CN113310438B

CN113310438B - Flatness measuring method, flatness measuring device, computer equipment and storage medium

Info

Publication number: CN113310438B
Application number: CN202010118310.9A
Authority: CN
Inventors: 赵闻迪; 郭小凡
Original assignee: Guangdong Bozhilin Robot Co Ltd
Current assignee: Guangdong Bozhilin Robot Co Ltd
Priority date: 2020-02-26
Filing date: 2020-02-26
Publication date: 2023-04-07
Anticipated expiration: 2040-02-26
Also published as: CN113310438A

Abstract

The application relates to a flatness measuring method, a flatness measuring device, a flatness measuring system, a computer device and a storage medium. The method comprises the following steps: acquiring an initial stripe image; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals: projecting the initial stripe image to a surface to be measured to form a stripe projection image on the surface to be measured; acquiring a fringe projection image of the surface to be detected; and determining flatness information of the surface to be measured according to the stripe bending characteristics in the stripe projection images and the stripe sparse characteristics in the stripe projection images. By adopting the method, the measuring efficiency of the wall surface flatness can be improved.

Description

Flatness measuring method, flatness measuring device, computer equipment and storage medium

Technical Field

The application relates to the technical field of intelligent buildings, in particular to a flatness measuring method and device, computer equipment and a storage medium.

Background

When the prior art is used for measuring the wall surface flatness of a building, measuring tools such as professional wall surface flatness measuring scales are often needed to manually measure the flatness of the wall surface. This also makes the measuring efficiency of wall face roughness not high when measurement personnel face the large tracts of land wall face roughness under measuring the scene.

Therefore, the prior art has the problem of low efficiency in the process of measuring the flatness of the wall surface.

Disclosure of Invention

In view of the foregoing, it is necessary to provide a flatness measuring method, apparatus, computer device and storage medium capable of improving the efficiency of measuring the flatness of a wall surface.

A flatness measuring method, the method comprising:

acquiring an initial stripe image; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals:

projecting the initial fringe image to a surface to be measured to form a fringe projection image on the surface to be measured;

acquiring a fringe projection image of the surface to be detected;

and determining flatness information of the surface to be measured according to the stripe bending characteristics in the stripe projection images and the stripe sparse characteristics in the stripe projection images.

In one embodiment, the determining flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image includes:

inputting the fringe projection images to a pre-trained recognition model;

extracting a stripe bending feature in the stripe projection image and a stripe sparse feature in the stripe projection image through the pre-trained recognition model, and generating a model output result of the stripe projection image according to the stripe bending feature and the stripe sparse feature;

and determining the flatness information of the surface to be detected according to the model output result of the fringe projection image.

In one embodiment, the determining flatness information of the surface to be measured according to the model output result of the fringe projection image includes:

determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured;

determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region;

and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.

In one embodiment, before the step of inputting the fringe projection image into a pre-trained recognition model, the method further includes:

acquiring a fringe projection sample image;

inputting the fringe projection sample image into a recognition model to be trained; the identification model to be trained is used for processing an input fringe projection sample image to obtain a model output result of the fringe projection sample image; the fringe projection sample image has corresponding label information;

updating model parameters of the recognition model to be trained based on the model output result of the stripe projection sample image and the label information of the stripe projection sample image to obtain the trained recognition model, and taking the trained recognition model as the recognition model to be trained;

and repeatedly executing the steps until the pre-trained recognition model is obtained.

In one embodiment, the acquiring a fringe projection image of the surface-to-be-measured includes:

acquiring an original fringe projection image;

identifying the original fringe projection image, and determining a fringe projection pattern boundary in the original fringe projection image;

and cutting the original fringe projection image according to the fringe projection pattern boundary to obtain the fringe projection image.

In one embodiment, the method further comprises the following steps:

generating a to-be-projected image according to the flatness information of the surface to be detected;

projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat area of the surface to be measured.

A flatness measuring method, the method comprising:

acquiring a fringe projection image of the surface to be detected; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals:

A flatness measurement system, the system comprising: the device comprises a projection device, an image acquisition device and a measurement device;

the projection device is used for acquiring an initial stripe image and projecting the initial stripe image to a surface to be measured so as to form a stripe projection image on the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals:

the image acquisition device is used for shooting a stripe projection image of the surface to be measured and sending the stripe projection image to the measuring device;

and the measuring device is used for determining the flatness information of the surface to be measured according to the strip bending characteristics in the strip projection image and the strip sparse characteristics in the strip projection image.

In one embodiment, the measuring device is further configured to generate an image to be projected according to the flatness information of the surface to be measured, and send the image to be projected to the projecting device;

the projection device is also used for receiving the image to be projected and projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat area of the surface to be measured.

A flatness measuring apparatus, the apparatus comprising:

the acquisition module is used for acquiring an initial stripe image; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

the projection module is used for projecting the initial stripe image to a surface to be measured so as to form a stripe projection image on the surface to be measured;

the acquisition module is used for acquiring a fringe projection image of the surface to be detected;

and the measurement module is used for determining the flatness information of the surface to be measured according to the stripe bending characteristic in the stripe projection image and the stripe sparse characteristic in the stripe projection image.

