Visual image processing method, device, equipment and medium based on strain mechanism

Abstract

The present invention discloses a visual image processing method, device, equipment and medium based on a strain mechanism, including: obtaining a plurality of photon energy information based on a charge coupled device camera or an infrared camera, and extracting the change elements between the photons based on the photon energy information, wherein the change elements include fluctuation difference change, dimension change and frequency change; generating a plurality of energy fields according to the change elements between the photons, wherein the energy fields include a plurality of feature information, and the types of feature information include boundary features, morphological features and scale features; performing spatial reasoning according to the feature information of the energy fields, and splicing the energy fields to obtain the geometric shape of the object. The present invention belongs to the field of image processing. The present invention realizes a "universal algorithm" for visual image processing based on a strain mechanism, solves the problem of global application, can accurately and reliably find the target of interest in any environment, and reduces energy consumption.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a visual image processing method, device, equipment and medium based on a strain mechanism. Background Art

[0002] Visual image processing is an interdisciplinary field that combines knowledge from computer science, mathematics, physics, and engineering, focusing on extracting useful information from digital images or video sequences. Visual image processing aims to simulate the capabilities of the human visual system to automatically interpret, understand, and manipulate image data, thereby achieving a range of applications such as object recognition, scene understanding, image enhancement, medical diagnosis, etc.

[0003] With the continuous development of artificial intelligence technology, visual image processing technology has also developed rapidly. The currently widely used technologies are deep learning and large model technologies based on neural networks. However, visual image processing technology requires a large amount of sample data to train the model. However, the environment is ever-changing, and it is difficult to obtain high-quality training samples in various situations. In addition, the model has more and more parameters and is more and more complex. It requires powerful hardware support, resulting in problems such as high computing power, high energy consumption, and high cost. Therefore, it is urgent to propose a low-cost visual image processing method. Summary of the invention

[0004] The present invention solves the technical problem of high energy consumption in image visual processing in the prior art by providing a visual image processing method, device, equipment and medium based on a strain mechanism, and achieves the technical effect of performing image processing with low energy consumption.

[0005] In a first aspect, the present invention provides a visual image processing method based on a strain mechanism, the method comprising:

[0006] Acquire energy information of a number of photons based on a charge coupled device camera or an infrared camera, and extract change factors between photons based on the energy information of the photons, wherein the change factors include fluctuation difference change, dimension change and frequency change;

[0007] According to the change factors between the light quanta, a number of energy fields are generated, wherein the energy fields include a number of characteristic information, and the types of characteristic information include boundary characteristics, morphological characteristics and scale characteristics;

[0008] Based on the characteristic information of the energy field, spatial reasoning is performed, and the energy field is spliced ​​to obtain the geometric shape of the object.

[0009] Furthermore, obtaining some photon energy information based on a charge coupled device camera or an infrared camera also includes:

[0010] A CCD camera or an infrared camera acquires a certain amount of photon energy information and converts the certain amount of photon energy information into an electronic signal;

[0011] The CCD camera or infrared camera generates a target image corresponding to a certain amount of light quantum energy information based on the electronic signal.

[0012] Furthermore, based on the photon energy information, the variation factors between photons are extracted, including:

[0013] Based on a preset detection algorithm, the fluctuation difference between the photon energy of each pixel point in each row of pixels in the target image is extracted;

[0014] According to the number of fluctuation differences in each row, it is divided into several energy segments;

[0015] The frequency of each energy segment is obtained, and the starting spatial position, ending spatial position and length corresponding to the energy segment are determined.

[0016] Furthermore, according to the fluctuation differences in each row, several energy segments are obtained, including:

[0017] Determine the fluctuation difference between each pixel point in each row of the target image in sequence according to the arrangement order of each pixel point in each row of pixels in the target image;

[0018] When the fluctuation difference between the pixels in each row is greater than the preset fluctuation threshold, it is divided once to obtain an energy segment.

[0019] Furthermore, according to the changing factors between light quanta, several energy fields are generated, including:

[0020] According to the starting spatial positions, ending spatial positions and lengths corresponding to the energy segments, adjacent energy segments with the same photon energy are merged to obtain several energy fields;

[0021] Boundary information of each energy field is extracted to obtain characteristic information corresponding to each energy field.

