CN113048899A - Thickness measuring method and system based on line structured light - Google Patents

Abstract

The invention provides a thickness measurement method and system based on line structured light. The method obtains a target image of a target object irradiated by the line structured light; inputs the target image into a semantic segmentation model, and obtains the first image in the target image output by the semantic segmentation model. A probability map of a light bar line segment, a second light bar line segment and a third light bar line segment, the second light bar line segment is located between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located in the target image. The surface of the target object; based on the probability map of the first light line segment, the second light line segment and the third light line segment and the target image, determine the thickness of the target object, this method can increase the saliency of the laser line in the complex background image, By extracting the key line segments or points of the laser line projected on the complex target object, the influence of the shape change of the laser line irrelevant to the measurement on the final result is reduced, so that the thickness of the measured target object is more accurate and can be applied to texture in more complex scenarios.

Description

Thickness measurement method and system based on line structured light

technical field

The invention relates to the field of machine vision, in particular to a method and system for thickness measurement based on line structured light.

Background technique

Line structured light has become a classic and popular method in many industrial measurement tasks, such as track profile measurement, weld location, terrain surface reconstruction, robot navigation, and thickness measurement of target objects.

For the thickness measurement method based on line structured light, the measurement effect depends on the performance of the line structured light, which largely depends on the mature camera calibration method and the fixed 2D pixel to 3D target point conversion.

Since the thickness measurement method based on line structured light in the prior art has nothing to do with the visual characteristics of the target object, this will lead to inaccurate thickness measurement of the target object, thus hindering the 3D visual measurement of the target object in scenes with more complex textures application.

SUMMARY OF THE INVENTION

The invention provides a thickness measurement method and system based on line structured light, which is used to solve the defect that the thickness measurement method of line structured light in the prior art has nothing to do with the visual characteristics of the target object, and realizes the detection of target objects in scenes with more complex textures. 3D vision measurement applications.

The present invention provides a thickness measurement method based on line structured light, comprising:

Obtain the target image of the target object illuminated by the line structured light;

The target image is input into the semantic segmentation model, and the probability map of the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model is obtained, and the second light line segment is obtained. The light bar line segment is located between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located on the surface of the target object in the target image;

determining the thickness of the target object based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image;

Wherein, the semantic segmentation model is obtained by training based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

According to the present invention, a method for measuring thickness based on line structured light is provided, which is based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image , determine the thickness of the target object, specifically including:

Based on the probability map of the first light line segment, the second light line segment and the third light line segment and the target image, extract the first light line segment and the second light line segment respectively and the center of the laser line of the third light line segment;

Based on the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment, and the third light line segment in the camera coordinate system, determine the relationship between the second light line segment and the third light line segment. a first distance of a light bar line segment and a second distance between the second light bar line segment and the third light bar line segment;

The thickness of the target object is determined based on the first distance and the second distance.

According to a method for thickness measurement based on line structured light provided by the present invention, the method is based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image , respectively extracting the laser line centers of the first light bar line segment, the second light bar line segment and the third light bar line segment, specifically including:

For any light line segment among the first light line segment, the second light line segment and the third light line segment, compare any element in the probability map of the any light line segment with the target image The elements at the corresponding positions are multiplied or added to obtain a new target image;

Based on the new target image, the laser line center of any of the light line segments is extracted.

According to a thickness measurement method based on line structured light provided by the present invention, the target image is acquired based on a camera;

Correspondingly, the three-dimensional space representation of the laser line centers of the first light bar line segment, the second light bar line segment, and the third light bar line segment in the camera coordinate system is determined in the following manner:

Acquire the internal parameter matrix of the camera, and determine the laser plane generated by the line structured light irradiating the calibration object during the calibration process of the camera;

Based on the internal reference matrix and the laser plane, the three-dimensional space representations of the laser line centers of the first light line segment, the second light line segment, and the third light line segment in the camera coordinate system are respectively determined.

According to a thickness measurement method based on line structured light provided by the present invention, the determining of the laser plane generated by the line structured light irradiating the calibration object during the calibration process of the camera specifically includes:

determining the laser line projection generated by the line structured light irradiating the calibration object during the calibration process of the camera, and extracting the laser line center of the laser line projection;

Based on the three-dimensional representation of the laser line center projected by the laser line in the camera coordinate system, the laser plane is obtained by fitting.

According to a thickness measurement method based on line structured light provided by the present invention, the first light line segment, the second light line segment and the first light line segment are determined based on the internal reference matrix and the laser plane, respectively. The three-dimensional space representation of the laser line center of the three-light line segment in the camera coordinate system, including:

For any light line segment among the first light line segment, the second light line segment, and the third light line segment, based on the internal reference matrix, it is determined that the laser line center of the any light line segment is normalized The three-dimensional space representation in the camera coordinate system;

determining a scaling factor based on the laser plane and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system;

Based on the scaling factor and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system is determined.

According to a thickness measurement method based on line structured light provided by the present invention, the center of the laser line based on the first light line segment, the second light line segment and the third light line segment is in a camera coordinate system The three-dimensional space representation below, determining the first distance between the second light bar line segment and the first light bar line segment and the second distance between the second light bar line segment and the third light bar line segment, specifically including:

Based on the three-dimensional representation of the laser line center of the second light line segment in the camera coordinate system, it is determined that the second light line segment is close to the first end point of the first light line segment and the second light line The line segment is close to the second end point of the third light bar line segment;

Based on the three-dimensional representation of the laser line center of the first light line segment in the camera coordinate system, a first straight line where the first light line segment is located is determined, and based on the laser line center of the third light line segment In the three-dimensional space representation in the camera coordinate system, determine the second straight line where the third light line segment is located;

The distance between the first endpoint and the first straight line is determined as the first distance, and the distance between the second endpoint and the second straight line is determined as the second distance.

The present invention also provides a thickness measurement system based on line structured light, comprising:

The target image acquisition module is used to acquire the target image of the target object illuminated by the line structured light;

The semantic segmentation module is used to input the target image into the semantic segmentation model, and obtain the probability of the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model In the figure, the second light line segment is located between the first light line segment and the third light line segment, and the second light line segment is located on the surface of the target object in the target image;

a thickness determination module, configured to determine the thickness of the target object based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image;

Wherein, the semantic segmentation model is obtained by training based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

The present invention also provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, the processor implements any one of the above when executing the computer program The steps of the thickness measurement method based on line structured light.