A flatness measuring apparatus, the apparatus comprising:

the image acquisition module is used for acquiring a fringe projection image of the surface to be detected; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

and the determining module is used for determining the flatness information of the surface to be measured according to the stripe bending characteristic in the stripe projection image and the stripe sparse characteristic in the stripe projection image.

A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

projecting the initial stripe image to a surface to be measured to form a stripe projection image on the surface to be measured;

acquiring a fringe projection image of the surface to be detected;

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

acquiring an initial stripe image; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

acquiring a fringe projection image of the surface to be detected;

acquiring a fringe projection image of the surface to be detected; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

According to the flatness measuring method, the flatness measuring device, the flatness measuring system, the computer equipment and the storage medium, an initial stripe image comprising a plurality of linear stripes which are equidistantly distributed is obtained; projecting the initial stripe image to the surface to be measured, so that stripes in the stripe projection image projected on the wall surface can be distorted due to the convex part or the concave part in the wall surface to be measured when the wall surface to be measured originally lacks texture information and a geometric structure, further forming a stripe projection image carrying depth information on the wall surface to be measured, and collecting the stripe projection image; and determining flatness information of the surface to be measured according to the strip bending characteristics in the strip projection image and the strip sparse characteristics in the strip projection image, thereby stably and efficiently measuring the flatness of the large-area wall surface to be measured under the condition of not contacting the wall surface to be measured, and improving the measurement efficiency of the flatness of the wall surface.

Drawings

FIG. 1 is a block diagram of a flatness measurement system in one embodiment;

FIG. 2 is a schematic flow chart of a flatness measuring method according to an embodiment;

FIG. 3 is a schematic diagram of an initial fringe image in one embodiment;

FIG. 4 is a schematic illustration of a fringe projection image in one embodiment;

FIG. 5 is a schematic illustration of a fringe distortion zone in a fringe projection image in one embodiment;

FIG. 6 is a diagram of an application scenario for a flatness cue image, under an embodiment;

FIG. 7 is a flow chart illustrating a flatness measuring method according to another embodiment;

FIG. 8 is a schematic flow chart of another flatness measuring method in one embodiment;

FIG. 9 is a block diagram showing a structure of a flatness measuring apparatus according to an embodiment;

FIG. 10 is a block diagram showing a structure of a flatness measuring apparatus in another embodiment;

FIG. 11 is a schematic flow chart diagram illustrating a method for measuring flatness of a wall surface in one embodiment;

FIG. 12 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The application provides a flatness measuring method, which can be applied to an application environment as shown in fig. 1 to provide a flatness measuring system. The system includes, among other things, a projection device 110, an image acquisition device 120, and a measurement device 130. The projection device 110, the image capturing device 120, and the measuring device 130 are all in communication via a network. The measuring device 130 acquires an initial fringe image; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals: then, the measuring device 130 projects the initial fringe image to a surface to be measured through the projecting device 110 to form a fringe projection image on the surface to be measured; then, the measuring device 130 collects the fringe projection image of the surface to be measured through the image collecting device 120; finally, the measuring device 130 determines the flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image. In practical applications, the projection device 110 may refer to a projection apparatus, such as a projector, a high definition projector, or the like. The projection device 110 may also be a laser emitter for projecting a plurality of line lasers. The image capturing device 120 may refer to a camera, a video camera, and the like, for example, an industrial camera, a single lens reflex camera, a camera, and the like. The measuring device 130 may be a computer device such as a terminal, a server, etc. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server can be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, there is provided a flatness measuring method including the steps of:

step S210, obtaining an initial stripe image; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals.

Wherein, the initial stripe image is an image comprising a plurality of linear stripes which are arranged at equal intervals. As shown in fig. 3, fig. 3 provides a schematic illustration of an initial fringe image.

In a specific implementation, when the flatness of the surface to be measured needs to be measured, the measuring device 130 first obtains an initial stripe image that is preset by a user and includes a plurality of linear stripes arranged at equal intervals.

Step S220, projecting the initial fringe image onto the surface to be measured to form a fringe projection image on the surface to be measured.

The surface to be measured may be a target surface whose flatness needs to be measured. In practical application, the surface to be measured can be a plane such as a wall surface to be measured, a ground surface to be measured, a road surface to be measured, a desktop to be measured and the like.

In a specific implementation, taking the surface to be measured as a wall surface to be measured as an example, after the measuring device 130 obtains the initial stripe image, the measuring device 130 may project the initial stripe image to the wall surface to be measured through the projecting device 110; specifically, measuring device 130 can send the image signal that initial stripe image corresponds to projection arrangement 110, and then supplies projection arrangement 110 to project initial stripe image to the wall that awaits measuring, after the wall that awaits measuring forms the stripe projection image, originally lack the wall that awaits measuring of texture information and geometric structure this moment, can make the stripe in the stripe projection image of projection on the wall appear the distortion because of bulge or depressed part in the wall that awaits measuring, and then form the stripe projection image that carries with depth information at the wall that awaits measuring. As shown in fig. 4, fig. 4 provides a schematic illustration of a fringe projection image.