[0022] Furthermore, according to the starting spatial positions, ending spatial positions and lengths corresponding to the energy segments, the adjacent energy segments with the same photon energy are merged to obtain several energy fields, including:

[0023] According to the starting spatial position and the ending spatial position of the energy segments with the same photon energy, it is determined whether the energy segments with the same photon energy are adjacent;

[0024] Adjacent energy segments with the same photon energy are spliced ​​together according to the length of each energy segment to obtain an energy field.

[0025] Furthermore, spatial reasoning is performed based on the characteristic information of the energy field, and the energy field is spliced ​​to obtain the geometric shape of the object, including:

[0026] According to the morphological characteristics of each energy field, adjacent spaces are spliced ​​together to obtain the main body form;

[0027] Analyze the geometric features of the body morphology to obtain the geometric center point;

[0028] Construct geometric skeleton line segments based on geometric center points;

[0029] The geometric shape of the object in the target image is obtained according to the geometric skeleton line segments.

[0030] In a second aspect, the present invention provides a visual image processing device based on a strain mechanism, the device comprising:

[0031] An element extraction module is used to obtain a number of photon energy information based on a charge coupled device camera or an infrared camera, and extract the change elements between photons based on the photon energy information, wherein the change elements include fluctuation difference change, dimension change and frequency change;

[0032] An energy field division module is used to generate a number of energy fields according to the change elements between light quanta, wherein the energy fields include a number of characteristic information, and the types of characteristic information include boundary characteristics, morphological characteristics and scale characteristics;

[0033] The shape generation module is used to perform spatial reasoning based on the characteristic information of the energy field and to splice the energy field to obtain the geometric shape of the object.

[0034] In a third aspect, the present invention provides an electronic device, comprising:

[0035] processor;

[0036] a memory for storing processor-executable instructions;

[0037] The processor is configured to execute to implement the visual image processing method based on the strain mechanism as provided in the first aspect.

[0038] In a fourth aspect, the present invention provides a non-temporary computer-readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to implement the visual image processing method based on the strain mechanism as provided in the first aspect.

[0039] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0040] The present invention provides a visual image processing method based on a strain mechanism, the method comprising: obtaining a number of photon energy information based on a charge coupled device camera or an infrared camera, and extracting the change elements between the photons based on the photon energy information, wherein the change elements include fluctuation difference change, dimension change and frequency change; generating a number of energy fields according to the change elements between the photons, wherein the energy fields include a number of feature information, and the types of feature information include boundary features, morphological features and scale features; performing spatial reasoning according to the feature information of the energy fields, and splicing the energy fields to obtain the geometric shape of the object. The present invention implements a "universal algorithm" for visual image processing based on a strain mechanism, solves the global application problem, and can accurately and reliably find the target of interest in any environment; no training and learning are required, which reduces computing power and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A schematic flow chart of the visual image processing method based on the strain mechanism provided by the present invention. DETAILED DESCRIPTION

[0043] The embodiment of the present invention solves the technical problem of high energy consumption in image visual processing in the prior art by providing a visual image processing method based on a strain mechanism.

[0044] The technical solution of the present invention is to solve the above technical problems, and the overall idea is as follows:

[0045] A visual image processing method based on strain mechanism, the method comprising: obtaining a plurality of photon energy information based on a charge coupled device camera or an infrared camera, and extracting change factors between photons based on the photon energy information, wherein the change factors include fluctuation difference change, dimensional change and frequency change; generating a plurality of energy fields according to the change factors between photons, wherein the energy fields include a plurality of feature information, and the types of feature information include boundary features, morphological features and scale features; performing spatial reasoning according to the feature information of the energy fields, and splicing the energy fields to obtain the geometric shape of the object.

[0046] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0047] First of all, the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0048] The present invention provides Figure 1 The visual image processing method based on the strain mechanism shown includes steps S11-S13:

[0049] Step S11, acquiring energy information of a number of photons based on a charge coupled device camera or an infrared camera, and extracting change factors between photons based on the energy information of the photons, wherein the change factors include fluctuation difference change, dimension change and frequency change.