The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of any of the above-mentioned methods for thickness measurement based on line structured light.

In the method and system for thickness measurement based on line structured light provided by the present invention, through the thickness measurement method based on line structured light in the embodiment of the present invention, the target image of the target object is segmented by using a semantic segmentation model to obtain a first light bar The probability map of the line segment, the second light line segment and the third light line segment, and then determine the thickness of the target object according to the probability map of the three types of light line segments and the target image. This method introduces semantic features, which can increase the saliency of laser lines in complex background images. By extracting key segments or points of laser lines projected on complex target objects, it reduces the influence of laser line morphological changes that are not related to measurement. The influence of the final result makes the measured thickness of the target object more accurate, and enables the thickness measurement method based on line structured light to be applied to scenes with more complex textures.

Description of drawings

In order to explain the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are of the present invention. For some embodiments of the present invention, for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

1 is a schematic flowchart of a thickness measurement method based on line structured light provided by an embodiment of the present invention;

2 is a schematic diagram of a measurement scene of a thickness measurement method based on line structured light provided by an embodiment of the present invention;

3 is a schematic diagram of a fitting result of a laser plane in an embodiment of the present invention;

4 is a schematic diagram of a measurement error of a thickness measurement method based on line structured light provided by an embodiment of the present invention;

Fig. 5 is the line segment fitting schematic diagram of point A in Fig. 4;

Fig. 6 is the line segment fitting schematic diagram of point B in Fig. 4;

FIG. 7 is a schematic flow chart of a thickness measurement method based on line structured light provided by an embodiment of the present invention;

8 is a schematic structural diagram of a thickness measurement system based on line structured light provided by an embodiment of the present invention;

FIG. 9 is a schematic structural diagram of an electronic device provided by the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention. , not all examples. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Since the current method of measuring the thickness of the target object based on line structured light has nothing to do with the visual characteristics of the target object, this will lead to inaccurate thickness of the measured target object, thus hindering the application of 3D vision measurement of the target object in scenes with more complex textures .

Therefore, the present invention provides a thickness measurement method based on line structured light. FIG. 1 is a schematic flowchart of a thickness measurement method based on line structured light provided by an embodiment of the present invention. As shown in FIG. 1 , the method includes:

S1, acquiring a target image of the target object irradiated by the line structured light;

S2, the target image is input into the semantic segmentation model, and the probability map of the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model is obtained. The second light bar line segment is located between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located on the surface of the target object in the target image;

S3, determining the thickness of the target object based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image;

Wherein, the semantic segmentation model is obtained by training based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

Specifically, in the thickness measurement method based on line structured light provided in the embodiment of the present invention, the execution body is a thickness measurement device, and the device includes an image acquisition device, a laser line transmitter, a plane capable of placing a target object, and an image processing device. The image processing device may be a server, the server may be a local server, or a cloud server, and the local server may specifically be a computer, a tablet computer, a smart phone, or the like, which is not specifically limited in this embodiment of the present invention.

Step S1 is performed first. In the embodiment of the present invention, a laser line emitter can be used to project the line structured light onto the surface of the target object, and the line structured light is evenly projected onto the surface of the target object when irradiating the target object. The laser fringe image on the surface, the laser fringe image can be a color image, and for subsequent operations, the color image can be converted into a grayscale image to obtain a grayscale image of the laser fringe image on the surface of the target object, which is the target image. The target object may be an object of any thickness, especially an object with a more complex texture.

Then step S2 is performed. After the target image is acquired, the target image can be input into the semantic segmentation model. After segmentation by the semantic segmentation model, the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model can be obtained. Probability plot of light line segments. The second light bar line segment is located between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located on the surface of the target object in the target image. The semantic segmentation model is trained based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

The first light bar line segment, the second light bar line segment and the third light bar line segment mean that when the line structured light is irradiated on the surface of the target object with a suitable height and brightness, the line structured light beam will form a light bar line segment on the surface of the target object , that is, the line structured light beam will be divided into three segments by the target object, which are the light bar line segments on both sides of the target object and the light bar line segments on the surface of the target object. In this embodiment of the present invention, the light line segment on one side of the target object may be determined as the first light line segment, the light line segment on the surface of the target object may be determined as the second light line segment, and the light line segment on the other side of the target object may be determined as the second light line segment. Determined as the third light line segment. According to the positional relationship of the three light line segments in the target image, the first light line segment may be the upper line segment in the target image, and the third light line segment may be the lower line segment in the target image. The second light bar line segment is a middle line segment between the first light bar line segment and the third light bar line segment.

The input of the semantic segmentation model is the target image I (the width of the target image I is w and the height is h), and the output is a four-channel probability map. The categories corresponding to each channel are the background, the first light line segment, and the second light. line segment and a third light bar line segment. Among them, the probability of a pixel in the probability map of any channel is the probability that the model predicts the class corresponding to the channel at the current pixel position. The probability map type in the embodiment of the present invention may be selected according to actual needs, which is not specifically limited in the embodiment of the present invention.

The semantics in the semantic segmentation model refers to the semantic features of line segments or key points oriented to a specific target, for example, the semantics can refer to the semantic features of the second light line segment and so on. The semantic segmentation model in the embodiment of the present invention may be an existing semantic segmentation model. For example, the semantic segmentation model may use a fully convolutional network, a U-shaped network, a deformed network, or Deeplab v3 using a 50-layer residual network as a feature extraction network, etc., which is not specifically limited in this embodiment of the present invention.

The semantic segmentation model can predict the category of each pixel in the target image by segmenting the target image, that is, classifying each pixel in the target image as the background, the first light line segment, the second light line segment and the third light line segment one of the categories. After the semantic segmentation is completed, the position of any pixel in the first light line segment, the second light line segment and the third light line segment in the target image can be obtained.