And step S230, acquiring a fringe projection image of the surface to be measured.

In a specific implementation, after the projection device 110 projects the initial stripe image to the wall surface to be measured to form a stripe projection image on the surface to be measured, the measurement device 130 may collect the stripe projection image of the surface to be measured through the image collection device 120. Specifically, the measurement device 130 may send a control signal to the image capturing device 120, so that the image capturing device 120 captures a stripe projection image on the wall surface to be measured, and returns the stripe projection image to the measurement device 130.

And S240, determining flatness information of the surface to be measured according to the strip bending characteristics in the strip projection image and the strip sparse characteristics in the strip projection image.

The fringe-bending feature may refer to a feature corresponding to a bending fringe in the fringe projection image.

The stripe sparse feature may refer to a feature corresponding to sparse arrangement between stripes in a stripe projection image.

In a specific implementation, after the measuring device 130 acquires the stripe projection image of the wall surface to be measured, the measuring device 130 may determine the flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image. Specifically, the measurement device 130 may process the fringe projection image through a pre-trained neural network, extract a fringe bending feature in the fringe projection image and a fringe sparse feature in the fringe projection image, and then determine the flatness information of the surface to be measured according to the fringe bending feature and the fringe sparse feature. Meanwhile, the measuring device 130 can display the flatness information of the surface to be measured, so that the user can find the flatness of the wall surface to be measured in time.

In the flatness measuring method, an initial stripe image comprising a plurality of linear stripes which are equidistantly arranged is obtained; projecting the initial stripe image to the surface to be measured, so that stripes in a stripe projection image projected on the wall surface to be measured can be distorted due to the convex part or the concave part in the wall surface to be measured when the wall surface to be measured originally lacks texture information and a geometric structure, further forming a stripe projection image carrying depth information on the wall surface to be measured, and collecting the stripe projection image; and determining flatness information of the surface to be measured according to the strip bending characteristics in the strip projection image and the strip sparse characteristics in the strip projection image, thereby stably and efficiently measuring the flatness of the large-area wall surface to be measured under the condition of not contacting the wall surface to be measured, and improving the measurement efficiency of the flatness of the wall surface.

In another embodiment, determining flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image comprises: inputting the fringe projection image into a pre-trained recognition model; extracting a stripe bending characteristic in the stripe projection image and a stripe sparse characteristic in the stripe projection image through a pre-trained recognition model, and generating a model output result of the stripe projection image according to the stripe bending characteristic and the stripe sparse characteristic; and determining the flatness information of the surface to be measured according to the model output result of the fringe projection image.

Wherein, the recognition model can be a picture recognition model based on a neural network. In practical applications, the recognition model may be a picture recognition model based on Faster R-CNN (a convolutional neural network). Of course, the recognition model may be a neural network model of SSD series, YOLO series, or the like.

In a specific implementation, when the measuring device 130 determines the flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image, the measuring device 130 may input the acquired stripe projection image to the pre-trained recognition model as an input parameter of the pre-trained recognition model; in this way, the measurement device 130 extracts the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image through the pre-trained recognition model; meanwhile, the measuring device 130 outputs a model output result corresponding to the fringe projection image according to the fringe bending characteristic and the fringe sparse characteristic through the pre-trained recognition model. Finally, the measuring device 130 determines the flatness information of the surface to be measured according to the model output result of the pre-trained recognition model.

According to the technical scheme of the embodiment, the fringe projection image is input into a pre-trained recognition model; the strip bending characteristics in the strip projection images are extracted rapidly and efficiently through the pre-trained recognition model, the strip sparse characteristics in the strip projection images are extracted, the flatness information of the surface to be measured is accurately determined according to the strip bending characteristics and the strip sparse characteristics, and therefore the flatness measurement of the large-area wall surface to be measured is stably and efficiently carried out, and the measurement efficiency of the flatness of the wall surface is improved.

In another embodiment, determining flatness information of the surface to be measured based on the model output result of the fringe projection image includes: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as flatness information of the surface to be measured.

Wherein the fringe distortion area corresponds to a non-flat area of the surface to be measured. The fringe distortion region may be a region in which a fringe distortion such as a curve, an excessively dense fringe, or the like occurs in a fringe projection image. For the understanding of those skilled in the art, FIG. 5 provides a schematic illustration of the fringe distortion regions in a fringe projection image. Here, 510 is a fringe projection image, and 520 is a fringe distortion region.

Wherein the distortion degree value may be a value for characterizing a distortion degree of the streak distortion region. In practical application, the distortion degree value corresponds to the flatness of the surface to be measured.

In a specific implementation, the process of determining the flatness information of the surface to be measured by the measuring device 130 according to the model output result of the fringe projection image specifically includes: after the measuring device 130 obtains the model output result corresponding to the pre-trained recognition model output and the stripe projection image, the measuring device 130 determines a stripe distortion region corresponding to the non-flat region of the surface to be measured in the stripe projection image in the model output result of the stripe projection image; then, the measuring device 130 determines the position coordinates of the fringe distortion region in the fringe projection image and determines the distortion degree value corresponding to the fringe distortion region; and the position coordinates and the distortion degree value are used as flatness information of the surface to be measured.

