Laser quality detection method and device, electronic equipment and storage medium thereof

Abstract

The embodiment of the invention provides a laser quality detection method and device, and the method comprises the steps: obtaining light field image information of a target object, and the light field image information comprises light field intensity information and light direction information; performing factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain a factor value corresponding to the target object; and determining the laser quality corresponding to the target object based on the factor value. According to the method, factor extraction is carried out on the obtained light field image of the target object through the preset laser measurement model, and in the extraction process, the preset laser measurement model analyzes the light field intensity information and the light direction information of the target object to obtain the factor value corresponding to the target object; and finally, the laser quality of the target object is determined according to the factor value, so that the laser quality can be detected through a deep learning model, the laser detection accuracy is improved, the laser detection process is simplified, and the laser detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of light beam measurement, and in particular to a laser quality detection method, device, electronic equipment and storage medium thereof. Background Art

[0002] With the continuous development of science and technology, optical measurement and image processing technology have shown great potential in many fields, especially in the laser quality analysis of target objects.

[0003] In existing laser measurement technology, the evaluation index factor of the light beam can only be obtained by performing complex calculations on the light field intensity of the light beam and the measured phase distribution. Therefore, the existing laser quality detection method has the defects of complex measurement process and low accuracy because it needs to perform complex calculations on the light field intensity of the light beam and the measured phase distribution to obtain the evaluation index factor of the light beam. Summary of the invention

[0004] An embodiment of the present invention provides a laser quality detection method, which extracts factors from an acquired light field image of a target object through a preset laser measurement model. During the extraction process, the preset laser measurement model analyzes the light field intensity information and light direction information of the target object to obtain a factor value corresponding to the target object, and finally determines the laser quality of the target object based on the factor value.

[0005] In a first aspect, an embodiment of the present invention provides a laser quality detection method, the method comprising the following steps: Acquire a light field image of a target object, wherein the light field image information includes light field intensity information and light direction information; Performing factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain a factor value corresponding to the target object; Based on the factor value, the laser quality corresponding to the target object is determined.

[0006] Optionally, acquiring light field image information of the target object includes: Using a light field camera to photograph the target object in multiple directions to obtain the light field images in multiple directions; Normalization processing is performed on the light field images in the multiple directions to obtain light field image information of the target object.

[0007] Optionally, before performing factor extraction processing on the light field intensity information and the light direction information by using a preset laser measurement model to obtain the factor value of the target object, the method further includes: Acquire a laser measurement model to be trained and a light field image sample set, wherein the light field image sample set includes a light field image and a factor value label corresponding to the light field image; Based on the light field image and the factor value label corresponding to the light field image, the laser measurement model to be trained is iteratively trained, and a preset laser measurement model is obtained after the iterative training is completed.

[0008] Optionally, the iterative training of the laser measurement model to be trained is performed based on the light field image and the factor value label corresponding to the light field image, and a preset laser measurement model is obtained after the iterative training is completed, including: Performing factor extraction processing on the light field image by using the laser measurement model to be trained to obtain a training factor value of the light field image; Determining a factor loss value based on the training factor value and the factor value label; Based on the factor loss value, the laser measurement model to be trained is iteratively trained, and a preset laser measurement model is obtained after the iterative training is completed.

[0009] Optionally, the performing factor extraction processing on the light field intensity information and the light direction information by using a preset laser measurement model to obtain the factor value of the target object includes: Processing the light field intensity information through a convolution layer to obtain a first factor value; Processing the direction information of the light through a convolution layer to obtain a second factor value; Based on the first factor value and the second factor value, factor regression is performed in a fully connected layer to obtain the factor value of the target object.

[0010] Optionally, determining the laser quality corresponding to the target object based on the factor value includes: Based on the factor value, determining the laser characteristics corresponding to the factor value; Based on the laser characteristics, a laser quality corresponding to the target object is determined.

[0011] In a second aspect, an embodiment of the present invention further provides a laser quality detection device, the laser quality detection device comprising: A first acquisition module is used to acquire light field image information of a target object, wherein the light field image information includes light field intensity information and light direction information; The second acquisition module is used to perform factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain the factor value of the target object.