Before using the semantic segmentation model to segment the target image, the semantic segmentation model needs to be trained first. The semantic segmentation model is trained based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

When training the semantic segmentation model, each obtained image sample can be manually marked, and the real bounding boxes b _t , b _m and the first light line segment, the second light line segment and the third light line segment can be marked. b _b is marked out to obtain image samples carrying the first light line segment label, the second light line segment label and the third light line segment label, and use these image samples to train the semantic segmentation model.

When training the semantic segmentation model, the center of the laser lines within each bounding box can also be extracted using the gray center method. Among them, the gray center method can extract the laser line center of each bounding box according to the following formula:

（1）

(1)

指线段的类别，即第一光条线段、第二光条线段和第三光条线段；

是指 某一类光条线段的第y列的激光中心；x指第x行；

指第x行第y列处的元素的像素值；

指按元素乘法，即对目标图像中的每一个元素点操作。

Refers to the category of the line segment, namely the first light bar line segment, the second light bar line segment and the third light bar line segment;

refers to the laser center of the yth column of a certain type of light line segment; x refers to the xth row;

Refers to the pixel value of the element at row x and column y;

Refers to element-wise multiplication, that is, operating on each element point in the target image.

Before using the gray center method to extract the center of the laser line in each bounding box, the probability maps of different categories can also be thresholded to obtain a binary map; that is, the semantic segmentation model outputs the first light line segment and the second light line. The probability map of the three categories of line segment and line segment of the third light line. For each probability map, when the probability of the pixel in the map is greater than the specified threshold, the pixel at the same position in the binary map is set to 1, otherwise it is set to 0. The range of the threshold is between 0 and 1, which may be set according to actual needs, for example, set to 0.5, which is not specifically limited in this embodiment of the present invention.

After thresholding, three different types of binary images can be obtained, that is, three types of binary images of the first light line segment, the second light line segment and the third light line segment are obtained. Then use the gray center method for the elements whose pixel is 1 in these binary images.

In the above process, in order to obtain the real semantic mask, use all 1 to initialize the mask of channel 1, set the pixels containing the light line segment to 0 in the mask of channel 1; use all 0 to initialize channels 2 to 4 mask, set the pixel in the center of the laser line of each type of light line segment to 1 in the mask of the corresponding type. Wherein, channel one is the background image channel, and channels two to four correspond to the channels of the first light bar line segment, the second light bar line segment, and the third light bar line segment, respectively.

In order to achieve a better model training effect, the Focal loss function can also be used to supervise the training process of the semantic segmentation model. Among them, the Focal loss function is mainly to solve the problem of serious imbalance in the proportion of positive and negative samples in target detection. The use of the Focal loss function in the semantic segmentation model training can reduce the weight of a large number of simple negative samples in training, and achieve better training. Effect.

Finally, step S3 is performed. After acquiring the probability maps of the first light line segment, the second light line segment and the third light line segment, the thickness of the target object can be determined according to the three types of light line segments and the target image. Since the positional relationship of the first light line segment, the second light line segment and the third light line segment in the target image can be obtained through semantic segmentation, the mapping relationship between the pixel coordinate system where the target image is located and the real world coordinate system can be obtained. Map the position relationship of the first light line segment, the second light line segment and the third light line segment in the target image to the real world coordinate system, and then according to the position relationship of these three types of light line segments in the real world coordinate system , the thickness of the target object can be determined.

In the thickness measurement method based on line structured light in the embodiment of the present invention, the target image of the target object is segmented by using the semantic segmentation model to obtain the probability map of the first light line segment, the second light line segment and the third light line segment , and then determine the thickness of the target object according to the probability map of the three types of light line segments and the target image. This method introduces semantic features, which can increase the saliency of laser lines in complex background images. By extracting key segments or points of laser lines projected on complex target objects, it reduces the influence of laser line morphological changes that are not related to measurement. The influence of the final result makes the measured thickness of the target object more accurate, and enables the thickness measurement method based on line structured light to be applied to scenes with more complex textures.

On the basis of the above-mentioned embodiments, in the thickness measurement method based on line structured light provided by the embodiments of the present invention, the thickness measurement method based on the first light bar line segment, the second light bar line segment and the third light bar line segment The probability map and the target image to determine the thickness of the target object, specifically including:

Based on the probability map of the first light line segment, the second light line segment and the third light line segment and the target image, extract the first light line segment and the second light line segment respectively and the center of the laser line of the third light line segment;

Based on the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment, and the third light line segment in the camera coordinate system, determine the relationship between the second light line segment and the third light line segment. a first distance of a light bar line segment and a second distance between the second light bar line segment and the third light bar line segment;

The thickness of the target object is determined based on the first distance and the second distance.

Specifically, in this embodiment of the present invention, after the probability maps of the first light line segment, the second light line segment, and the third light line segment are obtained, the first light line segment, the second light line segment and the second light line segment can be extracted in combination with the target image, respectively. The laser line center of the light bar line segment and the third light bar line segment, that is, when extracting the laser line center, both the target image and the probability map should be considered. The method for extracting the laser line center may be weighted average according to the column in the image, or may be operated according to the row in the image, which is not specifically limited in this embodiment of the present invention.

After the laser line center of any light line segment is extracted, the obtained laser line center is the two-dimensional laser line center in the pixel coordinate system because the extraction is carried out in combination with the target image and the probability map. The laser line center of the line segment is mapped to the three-dimensional space to obtain the three-dimensional space representation of the laser line center of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system; then based on the first light bar The three-dimensional space representation of the laser line centers of the line segment, the second light line segment and the third light line segment in the camera coordinate system determines the first distance between the second light line segment and the first light line segment and the second light line segment a second distance from the third light bar segment. Wherein, the first distance and the second distance may be determined according to the positional relationship of the laser line centers of the first light line segment, the second light line segment and the third light line segment in the three-dimensional space under the camera coordinate system.

After the first distance and the second distance are acquired, the thickness of the target object can be determined according to the first distance and the second distance. The thickness of the target object may be an average value of the first distance and the second distance.

In the thickness measurement method based on line structured light in the embodiment of the present invention, the laser line center of any light line segment is extracted, and then the second light line segment is determined according to the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system The first distance from the first light line segment and the second distance between the second light line segment and the third light line segment are determined, and the average value of the first distance and the second distance is taken as the thickness of the target object, and the center of the extracted laser line is Semantics are introduced to make the measurement of target object thickness more accurate.