It should be noted that, in the process of training the neural network of the recognition model to be trained to obtain the pre-trained recognition model, the stripe distortion regions, such as the stripes in the stripe projection sample image for training being bent and the stripes being too dense, may be labeled first to obtain the stripe distortion labeling regions; and marking a corresponding distortion degree marking value for the stripe distortion marking area according to the distortion degree of the stripes in the stripe distortion marking area. Taking a plurality of stripe projection sample images with training labels as a training set, and carrying out neural network training on the recognition model to be trained to obtain a trained recognition model; in this way, the measurement device 130 can accurately determine the fringe distortion region in the fringe projection image and the distortion degree value corresponding to the fringe distortion region. In practical application, image labeling tools such as Labelme or LabelImg can be used for labeling, and a data set is created after the labeling is completed.

In practical applications, a person skilled in the art can label a corresponding distortion degree label value for the stripe distortion label area according to the distortion degree of the stripe in the stripe distortion label area according to an actual situation, which is not limited herein.

According to the technical scheme, the stripe distortion area in the stripe projection image is determined through the model output result according to the stripe projection image, the position coordinates of the stripe distortion area in the stripe projection image and the distortion degree value corresponding to the stripe distortion area are obtained, the flatness information capable of representing the surface flatness to be measured in detail and accurately is obtained, and the measurement efficiency of the wall flatness is improved.

In another embodiment, before the step of inputting the fringe projection image into the pre-trained recognition model, the method further comprises: acquiring a fringe projection sample image; inputting the fringe projection sample image into a recognition model to be trained; the recognition model to be trained is used for processing the input fringe projection sample image to obtain a model output result of the fringe projection sample image; the fringe projection sample image has corresponding label information; updating model parameters of the recognition model to be trained based on the model output result of the stripe projection sample image and the label information of the stripe projection sample image to obtain the trained recognition model, and taking the trained recognition model as the recognition model to be trained; and repeatedly executing the steps until a pre-trained recognition model is obtained.

The fringe projection sample image may be an image used for performing a neural network on the recognition model to be trained.

Wherein the fringe projection sample image has corresponding label information. In practical application, the label information includes a stripe distortion labeling area and a distortion degree labeling value corresponding to the stripe distortion labeling area.

The identification model to be trained may refer to an untrained identification model.

The identification model to be trained is used for processing the input fringe projection sample image to obtain a model output result of the fringe projection sample image.

In a specific implementation, before the step of inputting the fringe projection image into the pre-trained recognition model by the measurement apparatus 130, the measurement apparatus 130 further needs to acquire a fringe projection sample image with corresponding label information. In the process of obtaining the stripe projection sample image with the corresponding label information, the projection device 110 and the image acquisition device 120 can be enabled to take different distances (such as 1 meter, 1.5 meters, 2 meters, 2.5 meters and the like) from the sample plane and various position angles (positive shooting, oblique shooting, upward shooting, downward shooting and the like) so as to increase the data characteristics of the acquired stripe projection sample image, so that not only can the final recognition model be more flexible, but also the diversity of the sample is increased during training, and the recognition model finally trained can be ensured to be capable of detecting the unqualified area with plane flatness at each position, angle and distance

Then, the measurement apparatus 130 inputs the fringe projection sample image to the recognition model to be trained as an input parameter of the recognition model to be trained. And processing the input fringe projection sample image through the identification model to be trained to obtain a model output result of the fringe projection sample image. Then, the measurement device 130 may determine a loss of the recognition model to be trained according to the model output result of the stripe projection sample image and the label information of the stripe projection sample image, update the model parameters of the recognition model to be trained according to the loss to obtain the trained recognition model, and use the trained recognition model as the recognition model to be trained; and repeating the steps by using a gradient descent method and the like until a pre-trained recognition model is obtained.

According to the technical scheme of the embodiment, the fringe projection sample image with the corresponding label information is input to the recognition model to be trained; updating model parameters of the recognition model to be trained based on the model output result of the stripe projection sample image and the label information of the stripe projection sample image to obtain the trained recognition model, and taking the trained recognition model as the recognition model to be trained; the steps are repeatedly executed, so that the strip bending characteristics in the strip projection images can be quickly and efficiently extracted by the obtained pre-trained recognition model, the strip sparse characteristics in the strip projection images are extracted, the flatness information of the surface to be measured is accurately determined according to the strip bending characteristics and the strip sparse characteristics, the flatness measurement of a large-area wall surface to be measured is stably and efficiently carried out, and the measurement efficiency of the flatness of the wall surface is improved.

In another embodiment, acquiring fringe projection images of the surface under test comprises: acquiring an original fringe projection image; identifying an original fringe projection image, and determining a fringe projection pattern boundary in the original fringe projection image; and cutting the original fringe projection image according to the fringe projection pattern boundary to obtain a fringe projection image.