[0012] In a third aspect, an embodiment of the present invention further provides another laser quality detection device, wherein the another laser quality detection device further includes: A third acquisition module is used to acquire a laser measurement model to be trained and a light field image sample set, wherein the light field image sample set includes a light field image and a factor value label corresponding to the light field image; The fourth acquisition module is used to iteratively train the laser measurement model to be trained based on the light field image and the factor value label corresponding to the light field image, and obtain a preset laser measurement model after the iterative training is completed.

[0013] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the laser quality detection method provided in the embodiment of the present invention when executing the computer program.

[0014] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the laser quality detection method provided in the embodiment of the invention are implemented.

[0015] In an embodiment of the present invention, a light field image of a target object is obtained, wherein the light field image information includes light field intensity information and light direction information; the light field intensity information and light direction information are subjected to factor extraction processing by a preset laser measurement model to obtain a factor value corresponding to the target object; and the laser quality corresponding to the target object is determined based on the factor value. The light field image of the target object obtained is subjected to factor extraction by a preset laser measurement model. During the extraction process, the preset laser measurement model parses the light field intensity information and light direction information of the target object to obtain a factor value corresponding to the target object. Finally, the laser quality of the target object is determined based on the factor value, thereby enabling the quality of the laser to be detected by a deep learning model, thereby improving the accuracy of laser detection, simplifying the laser detection process, and improving the efficiency of laser detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of a laser quality detection method provided by an embodiment of the present invention; Figure 2 is a structural schematic diagram of a laser quality detection device provided in an embodiment of the present invention; Figure 3 is a schematic structural diagram of another laser quality detection device provided in an embodiment of the present invention; Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, Figure 1 : is a flow chart of a laser quality detection method provided by an embodiment of the present invention, the laser quality detection method comprising the steps of: 101. Obtain light field image information of the target object.

[0020] In an embodiment of the present invention, the above-mentioned laser quality detection method can be applied to a laser quality detection platform. The above-mentioned laser quality detection platform has functions such as light field image information acquisition, light field image information processing and light field image information storage, and can be constructed based on a server or a server cluster. The above-mentioned server or server cluster can be an electronic device with laser quality detection processing capabilities.

[0021] The light field image information may include but is not limited to light field intensity information and light direction information. The light field intensity information may be used to describe the intensity distribution of light in a certain area. It is conceivable that the greater the unit light intensity in an area, the stronger the light field intensity in the area.

[0022] The above-mentioned light direction information may be the propagation direction of the light, and in this embodiment, it may generally refer to the propagation direction of the laser. Specifically, the light direction information may include but is not limited to data such as the incident angle, propagation direction, and polarization direction of the laser. It is understandable that the data in the above-mentioned light direction information may be determined according to the optical characteristics of the laser.

[0023] Specifically, the light field image information can be obtained by detecting light field intensity information in a certain area through light capture devices such as photoelectric detectors, interferometers, and light field cameras.

[0024] In a possible embodiment, the laser quality detection platform acquires light field intensity information in a certain area through auxiliary electronic equipment and light capture equipment.

[0025] 102. Perform factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain the factor value corresponding to the target object.

[0026] In an embodiment of the present invention, the preset laser measurement model may be a deep learning model that can parse the input light field image and then output the factor value corresponding to the light field image. Specifically, the preset laser measurement model in this embodiment may be a deep learning model improved based on the VGG16 convolutional neural network, wherein the model may be composed of 13 convolutional layers and 3 fully connected layers, the specific number of layers may be confirmed according to the specific implementation plan, and the activation function of the last fully connected layer may be deleted, and the number of neurons may be set to 1. The above neurons may be used to regress and output the factor value describing the laser quality.

[0027] The preset laser measurement model can also be obtained by training the laser measurement model to be trained, and the performance of the preset laser measurement model can be evaluated by testing multiple data sets.