On the basis of the above-mentioned embodiments, in the thickness measurement method based on line structured light provided by the embodiments of the present invention, the thickness measurement method based on the first light bar line segment, the second light bar line segment and the third light bar line segment The probability map and the target image, respectively extract the laser line centers of the first light line segment, the second light line segment and the third light line segment, specifically including:

For any light line segment among the first light line segment, the second light line segment and the third light line segment, compare any element in the probability map of the any light line segment with the target image The elements at the corresponding positions are multiplied or added to obtain a new target image;

Based on the new target image, the laser line center of any of the light line segments is extracted.

Specifically, in this embodiment of the present invention, for any light bar segment among the first light bar line segment, the second light bar line segment, and the third light bar line segment, any element in the probability map of any light bar line segment may be associated with the target The elements of the corresponding positions in the image are multiplied or added to obtain a new target image, and then the center of the laser line of any light line segment is extracted according to the new target image.

When any element in the probability map of any light line segment is multiplied by the element at the corresponding position in the target image, that is, an AND operation is used to obtain a new target image, which enhances the semantic part of the center of the laser line.

For example, when the probability map of the first light line segment and the target image are multiplied element-wise, the value of the pixel with a higher probability of being the first light line segment category in the target image will be relatively larger, while the value of the pixel with a higher probability of being the first light line segment in the target image Pixels with a probability of being a category other than the first light line segment (ie, with a higher probability of being the second light line segment, the third light line segment, or the background category) will have relatively smaller values.

When the AND operation is finished, the laser line center of any light line segment can be extracted according to the new target image.

According to the column of the new target image, the center of any light line segment in each column of the new target image can be obtained, and after the AND operation, the laser line center of any light line segment can be extracted according to the following formula.

（2）

(2)

指某一类线段的概率图中第x行第y列处的概率值，公式中剩余部分 表征的含义与公式（1）中相同。 in,

Refers to the probability value at row x, column y in the probability map of a certain type of line segment. The meaning of the rest of the formula is the same as that in formula (1).

When any element in the probability map of any light line segment is added to the element at the corresponding position in the target image, using the or operation to obtain a new target image also enhances the semantic part of the laser line center.

The OR operation trades off the detail information in the target image and the structural information in the semantic mask. After or after the operation, the laser line center of any light line segment can also be extracted according to the new target image.

Similarly, according to the column of the new target image, obtain the center of any light line segment in each column of the new target image. After the OR operation, the laser line center of any light line segment can be extracted according to the following formula.

（3）

(3)

是权重参数，可以根据实际需要进行设置，本发明实施例对此不作具体 限定，其余参数表征含义与公式（2）相同。 in,

is a weight parameter, which can be set according to actual needs, which is not specifically limited in this embodiment of the present invention, and the meanings of other parameters are the same as those of formula (2).

In this embodiment of the present invention, the AND operation or the OR operation may be selected according to actual needs, which is not specifically limited in the present invention, and only needs to be guaranteed to achieve the effect of enhancing semantics. However, the OR operation will only have the effect of enhancing semantics when the resolution of the target image and the image output by the semantic segmentation model are the same. Therefore, when the resolution of the target image and the image output by the semantic segmentation model are different, the AND operation needs to be used to enhance the semantics.

In the thickness measurement method based on line structured light in the embodiment of the present invention, the semantic part of the laser line center is enhanced by the AND operation or OR operation, and then the laser line center of any light line segment is obtained according to the weighted average method, so that the extracted laser line The center is more accurate, resulting in a more accurate thickness measurement.

On the basis of the above embodiments, in the thickness measurement method based on line structured light provided by the embodiments of the present invention, the target image is acquired based on a camera;

Correspondingly, the three-dimensional space representation of the laser line centers of the first light bar line segment, the second light bar line segment, and the third light bar line segment in the camera coordinate system is determined in the following manner:

Acquire the internal parameter matrix of the camera, and determine the laser plane generated by the line structured light irradiating the calibration object during the calibration process of the camera;

Based on the internal reference matrix and the laser plane, the three-dimensional space representations of the laser line centers of the first light line segment, the second light line segment, and the third light line segment in the camera coordinate system are respectively determined.

Specifically, in this embodiment of the present invention, the target image is acquired by a camera. As shown in Figure 2, when the laser line transmitter projects a bar-shaped laser beam to the surface of the target object to form a laser fringe image, a camera can be used to capture the laser fringe image. The laser stripe image captured by the camera can be a color image, which is converted into grayscale, and the converted grayscale image is the target image. The camera may be selected according to actual needs, and may be, for example, a charge-coupled device (Charge-coupled Device, CCD) camera, which is not specifically limited in this embodiment of the present invention.

Before determining the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system, the internal parameter matrix of the camera used needs to be obtained. The internal parameter matrix of the camera can be obtained by calibrating the camera. At the same time, in the process of calibration, it is also necessary to determine the laser plane generated by the linear structured light irradiating the calibration object. After the internal parameter matrix and the laser plane of the camera are determined, the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system can be determined .

The method for calibrating the camera to obtain the internal parameter matrix of the camera may be a single-plane checkerboard calibration method. The steps of the calibration method include: printing a checkerboard, sticking it on a plane as a calibration object, by adjusting the direction of the camera or the calibration object, taking some photos in different directions for the calibration object, and extracting the checkerboard from the photo Corner points, estimate the values of five internal parameters and six external parameters in the ideal case of no distortion, and obtain the camera's internal parameter matrix and external parameter matrix.

The internal parameter matrix is a 3×3 matrix that can be expressed as:

（4）

(4)

分别表示x轴和y轴的焦距以及光轴在x轴和y轴上的偏移。 in,

represent the focal length of the x-axis and y-axis and the offset of the optical axis on the x-axis and y-axis, respectively.

In the embodiment of the present invention, since the image captured by the camera may be distorted, the distortion refers to an offset of the straight line projection, which is an inherent characteristic of the camera itself, so the distortion correction can be performed during the camera calibration process. Moreover, since the distortion of the camera is only related to the target image acquired by the camera, if the target image has no distortion, the distortion coefficient of the camera can be ignored.