The original fringe projection image may be an unprocessed fringe projection image.

Wherein, the fringe projection pattern boundary may refer to a pattern boundary of a fringe pattern in the original fringe projection image.

In specific implementation, the process of collecting the fringe projection image of the surface to be measured by the measuring device 130 specifically includes: after the measuring device 130 sends the control signal to the image collecting device 120, the image collecting device 120 collects the image of the wall surface to be measured to obtain an original stripe projection image; the image acquisition device 120 then returns the acquired raw fringe projection image to the measurement device 130.

After the measuring device 130 receives the original fringe projection image, the measuring device 130 may identify the original fringe projection image, and determine a fringe projection pattern boundary in the original fringe projection image; then, the measuring device 130 cuts the original fringe projection image based on the fringe projection pattern boundary in the original fringe projection image, and obtains the cut original fringe projection image as a fringe projection image.

Meanwhile, the measuring device 130 may further adjust the image size of the stripe projection image, so that the image size of the stripe projection image matches the preset image size, and then the stripe projection image is conveniently input to the pre-trained recognition model for processing.

According to the technical scheme of the embodiment, an original fringe projection image is obtained; identifying an original fringe projection image, and determining a fringe projection pattern boundary in the original fringe projection image; according to the fringe projection pattern boundary, the original fringe projection image is cut to obtain the fringe projection image, redundant image information is removed, so that the parameter processing amount of the recognition model can be reduced, the fringe bending characteristic and the fringe sparse characteristic in the fringe projection image extracted by the recognition model are improved, the flatness information efficiency of the surface to be measured is accurately determined according to the fringe bending characteristic and the fringe sparse characteristic, the flatness measurement of a large-area wall surface to be measured is further stably and efficiently realized, and the measurement efficiency of the wall surface flatness is improved.

In another embodiment, the method further comprises: generating a to-be-projected image according to the flatness information of the surface to be detected; projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat region of the surface to be measured.

The flatness prompt image is used for a user to determine a non-flat area of the surface to be measured.

In a specific implementation, after the measuring device 130 determines the flatness information of the surface to be measured, the measuring device 130 may further generate a to-be-projected image according to the flatness information of the surface to be measured; specifically, the measurement device 130 determines a fringe distortion region in the fringe projection image in the flatness information of the surface to be measured; then, the measurement device 130 may generate a flat information prompt box corresponding to the fringe distortion region according to the image size of the fringe distortion region; then, the measuring device 130 generates a to-be-projected image according to the position coordinates of the fringe distortion region in the fringe projection image and the flat information prompt box corresponding to the fringe distortion region.

Then, the measuring device 130 may project the image to be projected onto the surface to be measured through the projecting device 110 to form a flatness indication image on the surface to be measured. Specifically, the measurement device 130 sends an image signal corresponding to the image to be projected to the projection device 110, so that the projection device 110 projects the image to be projected to the surface to be measured after receiving the image signal corresponding to the image to be projected, so as to form a flatness prompt image on the surface to be measured, where the flatness prompt image is used for a user to determine a non-flat region of the surface to be measured.

To facilitate understanding by those skilled in the art, fig. 6 provides an application scenario diagram of a flatness cue image. Here, 610 is a fringe projection image, and 620 is a flatness indication image.

According to the technical scheme of the embodiment, the image to be projected is generated according to the flatness information of the surface to be measured; the image to be projected is projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured, so that a measurer can visually observe the flatness area of the surface to be measured, and the surface to be measured can be conveniently processed subsequently.

In another embodiment, as shown in fig. 7, there is provided a flatness measuring method including the steps of: step S702, acquiring an initial stripe image; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals: step S704, projecting the initial fringe image onto the surface to be measured to form a fringe projection image on the surface to be measured. Step S706, acquiring a fringe projection image of the surface to be measured. In step S708, the fringe projection image is input to the pre-trained recognition model. And step S710, extracting the stripe bending feature in the stripe projection image through the pre-trained recognition model, extracting the stripe sparse feature in the stripe projection image, and generating a model output result of the stripe projection image according to the stripe bending feature and the stripe sparse feature. Step S712, determining a fringe distortion area in the fringe projection image according to the model output result of the fringe projection image; the fringe distortion zone corresponds to a non-flat zone of the surface to be measured. Step S714, determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region. Step S716, generating an image to be projected according to the position coordinates and the distortion degree value. Step S718, projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat region of the surface to be measured. The specific limitations of the above steps can be referred to the above specific limitations of a flatness measuring method, and are not described herein again.

In one embodiment, as shown in fig. 8, another flatness measuring method is provided, including the steps of:

step S802, obtaining a stripe projection image of the surface to be measured; generating a fringe projection image according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals.

The initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals.

In a specific implementation, the projection device 110 may also be a laser emitter, and the laser emitter projects a preset initial fringe image onto the surface to be measured in a multi-line laser projection manner, so that the surface to be measured forms a fringe projection image. Then, the measurement device 130 may acquire a fringe projection image of the surface to be measured through the image acquisition device 120. Specifically, the measurement device 130 may send a control signal to the image capturing device 120, so that the image capturing device 120 captures a stripe projection image on the wall surface to be measured, and returns the stripe projection image to the measurement device 130.

