edge pixel points, but also the non-edge pixel points generated by noise can be further removed by determining whether the pixel points whose second gradient amplitude is greater than the first threshold and less than the second threshold can be combined with the pixel points of the high threshold to form a curve, so that the accuracy of extracting the edge contour features of the target object is ensured.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for extracting features of a target object, comprising:
obtaining a Stokes parameter map according to the infrared radiation image of the target object;
obtaining a polarization information image of the surface of the target object through the Stokes parameter map, wherein the polarization information image is used for representing the polarization degree value of the surface of the target object;
and performing feature extraction on the polarization information image by using a Canny operator to obtain a polarization information feature image, wherein the polarization information feature image represents the outline of the target object.
2. The method according to claim 1, wherein the obtaining a Stokes reference map from an infrared radiation image of a target object comprises:
respectively collecting infrared radiation images I of the target objects0°、I45°、I90°And I135°Wherein the infrared radiation image I0°、I45°、I90°And I135°Obtained at polarization directions of 0 °, 45 °, 90 ° and 135 °, respectively;
calculating the Stokes parameters of the infrared radiation image according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPFor characterizing the right-hand circular polarization of the infrared radiation image, ILCPFor characterizing the left-hand circular polarization of the infrared radiation image.
3. The method of claim 2, wherein obtaining the polarization information image of the target object surface through the Stokes parameter map comprises:
calculating and obtaining a polarization information image of the surface of the target object according to the following formula by using the Stokes parameter map:
wherein p is used for characterizing the polarization degree of the polarization information image, and α is used for characterizing the polarization angle of the polarization information image.
4. The method according to claim 1, wherein the performing feature extraction on the polarization information image by using a Canny operator to obtain a polarization information feature image comprises:
performing Gaussian filtering on the polarization information image to obtain a first characteristic image, wherein the first characteristic image is used for representing the image of the polarization information image after removing noise points;
determining at least one first gradient amplitude of the first characteristic image by utilizing finite difference calculation, wherein the first gradient amplitude is the amplitude of a partial derivative of the first characteristic image along the coordinate axis direction, and each first gradient amplitude corresponds to one pixel position;
acquiring a second gradient amplitude from the first gradient amplitude, wherein the second gradient amplitude is an amplitude image without non-edge pixels;
and determining a polarization information characteristic image from the second gradient amplitude by using a preset double-threshold algorithm.
5. The method of claim 4, wherein determining a polarization information signature image from the second gradient magnitude using a pre-defined dual threshold algorithm comprises:
determining a first threshold value and a second threshold value according to the polarization degree of the polarization information image, wherein the second threshold value is larger than the first threshold value;
for each pixel in the polarization information image, performing:
if the second gradient amplitude corresponding to the pixel is larger than or equal to the second threshold value, determining the pixel as an edge pixel of the target object;
if the second gradient amplitude corresponding to the pixel is larger than the first threshold and smaller than the second threshold, and the second gradient amplitude corresponding to at least one pixel adjacent to the pixel in the polarization information image is larger than or equal to the second threshold, determining the pixel as an edge pixel of the target object;
and connecting the edge pixels to obtain the polarization information characteristic image.
6. A feature extraction device of a target object, characterized by comprising: the device comprises a first determining module, a second determining module and a third determining module;
the first determination module is used for obtaining a Stokes parameter map according to the infrared radiation image of the target object;
the second determining module is configured to obtain a polarization information image of the target object surface through the Stokes parameter map determined by the first determining module, where the polarization information image is used to characterize a polarization degree value of the target object surface;
the third determining module is configured to perform feature extraction on the polarization information image determined by the second determining module by using a Canny operator to obtain a polarization information feature image, where the polarization information feature image represents a contour of the target object.
7. The apparatus of claim 6,
the first determining module is configured to perform the following operations:
respectively collecting infrared radiation images I of the target objects0°、I45°、I90°And I135°Wherein the infrared radiation image I0°、I45°、I90°And I135°Obtained at polarization directions of 0 °, 45 °, 90 ° and 135 °, respectively;
calculating the Stokes parameters of the infrared radiation image according to the following formula:
wherein S is used for representing Stokes parameters, S0、S1、S2And S3Are all components of the Stokes parameter S, IRCPFor characterizing the right-hand circular polarization of the infrared radiation image, ILCPFor characterizing the left-hand circular polarization of the infrared radiation image.
8. The apparatus of claim 7,
the second determining module is configured to perform the following operations:
calculating and obtaining a polarization information image of the surface of the target object according to the following formula by using the Stokes parameter map:
wherein p is used for characterizing the polarization degree of the polarization information image, and α is used for characterizing the polarization angle of the polarization information image.
9. A feature extraction device of a target object, characterized by comprising: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor, configured to invoke the machine readable program, to perform the method of any of claims 1 to 5.