[0028] The factor processing may be performed by calculating the light field intensity information and the light direction information of the target object to obtain a factor value, and the factor value may be used to evaluate the light beam quality of the target object.

[0029] The target object may be any form of laser or light beam, and a light field image can be acquired.

[0030] The above factor value can be an indicator that can evaluate the quality of the laser beam. Generally speaking, the quality of the laser beam can be determined by the size of the factor value. It is conceivable that the factor values ​​emitted by the beam in different environments under the influence of the outside world are different.

[0031] In a possible embodiment, the laser quality measurement platform performs factor extraction processing on the light field intensity information and light direction information of the target object through an attached preset laser measurement model to obtain the factor value of the target object.

[0032] 103. Based on the factor value, determine the laser quality corresponding to the target object.

[0033] In the embodiment of the present invention, the laser quality can be judged by the factor value. Generally speaking, the factor value is an indicator describing the focusing ability of the beam and the performance relative to the ideal Gaussian beam. When the factor value is closer to 1, it means that the beam quality is higher and the focusing ability is better.

[0034] Specifically, the laser quality can also be judged by factor data such as divergence, beam diameter, wavelength, and coherence length, and the above factor data can be obtained by extracting factors from the above target object using the above preset laser measurement model. That is, the factor value corresponding to the above target object can be determined by the above light field intensity information, light direction information, and the above factor data.

[0035] In a possible embodiment, the laser quality detection platform determines the laser quality corresponding to the target object by confirming the factor value corresponding to the target object.

[0036] In an embodiment of the present invention, a light field image of a target object is obtained, and the light field image information includes light field intensity information and light direction information; the light field intensity information and light direction information are subjected to factor extraction processing by a preset laser measurement model to obtain a factor value corresponding to the target object; based on the factor value, the laser quality corresponding to the target object is determined. The light field image of the target object obtained is subjected to factor extraction by a preset laser measurement model. During the extraction process, the preset laser measurement model parses the light field intensity information and light direction information of the target object to obtain a factor value corresponding to the target object. Finally, the laser quality of the target object is determined based on the factor value, so that the quality of the laser can be detected by a deep learning model, thereby improving the accuracy of laser detection, simplifying the laser detection process, and improving the efficiency of laser detection.

[0037] Optionally, in the step of obtaining light field image information of the target object, the target object may be photographed in multiple orientations by a light field camera to obtain light field images in multiple orientations, and then the light field images in multiple orientations may be normalized to obtain the light field image information of the target object.

[0038] In the embodiment of the present invention, the light field camera is a camera that can capture the distribution and direction information of light in space. Its core principle is to record light field information, that is, the intensity, direction and position information of light in three-dimensional space.

[0039] The light field images in the multiple directions may be obtained by collecting light from different directions of the target object through the light field camera.

[0040] The light field image information may be obtained by normalizing the light field images in the multiple directions, so as to obtain a light field image that can represent the direction information of the light of the target object.

[0041] In a possible embodiment, the laser quality measurement platform captures the light field image of the target object from multiple angles using a light field camera, and normalizes the captured light field images from multiple angles to obtain light field image information of the target object.

[0042] Optionally, in the step before extracting factors from the light field intensity information and the light direction information using a preset laser measurement model to obtain the factor values ​​of the target object, the laser measurement model to be trained and the light field image sample set can be obtained, and then the laser measurement model to be trained can be iteratively trained based on the light field image and the factor value labels corresponding to the light field image, and the preset laser measurement model can be obtained after the iterative training is completed.

[0043] In an embodiment of the present invention, the laser measurement model to be trained may be a deep learning model that performs factor extraction processing on an input light field image but is unable to obtain corresponding correct factor values.

[0044] The light field image sample set may include but is not limited to a light field image and a factor value label corresponding to the light field image. The factor value label may be a standard factor value corresponding to the light field image obtained by measuring the light field image using a traditional beam quality factor measurement method.