And step S804, determining flatness information of the surface to be measured according to the stripe bending characteristic in the stripe projection image and the stripe sparse characteristic in the stripe projection image.

In the flatness measuring method, an initial stripe image comprising a plurality of linear stripes which are arranged at equal intervals is obtained; projecting the initial stripe image to the surface to be measured, so that stripes in the stripe projection image projected on the wall surface can be distorted due to the convex part or the concave part in the wall surface to be measured when the wall surface to be measured originally lacks texture information and a geometric structure, further forming a stripe projection image carrying depth information on the wall surface to be measured, and collecting the stripe projection image; and determining flatness information of the surface to be measured according to the strip bending characteristics in the strip projection image and the strip sparse characteristics in the strip projection image, thereby stably and efficiently measuring the flatness of the large-area wall surface to be measured under the condition of not contacting the wall surface to be measured, and improving the measurement efficiency of the flatness of the wall surface.

It should be understood that although the steps in the flowcharts of fig. 2, 7 and 8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 7, and 8 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.

A flatness measuring system, as shown in fig. 1, the system comprising: a projection device 110, an image acquisition device 120 and a measurement device 130;

the projection device 110 is configured to obtain an initial fringe image and project the initial fringe image onto a surface to be measured, so as to form a fringe projection image on the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals.

In practical applications, when the projection apparatus 110 is a projection apparatus, the projection apparatus 110 may form a fringe projection image on the surface to be measured by receiving an image signal corresponding to the initial fringe image sent by the measurement apparatus 130 and projecting the initial fringe image onto the surface to be measured according to the image signal corresponding to the initial fringe image.

Of course, the projection device 110 may also be a laser transmitter, and the laser transmitter projects a preset initial stripe image onto the surface to be measured by laser projection in multiple lines, so that the surface to be measured forms a stripe projection image.

And the image acquisition device 120 is used for shooting the stripe projection image of the surface to be measured and sending the stripe projection image to the measuring device.

In a specific implementation, the image capturing device 120 may receive a control signal sent by the measuring device 130; in response to the control signal, a fringe projection image on the wall surface to be measured is collected and returned to the measuring device 130.

And the measuring device 130 is used for determining the flatness information of the surface to be measured according to the stripe bending characteristic in the stripe projection image and the stripe sparse characteristic in the stripe projection image.

In a specific implementation, after the measuring device 130 acquires the stripe projection image of the wall surface to be measured, the measuring device 130 may determine the flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image. Specifically, the measuring apparatus 130 may process the fringe projection image through a pre-trained neural network, extract a fringe bending feature in the fringe projection image and a fringe sparseness feature in the fringe projection image, and then determine flatness information of the surface to be measured according to the fringe bending feature and the fringe sparseness feature. Meanwhile, the measuring device 130 can display the flatness information of the surface to be measured, so that the user can find the flatness of the wall surface to be measured in time.

In the flatness measuring system, the initial stripe image comprising a plurality of linear stripes which are arranged at equal intervals is obtained; projecting the initial stripe image to the surface to be measured, so that stripes in a stripe projection image projected on the wall surface to be measured can be distorted due to the convex part or the concave part in the wall surface to be measured when the wall surface to be measured originally lacks texture information and a geometric structure, further forming a stripe projection image carrying depth information on the wall surface to be measured, and collecting the stripe projection image; and determining flatness information of the surface to be measured according to the strip bending characteristics in the strip projection image and the strip sparse characteristics in the strip projection image, thereby stably and efficiently measuring the flatness of the large-area wall surface to be measured under the condition of not contacting the wall surface to be measured, and improving the measurement efficiency of the flatness of the wall surface.

In another embodiment, the measuring device 130 is further configured to generate an image to be projected according to the flatness information of the surface to be measured, and send the image to be projected to the projecting device 110; the projection device 110 is further configured to receive the image to be projected, and project the image to be projected onto the surface to be measured, so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat region of the surface to be measured.

In a specific implementation, after the measuring device 130 determines the flatness information of the surface to be measured, the measuring device 130 may further generate a projected image according to the flatness information of the surface to be measured; specifically, the measurement device 130 determines a fringe distortion region in the fringe projection image in the flatness information of the surface to be measured; then, the measurement device 130 may generate a flat information prompt box corresponding to the fringe distortion region according to the image size of the fringe distortion region; then, the measuring device 130 generates a to-be-projected image according to the position coordinates of the fringe distortion region in the fringe projection image and the flat information prompt box corresponding to the fringe distortion region.

In one embodiment, as shown in fig. 9, there is provided a flatness measuring apparatus including:

an obtaining module 910, configured to obtain an initial stripe image; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

the projection module 920 is configured to project the initial fringe image onto a surface to be measured, so as to form a fringe projection image on the surface to be measured;

an acquisition module 930, configured to acquire a fringe projection image of the surface to be measured;

and the measuring module 940 is configured to determine flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image.