[0050] Specifically, it also includes: a CCD camera or an infrared camera acquires a number of photon energy information and converts the a number of photon energy information into electronic signals; the CCD camera or the infrared camera generates a target image corresponding to the a number of photon energy information based on the electronic signals.

[0051] Infrared cameras or charge-coupled device (CCD) cameras have a charge-coupled device as a photosensitive element. When a photon hits a pixel on the CCD, a certain number of electron-hole pairs are generated according to the photoelectric effect. The number of electrons generated is proportional to the energy of the incident photon, and the electrons are collected and stored in a capacitor. The accumulated charge is converted into a digital signal through an analog-to-digital converter (ADC), forming an energy value in the image.

[0052] Extracting variation factors between photons based on photon energy information, including: extracting the fluctuation difference between the photon energies of each pixel point in each row of pixels in the target image based on a preset detection algorithm; dividing the energy segments according to a number of fluctuation differences in each row to obtain a number of energy segments; obtaining the frequency of each energy segment, and determining the starting spatial position, ending spatial position and length corresponding to the energy segment.

[0053] The preset detection algorithm may be an edge detection algorithm, etc., which is not limited here. It is understandable that the target image is composed of a number of pixels, there are a number of rows of pixels in the target image, there are a number of pixels in each row, and each pixel has a fixed photon energy value (or a fixed grayscale value). In each row of pixels, the energy value difference of each pixel is the fluctuation difference between the pixels.

[0054] According to a number of fluctuation differences existing in each row, division is performed to obtain a number of energy segments, including: determining the fluctuation difference between each pixel point in each row of the target image in sequence according to the arrangement order of each pixel point in each row of pixels in the target image; when the fluctuation difference between each pixel point in each row is greater than a preset fluctuation threshold, division is performed once to obtain an energy segment.

[0055] For example, there are 10 pixels in the first row of the target image, and their energy values ​​are 1, 1, 2, 2, 3, 1, 5, 4, 6, and 5. The energy value of the first pixel is calculated in turn with the energy values ​​of the following 9 pixels. When the difference between the energy value of the first pixel and the energy value of a certain pixel in the same row is greater than the preset fluctuation threshold, the pixels before the certain pixel in the same row are divided into an energy segment. For example, if the preset fluctuation threshold is 2, the energy value of the first pixel is not greater than 2 until the difference between the energy value of the first pixel and the energy value of the seventh pixel. In this case, the first pixel to the sixth pixel are divided into an energy segment, and the seventh pixel is used as a new starting point to restart the calculation.

[0056] The frequency of an energy band refers to the number of photons that fall into the energy band within a certain period of time. The number of photons can be used to know the radiation intensity or brightness level corresponding to the energy band.

[0057] For the target image, each pixel has coordinates (x, y). The starting spatial position corresponding to the energy segment is the position where the pixel in the energy segment first appears, that is, the coordinate pair consisting of the minimum row number and column number. The ending spatial position corresponding to the energy segment is the position where the pixel in the energy segment last appears, that is, the coordinate pair consisting of the maximum row number and column number. The length of the energy segment is the number of pixels in the area (it can also be the maximum distance in the row direction).

[0058] Step S12, generating a plurality of energy fields according to the change factors between the photons, wherein the energy fields include a plurality of characteristic information, and the types of the characteristic information include boundary characteristics, morphological characteristics and scale characteristics.

[0059] According to the changing factors between photons, several energy fields are generated, including: according to the starting spatial positions, ending spatial positions and lengths corresponding to several energy segments, adjacent energy segments with the same photon energy are merged to obtain several energy fields; boundary information of each energy field is extracted to obtain the characteristic information corresponding to each energy field.

[0060] Having the same photon energy means that the energy values ​​of the two energy ranges are the same.

[0061] According to the starting spatial positions, ending spatial positions and lengths corresponding to several energy segments, adjacent energy segments with the same photon energy are merged to obtain several energy fields, including: judging whether the energy segments with the same photon energy are adjacent according to the starting spatial positions and ending spatial positions of the energy segments with the same photon energy; and splicing the adjacent energy segments with the same photon energy according to the lengths of each energy segment to obtain an energy field.