[0045] The above-mentioned iterative training process can process the above-mentioned light field image through the above-mentioned laser measurement model to be trained to obtain a factor value, and compare and calculate the factor value with the factor value label corresponding to the above-mentioned light field image, so as to determine how big the gap between the two factor values ​​is. When this gap is infinitely close to 0, it is considered that the laser measurement model to be trained is trained and the preset laser measurement model is obtained.

[0046] Specifically, during the training process, by determining the gap between the two factor values, the optimization goal is to infinitely reduce the gap, and the parameters of the laser measurement model to be trained are continuously updated. When an output factor value is infinitely close to the factor value label, the laser measurement model training is completed.

[0047] Optionally, in the step of iteratively training the laser measurement model to be trained based on the light field image and the factor value labels corresponding to the light field image, and obtaining the preset laser measurement model after the iterative training is completed, the light field image can also be subjected to factor extraction processing by the laser measurement model to be trained to obtain the training factor value of the light field image, and then the factor loss value is determined based on the training factor value and the factor value label, and then the laser measurement model to be trained is iteratively trained based on the factor loss value, and the preset laser measurement model is obtained after the iterative training is completed.

[0048] In an embodiment of the present invention, the above-mentioned training factor value is the factor value corresponding to the light field image obtained after the laser measurement model to be trained performs factor extraction processing on the light field image, but the factor value is different from the standard factor value corresponding to the light field image obtained by measuring the light field image through the traditional beam quality factor measurement method.

[0049] The above-mentioned factor loss value can be the difference between the above-mentioned training factor value and the above-mentioned factor value label. By calculating the difference between the training factor value and the factor value label, minimizing the difference as the optimization direction, and optimizing the parameters of the above-mentioned laser measurement model to be trained, when the difference between the above-mentioned training factor value and the factor value label is infinitely close to 0, it means that the current laser measurement model to be trained has been trained and the preset laser measurement model is obtained.

[0050] In a possible embodiment, when calculating the difference between the training factor value and the factor value label, when the difference is less than a preset difference threshold, it is determined that the training of the laser measurement model to be trained is completed. The preset difference threshold can be determined according to the specific implementation scheme and the difference between the training factor value and the factor value label calculated for the first time.

[0051] In another possible embodiment, after obtaining the trained laser measurement model, the trained laser measurement model can also be tested using a test data set. If, after the trained laser measurement model is tested using the test data set, the difference between the output factor value and the corresponding factor value label is less than a preset difference threshold, then it is determined that the trained laser measurement model has passed the test, that is, it can be determined as the preset laser measurement model.

[0052] It is understandable that the above-mentioned preset laser measurement model can also be used for real-time automatic detection of m2 during the laser production process, automatic monitoring and early warning of subsequent after-sales maintenance, and possible intelligent correction of laser parameters in the future.

[0053] Optionally, in the step of performing factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain the factor value of the target object, the light field intensity information can also be processed through a convolution layer to obtain a first factor value, and then the light direction information is processed through a convolution layer to obtain a second factor value, and finally, based on the first factor value and the second factor value, factor regression is performed in a fully connected layer to obtain the factor value of the target object.

[0054] In an embodiment of the present invention, the first factor value may be obtained by processing the light field intensity information through a convolution layer in the preset laser measurement model. Specifically, the target object is scaled to 224*224 and input into the preset laser measurement model for factor extraction to obtain the first factor value, and the light direction information is subjected to factor extraction to obtain the second factor value.

[0055] The first factor value and the second factor value are regressed and outputted through the neurons in the last layer of the fully connected layer, and the factor value of the target object is outputted after being combined.

[0056] Optionally, in the step of determining the laser quality corresponding to the target object based on the factor value, it is also possible to determine the laser characteristics corresponding to the factor value based on the factor value, and then determine the laser quality corresponding to the target object based on the laser characteristics.

[0057] In the embodiment of the present invention, the laser characteristics may be the wavelength, diffraction, scattering, coherence and other characteristics of the light beam. Generally speaking, when the factor value is different, the properties of the laser are different. For example, the higher the factor value, the more stable the laser property is, and the diffraction, scattering and other characteristics of the laser will be reduced.