In one embodiment, the measurement module 940 is specifically configured to input the fringe projection image into a pre-trained recognition model; extracting a stripe bending characteristic in the stripe projection image and a stripe sparse characteristic in the stripe projection image through a pre-trained recognition model, and generating a model output result of the stripe projection image according to the stripe bending characteristic and the stripe sparse characteristic; and determining the flatness information of the surface to be measured according to the model output result of the fringe projection image.

In one embodiment, the measuring module 940 is specifically configured to determine a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.

In one embodiment, the measurement module 940 is further configured to obtain a fringe projection sample image; inputting the fringe projection sample image into a recognition model to be trained; the recognition model to be trained is used for processing the input fringe projection sample image to obtain a model output result of the fringe projection sample image; the fringe projection sample image has corresponding label information; updating model parameters of the recognition model to be trained based on the model output result of the stripe projection sample image and the label information of the stripe projection sample image to obtain the trained recognition model, and taking the trained recognition model as the recognition model to be trained; and repeatedly executing the steps until a pre-trained recognition model is obtained.

In one embodiment, the acquisition module 930 is specifically configured to acquire an original fringe projection image; identifying an original fringe projection image, and determining a fringe projection pattern boundary in the original fringe projection image; and cutting the original fringe projection image according to the fringe projection pattern boundary to obtain the fringe projection image.

In one embodiment, the flatness measuring apparatus further includes: the image generation module is used for generating a to-be-projected image according to the flatness information of the surface to be measured; the projection module is used for projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat region of the surface to be measured.

In one embodiment, as shown in fig. 10, there is provided a flatness measuring apparatus including:

the image acquisition module 1010 is used for acquiring a fringe projection image of the surface to be detected; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

a determining module 1020, configured to determine flatness information of the surface to be measured according to a stripe bending feature in the stripe projection image and a stripe sparse feature in the stripe projection image.

For the specific definition of the flatness measuring device, reference may be made to the above definition of the flatness measuring method, which is not described herein again. The various modules in the flatness measuring apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

To facilitate understanding of those skilled in the art, fig. 11 is a schematic flow chart of a wall flatness measuring method according to an embodiment, as shown in fig. 11, the apparatus is first moved to different positions, distances, and angles; then, projecting the wall surface by using a projector or a laser transmitter; shooting the wall surface with the characteristic information by adopting a high-precision industrial camera; when enough samples are collected, labeling unqualified areas for all samples; and training the detection model by using the sample data until the model is verified to be qualified.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 12. The computer device comprises a processor, a memory, a communication interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a flatness measuring method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 12 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of:

step S210, obtaining an initial stripe image; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals:

step S220, projecting the initial stripe image to a surface to be measured so as to form a stripe projection image on the surface to be measured;

step S230, acquiring a fringe projection image of the surface to be detected;

and S240, determining the flatness information of the surface to be measured according to the stripe bending characteristic in the stripe projection image and the stripe sparse characteristic in the stripe projection image.

In one embodiment, the processor, when executing the computer program, further performs the steps of: inputting the fringe projection images to a pre-trained recognition model; extracting a stripe bending feature in the stripe projection image and a stripe sparse feature in the stripe projection image through the pre-trained recognition model, and generating a model output result of the stripe projection image according to the stripe bending feature and the stripe sparse feature; and determining the flatness information of the surface to be detected according to the model output result of the fringe projection image.

In one embodiment, the processor, when executing the computer program, further performs the steps of: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.

In one embodiment, the processor when executing the computer program further performs the steps of: acquiring a fringe projection sample image; inputting the fringe projection sample image into a recognition model to be trained; the identification model to be trained is used for processing an input fringe projection sample image to obtain a model output result of the fringe projection sample image; the fringe projection sample image has corresponding label information; updating model parameters of the recognition model to be trained based on a model output result of the fringe projection sample image and label information of the fringe projection sample image to obtain a trained recognition model, and taking the trained recognition model as the recognition model to be trained; and repeatedly executing the steps until the pre-trained recognition model is obtained.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring an original fringe projection image; identifying the original fringe projection image, and determining a fringe projection pattern boundary in the original fringe projection image; and cutting the original fringe projection image according to the fringe projection pattern boundary to obtain the fringe projection image.

In one embodiment, the processor, when executing the computer program, further performs the steps of: generating a to-be-projected image according to the flatness information of the surface to be detected; projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat area of the surface to be measured.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

step S802, obtaining a stripe projection image of the surface to be measured; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals:

step S804, determining flatness information of the surface to be measured according to the stripe bending feature in the stripe projection image and the stripe sparse feature in the stripe projection image.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

step S230, acquiring a fringe projection image of the surface to be detected;

In one embodiment, the computer program when executed by the processor further performs the steps of: inputting the fringe projection images to a pre-trained recognition model; extracting a stripe bending characteristic in the stripe projection image through the pre-trained recognition model, extracting a stripe sparse characteristic in the stripe projection image, and generating a model output result of the stripe projection image according to the stripe bending characteristic and the stripe sparse characteristic; and determining the flatness information of the surface to be detected according to the model output result of the fringe projection image.