[0062] It should be noted that non-adjacent energy segments with the same photon energy shall not be classified as the same energy field. Adjacent means that there is at least one identical y value between the pixels of the energy segment, and the difference between the x values ​​is 1. For example, the starting spatial position of a certain energy segment A in the first row is (1.1) and the ending spatial position is (1.10), the starting spatial position of a certain energy segment B in the second row is (2.5) and the ending spatial position is (2.10), the starting spatial position of a certain energy segment C in the third row is (3.9) and the ending spatial position is (3.10), the starting spatial position of a certain energy segment D in the third row is (3.20) and the ending spatial position is (3.22), and the energy values ​​of energy segments A, B, C, and D are all the same.

[0063] Obviously, energy segment A is adjacent to energy segment B, energy segment B is adjacent to energy segment C, and energy segment B is not adjacent to energy segment D. Then energy segment A, energy segment B and energy segment C are spliced ​​together to obtain an energy field.

[0064] By performing the boundary information extraction process on each energy field, the outer contour of each energy segment can be accurately identified and depicted, and the geometric shape, structural complexity and spatial extension of the energy field can be further analyzed, ultimately obtaining boundary features (such as boundary length, curvature), morphological features (such as area, circumference, circularity, main axis direction) and scale features (such as center of mass position, bounding box size, equivalent diameter).

[0065] Step S13, performing spatial reasoning based on the characteristic information of the energy field, and splicing the energy field to obtain the geometric shape of the object.

[0066] According to the characteristic information of the energy field, spatial reasoning is performed and the energy fields are spliced ​​to obtain the geometric shape of the object, including: according to the morphological characteristics of each energy field, spatial adjacent splicing is performed to obtain the main body shape; geometric feature analysis is performed on the main body shape to obtain the geometric center point and construct geometric skeleton line segments with the geometric center point; the geometric shape of the object in the target image is obtained according to the geometric skeleton line segments.

[0067] First, by analyzing the morphological characteristics of each energy field, the specific shape, size and spatial distribution of each energy segment are identified. Based on the morphological characteristics, the spatial adjacent splicing technology is used to reassemble the parts that belong to the same object but are divided into different energy segments to form a complete body morphology. After the splicing is completed, the geometric characteristics of the body morphology are analyzed to accurately calculate its geometric center point. The geometric center point is the average position of the coordinates of all points inside the morphology and represents the spatial positioning core of the morphology. Based on this geometric center point, the geometric skeleton line segments are constructed, that is, the main extension directions of the morphology are found through principal component analysis (PCA) or other methods, and line segments are drawn along these directions. These line segments reflect the basic framework and structural characteristics of the morphology. Finally, based on the constructed geometric skeleton line segments, the geometric shape of the object in the target image can be obtained.

[0068] In summary, the present invention provides a visual image processing method based on a strain mechanism, the method comprising: obtaining a number of photon energy information based on a charge coupled device camera or an infrared camera, and extracting the change elements between photons based on the photon energy information, wherein the change elements include fluctuation difference change, dimension change and frequency change; generating a number of energy fields according to the change elements between photons, wherein the energy field includes a number of feature information, and the types of feature information include boundary features, morphological features and scale features; performing spatial reasoning according to the feature information of the energy field, and splicing the energy field to obtain the geometric shape of the object. The present invention implements a "universal algorithm" for visual image processing based on a strain mechanism, solves the problem of global application, and can accurately and reliably find the target of interest in any environment; no training and learning are required, which reduces computing power and energy consumption.

[0069] Based on the same inventive concept, the present invention provides a visual image processing device based on a strain mechanism, the device comprising:

[0070] An element extraction module is used to obtain a number of photon energy information based on a charge coupled device camera or an infrared camera, and extract the change elements between photons based on the photon energy information, wherein the change elements include fluctuation difference change, dimension change and frequency change;

[0071] An energy field division module is used to generate a number of energy fields according to the change elements between light quanta, wherein the energy fields include a number of characteristic information, and the types of characteristic information include boundary characteristics, morphological characteristics and scale characteristics;

[0072] The shape generation module is used to perform spatial reasoning based on the characteristic information of the energy field and to splice the energy field to obtain the geometric shape of the object.