[0058] In a possible embodiment, the laser quality detection platform may be used to determine the laser characteristics of the laser based on the measured factor values, and then the laser characteristics may be analyzed to determine the laser quality of the laser.

[0059] like Figure 2 As shown, an embodiment of the present invention further provides a laser quality detection device, the laser quality detection device comprising: A first acquisition module 201 is used to acquire light field image information of a target object, where the light field image information includes light field intensity information and light direction information; A second acquisition module 202 is used to perform factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain a factor value of the target object; The determination module 203 is used to determine the laser quality corresponding to the target object based on the factor value.

[0060] Optionally, the first acquisition module 201 includes: A first acquisition submodule is used to shoot the target object in multiple directions by using a light field camera to obtain the light field images in multiple directions; The second acquisition submodule is used to perform normalization processing on the light field images in the multiple orientations to obtain light field image information of the target object.

[0061] Optionally, the above device further includes: A third acquisition module 301 is used to acquire a laser measurement model to be trained and a light field image sample set, wherein the light field image sample set includes a light field image and a factor value label corresponding to the light field image; The fourth acquisition module 302 is used to iteratively train the laser measurement model to be trained based on the light field image and the factor value label corresponding to the light field image, and obtain a preset laser measurement model after the iterative training is completed.

[0062] Optionally, the fourth acquisition module includes: A third acquisition submodule is used to perform factor extraction processing on the light field image through the laser measurement model to be trained to obtain a training factor value of the light field image; A first determination submodule, configured to determine a factor loss value based on the training factor value and the factor value label; The training submodule is used to iteratively train the laser measurement model to be trained based on the factor loss value, and obtain a preset laser measurement model after the iterative training is completed.

[0063] Optionally, the second acquisition module 202 includes: a fourth acquisition submodule, configured to process the light field intensity information through a convolution layer to obtain a first factor value; a fifth acquisition submodule, configured to process the direction information of the light through a convolution layer to obtain a second factor value; The regression submodule is used to perform factor regression in a fully connected layer based on the first factor value and the second factor value to obtain the factor value of the target object.

[0064] Optionally, the determination module 203 includes: A second determination submodule, configured to determine, based on the factor value, a laser feature corresponding to the factor value; The third determination submodule is used to determine the laser quality corresponding to the target object based on the laser characteristics.

[0065] like Figure 4 As shown, an embodiment of the present invention further provides an electronic device, including a processor, and the processor can execute any one of the above-mentioned laser quality detection methods.

[0066] Specifically, it includes a processor 401 and a memory 402, and a computer program for executing the laser quality detection method stored in the memory 402 and capable of running on the processor 401, wherein: The processor 401 runs the computer program of the laser quality detection method stored in the memory 402 to perform the following steps: Acquire light field image information of the target object, wherein the light field image information includes light field intensity information and light direction information; Performing factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain a factor value corresponding to the target object; Based on the factor value, the laser quality corresponding to the target object is determined.

[0067] Optionally, the processor 401 executes the step of acquiring light field image information of the target object, including: Using a light field camera to photograph the target object in multiple directions to obtain the light field images in multiple directions; Normalization processing is performed on the light field images in the multiple directions to obtain light field image information of the target object.

[0068] Optionally, the processor 401 executes the step before performing factor extraction processing on the light field intensity information and the light direction information by using a preset laser measurement model to obtain the factor value of the target object, the method further includes: acquiring a laser measurement model to be trained and a light field image sample set, the light field image sample set including a light field image and a factor value label corresponding to the light field image; Based on the light field image and the factor value label corresponding to the light field image, the laser measurement model to be trained is iteratively trained, and a preset laser measurement model is obtained after the iterative training is completed.

[0069] Optionally, the processor 401 executes the step of iteratively training the laser measurement model to be trained based on the light field image and the factor value label corresponding to the light field image, and obtaining a preset laser measurement model after the iterative training is completed, including: Performing factor extraction processing on the light field image by using the laser measurement model to be trained to obtain a training factor value of the light field image; Determining a factor loss value based on the training factor value and the factor value label; Based on the factor loss value, the laser measurement model to be trained is iteratively trained, and a preset laser measurement model is obtained after the iterative training is completed.