In the embodiment of the present invention, if the target image obtained by the camera has distortion, the radial distortion of the camera can be corrected. Radial distortion includes barrel distortion and pincushion distortion. The radial distortion comes from the lens shape. For radial distortion, the distortion in the center of the camera is 0, and the distortion becomes more and more serious as it moves to the edge. Wherein, the preset distortion coefficient of radial distortion can be calculated through the above-mentioned camera calibration process, so as to correct the position information. The internal parameter matrix and external parameter matrix of the camera are obtained first, and then the least squares method is applied to estimate the distortion coefficient under the actual radial distortion.

After acquiring the internal parameter matrix of the camera, it is also necessary to determine the laser plane generated by the linear structured light irradiating the calibration object in the calibration process of the camera. As shown in Figure 2, during the calibration process of the camera, the cube, that is, the plane on which the target object is placed, is changed to a calibration object, and the calibration object can be a small-sized checkerboard. In the camera calibration process, the laser plane generated by the linear structured light irradiating the calibration object is the laser plane that needs to be determined.

After the camera's internal parameter matrix and laser plane are determined, the laser line centers of the first, second, and third light line segments can be converted from the two-dimensional pixel coordinate system to the three-dimensional coordinate system according to the camera's internal parameter matrix. In the space coordinate system, the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system is determined according to the laser plane.

In the thickness measurement method based on line structured light in the embodiment of the present invention, by calibrating the camera, the internal parameter matrix of the camera and the laser plane generated by the line structured light irradiating the calibration object during the calibration process are obtained, so that the determined first light bar The three-dimensional space representation of the laser line centers of the line segment, the second light line segment and the third light line segment in the camera coordinate system is more accurate, thereby reducing the error of the measured thickness of the target object.

On the basis of the above embodiments, in the thickness measurement method based on line structured light provided by the embodiment of the present invention, the determining of the laser plane generated by the line structured light irradiating the calibration object during the calibration process of the camera specifically includes:

determining the laser line projection generated by the line structured light irradiating the calibration object during the calibration process of the camera, and extracting the laser line center of the laser line projection;

Based on the three-dimensional representation of the laser line center projected by the laser line in the camera coordinate system, the laser plane is obtained by fitting.

Specifically, in the embodiment of the present invention, the laser line projection generated by the linear structured light irradiating the calibration object during the calibration process of the camera can be determined first, the laser line center of the laser line projection can be extracted, and then the extracted laser line center can be mapped to the camera coordinate system. Then, the three-dimensional space representation of the laser line center under the camera coordinate system is obtained, that is, the coordinates of the laser line center under the camera coordinate system are obtained, and the laser plane is obtained by fitting the three-dimensional space representation of the laser line center under the camera coordinate system. .

The calibration object is the same as the above, and can be a small-sized checkerboard, that is, the calibration object is irradiated with a line structured light to generate a laser line projection, and an image of the laser line projection is obtained. Extract the laser line center from the image projected by the laser line to obtain the laser line center projected by the laser line. The method for extracting the center of the laser line may be the above-mentioned gray-scale center method.

After obtaining the laser line center projected by the laser line, the position of the laser line center projected by the laser line in the pixel coordinate system is obtained, and the three-dimensional image of the laser line center projected by the laser line in the camera coordinate system can be determined according to the camera's internal parameter matrix. Spatial representation.

FIG. 3 is a schematic diagram of a fitting result of a laser plane in an embodiment of the present invention. Since the laser plane contains the laser line centers projected by different laser lines, the laser plane can be determined by fitting the three-dimensional space representation of the laser line centers projected by these laser lines in the camera coordinate system.

The laser plane can be defined using a system of linear ternary equations, and the laser plane can be expressed as:

（5）

(5)

、

和

为三元一次方程的参数，

、

和

是激光线中心在 相机坐标系下的三维空间表示，即在相机坐标系下的坐标。 in,

,

and

are the parameters of the ternary linear equation,

,

and

is the three-dimensional representation of the laser line center in the camera coordinate system, that is, the coordinates in the camera coordinate system.

In order to get a more accurate laser plane, the RANSAC estimation can be used to fit the laser plane. The fitting process of RANSAC can be as follows: first determine the above-mentioned laser plane equation by the three-dimensional space coordinates of the laser line centers projected by some laser lines; Three-dimensional space coordinates, if the three-dimensional space coordinates of the center of the laser line projected by a laser line conform to the equation of the determined laser plane, it is considered to be an in-office point, otherwise it is an out-of-office point; if there are enough in-office points, the laser plane equation If it is reasonable, the parameters of the laser plane equation are re-estimated by using the intra-office point; the laser plane is finally determined by an iterative method.

The thickness measurement method based on line structured light in the embodiment of the present invention extracts the laser line center projected by the laser line, and obtains the laser line by fitting based on the three-dimensional space representation of the laser line center projected by the laser line in the camera coordinate system. The plane makes the obtained laser plane more accurate, which is convenient for subsequent thickness measurement of the target object.

On the basis of the above embodiment, in the thickness measurement method based on line structured light provided by the embodiment of the present invention, the first light line segment, the second light line segment and the second light line segment are respectively determined based on the internal reference matrix and the laser plane. The three-dimensional space representation of the light bar line segment and the laser line center of the third light bar line segment in the camera coordinate system, specifically including:

For any light line segment among the first light line segment, the second light line segment, and the third light line segment, based on the internal reference matrix, it is determined that the laser line center of the any light line segment is normalized The three-dimensional space representation in the camera coordinate system;

determining a scaling factor based on the laser plane and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system;

Based on the scaling factor and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system is determined.

Specifically, in the embodiment of the present invention, based on the internal parameter matrix of the camera, the laser line center of any one of the first light line segment, the second light line segment, and the third light line segment can be mapped from the pixel coordinate system to the normalized laser line. In the normalized camera coordinate system, that is, the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system is obtained. After obtaining the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system, the scaling factor can also be determined in combination with the laser plane obtained by the above fitting. Based on the scaling factor and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system can be determined.

Wherein, the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system can be determined based on the internal parameter matrix by the following formula.