In one embodiment, the computer program when executed by the processor further performs the steps of: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a fringe projection sample image; inputting the fringe projection sample image into a recognition model to be trained; the identification model to be trained is used for processing an input fringe projection sample image to obtain a model output result of the fringe projection sample image; the fringe projection sample image has corresponding label information; updating model parameters of the recognition model to be trained based on the model output result of the stripe projection sample image and the label information of the stripe projection sample image to obtain the trained recognition model, and taking the trained recognition model as the recognition model to be trained; and repeatedly executing the steps until the pre-trained recognition model is obtained.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring an original fringe projection image; identifying the original fringe projection image, and determining a fringe projection pattern boundary in the original fringe projection image; and cutting the original fringe projection image according to the fringe projection pattern boundary to obtain the fringe projection image.

In one embodiment, the computer program when executed by the processor further performs the steps of: generating a projected image to be projected according to the flatness information of the surface to be measured; projecting the image to be projected to the surface to be measured so as to form a flatness prompt image on the surface to be measured; the flatness prompt image is used for a user to determine a non-flat area of the surface to be measured.

step S802, obtaining a fringe projection image of the surface to be measured; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes arranged at equal intervals:

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A flatness measuring method, characterized in that the method comprises:

acquiring a fringe projection image of the surface to be detected;

inputting the fringe projection images to a pre-trained recognition model;

determining flatness information of the surface to be detected according to a model output result of the fringe projection image; the method specifically comprises the following steps: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the fringe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as flatness information of the surface to be measured.

2. The method of claim 1, further comprising, prior to the step of inputting the fringe projection images to a pre-trained recognition model:

acquiring a fringe projection sample image;

inputting the fringe projection sample image into a recognition model to be trained; the identification model to be trained is used for processing the input fringe projection sample image to obtain a model output result of the fringe projection sample image; the fringe projection sample image has corresponding label information;

updating model parameters of the recognition model to be trained based on a model output result of the fringe projection sample image and the label information of the fringe projection sample image to obtain a trained recognition model, and taking the trained recognition model as the recognition model to be trained;

3. The method of claim 1, wherein the acquiring fringe projection images of the surface under test comprises:

acquiring an original fringe projection image;

4. The method of any one of claims 1 to 3, further comprising:

5. A flatness measuring method, characterized in that the method comprises:

acquiring a fringe projection image of the surface to be detected; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals;

inputting the fringe projection image into a pre-trained recognition model;

determining flatness information of the surface to be detected according to a model output result of the fringe projection image; the method specifically comprises the following steps: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.

6. A flatness measurement system, the system comprising: the device comprises a projection device, an image acquisition device and a measurement device;

the measuring device is used for inputting the fringe projection image to a pre-trained recognition model; extracting a stripe bending feature in the stripe projection image and a stripe sparse feature in the stripe projection image through the pre-trained recognition model, and generating a model output result of the stripe projection image according to the stripe bending feature and the stripe sparse feature; determining flatness information of the surface to be detected according to a model output result of the fringe projection image; the method specifically comprises the following steps: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as flatness information of the surface to be measured.

7. The system of claim 6, wherein the measuring device is further configured to generate an image to be projected according to the flatness information of the surface to be measured, and send the image to be projected to the projecting device;

8. A flatness measuring apparatus, comprising:

the projection module is used for projecting the initial fringe image to a surface to be measured so as to form a fringe projection image on the surface to be measured;

the input module is used for inputting the fringe projection images to a pre-trained recognition model;

the extraction module is used for extracting the stripe bending feature in the stripe projection image through the pre-trained recognition model, extracting the stripe sparse feature in the stripe projection image, and generating a model output result of the stripe projection image according to the stripe bending feature and the stripe sparse feature;

the determining module is used for determining the flatness information of the surface to be detected according to the model output result of the fringe projection image; the method specifically comprises the following steps: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.

9. A flatness measuring apparatus, comprising:

the image acquisition module is used for acquiring a fringe projection image of the surface to be detected; the fringe projection image is generated according to the initial fringe image projected to the surface to be measured; the initial stripe image comprises a plurality of linear stripes which are arranged at equal intervals;

the image input module is used for inputting the fringe projection image to a pre-trained recognition model;

the characteristic extraction module is used for extracting the stripe bending characteristic in the stripe projection image through the pre-trained recognition model, extracting the stripe sparse characteristic in the stripe projection image, and generating a model output result of the stripe projection image according to the stripe bending characteristic and the stripe sparse characteristic;

the information determining module is used for determining the flatness information of the surface to be measured according to the model output result of the fringe projection image; the method specifically comprises the following steps: determining a fringe distortion area in the fringe projection image according to a model output result of the fringe projection image; the stripe distortion area corresponds to a non-flat area of the surface to be measured; determining the position coordinates of the fringe distortion region in the fringe projection image, and determining the distortion degree value corresponding to the fringe distortion region; and taking the position coordinates and the distortion degree value as the flatness information of the surface to be measured.