[0070] Optionally, the processor 401 performs factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain the factor value of the target object, including: Processing the light field intensity information through a convolution layer to obtain a first factor value; Processing the direction information of the light through a convolution layer to obtain a second factor value; Based on the first factor value and the second factor value, factor regression is performed in a fully connected layer to obtain the factor value of the target object.

[0071] Optionally, the processor 401 performs a step of determining the laser quality corresponding to the target object based on the factor value, including: Based on the factor value, determining the laser characteristics corresponding to the factor value; Based on the laser characteristics, a laser quality corresponding to the target object is determined.

[0072] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the laser quality detection method or the application-end laser quality detection method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0073] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0074] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A laser quality detection method, characterized in that: include: Acquire light field image information of the target object, wherein the light field image information includes light field intensity information and light direction information; Performing factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain a factor value corresponding to the target object; Based on the factor value, the laser quality corresponding to the target object is determined.

2. The laser quality detection method according to claim 1, characterized in that: The step of acquiring light field image information of the target object includes: Using a light field camera to photograph the target object in multiple directions to obtain the light field images in multiple directions; Normalization processing is performed on the light field images in the multiple directions to obtain light field image information of the target object.

3. The laser quality detection method according to claim 1, characterized in that: Before the factor extraction process is performed on the light field intensity information and the light direction information by using a preset laser measurement model to obtain the factor value of the target object, the method further includes: Acquire a laser measurement model to be trained and a light field image sample set, wherein the light field image sample set includes a light field image and a factor value label corresponding to the light field image; Based on the light field image and the factor value label corresponding to the light field image, the laser measurement model to be trained is iteratively trained, and a preset laser measurement model is obtained after the iterative training is completed.

4. The laser quality detection method according to claim 3, characterized in that: The laser measurement model to be trained is iteratively trained based on the light field image and the factor value label corresponding to the light field image, and a preset laser measurement model is obtained after the iterative training is completed, including: Performing factor extraction processing on the light field image by using the laser measurement model to be trained to obtain a training factor value of the light field image; Determining a factor loss value based on the training factor value and the factor value label; Based on the factor loss value, the laser measurement model to be trained is iteratively trained, and a preset laser measurement model is obtained after the iterative training is completed.

5. The laser quality detection method according to claim 1, characterized in that: The step of performing factor extraction processing on the light field intensity information and the light direction information by using a preset laser measurement model to obtain the factor value of the target object includes: Processing the light field intensity information through a convolution layer to obtain a first factor value; Processing the direction information of the light through a convolution layer to obtain a second factor value; Based on the first factor value and the second factor value, factor regression is performed in a fully connected layer to obtain the factor value of the target object.

6. The laser quality detection method according to claim 5, characterized in that: The step of determining the laser quality corresponding to the target object based on the factor value includes: Based on the factor value, determining the laser characteristics corresponding to the factor value; Based on the laser characteristics, a laser quality corresponding to the target object is determined.

7. A laser quality detection device, characterized in that: The laser measuring device comprises: A first acquisition module is used to acquire light field image information of a target object, wherein the light field image information includes light field intensity information and light direction information; A second acquisition module is used to perform factor extraction processing on the light field intensity information and the light direction information through a preset laser measurement model to obtain a factor value of the target object; A determination module is used to determine the laser quality corresponding to the target object based on the factor value.

8. The laser quality detection device according to claim 7, characterized in that: The device also includes: A third acquisition module is used to acquire a laser measurement model to be trained and a light field image sample set, wherein the light field image sample set includes a light field image and a factor value label corresponding to the light field image; The fourth acquisition module is used to iteratively train the laser measurement model to be trained based on the light field image and the factor value label corresponding to the light field image, and obtain a preset laser measurement model after the iterative training is completed.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the laser quality detection method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the laser quality detection method according to any one of claims 1 to 6 are implemented.

Images