（6）

(6)

是无畸变目标图像中的任一光条线段的激光线中心的坐标点，即任一光 条线段的激光线中心在像素坐标系中的坐标，

是任一光条线段的激光线中 心在像素坐标系中的坐标映射到归一化相机坐标系中的坐标，即任一光条线段的激光线中 心在归一化相机坐标系下的三维空间表示。

is the coordinate point of the laser line center of any light line segment in the undistorted target image, that is, the coordinates of the laser line center of any light line segment in the pixel coordinate system,

is the coordinate of the laser line center of any light line segment in the pixel coordinate system mapped to the coordinates in the normalized camera coordinate system, that is, the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system.

After the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system is determined, the scaling factor can also be determined in combination with the above-mentioned laser plane equation. where, modifying the laser plane equation according to the scaling factor can be:

（7）

(7)

Then the scaling factor is:

（8）

(8)

After the scaling factor is determined, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system can be determined by the following formula.

（9）

(9)

即为任一光条线段的激光线中心在相机坐标系下的三 维空间表示。 in,

That is, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system.

The thickness measurement method based on line structured light in the embodiment of the present invention determines the scaling factor and is represented by the scaling factor and the three-dimensional space of the laser line center of any light line segment in the normalized camera coordinate system, to determine the thickness of any light line segment. The 3D space representation of the laser line center in the camera coordinate system eliminates the scaling problem in the normalized camera coordinate system, making the distances between different points consistent with their distances in the real world coordinate system.

On the basis of the above-mentioned embodiments, in the thickness measurement method based on line structured light provided by the embodiments of the present invention, the thickness measurement method based on the first light bar line segment, the second light bar line segment and the third light bar line segment The three-dimensional space representation of the center of the laser line in the camera coordinate system, determining the first distance between the second light line segment and the first light line segment and the distance between the second light line segment and the third light line segment The second distance includes:

Based on the three-dimensional representation of the laser line center of the second light line segment in the camera coordinate system, it is determined that the second light line segment is close to the first end point of the first light line segment and the second light line The line segment is close to the second end point of the third light bar line segment;

Based on the three-dimensional representation of the laser line center of the first light line segment in the camera coordinate system, a first straight line where the first light line segment is located is determined, and based on the laser line center of the third light line segment In the three-dimensional space representation in the camera coordinate system, determine the second straight line where the third light line segment is located;

The distance between the first endpoint and the first straight line is determined as the first distance, and the distance between the second endpoint and the second straight line is determined as the second distance.

Specifically, in the embodiment of the present invention, the two end points of the second light line segment can be determined according to the three-dimensional space representation of the laser line center of the second light line segment in the camera coordinate system, and the two end points of the second light line segment are located close to the first light line segment. as the first endpoint; take the segment close to the third light line segment as the second endpoint.

Similarly, the first straight line where the first light line segment is located can also be determined according to the three-dimensional representation of the laser line center of the first light line segment in the camera coordinate system; according to the laser line center of the third light line segment in the camera The three-dimensional space representation in the coordinate system determines the second straight line where the third light bar line segment is located.

Finally, calculating the distance between the first endpoint and the first straight line is the first distance, and calculating the distance between the second endpoint and the second straight line is the second distance.

Wherein, according to the three-dimensional space representation of the laser line center of the second light line segment in the camera coordinate system, the two end points of the second light line segment and the three-dimensional representation of the laser line center of the first light line segment under the camera coordinate system are determined Spatial representation, the method of determining the first straight line where the first light line segment is located and the three-dimensional space representation of the laser line center of the third light line segment in the camera coordinate system to determine the second straight line where the third light line segment is located are both. Huber can be used for fitting, and the parameters of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system are obtained by fitting, that is, the first light line segment, the second light line segment and the third light line segment. The slope and offset of the three-light line segment in the camera coordinate system.

After using Huber fitting to determine the parameters of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system, the first endpoint and the second endpoint of the midline segment can be determined, or the The first straight line and the second straight line. Then according to the distance formula from the point to the line, the first distance and the second distance can be calculated.

，第一直线是经过第一光条线段的起始点

和 第一光条线段的终止点

的被拟合直线；同样的，第二端点是

，第二直线是经过第三 光条线段的起始点

和第三光条线段的终止点

的被拟合直线。 For example, the first endpoint identified is

, the first straight line is the starting point of the first light line segment

and the end point of the first ray segment

is the fitted line; similarly, the second endpoint is

, the second straight line is the starting point of the line segment passing through the third light bar

and the termination point of the third light bar segment

the fitted straight line.

Then the first distance can be determined by the following formula:

（10）

(10)

Similarly, the second distance can be determined by the following formula:

（11）

(11)

FIG. 4 is a schematic diagram of a measurement error of a thickness measurement method based on line structured light provided by an embodiment of the present invention. As shown in FIG. 5 , FIG. 5 is a schematic diagram of line segment fitting at point A in FIG. 4 ; FIG. 6 is a schematic diagram of line segment fitting at point B in FIG. 4 .

In the thickness measurement method based on line structured light in the embodiment of the present invention, the two end points of the second light bar line segment, the first straight line where the first light bar line segment is located, and the second light bar line segment where the third light bar line segment is located are determined by fitting. The first distance and the second distance are determined according to the distance from the point to the straight line, which improves the accuracy of the thickness measurement of the target object.

FIG. 7 is a schematic flow chart of a thickness measurement method based on line structured light provided by an embodiment of the present invention. As shown in FIG. 7 , the method includes:

Input the target image into the semantic segmentation model, and obtain the probability map that the semantic segmentation model outputs the first light line segment, the second light line segment and the third light line segment;

Multiplying or adding the target image with the probability map of the first light line segment, the second light line segment and the third light line segment to obtain a new target image;

Based on three new target images, the laser line center of any light line segment is extracted respectively, and the new target image can be binarized during extraction;

Perform distortion correction on the laser line center of any extracted light line segment, and determine the three-dimensional space representation of the laser line center of any light line segment;

Fitting is performed based on the three-dimensional space representation of the laser line center of any light line segment, and the two end points of the second light line segment, the line where the first light line segment is located, and the straight line where the third light line segment is located are determined;

The thickness of the target object is determined according to the distance from the point to the straight line based on the two end points of the second light bar segment, the straight line where the first light bar segment is located, and the straight line where the third light bar segment is located.