[0073] Based on the same inventive concept, the present invention also provides an electronic device as shown, including:

[0074] processor;

[0075] a memory for storing processor-executable instructions;

[0076] The processor is configured to execute to implement the visual image processing method based on the strain mechanism as provided above.

[0077] Based on the same inventive concept, the present invention also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement the visual image processing method based on the strain mechanism as provided above.

[0078] Since the electronic device introduced in this embodiment is an electronic device used to implement the information processing method in the embodiment of the present invention, based on the information processing method introduced in the embodiment of the present invention, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present invention is not described in detail here. As long as the electronic device used by a person skilled in the art to implement the information processing method in the embodiment of the present invention, it belongs to the scope of protection of the present invention.

[0079] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A visual image processing method based on a strain mechanism, characterized in that: The method comprises: Acquire a number of photon energy information based on a charge coupled device camera or an infrared camera, and extract the change factors between photons based on the photon energy information, wherein the change factors include fluctuation difference change, dimension change and frequency change, wherein acquiring a number of photon energy information based on a charge coupled device camera or an infrared camera also includes: a CCD camera or an infrared camera acquires a number of photon energy information, and converts the number of photon energy information into electronic signals; the CCD camera or the infrared camera generates a target image corresponding to the number of photon energy information according to the electronic signals; extracting the change factors between photons based on the photon energy information includes: extracting the fluctuation difference between the photon energy of each pixel point in each row of pixels in the target image based on a preset detection algorithm; dividing according to the number of fluctuation differences in each row to obtain a number of energy segments; acquiring the frequency of each energy segment, and determining the starting spatial position, ending spatial position and length corresponding to the energy segment; According to the change factors between photons, several energy fields are generated, wherein the energy fields include several characteristic information, and the types of characteristic information include boundary characteristics, morphological characteristics and scale characteristics, wherein: according to the starting spatial positions, ending spatial positions and lengths corresponding to several energy segments, adjacent energy segments with the same photon energy are merged to obtain several energy fields; boundary information is extracted from each energy field to obtain characteristic information corresponding to each energy field; According to the characteristic information of the energy field, spatial reasoning is performed, and the energy fields are spliced ​​to obtain the geometric shape of the object, which includes: according to the morphological characteristics of each energy field, spatial adjacent splicing is performed to obtain the main body form; geometric feature analysis is performed on the main body form to obtain the geometric center point; geometric skeleton line segments are constructed with the geometric center point; and the geometric shape of the object in the target image is obtained according to the geometric skeleton line segments.

2. The visual image processing method based on the strain mechanism according to claim 1, characterized in that: According to the fluctuation differences in each row, several energy segments are obtained, including: Determine the fluctuation difference between each pixel point in each row of the target image in sequence according to the arrangement order of each pixel point in each row of pixels in the target image; When the fluctuation difference between the pixels in each row is greater than the preset fluctuation threshold, it is divided once to obtain an energy segment.

3. The visual image processing method based on strain mechanism as claimed in claim 1, characterized in that: According to the starting spatial position, ending spatial position and length corresponding to several energy segments, adjacent energy segments with the same photon energy are merged to obtain several energy fields, including: According to the starting spatial position and the ending spatial position of the energy segments with the same photon energy, it is determined whether the energy segments with the same photon energy are adjacent; Adjacent energy segments with the same photon energy are spliced ​​together according to the length of each energy segment to obtain an energy field.

4. A visual image processing device based on a strain mechanism, characterized in that: The visual image processing method based on the strain mechanism applied to any one of claims 1 to 3, wherein the device comprises: An element extraction module is used to obtain a number of photon energy information based on a charge coupled device camera or an infrared camera, and extract the change elements between photons based on the photon energy information, wherein the change elements include fluctuation difference change, dimension change and frequency change; An energy field division module is used to generate a number of energy fields according to the change elements between light quanta, wherein the energy fields include a number of characteristic information, and the types of characteristic information include boundary characteristics, morphological characteristics and scale characteristics; The shape generation module is used to perform spatial reasoning based on the characteristic information of the energy field and to splice the energy field to obtain the geometric shape of the object.

5. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute to implement the visual image processing method based on the strain mechanism as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement the visual image processing method based on the strain mechanism as described in any one of claims 1 to 3.

Images