10. A computer readable medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011065455.3A CN112163587A (en) | 2020-09-30 | 2020-09-30 | Feature extraction method and device of target object and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011065455.3A CN112163587A (en) | 2020-09-30 | 2020-09-30 | Feature extraction method and device of target object and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112163587A true CN112163587A (en) | 2021-01-01 |
Family
ID=73861253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011065455.3A Pending CN112163587A (en) | 2020-09-30 | 2020-09-30 | Feature extraction method and device of target object and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163587A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674197A (en) * | 2021-07-02 | 2021-11-19 | 华南理工大学 | Method for dividing back electrode of solar cell |
| CN116907677A (en) * | 2023-09-15 | 2023-10-20 | 山东省科学院激光研究所 | Distributed optical fiber temperature sensing system for concrete structure and measuring method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033599A (en) * | 2015-03-20 | 2016-10-19 | 南京理工大学 | Visible light enhancement method based on polarized imaging |
| CN108596931A (en) * | 2018-05-11 | 2018-09-28 | 浙江大学 | A kind of noise robustness hub edge detection algorithm based on Canny operators |
| CN111667519A (en) * | 2020-06-05 | 2020-09-15 | 北京环境特性研究所 | Registration method and device for polarized images with different fields of view |
-
2020
- 2020-09-30 CN CN202011065455.3A patent/CN112163587A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033599A (en) * | 2015-03-20 | 2016-10-19 | 南京理工大学 | Visible light enhancement method based on polarized imaging |
| CN108596931A (en) * | 2018-05-11 | 2018-09-28 | 浙江大学 | A kind of noise robustness hub edge detection algorithm based on Canny operators |
| CN111667519A (en) * | 2020-06-05 | 2020-09-15 | 北京环境特性研究所 | Registration method and device for polarized images with different fields of view |
Non-Patent Citations (2)
| Title |
|---|
| TECHARTISAN6: "数字图像处理(20): 边缘检测算子(Canny算子)", pages 1 - 6, Retrieved from the Internet <URL:https://blog.csdn.net/zaishuiyifangxym/article/details/90142702> * |
| 徐文斌；陈伟力；李军伟: "长波红外高光谱偏振特性的伪装目标识别方法", 《光谱学与光谱分析》, pages 235 - 240 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674197A (en) * | 2021-07-02 | 2021-11-19 | 华南理工大学 | Method for dividing back electrode of solar cell |
| CN113674197B (en) * | 2021-07-02 | 2022-10-04 | 华南理工大学 | Method for dividing back electrode of solar cell |
| CN116907677A (en) * | 2023-09-15 | 2023-10-20 | 山东省科学院激光研究所 | Distributed optical fiber temperature sensing system for concrete structure and measuring method thereof |
| CN116907677B (en) * | 2023-09-15 | 2023-11-21 | 山东省科学院激光研究所 | Distributed optical fiber temperature sensing system for concrete structure and measuring method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ahmed | Comparative study among Sobel, Prewitt and Canny edge detection operators used in image processing | |
| CN107220988B (en) | Part image edge extraction method based on improved canny operator | |
| Yu et al. | Efficient patch-wise non-uniform deblurring for a single image | |
| KR20150117646A (en) | Method and apparatus for image enhancement and edge verification using at least one additional image | |
| JP2012008100A (en) | Image processor, image processing method and image processing program | |
| WO2021217642A1 (en) | Infrared image processing method and apparatus, and movable platform | |
| CN110378902B (en) | Scratch detection method under high noise background | |
| KR101928391B1 (en) | Method and apparatus for data fusion of multi spectral image and radar image | |
| CN112163587A (en) | Feature extraction method and device of target object and computer readable medium | |
| Chen et al. | Median filtering detection using edge based prediction matrix | |
| Lawgaly et al. | Image sharpening for efficient source camera identification based on sensor pattern noise estimation | |
| Barros et al. | Single-shot underwater image restoration: A visual quality-aware method based on light propagation model | |
| CN114972123A (en) | Image denoising processing method and device, computer equipment and readable storage medium | |
| Wu et al. | Image haze removal: Status, challenges and prospects | |
| Wang et al. | Digital image forgery detection based on the consistency of defocus blur | |
| CN112163586A (en) | Feature extraction method and device of target object and computer readable medium | |
| CN116958058A (en) | Lens dirt detection method and device and image detection equipment | |
| CN116380918A (en) | Defect detection method, device and equipment | |
| CN111311610A (en) | Image segmentation method and terminal equipment | |
| Reich et al. | A Real-Time Edge-Preserving Denoising Filter. | |
| Singhal et al. | Speckle noise removal and edge detection using mathematical morphology | |
| Tao | Enhanced Canny Algorithm for Image Edge Detection in Print Quality Assessment | |
| CN115018817A (en) | Scratch detection method, scratch detection device, electronic equipment and readable storage medium | |
| Wang et al. | High-iso long-exposure image denoising based on quantitative blob characterization | |
| CN113052833A (en) | Non-vision field imaging method based on infrared thermal radiation |
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 |