As shown in FIG. 8 , on the basis of the above embodiment, an embodiment of the present invention provides a thickness measurement system based on line structured light, including:

A target image acquisition module 801, configured to acquire a target image of a target object illuminated by the line structured light;

The semantic segmentation module 802 is configured to input the target image into the semantic segmentation model, and obtain the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model. a probability map, the second light line segment is located between the first light line segment and the third light line segment, and the second light line segment is located on the surface of the target object in the target image;

a thickness determination module 803, configured to determine the thickness of the target object based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image;

Wherein, the semantic segmentation model is obtained by training based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

On the basis of the above embodiment, the embodiment of the present invention provides a thickness measurement system based on line structured light, and the thickness determination module specifically includes:

A laser line center extraction sub-module, configured to extract the first light bar based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image, respectively the laser line center of the line segment, the second light bar line segment and the third light bar line segment;

A distance determination submodule, configured to determine the second light line segment based on the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment and the third light line segment in the camera coordinate system a first distance between the light bar line segment and the first light bar line segment and a second distance between the second light bar line segment and the third light bar line segment;

A thickness determination submodule, configured to determine the thickness of the target object based on the first distance and the second distance.

On the basis of the above embodiment, the embodiment of the present invention provides a thickness measurement system based on line structured light, wherein the laser line center extraction sub-module specifically includes:

A new target image acquisition sub-unit is used for, for any one of the first light bar line segment, the second light bar line segment and the third light bar line segment, to map the probability map of the any light bar line segment. Any element of is multiplied or added with the element at the corresponding position in the target image to obtain a new target image;

The laser line center extraction subunit is used for extracting the laser line center of any one of the light line segments based on the new target image.

On the basis of the above embodiment, the embodiment of the present invention provides a thickness measurement system based on line structured light, wherein the target image is acquired based on a camera;

Correspondingly, the distance determination submodule specifically includes:

a laser plane determination subunit, used for acquiring the internal parameter matrix of the camera, and determining the laser plane generated by the linear structured light irradiating the calibration object during the calibration process of the camera;

The three-dimensional space representation determination subunit is used to determine the laser line center of the first light line segment, the second light line segment and the third light line segment respectively based on the internal parameter matrix and the laser plane. 3D space representation in the camera coordinate system.

On the basis of the above embodiment, the embodiment of the present invention provides a thickness measurement system based on line structured light, wherein the laser plane determination subunit is specifically used for:

determining the laser line projection generated by the line structured light irradiating the calibration object during the calibration process of the camera, and extracting the laser line center of the laser line projection;

Based on the three-dimensional representation of the laser line center projected by the laser line in the camera coordinate system, the laser plane is obtained by fitting.

On the basis of the above embodiment, the embodiment of the present invention provides a thickness measurement system based on line structured light, wherein the three-dimensional space representation determination subunit is specifically used for:

For any light line segment among the first light line segment, the second light line segment, and the third light line segment, based on the internal reference matrix, it is determined that the laser line center of the any light line segment is normalized The three-dimensional space representation in the camera coordinate system;

determining a scaling factor based on the laser plane and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system;

Based on the scaling factor and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system is determined.

On the basis of the above embodiment, the embodiment of the present invention provides a thickness measurement system based on line structured light, and the distance determination sub-module specifically further includes:

an endpoint determination subunit, configured to determine that the second light line segment is close to the first end of the first light line segment based on the three-dimensional space representation of the laser line center of the second light line segment in the camera coordinate system point and the second light bar line segment is close to the second end point of the third light bar line segment;

a straight line determination subunit, configured to determine a first straight line where the first light line segment is located based on the three-dimensional representation of the laser line center of the first light line segment in the camera coordinate system, and based on the third light line segment The three-dimensional space representation of the laser line center of the light bar line segment in the camera coordinate system, to determine the second straight line where the third light bar line segment is located;

A distance determination subunit, configured to determine the distance between the first endpoint and the first straight line as the first distance, and determine the distance between the second endpoint and the second straight line as the second distance distance.

Specifically, the functions of each module in the linear structured light-based thickness measurement system provided in the embodiment of the present invention correspond one-to-one with the operation flow of each step in the above-mentioned method embodiments, and the achieved effects are also consistent. For details, refer to In the above-mentioned embodiment, details are not repeated in this embodiment of the present invention.

FIG. 9 illustrates a schematic diagram of the physical structure of an electronic device. As shown in FIG. 9 , the electronic device may include: a processor (Processor) 910, a communication interface (Communication Interface) 920, a memory (Memory) 930, and a communication bus 940, The processor 910 , the communication interface 920 , and the memory 930 communicate with each other through the communication bus 940 . The processor 910 can call the logic instructions in the memory 930 to execute the thickness measurement method based on the line structured light provided by the above embodiments, the method includes: acquiring a target image of the target object irradiated by the line structured light; Input to the semantic segmentation model, and obtain the probability map of the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model, and the second light line segment is located in the between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located on the surface of the target object in the target image; based on the first light bar line segment, the second light bar line segment The probability map of the bar line segment and the third light bar line segment and the target image, to determine the thickness of the target object; wherein, the semantic segmentation model is based on carrying the first light bar line segment label, the second light bar line segment label and the image samples of the third light bar line segment label are obtained by training.

In addition, the above-mentioned logic instructions in the memory 930 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer During execution, the computer can execute the thickness measurement method based on the line structured light provided by the above embodiments, the method includes: acquiring a target image of the target object illuminated by the line structured light; inputting the target image into the semantic segmentation model to obtain the The probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment in the target image output by the semantic segmentation model, the second light bar line segment is located between the first light bar line segment and all the light bar line segments. between the third light bar line segments, and the second light bar line segment is located on the surface of the target object in the target image; based on the first light bar line segment, the second light bar line segment and the third light bar line segment The probability map of the line segment and the target image to determine the thickness of the target object; wherein, the semantic segmentation model is based on the training image samples.

In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored, and the computer program is implemented when executed by a processor to perform the line structured light-based thickness measurement provided by the above embodiments The method includes: acquiring a target image of a target object irradiated by line structured light; inputting the target image into a semantic segmentation model to obtain a first light line segment, a first light line segment, a second light line segment in the target image output by the semantic segmentation model A probability map of a second light bar line segment and a third light bar line segment, the second light bar line segment is located between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located at the the surface of the target object in the target image; based on the probability map of the first light line segment, the second light line segment and the third light line segment and the target image, determine the thickness of the target object; Wherein, the semantic segmentation model is obtained by training based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label.

The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on this understanding, the above-mentioned technical solutions can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic A disc, an optical disc, etc., includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. a thickness measurement method based on line structured light, is characterized in that, comprises: Obtain the target image of the target object illuminated by the line structured light; The target image is input into the semantic segmentation model, and the probability map of the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model is obtained, and the second light line segment is obtained. The light bar line segment is located between the first light bar line segment and the third light bar line segment, and the second light bar line segment is located on the surface of the target object in the target image; determining the thickness of the target object based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image; Wherein, the semantic segmentation model is obtained by training based on the image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label. 2 . The thickness measurement method based on line structured light according to claim 1 , wherein the probability based on the first light bar line segment, the second light bar line segment and the third light bar line segment. 3 . image and the target image to determine the thickness of the target object, specifically including: Based on the probability map of the first light line segment, the second light line segment and the third light line segment and the target image, extract the first light line segment and the second light line segment respectively and the center of the laser line of the third light line segment; Based on the three-dimensional space representation of the laser line centers of the first light line segment, the second light line segment, and the third light line segment in the camera coordinate system, determine the relationship between the second light line segment and the third light line segment. a first distance of a light bar line segment and a second distance between the second light bar line segment and the third light bar line segment; The thickness of the target object is determined based on the first distance and the second distance. 3 . The thickness measurement method based on line structured light according to claim 2 , wherein the probability based on the first light bar line segment, the second light bar line segment and the third light bar line segment is 3 . image and the target image, respectively extracting the laser line centers of the first light line segment, the second light line segment, and the third light line segment, specifically including: For any light line segment among the first light line segment, the second light line segment and the third light line segment, compare any element in the probability map of the any light line segment with the target image The elements at the corresponding positions are multiplied or added to obtain a new target image; Based on the new target image, the laser line center of any of the light line segments is extracted. 4. The thickness measurement method based on line structured light according to claim 2, wherein the target image is acquired based on a camera; Correspondingly, the three-dimensional space representation of the laser line centers of the first light bar line segment, the second light bar line segment, and the third light bar line segment in the camera coordinate system is determined in the following manner: Acquire the internal parameter matrix of the camera, and determine the laser plane generated by the line structured light irradiating the calibration object during the calibration process of the camera; Based on the internal reference matrix and the laser plane, the three-dimensional space representations of the laser line centers of the first light line segment, the second light line segment, and the third light line segment in the camera coordinate system are respectively determined. 5 . The thickness measurement method based on line structured light according to claim 4 , wherein determining the laser plane generated by the line structured light irradiating the calibration object during the calibration process of the camera, specifically comprising: 6 . determining the laser line projection generated by the line structured light irradiating the calibration object during the calibration process of the camera, and extracting the laser line center of the laser line projection; Based on the three-dimensional representation of the laser line center projected by the laser line in the camera coordinate system, the laser plane is obtained by fitting. 6 . The thickness measurement method based on line structured light according to claim 4 , wherein the first light bar line segment and the second light line segment are respectively determined based on the internal reference matrix and the laser plane. 7 . The three-dimensional space representation of the line segment and the laser line center of the third light line segment in the camera coordinate system, specifically including: For any light line segment among the first light line segment, the second light line segment, and the third light line segment, based on the internal reference matrix, it is determined that the laser line center of the any light line segment is normalized The three-dimensional space representation in the camera coordinate system; determining a scaling factor based on the laser plane and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system; Based on the scaling factor and the three-dimensional space representation of the laser line center of any light line segment in the normalized camera coordinate system, the three-dimensional space representation of the laser line center of any light line segment in the camera coordinate system is determined. 7 . The thickness measurement method based on line structured light according to any one of claims 2 to 6 , wherein the method based on the first light bar line segment, the second light bar line segment and the first light bar line segment The three-dimensional space representation of the laser line center of the three-beam line segment in the camera coordinate system, determining the first distance between the second light-line segment and the first light-line segment and the second light-line segment and the third light-line segment The second distance of the three-light bar line segment, specifically including: Based on the three-dimensional representation of the laser line center of the second light line segment in the camera coordinate system, it is determined that the second light line segment is close to the first end point of the first light line segment and the second light line The line segment is close to the second end point of the third light bar line segment; Based on the three-dimensional representation of the laser line center of the first light line segment in the camera coordinate system, a first straight line where the first light line segment is located is determined, and based on the laser line center of the third light line segment In the three-dimensional space representation in the camera coordinate system, determine the second straight line where the third light line segment is located; The distance between the first endpoint and the first straight line is determined as the first distance, and the distance between the second endpoint and the second straight line is determined as the second distance. 8. A thickness measurement system based on line structured light, comprising: The target image acquisition module is used to acquire the target image of the target object illuminated by the line structured light; A semantic segmentation module, configured to input the target image into a semantic segmentation model, and obtain the probability of the first light line segment, the second light line segment and the third light line segment in the target image output by the semantic segmentation model In the figure, the second light line segment is located between the first light line segment and the third light line segment, and the second light line segment is located on the surface of the target object in the target image; a thickness determination module, configured to determine the thickness of the target object based on the probability map of the first light bar line segment, the second light bar line segment and the third light bar line segment and the target image; Wherein, the semantic segmentation model is obtained by training based on image samples carrying the first light bar line segment label, the second light bar line segment label and the third light bar line segment label. 9. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements the program as claimed in claim 1 when executing the program Steps of any one of the method for thickness measurement based on line structured light described in any one of to 7. 10. A non-transitory computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the wire-structured light-based system according to any one of claims 1 to 7 is implemented. The steps of the thickness measurement method.

Images